{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2e64172a",
   "metadata": {},
   "source": [
    "# Alternative solution using pressure values as independent variables\n",
    "The purpose of MICP experiments is to measure injected mercury volume as a function of pressure, so, in my opinion, pressure values should be independent variables. They may be unknown, in which case it is possible to use the maximum range from 0 to 60,000 psi (maximum pressure in MICP experiments)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "444d3eb9",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.metrics import mean_absolute_percentage_error\n",
    "from sklearn.multioutput import MultiOutputRegressor\n",
    "import chime\n",
    "import optuna\n",
    "from sklearn.model_selection import cross_val_score\n",
    "from sklearn.metrics import mean_absolute_percentage_error"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b51a469a",
   "metadata": {},
   "source": [
    "Visualization:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5878166e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from optuna.visualization.matplotlib import plot_optimization_history\n",
    "from optuna.visualization.matplotlib import plot_param_importances"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ae7acac4",
   "metadata": {},
   "source": [
    "Audible notification:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "068462fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext chime"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6bbadc41",
   "metadata": {},
   "source": [
    "# Model performance metric \n",
    "The target variables, bv and pc (i.e mercury volume and pressure) use different scales: pressure scale is 3 orders of magnitude larger. So the variables and their prediction errors are not comparable. Moreover, pressure and volume themselves vary across wide ranges (also a few order of magnitude wide). Therefore, I use mean average percentage error to evaluage model performance. "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff355bb1",
   "metadata": {},
   "source": [
    "# Data preparation\n",
    "- Group is a sequential well number that does not have physical sense. It is also uniquely defined by well coordinates. So I drop this column.\n",
    "- Well coordinates as such also do not determine anything but relative well proximity to each other can result in similarities, so I keep them in.\n",
    "- Same sample numbers across different wells do not result in any similarity so I drop this column as well.\n",
    "- The only categorical feature (and a very important one) is lithology, so I will one-hot encode it.\n",
    "- I will take logarithm of pressure due to a very wide range\n",
    "- All other values will be standardized as usual."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "200a6594",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>group</th>\n",
       "      <th>sample</th>\n",
       "      <th>depth</th>\n",
       "      <th>por</th>\n",
       "      <th>den</th>\n",
       "      <th>ct_1</th>\n",
       "      <th>ct_2</th>\n",
       "      <th>ct_3</th>\n",
       "      <th>ct_4</th>\n",
       "      <th>ct_5</th>\n",
       "      <th>...</th>\n",
       "      <th>pc_91</th>\n",
       "      <th>pc_92</th>\n",
       "      <th>pc_93</th>\n",
       "      <th>pc_94</th>\n",
       "      <th>pc_95</th>\n",
       "      <th>pc_96</th>\n",
       "      <th>pc_97</th>\n",
       "      <th>pc_98</th>\n",
       "      <th>pc_99</th>\n",
       "      <th>pc_100</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>52</td>\n",
       "      <td>1660.178974</td>\n",
       "      <td>18.556209</td>\n",
       "      <td>2.740942</td>\n",
       "      <td>1971.579998</td>\n",
       "      <td>2396.714551</td>\n",
       "      <td>2799.219912</td>\n",
       "      <td>1951.977330</td>\n",
       "      <td>2041.857394</td>\n",
       "      <td>...</td>\n",
       "      <td>20517.973164</td>\n",
       "      <td>23072.031367</td>\n",
       "      <td>25918.199746</td>\n",
       "      <td>29130.680234</td>\n",
       "      <td>32741.818105</td>\n",
       "      <td>36776.940391</td>\n",
       "      <td>41337.948828</td>\n",
       "      <td>46440.194570</td>\n",
       "      <td>52182.348633</td>\n",
       "      <td>58608.434023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>92</td>\n",
       "      <td>3890.779426</td>\n",
       "      <td>8.555400</td>\n",
       "      <td>2.834776</td>\n",
       "      <td>2513.180531</td>\n",
       "      <td>3001.782975</td>\n",
       "      <td>2348.160682</td>\n",
       "      <td>2414.636280</td>\n",
       "      <td>2798.706138</td>\n",
       "      <td>...</td>\n",
       "      <td>4178.079326</td>\n",
       "      <td>4564.280930</td>\n",
       "      <td>4987.905991</td>\n",
       "      <td>5457.903966</td>\n",
       "      <td>5976.209199</td>\n",
       "      <td>6537.572468</td>\n",
       "      <td>7149.014724</td>\n",
       "      <td>7826.130471</td>\n",
       "      <td>8559.884813</td>\n",
       "      <td>9368.567796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>90</td>\n",
       "      <td>2287.441253</td>\n",
       "      <td>-0.169935</td>\n",
       "      <td>2.761468</td>\n",
       "      <td>2274.773580</td>\n",
       "      <td>1083.899155</td>\n",
       "      <td>2974.647775</td>\n",
       "      <td>2713.863889</td>\n",
       "      <td>2381.094609</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.705605</td>\n",
       "      <td>23075.290605</td>\n",
       "      <td>25927.208926</td>\n",
       "      <td>29136.474492</td>\n",
       "      <td>32743.575156</td>\n",
       "      <td>36780.525273</td>\n",
       "      <td>41344.256875</td>\n",
       "      <td>46461.810508</td>\n",
       "      <td>52207.803164</td>\n",
       "      <td>58651.855859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>49</td>\n",
       "      <td>2144.788740</td>\n",
       "      <td>28.192998</td>\n",
       "      <td>2.637605</td>\n",
       "      <td>1776.270868</td>\n",
       "      <td>2374.721334</td>\n",
       "      <td>2670.367528</td>\n",
       "      <td>2814.751969</td>\n",
       "      <td>2919.311685</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.544570</td>\n",
       "      <td>23075.227422</td>\n",
       "      <td>25928.721426</td>\n",
       "      <td>29137.418496</td>\n",
       "      <td>32742.759414</td>\n",
       "      <td>36779.554531</td>\n",
       "      <td>41344.410508</td>\n",
       "      <td>46463.711484</td>\n",
       "      <td>52212.429531</td>\n",
       "      <td>58661.142344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>65</td>\n",
       "      <td>3754.453151</td>\n",
       "      <td>4.136069</td>\n",
       "      <td>2.900202</td>\n",
       "      <td>1787.771840</td>\n",
       "      <td>1893.016733</td>\n",
       "      <td>2818.411074</td>\n",
       "      <td>1542.522104</td>\n",
       "      <td>2246.952313</td>\n",
       "      <td>...</td>\n",
       "      <td>4223.781546</td>\n",
       "      <td>4615.144614</td>\n",
       "      <td>5045.280631</td>\n",
       "      <td>5520.831567</td>\n",
       "      <td>6044.115860</td>\n",
       "      <td>6611.085441</td>\n",
       "      <td>7231.857753</td>\n",
       "      <td>7913.697529</td>\n",
       "      <td>8657.308785</td>\n",
       "      <td>9475.725759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>450</th>\n",
       "      <td>5</td>\n",
       "      <td>51</td>\n",
       "      <td>2097.045676</td>\n",
       "      <td>14.781216</td>\n",
       "      <td>2.688458</td>\n",
       "      <td>2455.839335</td>\n",
       "      <td>2480.124636</td>\n",
       "      <td>2574.049871</td>\n",
       "      <td>2511.215039</td>\n",
       "      <td>2395.579990</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.071465</td>\n",
       "      <td>23074.956074</td>\n",
       "      <td>25926.207676</td>\n",
       "      <td>29135.754883</td>\n",
       "      <td>32743.289434</td>\n",
       "      <td>36780.388477</td>\n",
       "      <td>41343.607969</td>\n",
       "      <td>46459.794961</td>\n",
       "      <td>52204.491289</td>\n",
       "      <td>58646.683398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>451</th>\n",
       "      <td>5</td>\n",
       "      <td>35</td>\n",
       "      <td>2078.198020</td>\n",
       "      <td>19.385152</td>\n",
       "      <td>2.684518</td>\n",
       "      <td>2044.566279</td>\n",
       "      <td>2052.309283</td>\n",
       "      <td>2343.335254</td>\n",
       "      <td>2529.277934</td>\n",
       "      <td>2360.570479</td>\n",
       "      <td>...</td>\n",
       "      <td>20515.948887</td>\n",
       "      <td>23070.407505</td>\n",
       "      <td>25916.965068</td>\n",
       "      <td>29127.595225</td>\n",
       "      <td>32738.985176</td>\n",
       "      <td>36777.577871</td>\n",
       "      <td>41334.507256</td>\n",
       "      <td>46434.336172</td>\n",
       "      <td>52175.582588</td>\n",
       "      <td>58596.777002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>452</th>\n",
       "      <td>2</td>\n",
       "      <td>68</td>\n",
       "      <td>3672.405920</td>\n",
       "      <td>26.585923</td>\n",
       "      <td>2.772035</td>\n",
       "      <td>2040.649000</td>\n",
       "      <td>2573.163502</td>\n",
       "      <td>1292.780567</td>\n",
       "      <td>2079.696767</td>\n",
       "      <td>2355.948265</td>\n",
       "      <td>...</td>\n",
       "      <td>4384.635758</td>\n",
       "      <td>4792.584608</td>\n",
       "      <td>5241.195855</td>\n",
       "      <td>5734.702477</td>\n",
       "      <td>6275.782170</td>\n",
       "      <td>6869.952183</td>\n",
       "      <td>7510.868407</td>\n",
       "      <td>8221.208958</td>\n",
       "      <td>8994.294442</td>\n",
       "      <td>9843.708743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>453</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>2094.513127</td>\n",
       "      <td>16.977858</td>\n",
       "      <td>2.705836</td>\n",
       "      <td>2591.491630</td>\n",
       "      <td>2295.452470</td>\n",
       "      <td>2432.286576</td>\n",
       "      <td>2406.785838</td>\n",
       "      <td>2705.931007</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.289775</td>\n",
       "      <td>23073.814199</td>\n",
       "      <td>25925.970928</td>\n",
       "      <td>29138.137822</td>\n",
       "      <td>32746.070488</td>\n",
       "      <td>36781.718086</td>\n",
       "      <td>41348.267930</td>\n",
       "      <td>46455.386035</td>\n",
       "      <td>52207.608379</td>\n",
       "      <td>58647.802676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>5</td>\n",
       "      <td>40</td>\n",
       "      <td>2083.348434</td>\n",
       "      <td>21.551898</td>\n",
       "      <td>2.698208</td>\n",
       "      <td>2759.357112</td>\n",
       "      <td>2391.516056</td>\n",
       "      <td>2552.341865</td>\n",
       "      <td>2043.676110</td>\n",
       "      <td>2197.082350</td>\n",
       "      <td>...</td>\n",
       "      <td>20521.270671</td>\n",
       "      <td>23074.265576</td>\n",
       "      <td>25929.970017</td>\n",
       "      <td>29137.153210</td>\n",
       "      <td>32746.966450</td>\n",
       "      <td>36791.815923</td>\n",
       "      <td>41348.842178</td>\n",
       "      <td>46455.946401</td>\n",
       "      <td>52216.163403</td>\n",
       "      <td>58661.856567</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>455 rows × 222 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     group  sample        depth        por       den         ct_1  \\\n",
       "0        3      52  1660.178974  18.556209  2.740942  1971.579998   \n",
       "1        4      92  3890.779426   8.555400  2.834776  2513.180531   \n",
       "2        3      90  2287.441253  -0.169935  2.761468  2274.773580   \n",
       "3        3      49  2144.788740  28.192998  2.637605  1776.270868   \n",
       "4        2      65  3754.453151   4.136069  2.900202  1787.771840   \n",
       "..     ...     ...          ...        ...       ...          ...   \n",
       "450      5      51  2097.045676  14.781216  2.688458  2455.839335   \n",
       "451      5      35  2078.198020  19.385152  2.684518  2044.566279   \n",
       "452      2      68  3672.405920  26.585923  2.772035  2040.649000   \n",
       "453      5       6  2094.513127  16.977858  2.705836  2591.491630   \n",
       "454      5      40  2083.348434  21.551898  2.698208  2759.357112   \n",
       "\n",
       "            ct_2         ct_3         ct_4         ct_5  ...         pc_91  \\\n",
       "0    2396.714551  2799.219912  1951.977330  2041.857394  ...  20517.973164   \n",
       "1    3001.782975  2348.160682  2414.636280  2798.706138  ...   4178.079326   \n",
       "2    1083.899155  2974.647775  2713.863889  2381.094609  ...  20522.705605   \n",
       "3    2374.721334  2670.367528  2814.751969  2919.311685  ...  20522.544570   \n",
       "4    1893.016733  2818.411074  1542.522104  2246.952313  ...   4223.781546   \n",
       "..           ...          ...          ...          ...  ...           ...   \n",
       "450  2480.124636  2574.049871  2511.215039  2395.579990  ...  20522.071465   \n",
       "451  2052.309283  2343.335254  2529.277934  2360.570479  ...  20515.948887   \n",
       "452  2573.163502  1292.780567  2079.696767  2355.948265  ...   4384.635758   \n",
       "453  2295.452470  2432.286576  2406.785838  2705.931007  ...  20522.289775   \n",
       "454  2391.516056  2552.341865  2043.676110  2197.082350  ...  20521.270671   \n",
       "\n",
       "            pc_92         pc_93         pc_94         pc_95         pc_96  \\\n",
       "0    23072.031367  25918.199746  29130.680234  32741.818105  36776.940391   \n",
       "1     4564.280930   4987.905991   5457.903966   5976.209199   6537.572468   \n",
       "2    23075.290605  25927.208926  29136.474492  32743.575156  36780.525273   \n",
       "3    23075.227422  25928.721426  29137.418496  32742.759414  36779.554531   \n",
       "4     4615.144614   5045.280631   5520.831567   6044.115860   6611.085441   \n",
       "..            ...           ...           ...           ...           ...   \n",
       "450  23074.956074  25926.207676  29135.754883  32743.289434  36780.388477   \n",
       "451  23070.407505  25916.965068  29127.595225  32738.985176  36777.577871   \n",
       "452   4792.584608   5241.195855   5734.702477   6275.782170   6869.952183   \n",
       "453  23073.814199  25925.970928  29138.137822  32746.070488  36781.718086   \n",
       "454  23074.265576  25929.970017  29137.153210  32746.966450  36791.815923   \n",
       "\n",
       "            pc_97         pc_98         pc_99        pc_100  \n",
       "0    41337.948828  46440.194570  52182.348633  58608.434023  \n",
       "1     7149.014724   7826.130471   8559.884813   9368.567796  \n",
       "2    41344.256875  46461.810508  52207.803164  58651.855859  \n",
       "3    41344.410508  46463.711484  52212.429531  58661.142344  \n",
       "4     7231.857753   7913.697529   8657.308785   9475.725759  \n",
       "..            ...           ...           ...           ...  \n",
       "450  41343.607969  46459.794961  52204.491289  58646.683398  \n",
       "451  41334.507256  46434.336172  52175.582588  58596.777002  \n",
       "452   7510.868407   8221.208958   8994.294442   9843.708743  \n",
       "453  41348.267930  46455.386035  52207.608379  58647.802676  \n",
       "454  41348.842178  46455.946401  52216.163403  58661.856567  \n",
       "\n",
       "[455 rows x 222 columns]"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "train = pd.read_csv('train.csv'); train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "2c67ef18",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>group</th>\n",
       "      <th>sample</th>\n",
       "      <th>depth</th>\n",
       "      <th>por</th>\n",
       "      <th>den</th>\n",
       "      <th>ct_1</th>\n",
       "      <th>ct_2</th>\n",
       "      <th>ct_3</th>\n",
       "      <th>ct_4</th>\n",
       "      <th>ct_5</th>\n",
       "      <th>ct_6</th>\n",
       "      <th>ct_7</th>\n",
       "      <th>permeability</th>\n",
       "      <th>ntg</th>\n",
       "      <th>thickness_effective</th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "      <th>lithology</th>\n",
       "      <th>gr</th>\n",
       "      <th>rhob</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>52</td>\n",
       "      <td>1660.178974</td>\n",
       "      <td>18.556209</td>\n",
       "      <td>2.740942</td>\n",
       "      <td>1971.579998</td>\n",
       "      <td>2396.714551</td>\n",
       "      <td>2799.219912</td>\n",
       "      <td>1951.977330</td>\n",
       "      <td>2041.857394</td>\n",
       "      <td>2442.840273</td>\n",
       "      <td>2318.618853</td>\n",
       "      <td>6.425410</td>\n",
       "      <td>0.106890</td>\n",
       "      <td>5.658985</td>\n",
       "      <td>18985</td>\n",
       "      <td>5423</td>\n",
       "      <td>limestone</td>\n",
       "      <td>37.738168</td>\n",
       "      <td>2.664759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>92</td>\n",
       "      <td>3890.779426</td>\n",
       "      <td>8.555400</td>\n",
       "      <td>2.834776</td>\n",
       "      <td>2513.180531</td>\n",
       "      <td>3001.782975</td>\n",
       "      <td>2348.160682</td>\n",
       "      <td>2414.636280</td>\n",
       "      <td>2798.706138</td>\n",
       "      <td>3035.549168</td>\n",
       "      <td>2729.578887</td>\n",
       "      <td>14.300516</td>\n",
       "      <td>0.718312</td>\n",
       "      <td>4.483886</td>\n",
       "      <td>16790</td>\n",
       "      <td>3644</td>\n",
       "      <td>shale</td>\n",
       "      <td>42.371106</td>\n",
       "      <td>2.760788</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>90</td>\n",
       "      <td>2287.441253</td>\n",
       "      <td>-0.169935</td>\n",
       "      <td>2.761468</td>\n",
       "      <td>2274.773580</td>\n",
       "      <td>1083.899155</td>\n",
       "      <td>2974.647775</td>\n",
       "      <td>2713.863889</td>\n",
       "      <td>2381.094609</td>\n",
       "      <td>2085.069195</td>\n",
       "      <td>2747.971468</td>\n",
       "      <td>12.825353</td>\n",
       "      <td>0.639979</td>\n",
       "      <td>6.349391</td>\n",
       "      <td>18985</td>\n",
       "      <td>5423</td>\n",
       "      <td>sandstone</td>\n",
       "      <td>42.931089</td>\n",
       "      <td>2.624635</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>49</td>\n",
       "      <td>2144.788740</td>\n",
       "      <td>28.192998</td>\n",
       "      <td>2.637605</td>\n",
       "      <td>1776.270868</td>\n",
       "      <td>2374.721334</td>\n",
       "      <td>2670.367528</td>\n",
       "      <td>2814.751969</td>\n",
       "      <td>2919.311685</td>\n",
       "      <td>2016.024319</td>\n",
       "      <td>2546.626337</td>\n",
       "      <td>13.320168</td>\n",
       "      <td>0.288901</td>\n",
       "      <td>3.819145</td>\n",
       "      <td>18985</td>\n",
       "      <td>5423</td>\n",
       "      <td>limestone</td>\n",
       "      <td>39.485022</td>\n",
       "      <td>2.634539</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>65</td>\n",
       "      <td>3754.453151</td>\n",
       "      <td>4.136069</td>\n",
       "      <td>2.900202</td>\n",
       "      <td>1787.771840</td>\n",
       "      <td>1893.016733</td>\n",
       "      <td>2818.411074</td>\n",
       "      <td>1542.522104</td>\n",
       "      <td>2246.952313</td>\n",
       "      <td>1943.089817</td>\n",
       "      <td>1561.393112</td>\n",
       "      <td>7.183351</td>\n",
       "      <td>0.500868</td>\n",
       "      <td>6.593625</td>\n",
       "      <td>16169</td>\n",
       "      <td>5288</td>\n",
       "      <td>siltstome</td>\n",
       "      <td>34.846060</td>\n",
       "      <td>2.459622</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>450</th>\n",
       "      <td>5</td>\n",
       "      <td>51</td>\n",
       "      <td>2097.045676</td>\n",
       "      <td>14.781216</td>\n",
       "      <td>2.688458</td>\n",
       "      <td>2455.839335</td>\n",
       "      <td>2480.124636</td>\n",
       "      <td>2574.049871</td>\n",
       "      <td>2511.215039</td>\n",
       "      <td>2395.579990</td>\n",
       "      <td>2439.147140</td>\n",
       "      <td>2089.051532</td>\n",
       "      <td>41.015660</td>\n",
       "      <td>0.709441</td>\n",
       "      <td>7.313445</td>\n",
       "      <td>19850</td>\n",
       "      <td>3873</td>\n",
       "      <td>limestone</td>\n",
       "      <td>30.240244</td>\n",
       "      <td>2.562103</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>451</th>\n",
       "      <td>5</td>\n",
       "      <td>35</td>\n",
       "      <td>2078.198020</td>\n",
       "      <td>19.385152</td>\n",
       "      <td>2.684518</td>\n",
       "      <td>2044.566279</td>\n",
       "      <td>2052.309283</td>\n",
       "      <td>2343.335254</td>\n",
       "      <td>2529.277934</td>\n",
       "      <td>2360.570479</td>\n",
       "      <td>2256.546050</td>\n",
       "      <td>2663.343376</td>\n",
       "      <td>1.366440</td>\n",
       "      <td>0.554834</td>\n",
       "      <td>8.669671</td>\n",
       "      <td>19850</td>\n",
       "      <td>3873</td>\n",
       "      <td>limestone</td>\n",
       "      <td>14.771108</td>\n",
       "      <td>2.617332</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>452</th>\n",
       "      <td>2</td>\n",
       "      <td>68</td>\n",
       "      <td>3672.405920</td>\n",
       "      <td>26.585923</td>\n",
       "      <td>2.772035</td>\n",
       "      <td>2040.649000</td>\n",
       "      <td>2573.163502</td>\n",
       "      <td>1292.780567</td>\n",
       "      <td>2079.696767</td>\n",
       "      <td>2355.948265</td>\n",
       "      <td>2281.831720</td>\n",
       "      <td>2071.560649</td>\n",
       "      <td>3.371203</td>\n",
       "      <td>0.786869</td>\n",
       "      <td>4.971094</td>\n",
       "      <td>16169</td>\n",
       "      <td>5288</td>\n",
       "      <td>sandstone</td>\n",
       "      <td>41.162699</td>\n",
       "      <td>2.687207</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>453</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>2094.513127</td>\n",
       "      <td>16.977858</td>\n",
       "      <td>2.705836</td>\n",
       "      <td>2591.491630</td>\n",
       "      <td>2295.452470</td>\n",
       "      <td>2432.286576</td>\n",
       "      <td>2406.785838</td>\n",
       "      <td>2705.931007</td>\n",
       "      <td>2400.377198</td>\n",
       "      <td>2512.672454</td>\n",
       "      <td>16.081238</td>\n",
       "      <td>0.671111</td>\n",
       "      <td>7.022591</td>\n",
       "      <td>19850</td>\n",
       "      <td>3873</td>\n",
       "      <td>sandstone</td>\n",
       "      <td>37.093964</td>\n",
       "      <td>2.653836</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>5</td>\n",
       "      <td>40</td>\n",
       "      <td>2083.348434</td>\n",
       "      <td>21.551898</td>\n",
       "      <td>2.698208</td>\n",
       "      <td>2759.357112</td>\n",
       "      <td>2391.516056</td>\n",
       "      <td>2552.341865</td>\n",
       "      <td>2043.676110</td>\n",
       "      <td>2197.082350</td>\n",
       "      <td>2635.710708</td>\n",
       "      <td>2602.250347</td>\n",
       "      <td>6.585460</td>\n",
       "      <td>0.791506</td>\n",
       "      <td>4.847459</td>\n",
       "      <td>19850</td>\n",
       "      <td>3873</td>\n",
       "      <td>limestone</td>\n",
       "      <td>29.943692</td>\n",
       "      <td>2.578852</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>455 rows × 20 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     group  sample        depth        por       den         ct_1  \\\n",
       "0        3      52  1660.178974  18.556209  2.740942  1971.579998   \n",
       "1        4      92  3890.779426   8.555400  2.834776  2513.180531   \n",
       "2        3      90  2287.441253  -0.169935  2.761468  2274.773580   \n",
       "3        3      49  2144.788740  28.192998  2.637605  1776.270868   \n",
       "4        2      65  3754.453151   4.136069  2.900202  1787.771840   \n",
       "..     ...     ...          ...        ...       ...          ...   \n",
       "450      5      51  2097.045676  14.781216  2.688458  2455.839335   \n",
       "451      5      35  2078.198020  19.385152  2.684518  2044.566279   \n",
       "452      2      68  3672.405920  26.585923  2.772035  2040.649000   \n",
       "453      5       6  2094.513127  16.977858  2.705836  2591.491630   \n",
       "454      5      40  2083.348434  21.551898  2.698208  2759.357112   \n",
       "\n",
       "            ct_2         ct_3         ct_4         ct_5         ct_6  \\\n",
       "0    2396.714551  2799.219912  1951.977330  2041.857394  2442.840273   \n",
       "1    3001.782975  2348.160682  2414.636280  2798.706138  3035.549168   \n",
       "2    1083.899155  2974.647775  2713.863889  2381.094609  2085.069195   \n",
       "3    2374.721334  2670.367528  2814.751969  2919.311685  2016.024319   \n",
       "4    1893.016733  2818.411074  1542.522104  2246.952313  1943.089817   \n",
       "..           ...          ...          ...          ...          ...   \n",
       "450  2480.124636  2574.049871  2511.215039  2395.579990  2439.147140   \n",
       "451  2052.309283  2343.335254  2529.277934  2360.570479  2256.546050   \n",
       "452  2573.163502  1292.780567  2079.696767  2355.948265  2281.831720   \n",
       "453  2295.452470  2432.286576  2406.785838  2705.931007  2400.377198   \n",
       "454  2391.516056  2552.341865  2043.676110  2197.082350  2635.710708   \n",
       "\n",
       "            ct_7  permeability       ntg  thickness_effective      x     y  \\\n",
       "0    2318.618853      6.425410  0.106890             5.658985  18985  5423   \n",
       "1    2729.578887     14.300516  0.718312             4.483886  16790  3644   \n",
       "2    2747.971468     12.825353  0.639979             6.349391  18985  5423   \n",
       "3    2546.626337     13.320168  0.288901             3.819145  18985  5423   \n",
       "4    1561.393112      7.183351  0.500868             6.593625  16169  5288   \n",
       "..           ...           ...       ...                  ...    ...   ...   \n",
       "450  2089.051532     41.015660  0.709441             7.313445  19850  3873   \n",
       "451  2663.343376      1.366440  0.554834             8.669671  19850  3873   \n",
       "452  2071.560649      3.371203  0.786869             4.971094  16169  5288   \n",
       "453  2512.672454     16.081238  0.671111             7.022591  19850  3873   \n",
       "454  2602.250347      6.585460  0.791506             4.847459  19850  3873   \n",
       "\n",
       "     lithology         gr      rhob  \n",
       "0    limestone  37.738168  2.664759  \n",
       "1        shale  42.371106  2.760788  \n",
       "2    sandstone  42.931089  2.624635  \n",
       "3    limestone  39.485022  2.634539  \n",
       "4    siltstome  34.846060  2.459622  \n",
       "..         ...        ...       ...  \n",
       "450  limestone  30.240244  2.562103  \n",
       "451  limestone  14.771108  2.617332  \n",
       "452  sandstone  41.162699  2.687207  \n",
       "453  sandstone  37.093964  2.653836  \n",
       "454  limestone  29.943692  2.578852  \n",
       "\n",
       "[455 rows x 20 columns]"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "geology = train.iloc[:, :20]; geology"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f3e121ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pc_0</th>\n",
       "      <th>pc_1</th>\n",
       "      <th>pc_2</th>\n",
       "      <th>pc_3</th>\n",
       "      <th>pc_4</th>\n",
       "      <th>pc_5</th>\n",
       "      <th>pc_6</th>\n",
       "      <th>pc_7</th>\n",
       "      <th>pc_8</th>\n",
       "      <th>pc_9</th>\n",
       "      <th>...</th>\n",
       "      <th>pc_91</th>\n",
       "      <th>pc_92</th>\n",
       "      <th>pc_93</th>\n",
       "      <th>pc_94</th>\n",
       "      <th>pc_95</th>\n",
       "      <th>pc_96</th>\n",
       "      <th>pc_97</th>\n",
       "      <th>pc_98</th>\n",
       "      <th>pc_99</th>\n",
       "      <th>pc_100</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.535189</td>\n",
       "      <td>0.595750</td>\n",
       "      <td>0.665606</td>\n",
       "      <td>0.745420</td>\n",
       "      <td>0.835103</td>\n",
       "      <td>0.932039</td>\n",
       "      <td>1.038247</td>\n",
       "      <td>1.156261</td>\n",
       "      <td>1.292918</td>\n",
       "      <td>1.448585</td>\n",
       "      <td>...</td>\n",
       "      <td>20517.973164</td>\n",
       "      <td>23072.031367</td>\n",
       "      <td>25918.199746</td>\n",
       "      <td>29130.680234</td>\n",
       "      <td>32741.818105</td>\n",
       "      <td>36776.940391</td>\n",
       "      <td>41337.948828</td>\n",
       "      <td>46440.194570</td>\n",
       "      <td>52182.348633</td>\n",
       "      <td>58608.434023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.908788</td>\n",
       "      <td>1.038644</td>\n",
       "      <td>1.168391</td>\n",
       "      <td>1.298765</td>\n",
       "      <td>1.437975</td>\n",
       "      <td>1.558354</td>\n",
       "      <td>1.814425</td>\n",
       "      <td>1.966166</td>\n",
       "      <td>2.169002</td>\n",
       "      <td>2.359788</td>\n",
       "      <td>...</td>\n",
       "      <td>4178.079326</td>\n",
       "      <td>4564.280930</td>\n",
       "      <td>4987.905991</td>\n",
       "      <td>5457.903966</td>\n",
       "      <td>5976.209199</td>\n",
       "      <td>6537.572468</td>\n",
       "      <td>7149.014724</td>\n",
       "      <td>7826.130471</td>\n",
       "      <td>8559.884813</td>\n",
       "      <td>9368.567796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.531813</td>\n",
       "      <td>0.591931</td>\n",
       "      <td>0.661652</td>\n",
       "      <td>0.741723</td>\n",
       "      <td>0.831225</td>\n",
       "      <td>0.928339</td>\n",
       "      <td>1.035978</td>\n",
       "      <td>1.155482</td>\n",
       "      <td>1.291775</td>\n",
       "      <td>1.447311</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.705605</td>\n",
       "      <td>23075.290605</td>\n",
       "      <td>25927.208926</td>\n",
       "      <td>29136.474492</td>\n",
       "      <td>32743.575156</td>\n",
       "      <td>36780.525273</td>\n",
       "      <td>41344.256875</td>\n",
       "      <td>46461.810508</td>\n",
       "      <td>52207.803164</td>\n",
       "      <td>58651.855859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.530184</td>\n",
       "      <td>0.590141</td>\n",
       "      <td>0.659933</td>\n",
       "      <td>0.740125</td>\n",
       "      <td>0.829539</td>\n",
       "      <td>0.926774</td>\n",
       "      <td>1.034327</td>\n",
       "      <td>1.154018</td>\n",
       "      <td>1.290386</td>\n",
       "      <td>1.445932</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.544570</td>\n",
       "      <td>23075.227422</td>\n",
       "      <td>25928.721426</td>\n",
       "      <td>29137.418496</td>\n",
       "      <td>32742.759414</td>\n",
       "      <td>36779.554531</td>\n",
       "      <td>41344.410508</td>\n",
       "      <td>46463.711484</td>\n",
       "      <td>52212.429531</td>\n",
       "      <td>58661.142344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.908399</td>\n",
       "      <td>1.037779</td>\n",
       "      <td>1.167289</td>\n",
       "      <td>1.297142</td>\n",
       "      <td>1.436113</td>\n",
       "      <td>1.557094</td>\n",
       "      <td>1.813521</td>\n",
       "      <td>1.964542</td>\n",
       "      <td>2.168307</td>\n",
       "      <td>2.358832</td>\n",
       "      <td>...</td>\n",
       "      <td>4223.781546</td>\n",
       "      <td>4615.144614</td>\n",
       "      <td>5045.280631</td>\n",
       "      <td>5520.831567</td>\n",
       "      <td>6044.115860</td>\n",
       "      <td>6611.085441</td>\n",
       "      <td>7231.857753</td>\n",
       "      <td>7913.697529</td>\n",
       "      <td>8657.308785</td>\n",
       "      <td>9475.725759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>450</th>\n",
       "      <td>0.532050</td>\n",
       "      <td>0.592537</td>\n",
       "      <td>0.662303</td>\n",
       "      <td>0.742076</td>\n",
       "      <td>0.831483</td>\n",
       "      <td>0.928488</td>\n",
       "      <td>1.036162</td>\n",
       "      <td>1.155606</td>\n",
       "      <td>1.291590</td>\n",
       "      <td>1.447329</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.071465</td>\n",
       "      <td>23074.956074</td>\n",
       "      <td>25926.207676</td>\n",
       "      <td>29135.754883</td>\n",
       "      <td>32743.289434</td>\n",
       "      <td>36780.388477</td>\n",
       "      <td>41343.607969</td>\n",
       "      <td>46459.794961</td>\n",
       "      <td>52204.491289</td>\n",
       "      <td>58646.683398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>451</th>\n",
       "      <td>0.535261</td>\n",
       "      <td>0.596386</td>\n",
       "      <td>0.666660</td>\n",
       "      <td>0.745552</td>\n",
       "      <td>0.834887</td>\n",
       "      <td>0.932013</td>\n",
       "      <td>1.038366</td>\n",
       "      <td>1.156286</td>\n",
       "      <td>1.292117</td>\n",
       "      <td>1.448102</td>\n",
       "      <td>...</td>\n",
       "      <td>20515.948887</td>\n",
       "      <td>23070.407505</td>\n",
       "      <td>25916.965068</td>\n",
       "      <td>29127.595225</td>\n",
       "      <td>32738.985176</td>\n",
       "      <td>36777.577871</td>\n",
       "      <td>41334.507256</td>\n",
       "      <td>46434.336172</td>\n",
       "      <td>52175.582588</td>\n",
       "      <td>58596.777002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>452</th>\n",
       "      <td>0.908082</td>\n",
       "      <td>1.037725</td>\n",
       "      <td>1.166750</td>\n",
       "      <td>1.297510</td>\n",
       "      <td>1.436421</td>\n",
       "      <td>1.557271</td>\n",
       "      <td>1.813146</td>\n",
       "      <td>1.964591</td>\n",
       "      <td>2.167796</td>\n",
       "      <td>2.358566</td>\n",
       "      <td>...</td>\n",
       "      <td>4384.635758</td>\n",
       "      <td>4792.584608</td>\n",
       "      <td>5241.195855</td>\n",
       "      <td>5734.702477</td>\n",
       "      <td>6275.782170</td>\n",
       "      <td>6869.952183</td>\n",
       "      <td>7510.868407</td>\n",
       "      <td>8221.208958</td>\n",
       "      <td>8994.294442</td>\n",
       "      <td>9843.708743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>453</th>\n",
       "      <td>0.534512</td>\n",
       "      <td>0.593998</td>\n",
       "      <td>0.663882</td>\n",
       "      <td>0.744470</td>\n",
       "      <td>0.834432</td>\n",
       "      <td>0.932015</td>\n",
       "      <td>1.038154</td>\n",
       "      <td>1.156274</td>\n",
       "      <td>1.293843</td>\n",
       "      <td>1.448943</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.289775</td>\n",
       "      <td>23073.814199</td>\n",
       "      <td>25925.970928</td>\n",
       "      <td>29138.137822</td>\n",
       "      <td>32746.070488</td>\n",
       "      <td>36781.718086</td>\n",
       "      <td>41348.267930</td>\n",
       "      <td>46455.386035</td>\n",
       "      <td>52207.608379</td>\n",
       "      <td>58647.802676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>0.530512</td>\n",
       "      <td>0.589967</td>\n",
       "      <td>0.661031</td>\n",
       "      <td>0.740283</td>\n",
       "      <td>0.829952</td>\n",
       "      <td>0.928524</td>\n",
       "      <td>1.035100</td>\n",
       "      <td>1.154249</td>\n",
       "      <td>1.290490</td>\n",
       "      <td>1.445513</td>\n",
       "      <td>...</td>\n",
       "      <td>20521.270671</td>\n",
       "      <td>23074.265576</td>\n",
       "      <td>25929.970017</td>\n",
       "      <td>29137.153210</td>\n",
       "      <td>32746.966450</td>\n",
       "      <td>36791.815923</td>\n",
       "      <td>41348.842178</td>\n",
       "      <td>46455.946401</td>\n",
       "      <td>52216.163403</td>\n",
       "      <td>58661.856567</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>455 rows × 101 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         pc_0      pc_1      pc_2      pc_3      pc_4      pc_5      pc_6  \\\n",
       "0    0.535189  0.595750  0.665606  0.745420  0.835103  0.932039  1.038247   \n",
       "1    0.908788  1.038644  1.168391  1.298765  1.437975  1.558354  1.814425   \n",
       "2    0.531813  0.591931  0.661652  0.741723  0.831225  0.928339  1.035978   \n",
       "3    0.530184  0.590141  0.659933  0.740125  0.829539  0.926774  1.034327   \n",
       "4    0.908399  1.037779  1.167289  1.297142  1.436113  1.557094  1.813521   \n",
       "..        ...       ...       ...       ...       ...       ...       ...   \n",
       "450  0.532050  0.592537  0.662303  0.742076  0.831483  0.928488  1.036162   \n",
       "451  0.535261  0.596386  0.666660  0.745552  0.834887  0.932013  1.038366   \n",
       "452  0.908082  1.037725  1.166750  1.297510  1.436421  1.557271  1.813146   \n",
       "453  0.534512  0.593998  0.663882  0.744470  0.834432  0.932015  1.038154   \n",
       "454  0.530512  0.589967  0.661031  0.740283  0.829952  0.928524  1.035100   \n",
       "\n",
       "         pc_7      pc_8      pc_9  ...         pc_91         pc_92  \\\n",
       "0    1.156261  1.292918  1.448585  ...  20517.973164  23072.031367   \n",
       "1    1.966166  2.169002  2.359788  ...   4178.079326   4564.280930   \n",
       "2    1.155482  1.291775  1.447311  ...  20522.705605  23075.290605   \n",
       "3    1.154018  1.290386  1.445932  ...  20522.544570  23075.227422   \n",
       "4    1.964542  2.168307  2.358832  ...   4223.781546   4615.144614   \n",
       "..        ...       ...       ...  ...           ...           ...   \n",
       "450  1.155606  1.291590  1.447329  ...  20522.071465  23074.956074   \n",
       "451  1.156286  1.292117  1.448102  ...  20515.948887  23070.407505   \n",
       "452  1.964591  2.167796  2.358566  ...   4384.635758   4792.584608   \n",
       "453  1.156274  1.293843  1.448943  ...  20522.289775  23073.814199   \n",
       "454  1.154249  1.290490  1.445513  ...  20521.270671  23074.265576   \n",
       "\n",
       "            pc_93         pc_94         pc_95         pc_96         pc_97  \\\n",
       "0    25918.199746  29130.680234  32741.818105  36776.940391  41337.948828   \n",
       "1     4987.905991   5457.903966   5976.209199   6537.572468   7149.014724   \n",
       "2    25927.208926  29136.474492  32743.575156  36780.525273  41344.256875   \n",
       "3    25928.721426  29137.418496  32742.759414  36779.554531  41344.410508   \n",
       "4     5045.280631   5520.831567   6044.115860   6611.085441   7231.857753   \n",
       "..            ...           ...           ...           ...           ...   \n",
       "450  25926.207676  29135.754883  32743.289434  36780.388477  41343.607969   \n",
       "451  25916.965068  29127.595225  32738.985176  36777.577871  41334.507256   \n",
       "452   5241.195855   5734.702477   6275.782170   6869.952183   7510.868407   \n",
       "453  25925.970928  29138.137822  32746.070488  36781.718086  41348.267930   \n",
       "454  25929.970017  29137.153210  32746.966450  36791.815923  41348.842178   \n",
       "\n",
       "            pc_98         pc_99        pc_100  \n",
       "0    46440.194570  52182.348633  58608.434023  \n",
       "1     7826.130471   8559.884813   9368.567796  \n",
       "2    46461.810508  52207.803164  58651.855859  \n",
       "3    46463.711484  52212.429531  58661.142344  \n",
       "4     7913.697529   8657.308785   9475.725759  \n",
       "..            ...           ...           ...  \n",
       "450  46459.794961  52204.491289  58646.683398  \n",
       "451  46434.336172  52175.582588  58596.777002  \n",
       "452   8221.208958   8994.294442   9843.708743  \n",
       "453  46455.386035  52207.608379  58647.802676  \n",
       "454  46455.946401  52216.163403  58661.856567  \n",
       "\n",
       "[455 rows x 101 columns]"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pressure = train.filter(regex='^pc_'); pressure"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "eaf29f57",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>group</th>\n",
       "      <th>sample</th>\n",
       "      <th>depth</th>\n",
       "      <th>por</th>\n",
       "      <th>den</th>\n",
       "      <th>ct_1</th>\n",
       "      <th>ct_2</th>\n",
       "      <th>ct_3</th>\n",
       "      <th>ct_4</th>\n",
       "      <th>ct_5</th>\n",
       "      <th>...</th>\n",
       "      <th>pc_91</th>\n",
       "      <th>pc_92</th>\n",
       "      <th>pc_93</th>\n",
       "      <th>pc_94</th>\n",
       "      <th>pc_95</th>\n",
       "      <th>pc_96</th>\n",
       "      <th>pc_97</th>\n",
       "      <th>pc_98</th>\n",
       "      <th>pc_99</th>\n",
       "      <th>pc_100</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>52</td>\n",
       "      <td>1660.178974</td>\n",
       "      <td>18.556209</td>\n",
       "      <td>2.740942</td>\n",
       "      <td>1971.579998</td>\n",
       "      <td>2396.714551</td>\n",
       "      <td>2799.219912</td>\n",
       "      <td>1951.977330</td>\n",
       "      <td>2041.857394</td>\n",
       "      <td>...</td>\n",
       "      <td>20517.973164</td>\n",
       "      <td>23072.031367</td>\n",
       "      <td>25918.199746</td>\n",
       "      <td>29130.680234</td>\n",
       "      <td>32741.818105</td>\n",
       "      <td>36776.940391</td>\n",
       "      <td>41337.948828</td>\n",
       "      <td>46440.194570</td>\n",
       "      <td>52182.348633</td>\n",
       "      <td>58608.434023</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>92</td>\n",
       "      <td>3890.779426</td>\n",
       "      <td>8.555400</td>\n",
       "      <td>2.834776</td>\n",
       "      <td>2513.180531</td>\n",
       "      <td>3001.782975</td>\n",
       "      <td>2348.160682</td>\n",
       "      <td>2414.636280</td>\n",
       "      <td>2798.706138</td>\n",
       "      <td>...</td>\n",
       "      <td>4178.079326</td>\n",
       "      <td>4564.280930</td>\n",
       "      <td>4987.905991</td>\n",
       "      <td>5457.903966</td>\n",
       "      <td>5976.209199</td>\n",
       "      <td>6537.572468</td>\n",
       "      <td>7149.014724</td>\n",
       "      <td>7826.130471</td>\n",
       "      <td>8559.884813</td>\n",
       "      <td>9368.567796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>90</td>\n",
       "      <td>2287.441253</td>\n",
       "      <td>-0.169935</td>\n",
       "      <td>2.761468</td>\n",
       "      <td>2274.773580</td>\n",
       "      <td>1083.899155</td>\n",
       "      <td>2974.647775</td>\n",
       "      <td>2713.863889</td>\n",
       "      <td>2381.094609</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.705605</td>\n",
       "      <td>23075.290605</td>\n",
       "      <td>25927.208926</td>\n",
       "      <td>29136.474492</td>\n",
       "      <td>32743.575156</td>\n",
       "      <td>36780.525273</td>\n",
       "      <td>41344.256875</td>\n",
       "      <td>46461.810508</td>\n",
       "      <td>52207.803164</td>\n",
       "      <td>58651.855859</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>49</td>\n",
       "      <td>2144.788740</td>\n",
       "      <td>28.192998</td>\n",
       "      <td>2.637605</td>\n",
       "      <td>1776.270868</td>\n",
       "      <td>2374.721334</td>\n",
       "      <td>2670.367528</td>\n",
       "      <td>2814.751969</td>\n",
       "      <td>2919.311685</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.544570</td>\n",
       "      <td>23075.227422</td>\n",
       "      <td>25928.721426</td>\n",
       "      <td>29137.418496</td>\n",
       "      <td>32742.759414</td>\n",
       "      <td>36779.554531</td>\n",
       "      <td>41344.410508</td>\n",
       "      <td>46463.711484</td>\n",
       "      <td>52212.429531</td>\n",
       "      <td>58661.142344</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2</td>\n",
       "      <td>65</td>\n",
       "      <td>3754.453151</td>\n",
       "      <td>4.136069</td>\n",
       "      <td>2.900202</td>\n",
       "      <td>1787.771840</td>\n",
       "      <td>1893.016733</td>\n",
       "      <td>2818.411074</td>\n",
       "      <td>1542.522104</td>\n",
       "      <td>2246.952313</td>\n",
       "      <td>...</td>\n",
       "      <td>4223.781546</td>\n",
       "      <td>4615.144614</td>\n",
       "      <td>5045.280631</td>\n",
       "      <td>5520.831567</td>\n",
       "      <td>6044.115860</td>\n",
       "      <td>6611.085441</td>\n",
       "      <td>7231.857753</td>\n",
       "      <td>7913.697529</td>\n",
       "      <td>8657.308785</td>\n",
       "      <td>9475.725759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>450</th>\n",
       "      <td>5</td>\n",
       "      <td>51</td>\n",
       "      <td>2097.045676</td>\n",
       "      <td>14.781216</td>\n",
       "      <td>2.688458</td>\n",
       "      <td>2455.839335</td>\n",
       "      <td>2480.124636</td>\n",
       "      <td>2574.049871</td>\n",
       "      <td>2511.215039</td>\n",
       "      <td>2395.579990</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.071465</td>\n",
       "      <td>23074.956074</td>\n",
       "      <td>25926.207676</td>\n",
       "      <td>29135.754883</td>\n",
       "      <td>32743.289434</td>\n",
       "      <td>36780.388477</td>\n",
       "      <td>41343.607969</td>\n",
       "      <td>46459.794961</td>\n",
       "      <td>52204.491289</td>\n",
       "      <td>58646.683398</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>451</th>\n",
       "      <td>5</td>\n",
       "      <td>35</td>\n",
       "      <td>2078.198020</td>\n",
       "      <td>19.385152</td>\n",
       "      <td>2.684518</td>\n",
       "      <td>2044.566279</td>\n",
       "      <td>2052.309283</td>\n",
       "      <td>2343.335254</td>\n",
       "      <td>2529.277934</td>\n",
       "      <td>2360.570479</td>\n",
       "      <td>...</td>\n",
       "      <td>20515.948887</td>\n",
       "      <td>23070.407505</td>\n",
       "      <td>25916.965068</td>\n",
       "      <td>29127.595225</td>\n",
       "      <td>32738.985176</td>\n",
       "      <td>36777.577871</td>\n",
       "      <td>41334.507256</td>\n",
       "      <td>46434.336172</td>\n",
       "      <td>52175.582588</td>\n",
       "      <td>58596.777002</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>452</th>\n",
       "      <td>2</td>\n",
       "      <td>68</td>\n",
       "      <td>3672.405920</td>\n",
       "      <td>26.585923</td>\n",
       "      <td>2.772035</td>\n",
       "      <td>2040.649000</td>\n",
       "      <td>2573.163502</td>\n",
       "      <td>1292.780567</td>\n",
       "      <td>2079.696767</td>\n",
       "      <td>2355.948265</td>\n",
       "      <td>...</td>\n",
       "      <td>4384.635758</td>\n",
       "      <td>4792.584608</td>\n",
       "      <td>5241.195855</td>\n",
       "      <td>5734.702477</td>\n",
       "      <td>6275.782170</td>\n",
       "      <td>6869.952183</td>\n",
       "      <td>7510.868407</td>\n",
       "      <td>8221.208958</td>\n",
       "      <td>8994.294442</td>\n",
       "      <td>9843.708743</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>453</th>\n",
       "      <td>5</td>\n",
       "      <td>6</td>\n",
       "      <td>2094.513127</td>\n",
       "      <td>16.977858</td>\n",
       "      <td>2.705836</td>\n",
       "      <td>2591.491630</td>\n",
       "      <td>2295.452470</td>\n",
       "      <td>2432.286576</td>\n",
       "      <td>2406.785838</td>\n",
       "      <td>2705.931007</td>\n",
       "      <td>...</td>\n",
       "      <td>20522.289775</td>\n",
       "      <td>23073.814199</td>\n",
       "      <td>25925.970928</td>\n",
       "      <td>29138.137822</td>\n",
       "      <td>32746.070488</td>\n",
       "      <td>36781.718086</td>\n",
       "      <td>41348.267930</td>\n",
       "      <td>46455.386035</td>\n",
       "      <td>52207.608379</td>\n",
       "      <td>58647.802676</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>5</td>\n",
       "      <td>40</td>\n",
       "      <td>2083.348434</td>\n",
       "      <td>21.551898</td>\n",
       "      <td>2.698208</td>\n",
       "      <td>2759.357112</td>\n",
       "      <td>2391.516056</td>\n",
       "      <td>2552.341865</td>\n",
       "      <td>2043.676110</td>\n",
       "      <td>2197.082350</td>\n",
       "      <td>...</td>\n",
       "      <td>20521.270671</td>\n",
       "      <td>23074.265576</td>\n",
       "      <td>25929.970017</td>\n",
       "      <td>29137.153210</td>\n",
       "      <td>32746.966450</td>\n",
       "      <td>36791.815923</td>\n",
       "      <td>41348.842178</td>\n",
       "      <td>46455.946401</td>\n",
       "      <td>52216.163403</td>\n",
       "      <td>58661.856567</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>455 rows × 121 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     group  sample        depth        por       den         ct_1  \\\n",
       "0        3      52  1660.178974  18.556209  2.740942  1971.579998   \n",
       "1        4      92  3890.779426   8.555400  2.834776  2513.180531   \n",
       "2        3      90  2287.441253  -0.169935  2.761468  2274.773580   \n",
       "3        3      49  2144.788740  28.192998  2.637605  1776.270868   \n",
       "4        2      65  3754.453151   4.136069  2.900202  1787.771840   \n",
       "..     ...     ...          ...        ...       ...          ...   \n",
       "450      5      51  2097.045676  14.781216  2.688458  2455.839335   \n",
       "451      5      35  2078.198020  19.385152  2.684518  2044.566279   \n",
       "452      2      68  3672.405920  26.585923  2.772035  2040.649000   \n",
       "453      5       6  2094.513127  16.977858  2.705836  2591.491630   \n",
       "454      5      40  2083.348434  21.551898  2.698208  2759.357112   \n",
       "\n",
       "            ct_2         ct_3         ct_4         ct_5  ...         pc_91  \\\n",
       "0    2396.714551  2799.219912  1951.977330  2041.857394  ...  20517.973164   \n",
       "1    3001.782975  2348.160682  2414.636280  2798.706138  ...   4178.079326   \n",
       "2    1083.899155  2974.647775  2713.863889  2381.094609  ...  20522.705605   \n",
       "3    2374.721334  2670.367528  2814.751969  2919.311685  ...  20522.544570   \n",
       "4    1893.016733  2818.411074  1542.522104  2246.952313  ...   4223.781546   \n",
       "..           ...          ...          ...          ...  ...           ...   \n",
       "450  2480.124636  2574.049871  2511.215039  2395.579990  ...  20522.071465   \n",
       "451  2052.309283  2343.335254  2529.277934  2360.570479  ...  20515.948887   \n",
       "452  2573.163502  1292.780567  2079.696767  2355.948265  ...   4384.635758   \n",
       "453  2295.452470  2432.286576  2406.785838  2705.931007  ...  20522.289775   \n",
       "454  2391.516056  2552.341865  2043.676110  2197.082350  ...  20521.270671   \n",
       "\n",
       "            pc_92         pc_93         pc_94         pc_95         pc_96  \\\n",
       "0    23072.031367  25918.199746  29130.680234  32741.818105  36776.940391   \n",
       "1     4564.280930   4987.905991   5457.903966   5976.209199   6537.572468   \n",
       "2    23075.290605  25927.208926  29136.474492  32743.575156  36780.525273   \n",
       "3    23075.227422  25928.721426  29137.418496  32742.759414  36779.554531   \n",
       "4     4615.144614   5045.280631   5520.831567   6044.115860   6611.085441   \n",
       "..            ...           ...           ...           ...           ...   \n",
       "450  23074.956074  25926.207676  29135.754883  32743.289434  36780.388477   \n",
       "451  23070.407505  25916.965068  29127.595225  32738.985176  36777.577871   \n",
       "452   4792.584608   5241.195855   5734.702477   6275.782170   6869.952183   \n",
       "453  23073.814199  25925.970928  29138.137822  32746.070488  36781.718086   \n",
       "454  23074.265576  25929.970017  29137.153210  32746.966450  36791.815923   \n",
       "\n",
       "            pc_97         pc_98         pc_99        pc_100  \n",
       "0    41337.948828  46440.194570  52182.348633  58608.434023  \n",
       "1     7149.014724   7826.130471   8559.884813   9368.567796  \n",
       "2    41344.256875  46461.810508  52207.803164  58651.855859  \n",
       "3    41344.410508  46463.711484  52212.429531  58661.142344  \n",
       "4     7231.857753   7913.697529   8657.308785   9475.725759  \n",
       "..            ...           ...           ...           ...  \n",
       "450  41343.607969  46459.794961  52204.491289  58646.683398  \n",
       "451  41334.507256  46434.336172  52175.582588  58596.777002  \n",
       "452   7510.868407   8221.208958   8994.294442   9843.708743  \n",
       "453  41348.267930  46455.386035  52207.608379  58647.802676  \n",
       "454  41348.842178  46455.946401  52216.163403  58661.856567  \n",
       "\n",
       "[455 rows x 121 columns]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X = pd.concat([geology, pressure], axis=1); X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "b99dda6f",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>bv_0</th>\n",
       "      <th>bv_1</th>\n",
       "      <th>bv_2</th>\n",
       "      <th>bv_3</th>\n",
       "      <th>bv_4</th>\n",
       "      <th>bv_5</th>\n",
       "      <th>bv_6</th>\n",
       "      <th>bv_7</th>\n",
       "      <th>bv_8</th>\n",
       "      <th>bv_9</th>\n",
       "      <th>...</th>\n",
       "      <th>bv_91</th>\n",
       "      <th>bv_92</th>\n",
       "      <th>bv_93</th>\n",
       "      <th>bv_94</th>\n",
       "      <th>bv_95</th>\n",
       "      <th>bv_96</th>\n",
       "      <th>bv_97</th>\n",
       "      <th>bv_98</th>\n",
       "      <th>bv_99</th>\n",
       "      <th>bv_100</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>8.314193e-30</td>\n",
       "      <td>0.022937</td>\n",
       "      <td>0.175831</td>\n",
       "      <td>0.343738</td>\n",
       "      <td>0.457215</td>\n",
       "      <td>0.544975</td>\n",
       "      <td>0.619610</td>\n",
       "      <td>0.668326</td>\n",
       "      <td>0.714923</td>\n",
       "      <td>0.758957</td>\n",
       "      <td>...</td>\n",
       "      <td>18.272765</td>\n",
       "      <td>18.298018</td>\n",
       "      <td>18.320578</td>\n",
       "      <td>18.341130</td>\n",
       "      <td>18.359811</td>\n",
       "      <td>18.369696</td>\n",
       "      <td>18.377619</td>\n",
       "      <td>18.377846</td>\n",
       "      <td>18.378063</td>\n",
       "      <td>18.378261</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>8.404712e-30</td>\n",
       "      <td>0.065743</td>\n",
       "      <td>0.110847</td>\n",
       "      <td>0.149221</td>\n",
       "      <td>0.182478</td>\n",
       "      <td>0.207055</td>\n",
       "      <td>0.251148</td>\n",
       "      <td>0.264525</td>\n",
       "      <td>0.286616</td>\n",
       "      <td>0.296471</td>\n",
       "      <td>...</td>\n",
       "      <td>7.703552</td>\n",
       "      <td>7.729920</td>\n",
       "      <td>7.762970</td>\n",
       "      <td>7.786158</td>\n",
       "      <td>7.807564</td>\n",
       "      <td>7.832035</td>\n",
       "      <td>7.853543</td>\n",
       "      <td>7.873677</td>\n",
       "      <td>7.889946</td>\n",
       "      <td>7.903239</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>9.628115e-30</td>\n",
       "      <td>0.065462</td>\n",
       "      <td>0.126050</td>\n",
       "      <td>0.185575</td>\n",
       "      <td>0.236476</td>\n",
       "      <td>0.276897</td>\n",
       "      <td>0.326915</td>\n",
       "      <td>0.352935</td>\n",
       "      <td>0.379736</td>\n",
       "      <td>0.399494</td>\n",
       "      <td>...</td>\n",
       "      <td>3.323700</td>\n",
       "      <td>3.392507</td>\n",
       "      <td>3.455950</td>\n",
       "      <td>3.515671</td>\n",
       "      <td>3.572989</td>\n",
       "      <td>3.626552</td>\n",
       "      <td>3.677021</td>\n",
       "      <td>3.717735</td>\n",
       "      <td>3.751224</td>\n",
       "      <td>3.785149</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.001518e-29</td>\n",
       "      <td>0.035238</td>\n",
       "      <td>0.135762</td>\n",
       "      <td>0.260780</td>\n",
       "      <td>0.354239</td>\n",
       "      <td>0.437589</td>\n",
       "      <td>0.512409</td>\n",
       "      <td>0.573600</td>\n",
       "      <td>0.627993</td>\n",
       "      <td>0.674529</td>\n",
       "      <td>...</td>\n",
       "      <td>29.457616</td>\n",
       "      <td>29.462819</td>\n",
       "      <td>29.467363</td>\n",
       "      <td>29.471621</td>\n",
       "      <td>29.475390</td>\n",
       "      <td>29.477765</td>\n",
       "      <td>29.480009</td>\n",
       "      <td>29.482167</td>\n",
       "      <td>29.484013</td>\n",
       "      <td>29.485694</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.003009e-29</td>\n",
       "      <td>0.064098</td>\n",
       "      <td>0.117940</td>\n",
       "      <td>0.167830</td>\n",
       "      <td>0.213313</td>\n",
       "      <td>0.245085</td>\n",
       "      <td>0.286452</td>\n",
       "      <td>0.302900</td>\n",
       "      <td>0.324897</td>\n",
       "      <td>0.341102</td>\n",
       "      <td>...</td>\n",
       "      <td>3.721371</td>\n",
       "      <td>3.787876</td>\n",
       "      <td>3.844572</td>\n",
       "      <td>3.896132</td>\n",
       "      <td>3.944263</td>\n",
       "      <td>3.987842</td>\n",
       "      <td>4.027115</td>\n",
       "      <td>4.057976</td>\n",
       "      <td>4.080364</td>\n",
       "      <td>4.101747</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>450</th>\n",
       "      <td>8.405910e-30</td>\n",
       "      <td>0.011935</td>\n",
       "      <td>0.266474</td>\n",
       "      <td>0.392014</td>\n",
       "      <td>0.488393</td>\n",
       "      <td>0.561142</td>\n",
       "      <td>0.629793</td>\n",
       "      <td>0.674519</td>\n",
       "      <td>0.721665</td>\n",
       "      <td>0.761462</td>\n",
       "      <td>...</td>\n",
       "      <td>14.737324</td>\n",
       "      <td>14.754105</td>\n",
       "      <td>14.769177</td>\n",
       "      <td>14.782801</td>\n",
       "      <td>14.794812</td>\n",
       "      <td>14.805402</td>\n",
       "      <td>14.809196</td>\n",
       "      <td>14.809561</td>\n",
       "      <td>14.809862</td>\n",
       "      <td>14.810078</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>451</th>\n",
       "      <td>9.770500e-30</td>\n",
       "      <td>0.035415</td>\n",
       "      <td>0.148900</td>\n",
       "      <td>0.262791</td>\n",
       "      <td>0.349767</td>\n",
       "      <td>0.428302</td>\n",
       "      <td>0.524900</td>\n",
       "      <td>0.561232</td>\n",
       "      <td>0.611864</td>\n",
       "      <td>0.654517</td>\n",
       "      <td>...</td>\n",
       "      <td>19.464941</td>\n",
       "      <td>19.480960</td>\n",
       "      <td>19.495513</td>\n",
       "      <td>19.507846</td>\n",
       "      <td>19.517875</td>\n",
       "      <td>19.522732</td>\n",
       "      <td>19.525760</td>\n",
       "      <td>19.527513</td>\n",
       "      <td>19.529068</td>\n",
       "      <td>19.530144</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>452</th>\n",
       "      <td>9.858864e-30</td>\n",
       "      <td>0.035401</td>\n",
       "      <td>0.105316</td>\n",
       "      <td>0.252543</td>\n",
       "      <td>0.343569</td>\n",
       "      <td>0.436199</td>\n",
       "      <td>0.520484</td>\n",
       "      <td>0.579677</td>\n",
       "      <td>0.666790</td>\n",
       "      <td>0.735258</td>\n",
       "      <td>...</td>\n",
       "      <td>27.938931</td>\n",
       "      <td>27.943315</td>\n",
       "      <td>27.947413</td>\n",
       "      <td>27.951092</td>\n",
       "      <td>27.954383</td>\n",
       "      <td>27.956902</td>\n",
       "      <td>27.959231</td>\n",
       "      <td>27.961456</td>\n",
       "      <td>27.963561</td>\n",
       "      <td>27.965526</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>453</th>\n",
       "      <td>1.020829e-29</td>\n",
       "      <td>0.035444</td>\n",
       "      <td>0.181987</td>\n",
       "      <td>0.246770</td>\n",
       "      <td>0.296267</td>\n",
       "      <td>0.331121</td>\n",
       "      <td>0.381807</td>\n",
       "      <td>0.402956</td>\n",
       "      <td>0.436622</td>\n",
       "      <td>0.463018</td>\n",
       "      <td>...</td>\n",
       "      <td>15.804989</td>\n",
       "      <td>15.818642</td>\n",
       "      <td>15.830467</td>\n",
       "      <td>15.840493</td>\n",
       "      <td>15.845425</td>\n",
       "      <td>15.847699</td>\n",
       "      <td>15.848337</td>\n",
       "      <td>15.848766</td>\n",
       "      <td>15.849141</td>\n",
       "      <td>15.849408</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>1.126088e-29</td>\n",
       "      <td>0.041702</td>\n",
       "      <td>0.143468</td>\n",
       "      <td>0.244122</td>\n",
       "      <td>0.323763</td>\n",
       "      <td>0.397491</td>\n",
       "      <td>0.492625</td>\n",
       "      <td>0.538694</td>\n",
       "      <td>0.614895</td>\n",
       "      <td>0.679498</td>\n",
       "      <td>...</td>\n",
       "      <td>21.485961</td>\n",
       "      <td>21.496698</td>\n",
       "      <td>21.506562</td>\n",
       "      <td>21.514549</td>\n",
       "      <td>21.520342</td>\n",
       "      <td>21.524409</td>\n",
       "      <td>21.526741</td>\n",
       "      <td>21.528437</td>\n",
       "      <td>21.529944</td>\n",
       "      <td>21.531123</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>455 rows × 101 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             bv_0      bv_1      bv_2      bv_3      bv_4      bv_5      bv_6  \\\n",
       "0    8.314193e-30  0.022937  0.175831  0.343738  0.457215  0.544975  0.619610   \n",
       "1    8.404712e-30  0.065743  0.110847  0.149221  0.182478  0.207055  0.251148   \n",
       "2    9.628115e-30  0.065462  0.126050  0.185575  0.236476  0.276897  0.326915   \n",
       "3    1.001518e-29  0.035238  0.135762  0.260780  0.354239  0.437589  0.512409   \n",
       "4    1.003009e-29  0.064098  0.117940  0.167830  0.213313  0.245085  0.286452   \n",
       "..            ...       ...       ...       ...       ...       ...       ...   \n",
       "450  8.405910e-30  0.011935  0.266474  0.392014  0.488393  0.561142  0.629793   \n",
       "451  9.770500e-30  0.035415  0.148900  0.262791  0.349767  0.428302  0.524900   \n",
       "452  9.858864e-30  0.035401  0.105316  0.252543  0.343569  0.436199  0.520484   \n",
       "453  1.020829e-29  0.035444  0.181987  0.246770  0.296267  0.331121  0.381807   \n",
       "454  1.126088e-29  0.041702  0.143468  0.244122  0.323763  0.397491  0.492625   \n",
       "\n",
       "         bv_7      bv_8      bv_9  ...      bv_91      bv_92      bv_93  \\\n",
       "0    0.668326  0.714923  0.758957  ...  18.272765  18.298018  18.320578   \n",
       "1    0.264525  0.286616  0.296471  ...   7.703552   7.729920   7.762970   \n",
       "2    0.352935  0.379736  0.399494  ...   3.323700   3.392507   3.455950   \n",
       "3    0.573600  0.627993  0.674529  ...  29.457616  29.462819  29.467363   \n",
       "4    0.302900  0.324897  0.341102  ...   3.721371   3.787876   3.844572   \n",
       "..        ...       ...       ...  ...        ...        ...        ...   \n",
       "450  0.674519  0.721665  0.761462  ...  14.737324  14.754105  14.769177   \n",
       "451  0.561232  0.611864  0.654517  ...  19.464941  19.480960  19.495513   \n",
       "452  0.579677  0.666790  0.735258  ...  27.938931  27.943315  27.947413   \n",
       "453  0.402956  0.436622  0.463018  ...  15.804989  15.818642  15.830467   \n",
       "454  0.538694  0.614895  0.679498  ...  21.485961  21.496698  21.506562   \n",
       "\n",
       "         bv_94      bv_95      bv_96      bv_97      bv_98      bv_99  \\\n",
       "0    18.341130  18.359811  18.369696  18.377619  18.377846  18.378063   \n",
       "1     7.786158   7.807564   7.832035   7.853543   7.873677   7.889946   \n",
       "2     3.515671   3.572989   3.626552   3.677021   3.717735   3.751224   \n",
       "3    29.471621  29.475390  29.477765  29.480009  29.482167  29.484013   \n",
       "4     3.896132   3.944263   3.987842   4.027115   4.057976   4.080364   \n",
       "..         ...        ...        ...        ...        ...        ...   \n",
       "450  14.782801  14.794812  14.805402  14.809196  14.809561  14.809862   \n",
       "451  19.507846  19.517875  19.522732  19.525760  19.527513  19.529068   \n",
       "452  27.951092  27.954383  27.956902  27.959231  27.961456  27.963561   \n",
       "453  15.840493  15.845425  15.847699  15.848337  15.848766  15.849141   \n",
       "454  21.514549  21.520342  21.524409  21.526741  21.528437  21.529944   \n",
       "\n",
       "        bv_100  \n",
       "0    18.378261  \n",
       "1     7.903239  \n",
       "2     3.785149  \n",
       "3    29.485694  \n",
       "4     4.101747  \n",
       "..         ...  \n",
       "450  14.810078  \n",
       "451  19.530144  \n",
       "452  27.965526  \n",
       "453  15.849408  \n",
       "454  21.531123  \n",
       "\n",
       "[455 rows x 101 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y = train.filter(regex='^bv_'); y"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6a0e86bc",
   "metadata": {},
   "outputs": [],
   "source": [
    "class Preprocess():\n",
    "    def __init__(self):\n",
    "        pass\n",
    "    \n",
    "    def fit(self, X, y=None):\n",
    "        df = X.copy()\n",
    "        self.geology_cols = df.iloc[:, :20] \\\n",
    "            .drop(columns=['group', 'sample', 'lithology']) \\\n",
    "            .columns\n",
    "        self.pressure_cols = df.filter(regex='^pc_').columns\n",
    "        self.categoric_cols = df.select_dtypes(include='object').columns\n",
    "\n",
    "        ct = ColumnTransformer(\n",
    "            [\n",
    "                ('onehot', OneHotEncoder(handle_unknown='infrequent_if_exist', drop=None),\n",
    "                     self.categoric_cols),\n",
    "                ('scale', StandardScaler(), self.geology_cols)\n",
    "            ],\n",
    "            n_jobs=-1\n",
    "        )\n",
    "        self.transf = ct.fit(df)\n",
    "        self.features = ct.get_feature_names_out()\n",
    "        return self\n",
    "    \n",
    "    def transform(self, X, y=None):\n",
    "        df = X.copy().drop(columns=['group', 'sample'])\n",
    "        geology = pd.DataFrame(self.transf.transform(df), columns=self.features)\n",
    "        pressure = df[self.pressure_cols].apply(np.log)\n",
    "        return pd.concat([geology, pressure], axis=1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6fbe74a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "prep = Preprocess().fit(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "7a54d3f7",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>onehot__lithology_clay sandstone</th>\n",
       "      <th>onehot__lithology_limestone</th>\n",
       "      <th>onehot__lithology_sandstone</th>\n",
       "      <th>onehot__lithology_shale</th>\n",
       "      <th>onehot__lithology_siltstome</th>\n",
       "      <th>scale__depth</th>\n",
       "      <th>scale__por</th>\n",
       "      <th>scale__den</th>\n",
       "      <th>scale__ct_1</th>\n",
       "      <th>scale__ct_2</th>\n",
       "      <th>...</th>\n",
       "      <th>pc_91</th>\n",
       "      <th>pc_92</th>\n",
       "      <th>pc_93</th>\n",
       "      <th>pc_94</th>\n",
       "      <th>pc_95</th>\n",
       "      <th>pc_96</th>\n",
       "      <th>pc_97</th>\n",
       "      <th>pc_98</th>\n",
       "      <th>pc_99</th>\n",
       "      <th>pc_100</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-1.497434</td>\n",
       "      <td>0.249045</td>\n",
       "      <td>-0.111626</td>\n",
       "      <td>-1.219575</td>\n",
       "      <td>0.003803</td>\n",
       "      <td>...</td>\n",
       "      <td>9.929057</td>\n",
       "      <td>10.046376</td>\n",
       "      <td>10.162701</td>\n",
       "      <td>10.279547</td>\n",
       "      <td>10.396408</td>\n",
       "      <td>10.512626</td>\n",
       "      <td>10.629536</td>\n",
       "      <td>10.745921</td>\n",
       "      <td>10.862500</td>\n",
       "      <td>10.978634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.580383</td>\n",
       "      <td>-0.766025</td>\n",
       "      <td>1.035027</td>\n",
       "      <td>0.411760</td>\n",
       "      <td>1.682853</td>\n",
       "      <td>...</td>\n",
       "      <td>8.337607</td>\n",
       "      <td>8.426016</td>\n",
       "      <td>8.514771</td>\n",
       "      <td>8.604820</td>\n",
       "      <td>8.695542</td>\n",
       "      <td>8.785321</td>\n",
       "      <td>8.874730</td>\n",
       "      <td>8.965223</td>\n",
       "      <td>9.054842</td>\n",
       "      <td>9.145116</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.631928</td>\n",
       "      <td>-1.651635</td>\n",
       "      <td>0.139207</td>\n",
       "      <td>-0.306337</td>\n",
       "      <td>-3.639227</td>\n",
       "      <td>...</td>\n",
       "      <td>9.929287</td>\n",
       "      <td>10.046518</td>\n",
       "      <td>10.163048</td>\n",
       "      <td>10.279746</td>\n",
       "      <td>10.396462</td>\n",
       "      <td>10.512724</td>\n",
       "      <td>10.629689</td>\n",
       "      <td>10.746386</td>\n",
       "      <td>10.862987</td>\n",
       "      <td>10.979374</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.828762</td>\n",
       "      <td>1.227167</td>\n",
       "      <td>-1.374409</td>\n",
       "      <td>-1.807858</td>\n",
       "      <td>-0.057228</td>\n",
       "      <td>...</td>\n",
       "      <td>9.929279</td>\n",
       "      <td>10.046515</td>\n",
       "      <td>10.163107</td>\n",
       "      <td>10.279778</td>\n",
       "      <td>10.396437</td>\n",
       "      <td>10.512697</td>\n",
       "      <td>10.629693</td>\n",
       "      <td>10.746427</td>\n",
       "      <td>10.863076</td>\n",
       "      <td>10.979533</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.392278</td>\n",
       "      <td>-1.214581</td>\n",
       "      <td>1.834544</td>\n",
       "      <td>-1.773216</td>\n",
       "      <td>-1.393946</td>\n",
       "      <td>...</td>\n",
       "      <td>8.348486</td>\n",
       "      <td>8.437098</td>\n",
       "      <td>8.526209</td>\n",
       "      <td>8.616284</td>\n",
       "      <td>8.706840</td>\n",
       "      <td>8.796503</td>\n",
       "      <td>8.886251</td>\n",
       "      <td>8.976350</td>\n",
       "      <td>9.066159</td>\n",
       "      <td>9.156489</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>450</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.894639</td>\n",
       "      <td>-0.134112</td>\n",
       "      <td>-0.752990</td>\n",
       "      <td>0.239044</td>\n",
       "      <td>0.235264</td>\n",
       "      <td>...</td>\n",
       "      <td>9.929256</td>\n",
       "      <td>10.046503</td>\n",
       "      <td>10.163010</td>\n",
       "      <td>10.279721</td>\n",
       "      <td>10.396453</td>\n",
       "      <td>10.512720</td>\n",
       "      <td>10.629673</td>\n",
       "      <td>10.746343</td>\n",
       "      <td>10.862924</td>\n",
       "      <td>10.979286</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>451</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.920645</td>\n",
       "      <td>0.333181</td>\n",
       "      <td>-0.801132</td>\n",
       "      <td>-0.999735</td>\n",
       "      <td>-0.951913</td>\n",
       "      <td>...</td>\n",
       "      <td>9.928958</td>\n",
       "      <td>10.046306</td>\n",
       "      <td>10.162653</td>\n",
       "      <td>10.279441</td>\n",
       "      <td>10.396322</td>\n",
       "      <td>10.512644</td>\n",
       "      <td>10.629453</td>\n",
       "      <td>10.745794</td>\n",
       "      <td>10.862370</td>\n",
       "      <td>10.978435</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>452</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.279068</td>\n",
       "      <td>1.064050</td>\n",
       "      <td>0.268330</td>\n",
       "      <td>-1.011535</td>\n",
       "      <td>0.493444</td>\n",
       "      <td>...</td>\n",
       "      <td>8.385862</td>\n",
       "      <td>8.474825</td>\n",
       "      <td>8.564305</td>\n",
       "      <td>8.654291</td>\n",
       "      <td>8.744453</td>\n",
       "      <td>8.834912</td>\n",
       "      <td>8.924106</td>\n",
       "      <td>9.014473</td>\n",
       "      <td>9.104346</td>\n",
       "      <td>9.194588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>453</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.898133</td>\n",
       "      <td>0.088844</td>\n",
       "      <td>-0.540626</td>\n",
       "      <td>0.647638</td>\n",
       "      <td>-0.277197</td>\n",
       "      <td>...</td>\n",
       "      <td>9.929267</td>\n",
       "      <td>10.046454</td>\n",
       "      <td>10.163000</td>\n",
       "      <td>10.279803</td>\n",
       "      <td>10.396538</td>\n",
       "      <td>10.512756</td>\n",
       "      <td>10.629786</td>\n",
       "      <td>10.746248</td>\n",
       "      <td>10.862984</td>\n",
       "      <td>10.979305</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>454</th>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>-0.913539</td>\n",
       "      <td>0.553103</td>\n",
       "      <td>-0.633844</td>\n",
       "      <td>1.153259</td>\n",
       "      <td>-0.010623</td>\n",
       "      <td>...</td>\n",
       "      <td>9.929217</td>\n",
       "      <td>10.046473</td>\n",
       "      <td>10.163155</td>\n",
       "      <td>10.279769</td>\n",
       "      <td>10.396566</td>\n",
       "      <td>10.513031</td>\n",
       "      <td>10.629800</td>\n",
       "      <td>10.746260</td>\n",
       "      <td>10.863147</td>\n",
       "      <td>10.979545</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>455 rows × 123 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     onehot__lithology_clay sandstone  onehot__lithology_limestone  \\\n",
       "0                                 0.0                          1.0   \n",
       "1                                 0.0                          0.0   \n",
       "2                                 0.0                          0.0   \n",
       "3                                 0.0                          1.0   \n",
       "4                                 0.0                          0.0   \n",
       "..                                ...                          ...   \n",
       "450                               0.0                          1.0   \n",
       "451                               0.0                          1.0   \n",
       "452                               0.0                          0.0   \n",
       "453                               0.0                          0.0   \n",
       "454                               0.0                          1.0   \n",
       "\n",
       "     onehot__lithology_sandstone  onehot__lithology_shale  \\\n",
       "0                            0.0                      0.0   \n",
       "1                            0.0                      1.0   \n",
       "2                            1.0                      0.0   \n",
       "3                            0.0                      0.0   \n",
       "4                            0.0                      0.0   \n",
       "..                           ...                      ...   \n",
       "450                          0.0                      0.0   \n",
       "451                          0.0                      0.0   \n",
       "452                          1.0                      0.0   \n",
       "453                          1.0                      0.0   \n",
       "454                          0.0                      0.0   \n",
       "\n",
       "     onehot__lithology_siltstome  scale__depth  scale__por  scale__den  \\\n",
       "0                            0.0     -1.497434    0.249045   -0.111626   \n",
       "1                            0.0      1.580383   -0.766025    1.035027   \n",
       "2                            0.0     -0.631928   -1.651635    0.139207   \n",
       "3                            0.0     -0.828762    1.227167   -1.374409   \n",
       "4                            1.0      1.392278   -1.214581    1.834544   \n",
       "..                           ...           ...         ...         ...   \n",
       "450                          0.0     -0.894639   -0.134112   -0.752990   \n",
       "451                          0.0     -0.920645    0.333181   -0.801132   \n",
       "452                          0.0      1.279068    1.064050    0.268330   \n",
       "453                          0.0     -0.898133    0.088844   -0.540626   \n",
       "454                          0.0     -0.913539    0.553103   -0.633844   \n",
       "\n",
       "     scale__ct_1  scale__ct_2  ...     pc_91      pc_92      pc_93      pc_94  \\\n",
       "0      -1.219575     0.003803  ...  9.929057  10.046376  10.162701  10.279547   \n",
       "1       0.411760     1.682853  ...  8.337607   8.426016   8.514771   8.604820   \n",
       "2      -0.306337    -3.639227  ...  9.929287  10.046518  10.163048  10.279746   \n",
       "3      -1.807858    -0.057228  ...  9.929279  10.046515  10.163107  10.279778   \n",
       "4      -1.773216    -1.393946  ...  8.348486   8.437098   8.526209   8.616284   \n",
       "..           ...          ...  ...       ...        ...        ...        ...   \n",
       "450     0.239044     0.235264  ...  9.929256  10.046503  10.163010  10.279721   \n",
       "451    -0.999735    -0.951913  ...  9.928958  10.046306  10.162653  10.279441   \n",
       "452    -1.011535     0.493444  ...  8.385862   8.474825   8.564305   8.654291   \n",
       "453     0.647638    -0.277197  ...  9.929267  10.046454  10.163000  10.279803   \n",
       "454     1.153259    -0.010623  ...  9.929217  10.046473  10.163155  10.279769   \n",
       "\n",
       "         pc_95      pc_96      pc_97      pc_98      pc_99     pc_100  \n",
       "0    10.396408  10.512626  10.629536  10.745921  10.862500  10.978634  \n",
       "1     8.695542   8.785321   8.874730   8.965223   9.054842   9.145116  \n",
       "2    10.396462  10.512724  10.629689  10.746386  10.862987  10.979374  \n",
       "3    10.396437  10.512697  10.629693  10.746427  10.863076  10.979533  \n",
       "4     8.706840   8.796503   8.886251   8.976350   9.066159   9.156489  \n",
       "..         ...        ...        ...        ...        ...        ...  \n",
       "450  10.396453  10.512720  10.629673  10.746343  10.862924  10.979286  \n",
       "451  10.396322  10.512644  10.629453  10.745794  10.862370  10.978435  \n",
       "452   8.744453   8.834912   8.924106   9.014473   9.104346   9.194588  \n",
       "453  10.396538  10.512756  10.629786  10.746248  10.862984  10.979305  \n",
       "454  10.396566  10.513031  10.629800  10.746260  10.863147  10.979545  \n",
       "\n",
       "[455 rows x 123 columns]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_prep = prep.transform(X)\n",
    "X_prep"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "fda2f142",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_val, y_train, y_val = train_test_split(X_prep, y,\n",
    "                                                  test_size=45,\n",
    "                                                  random_state=8,\n",
    "                                                  shuffle=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ab79d111",
   "metadata": {},
   "source": [
    "# Baseline model. Ordinary least squares linear regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "12d17f47",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LinearRegression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "7fd23820",
   "metadata": {},
   "outputs": [],
   "source": [
    "lr = LinearRegression(n_jobs=-1).fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "8024db3f",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = lr.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "d373b5f3",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.5754477487658375"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_absolute_percentage_error(y_val, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cdd5e147",
   "metadata": {},
   "source": [
    "Example curve"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "f5e74f4f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAzYAAAPbCAYAAACOlR4dAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAACgHklEQVR4nOzdZ3hd1Zm38fuoS5Ys2VaxbMu94grYBlNN74SEDilkkpCZBDIZJiRDKslMIGUIzKS9mTRSgNAhdELvGBtcAPcqF1lu6l0674ctuYCNLelI+0i6f9d1rr1O2VuPSSzp77X2syLRaDSKJEmSJPVgCWEXIEmSJEmdZbCRJEmS1OMZbCRJkiT1eAYbSZIkST2ewUaSJElSj2ewkSRJktTjGWwkSZIk9XgGG0mSJEk9XlLYBXxQS0sLmzdvJisri0gkEnY5kiRJkkISjUaprKxkyJAhJCR89JxM3AWbzZs3U1RUFHYZkiRJkuJEcXExw4YN+8jPxF2wycrKAoLi+/fvH3I1kiRJksJSUVFBUVHR7ozwUeIu2LQtP+vfv7/BRpIkSdIh3aJi8wBJkiRJPZ7BRpIkSVKPZ7CRJEmS1OPF3T02kiRJUqw1NzfT2NgYdhnaj8TERJKSkjq91YvBRpIkSb1aVVUVGzduJBqNhl2KDiAjI4PCwkJSUlI6fA2DjSRJknqt5uZmNm7cSEZGBnl5eW4AH2ei0SgNDQ1s27aNtWvXMm7cuINuxHkgBhtJkiT1Wo2NjUSjUfLy8khPTw+7HO1Heno6ycnJrF+/noaGBtLS0jp0HZsHSJIkqddzpia+dXSWZp9rxKAOSZIkSQqVwUaSJElSj2ewkSRJkuLM3Llz+epXvxp2GTHRXX8Wg40kSZKkHs9gI0mSJOkjNTQ0hF3CQRlsJEmS1GdEo1FqGppCebR3g9CmpiauueYacnJyGDRoEN/+9reJRqPccMMNHH300R/6/LRp0/je97530OteddVVXHDBBXz/+98nPz+f/v3788UvfnGf8DJ37lyuueYarrvuOnJzcznttNMAeP/99zn77LPJzMykoKCAT33qU2zfvn33edXV1Xz6058mMzOTwsJCbrnllnb9mTvDfWwkSZLUZ9Q2NnPYd58K5Wu//4MzyEg59F+///SnP/G5z32ON998k/nz53P11VczYsQIrrzySn70ox+xevVqxowZA8B7773HkiVLuO+++w7p2s8++yxpaWk8//zzrFu3js9+9rPk5ubywx/+cJ+v/y//8i+8+uqrRKNRtmzZwoknnsgXvvAFfvazn1FbW8s3vvENLrnkEp577jkArr/+ep5//nkefPBBBg8ezDe/+U0WLFjAjBkzDv0/VAcZbCRJkqQ4VFRUxK233kokEmHChAksWbKEW2+9lS984QtMmzaNO++8k+985zsA3HHHHcyaNYvx48cf0rVTUlL4wx/+QEZGBpMnT+YHP/gB119/Pf/5n/+5e0+ZsWPH8pOf/GT3Od/97nc54ogjuOmmm3a/9oc//IGioiJWrFjBkCFD+P3vf8+f//zn3TM8f/rTnxg2bFis/pN8JIONJEmS+oz05ETe/8EZoX3t9jj66KP32Vh0zpw53HLLLTQ3N3PllVfyhz/8ge985ztEo1HuuuuudnUemz59OhkZGftcu6qqiuLiYkaMGAHAzJkz9zlnwYIFPP/882RmZn7oeqtXr6a2tpaGhgbmzJmz+/WBAwcyYcKEQ66rM9p1j83NN9/MrFmzyMrKIj8/nwsuuIDly5fv85mrrrqKSCSyz2N/awAlSZKk7haJRMhISQrlsXdI6awrrriCFStW8Pbbb/Paa69RXFzMZZdd1unr7l1jv3799nmvpaWF8847j4ULF+7zWLlyJSeccEK77yGKtXbN2Lz44ot8+ctfZtasWTQ1NfGtb32L008/nffff3+fP/iZZ57JH//4x93PU1JSYlexJEmS1Ae88cYbH3o+btw4EhMTGTZsGCeccAJ33HEHtbW1nHrqqRQUFBzytRctWkRtbS3p6em7r52ZmfmRy8aOOOII7r//fkaOHElS0odjxNixY0lOTuaNN95g+PDhAOzatYsVK1Zw4oknHnJtHdWuYPPkk0/u8/yPf/wj+fn5LFiwgBNOOGH366mpqQwePDg2FUqSJEl9UHFxMddddx1f/OIXefvtt/n5z3++T5exK6+8khtvvJGGhgZuvfXWdl27oaGBz33uc3z7299m/fr1fO973+Oaa67ZfX/N/nz5y1/mt7/9LZdffjnXX389ubm5rFq1ir/97W/89re/JTMzk8997nNcf/31DBo0iIKCAr71rW995DVjqVP32JSXlwPB2rm9vfDCC+Tn55OTk8OJJ57ID3/4Q/Lz8zvzpSRJkqQ+5dOf/jS1tbXMnj2bxMRErr32Wq6++urd71988cVce+21JCYmcsEFF7Tr2qeccgrjxo3jhBNOoL6+nssuu4wbb7zxI88ZMmQIr776Kt/4xjc444wzqK+vZ8SIEZx55pm7w8tPf/pTqqqqOP/888nKyuLf//3fd2eGrhaJdnAxXDQa5WMf+xi7du3i5Zdf3v363XffTWZmJiNGjGDt2rV85zvfoampiQULFpCamvqh69TX11NfX7/7eUVFBUVFRZSXl9O/f/+OlCZJkiQBUFdXx9q1axk1ahRpaWlhlxMXrrrqKsrKynjooYfCLmW3A/3vVFFRQXZ29iFlgw7P2FxzzTUsXryYV155ZZ/XL7300t3jKVOmMHPmTEaMGMFjjz3GJz7xiQ9d5+abb+b73/9+R8uQJEmSpPZ1RWtz7bXX8ve//53nn3/+oH2pCwsLGTFiBCtXrtzv+zfccAPl5eW7H8XFxR0pSZIkSRKQmZl5wMfeK616m3bN2ESjUa699loefPBBXnjhBUaNGnXQc3bs2EFxcTGFhYX7fT81NXW/S9QkSZIktd/ChQsP+N7QoUM5/vjju6+YbtSuYPPlL3+ZO++8k4cffpisrCxKSkoAyM7OJj09naqqKm688UYuvPBCCgsLWbduHd/85jfJzc3l4x//eJf8ASRJkiTtMXbs2LBLCEW7gs2vf/1rAObOnbvP63/84x+56qqrSExMZMmSJfz5z3+mrKyMwsJCTjrpJO6++26ysrJiVrQkSZIk7a3dS9E+Snp6Ok899VSnCpIkSZKk9uqe3XIkSZIkqQsZbCRJkiT1eAYbSZIkST2ewUaSJEmKM3PnzuWrX/1ql13/xhtvpKCggEgkwkMPPdRlX6c7GWwkSZKkPmTp0qV8//vf5ze/+Q1btmzhrLPO6vQ1b7/9dnJycjpfXCe0qyuaJEmSpJ5t9erVAHzsYx8jEomEXE3sOGMjSZKkviMahYbqcB4H2Trlg5qamrjmmmvIyclh0KBBfPvb3yYajXLDDTdw9NFHf+jz06ZN43vf+95HXvPGG2/kvPPOAyAhIWF3sHnrrbc47bTTyM3NJTs7mxNPPJG33357n3PLysq4+uqrKSgoIC0tjSlTpvDoo4/ywgsv8NnPfpby8nIikQiRSIQbb7yxXX/WWHDGRpIkSX1HYw3cNCScr/3NzZDS75A//qc//YnPfe5zvPnmm8yfP5+rr76aESNGcOWVV/KjH/2I1atXM2bMGADee+89lixZwn333feR1/za177GyJEj+exnP8uWLVt2v15ZWclnPvMZ/vd//xeAW265hbPPPpuVK1eSlZVFS0sLZ511FpWVlfz1r39lzJgxvP/++yQmJnLMMcdw22238d3vfpfly5cDkJmZ2d7/Op1msJEkSZLiUFFREbfeeiuRSIQJEyawZMkSbr31Vr7whS8wbdo07rzzTr7zne8AcMcddzBr1izGjx//kdfMzMzcfS/M4MGDd79+8skn7/O53/zmNwwYMIAXX3yRc889l2eeeYZ58+axdOnS3V9j9OjRuz+fnZ1NJBLZ55rdzWAjSZL20dISpbKuifLaRirqGimv3fOoaWhm+MAMDhvSnyHZab1qfb76iOSMYOYkrK/dDkcfffQ+f8fmzJnDLbfcQnNzM1deeSV/+MMf+M53vkM0GuWuu+7qVBe10tJSvvvd7/Lcc8+xdetWmpubqampYcOGDQAsXLiQYcOGHTQ4hclgI0lSH1Pf1MyCdbtYt6OGrRV1lFbWU9p2rKxje1UDzS0Hvxegf1oSkwr7c9iQ/kwq7M+MohzG5WcadhTfIpF2LQeLV1dccQX/8R//wdtvv01tbS3FxcVcdtllHb7eVVddxbZt27jtttsYMWIEqampzJkzh4aGBgDS09NjVXqXMdhIktQHlFbU8fzyUp5dWsqrq7ZT3dB80HPSkhPITk/e55GanMiabdWsKq2koq6JN9fu5M21O3efMyavH+dPH8r5M4YwKrfn//IohemNN9740PNx48aRmJjIsGHDOOGEE7jjjjuora3l1FNPpaCgoMNf6+WXX+ZXv/oVZ599NgDFxcVs37599/vTpk1j48aNrFixYr+zNikpKTQ3H/z7Slcy2EiS1Eut2FrJo4s289zyUt7dVLHPe3lZqUwbmk1+/zQK+qeSn5VGflYqBf3TyMtKZUC/ZFKTEg947YamFlaVVvH+lgqWbqng/c0VLNiwi9Xbqrn1mRXc+swKpg3L5vzpQzh32hAGZ6d19R9X6nWKi4u57rrr+OIXv8jbb7/Nz3/+c2655Zbd71955ZXceOONNDQ0cOutt3bqa40dO5a//OUvzJw5k4qKCq6//vp9ZmlOPPFETjjhBC688EJ+9rOfMXbsWJYtW0YkEuHMM89k5MiRVFVV8eyzzzJ9+nQyMjLIyGjf0rvOMthIktSLtLREeXHFNv7w6lpeXrnnX1sjEZg2LIeTJ+Rz8sR8Jg/pT0JCx5eMpSQlcNiQYBlam8q6Rp5+bysPL9rMq6u2s3hjOYs3lvPDx5cya+RATpmYz9wJ+YwvcLmadCg+/elPU1tby+zZs0lMTOTaa6/l6quv3v3+xRdfzLXXXktiYiIXXHBBp77WH/7wB66++moOP/xwhg8fzk033cTXvva1fT5z//3387WvfY3LL7+c6upqxo4dy49+9CMAjjnmGP75n/+ZSy+9lB07dvC9732v21s+R6LRdjbU7mIVFRVkZ2dTXl5O//79D36CJEmiur6J+9/eyO2vrmPN9moAEiJw8sQCzphcwNwJ+eRlpXZbPdur6nl8yRb+vnAz89fv2ue9IdlpnDghn7kT8jh2bC6Zqf47q7pOXV0da9euZdSoUaSlOXMYrw70v1N7soHfSSRJ6sE2l9Vy+2vruGveBirrmgDISkvisllFfHrOSIoGdu9SkDa5mal8es5IPj1nJBt31fDM+1t5YcU2Xl+9g83lddw1bwN3zdtAcmKEI0cM4PhxeZwwLq/TM0mS+i5nbCRJ6oGKd9bwqxdWc9+CYhqbgx/lIwdl8NljR3HhkcPidhakrrGZ19fs4MXl23hheSnrdtTs8/7AfikcNzaX48flcvy4PO/NUaf1xRmbj9oc84knnuD444/vxmoOjTM2kiT1MWu3V/PL51fx4DubdrdkPmrUQK4+YTQnTciP+9mOtORETpqQz0kT8oHJrNtezcsrt/HSyu28vnoHO6sb+Puizfx9UbDPSNHAdKYPy2FGUQ7Ti3KYMiSb9JQDNzWQFOw5cyBDhw7tvkK6mcFGkqQeYOXWSn7x/CoeWbSZti1mjh+Xy1dOGceskQPDLa4TRub2Y2RuPz41ZySNzS28s6EsCDortrF4UznFO2sp3lnLo4u3AJCYEGFcfiYzinI4dmwuJ4zLIzsjOeQ/hRRfxo4dG3YJoTDYSJIUx8pqGrjp8aXcu2AjbYvHT56Yz7Unj+Xw4QPCLS7GkhMTmD1qILNHDeTfT59AeW0jSzaWs2hjGQuLy1hUXEZpZT3LSipZVlLJ394qJiECRwwfwEkTg2YEhxX2t+Oa9ivO7r7QB8Tifx+DjSRJcSgajfL3RZv5wSPvs6M62Pn7jMkFXHvyOKYMzQ65uu6RnZ7MceNyOW5c7u7XSsrrWFhcxvx1O3lxxTZWllYxf/0u5q/fxU+fWk5+VionjM/j2LGDmDM613t0RGJisHSxoaFhn31ZFF9qaoL77ZKTOz4Da/MASZLizIYdNXzroSW796EZX5DJzZ+YypEjeu6Ss66ycVcNL7Q2Inh11Q5qG/fd+XxUbj/mjBnEnNGDOHr0oG5tea34EI1G2bBhA42NjQwZMoSEhISwS9JeotEoNTU1lJaWkpOTQ2Fh4T7vtycbGGwkSYoTTc0t/P6Vtdz6zArqGltISUrgKyeP5eoTxpCS5C9jB1Pf1My8tTt5ZeV2Xl+zg3c3le++H6nNxMFZnD55MKcfVsDkIS5b6ysaGhpYu3YtLS0tYZeiA8jJyWHw4MEf+jtpsJEkqYdZsH4X33noXd7fUgHAnNGD+OHHpzA678BtW/XRymsbmbd2J6+v3sFrq7ezrKRyn/eHDUjn9MMGc/rkAmaNHEhinHeUU+e0tLTQ0NAQdhnaj+Tk5N1LBj/IYCNJUg+xrbKeHz+5jPsWbAQgJyOZb509iYuOHOZsQoztqKrnheXbeOq9El5auY26xj3/ej+wXwqnTsrnrCmFHDN2EKlJtpSW4oHBRpKkONfY3MKfX1/Pbf9YQWV9EwCXzizi62dOYFCm94F0tdqGZl5aGYScZ5eWUl7buPu9rNQkTp6Uz1lTBnPi+Hz3zZFCZLCRJCmOvb56Bzf+/T2Wbw2WRk0bls0PPjaFGUU54RbWRzU2t/DW2p08+V4JT75bQmll/e730pMTmTshj9MnF3Di+HwG9ksJsVKp7zHYSJIUh3ZU1XPjI+/zyKLNAAzISOYbZ07kkplFJHh/R1xoaYnyTvEunlhSwhPvlrCprHb3ewkROHz4AE6emM9JE/KZVJjlckGpixlsJEmKMyXldVzxuzdYs62ahAh88ugRXHfaeHIynAGIV9FolHc3VfDke1t4dmnph5oPFGanMXdCPieOz2POmEFkp3d8/w1J+2ewkSQpjhTvrOHK373Jhp01DMlO4/8+PbPPbLLZm2wuq+X55aU8v6yUV1Zt36f5QEIEZhTlcNy4PI4fl8uMohySE23RLXWWwUaSpDixZlsVV/7uTbaU1zF8YAZ3fuEohg3ICLssdVJdYzNvrNnBC8u38dLKbazZVr3P+5mpScweNZDpw3KYXpTN9GE5DPD+HKndDDaSJMWB5SWVXPm7N9leVc+YvH7c8fmjGZydFnZZ6gKbymp5deV2Xlq5jVdXbWdXTeOHPjN8YAbTi3KYPiybiYP7MyqvH4X907y/SvoIBhtJkkL27qZyPvX7N9lV08ikwv785XOzybWNc5/Q0hLl/S0VzF+3k0Uby1m0sexDMzpt0pITGDmoH6Pz+jEqtx+jcjMZm5/JuPxM+qUmdXPlUvxpTzbwb4wkSTG2YP0urvrjPCrrmpg+LJs//dNsmwT0IQkJEaYMzd7nPqry2kaWtIacRcVlrN5WxYadNdQ1trCspPJDjQkAigamM6Egi/EFWUwYHBxH5fYjLdl9daT9ccZGkqQYem9zORf/v9epaWhm9siB/P6qmWSl2S1LH9bU3MLGXbWs3V7Nmu3VrNlWxZpt1azaVsW2vfbS2VskAkUDMhiT148xeZmMzstkTF4/RudlkpuZYvtp9TouRZMkKQQVdY2c9/NXWL+jhmPGDOJ3n5lJRoqLI9R+O6sbWLG1khVbK1le0vrYWkllXdMBz0lLTmDYgAyKBqQzbEAGw1qPRQPTGT4ww1lD9UguRZMkqZtFo1G+cd9i1u+oYWhOOr+68ghDjTpsYL8Ujh49iKNHD9r9WjQaZXtVA6u3VbG6dXanbbxxVy11jS2sKq1iVWnVfq/ZPy2J4YMyGD4wg6KBwXHkoODensE2MVAv4HdcSZJi4I+vruOJd0tITozwyyuP8F/HFXORSIS8rFTyslL3CTwA9U3NbCmrY+OuWjbuqqF4Vw0bd9VSvDM4llbWU1HXxLubKnh3U8WHrp2alMCo3H5B0Mnrx6hB/RiTHyx38//L6ikMNpIkddLbG3Zx0+NLAfj2OYcxoygn3ILU56QmJTIytx8jc/vt9/3ahmaKd9WwYUcNG3bueazbUc2GHTXUNx24icGgfimMycvcHXTG5GUyfnAWQ7LTvKdHccVgI0lSJ+yqbuCaO96mqSXKOVML+fScEWGXJH1Iekoi41s7rH1QU3MLm8pqWbO9mnXbq1nb+lizrZpNZbXsqG5gR/VO5q3buc95WalJjB8cdGyb0Nq5beLgLGd4FBqDjSRJHdTSEuW6exayubyOUbn9+NGFU/0XbPU4SYkJjBjUjxGD+sGEfd+raWjacy9PaRWrt1WzsrSSNduqqaxvYsH6XSxYv2ufc0YMymBGUQ4zinKYXpTD5CH9SU2yRbW6nsFGkqQO+n8vreb55dtITUrgV1ceYVtn9ToZKUkf2pMHoKGphbXbq1lWUrGnc9vWSop31rJ+Rw3rd9Tw8MLNACQnRjissD+HDx/ArJEDmTVqAPlZaWH8cdTL2e5ZkqQOeGPNDq747Ru0ROEnF07jkllFYZckha68ppFFG8tYWBxsRLqwuIwd1Q0f+tzIQRnMHDmQ2SMHMmvUQEYOynC2U/vlPjaSJHWhHVX1nPk/L7Otsp4LjxjGf188zV/KpP2IRqNs3FXLO8VlLFi3k3nrdrGspIIP/vY5NCeduRPyOHliPseMySU9xaVrChhsJEnqItFolC/d8TZPvFvC+IJMHv7ycf4SJrVDeW0jb2/YxVtrd/LWup0sKi6nobll9/upSQnMGTOIkyfmc9KEfIoGZoRYrcJmsJEkqYs8vHAT//q3hSQlRHj4mmOZPCT74CdJOqDahmZeX7Od55aV8vyybWwqq93n/dkjB/LJOSM4c/JgUpISQqpSYWlPNrB5gCRJh6i0oo7vPvweANeePM5QI8VAekoiJ08s4OSJBUSjUVZsreL55aU8t6yUBet3MW9d0Go6LyuVy2cVcflRwynMTg+7bMUhZ2wkSToE0WiUz/9pPs8uK2Xq0Gwe+NIxJCf6r8dSVyopr+OueRu4a94GSivrAUhMiHDapAI+PWcEc8YM8v62Xs6laJIkxdi984u5/r7FpCQm8OhXjtvvRoeSukZjcwtPvVfCX15fz5tr92wUOiq3H5fOKuKiI4eRm5kaYoXqKgYbSZJiaHNZLWfc+hKV9U1848yJ/MvcMWGXJPVZy0sq+csb63jonc1U1TcBwV45px1WwOWzh3PsmFwSEpzF6S0MNpIkxUg0GuXTf5jHyyu3M6Moh/v+eQ5JLkGTQldd38Sjizdz17xiFhaX7X69aGA6Fx4xjFMnFTB5SH+XqvVwBhtJkmLkjjfX860H3yU1KYHH//V4xuRlhl2SpA9YuqWCv83bwAPvbKKyrmn36/lZqZw0IZ+TJuZz3LhcMlPtm9XTGGwkSYqB4p01nHHbS9Q0NPPtcybx+eNHh12SpI9Q29DME+9u4cl3S3hl1XZqGpp3v5eSmMDsUQM5cXwex4wdxKTB/V2y1gMYbCRJ6qRoNMonf/8mr67aweyRA/nb1Uf7S5DUg9Q3NTNv7U6eXVrK88tLWb+jZp/3B2QkM2fMIOaMyeWYMYMYndvPZWtxyGAjSVInPbZ4C1++821SkxJ4+t9OYMSgfmGXJKmDotEoa7ZX8/yyUl5dtZ15a3dSvddsDsDg/mkcOWIAM4pymDE8hylDsklPSQypYrUx2EiS1Ak1DU2cesuLbC6v419PGce/nTY+7JIkxVBjcwuLN5bx2qodvLZ6BwvW76KhuWWfzyQmRJg4OIsZRTlML8ph+rAcxuT1s3lINzPYSJLUCbc8vZyfP7eKoTnpPPvvJ5KW7L/aSr1ZXWMzb2/YxcLiMhZuKGNhcdnuDUH3lp6cyOQh/Zk6LJtpw7KZOjSH0bn9XKbahdqTDWwNIUnSXjbsqOE3L60B4DvnTjLUSH1AWnIix4zJ5ZgxuUCwdG1LeV0QdIrLWFRcxrubyqluaGb++l3MX79r97npyYmMK8hkQkEWEwa3PgqyyMtK9Z6dbmawkSRpL//52Ps0NLVw3Nhczpg8OOxyJIUgEokwJCedITnpnD21EICWluA+nSWbyli8sZwlG8t5b3MFtY3NLN5YzuKN5ftcY0BGMuMKshhfkMn4gizG5QfjQZmpYfyR+gSXokmS1OrFFdv4zB/mkZQQ4Yl/PZ5xBVlhlyQpjjW3RFm/o5rlJZUs31oZHEsqWbejmpYD/IY9qF8K4woyGZOXyei8TEbn9WNMbiZDB6ST6JK2D3EpmiRJ7dTQ1ML3//4eAJ85ZqShRtJBJSZEWsNJJme1zuxAcM/OqtIqVmytZMXWKlZurWRFaSXFO2vZUd3AjjU7eWPNzn2ulZKUwMhBGYzOzWTEoAyKBmYwvPUxJCedlCSbFhyMwUaSJOCPr65lzfZqcjNT+ddTx4VdjqQeLC05kSlDs5kyNHuf12samloDTxVrtlWxZls1a7ZXsW57DQ1NLazYGrz3QQkRKMxOZ9iAYHnc4Ow0hmSnMTg7ncLsNAqz0xjYL6XP39NjsJEk9XlbK+r432dXAvCNMyfQPy055Iok9UYZKUlMG5bDtGE5+7ze3BJl065aVm+vYu22aop31VC8s4YNrY+6xhY2ldWyqaz2gNdOSogwKDOF3MxUBmWmkpuZQl5mKoMyU0hOTCAhEiESCe4figAJkQgJEXa/1va87XMJkQhHjRpIfv+0rv2PEkMGG0lSn/ejJ5ZR3dDM4cNzuPCIYWGXI6mPSUyIMHxQBsMHZXDShH3fi0ajbKuqp3hnDRt31bKlvI6S8jo2l9VSUlHH5rI6tlfV09QSZWtFPVsrPtymuqP++NlZBhtJknqK+et28uA7m4hE4PvnT3Y/CklxJRKJkJ+VRn5WGkeO2P9nGppa2FFdz/bKBrZX1bOtqp4dVcF4Z3UDjc0tRKMQJUo0Ci3RDx9bPvQ8yoCMlO79w3aSwUaS1Ge1tET5z0ffB+DSmUUfWh4iST1BSlIChdnpFGanh11KqGyvIEnqsx5ZvJlFG8vpl5LIv58+4eAnSJLilsFGktQn1TU285MnlwPwpZPGkpflpnmS1JMZbCRJfdLvX1nLprJahmSn8bnjRoVdjiSpkww2kqQ+Z3tVPb9+YTUA1585gbTkxJArkiR1lsFGktTn3PqPFVTVNzFtWDYfmz407HIkSTFgsJEk9Skrt1Zy17wNAHzr7Em2d5akXsJgI0nqU256fCktUTj9sAKOGj0o7HIkSTFisJEk9RmvrNzO88u3kZQQ4T/Omhh2OZKkGDLYSJL6hOaWKP/1WLAZ5yePHsHovMyQK5IkxZLBRpLUJ9y/YCPLSirpn5bEv54yLuxyJEkxZrCRJPV61fVN/PfTwWac1548jgH9UkKuSJIUawYbSVKv99uX11BaWc/wgRl8+pgRYZcjSeoCBhtJUq9WWlnH/720BoCvnzmB1CQ345Sk3shgI0nq1f732ZXUNDQzvSiHc6YWhl2OJKmLGGwkSb3W6m1V3DWvGIAbzppIJOJmnJLUWxlsJEm91k+fXE5zS5RTJuZztJtxSlKvZrCRJPVKC9bv4sn3SkiIwDfcjFOSej2DjSSp14lGo/zoiaUAXHTkMMYXZIVckSSpqxlsJEm9zj/e38pb63aRlpzAv502PuxyJEndwGAjSepVmppb+PGTywD4p2NHUZidHnJFkqTuYLCRJPUq9y7YyOpt1QzISOaf544JuxxJUjcx2EiSeo2ahiZ+9o8VAFx78jj6pyWHXJEkqbsYbCRJvcbvX17Ltsp6igamc+XRw8MuR5LUjQw2kqReYXtVPb95aQ0A158xkdSkxJArkiR1J4ONJKlX+OXzq6iqb2Lq0GzOnVoYdjmSpG5msJEk9Xiby2q5440NAHz9zAkkJERCrkiS1N0MNpKkHu/nz62kobmFo0YN5LixuWGXI0kKgcFGktSjrdtezT3zNwJw/RkTiEScrZGkvshgI0nq0W57ZgXNLVHmTshj5siBYZcjSQqJwUaS1GOt2FrJw4s2A/C10yeEXI0kKUwGG0lSj/Wzp1cQjcJZUwYzZWh22OVIkkJksJEk9UhLNpbz5HslRCJw3Wnjwy5HkhQyg40kqUf676eXA/DxGUMZV5AVcjWSpLAZbCRJPc5b63by4optJCVE+OqpztZIkgw2kqQeJhqN8tOngtmaS2YVMXxQRsgVSZLigcFGktSjvLxyO/PW7iQlKYFrTx4bdjmSpDhhsJEk9RjRaHT3vTWfOnoEhdnpIVckSYoXBhtJUo/x9PtbWbyxnIyURP5l7piwy5EkxRGDjSSpR2hpifKzp1cA8NljR5KbmRpyRZKkeGKwkST1CI8s3szyrZVkpSVx9fHO1kiS9mWwkSTFvabmFm57ZiUAXzxhNNkZySFXJEmKNwYbSVLce+CdTazdXs3AfilcdeyosMuRJMUhg40kKa7VNzXzP62zNf9y4hgyU5NCrkiSFI8MNpKkuHbPW8VsKqslPyuVTx49IuxyJElxymAjSYpbdY3N/Py5VQBcc/JY0lMSQ65IkhSvDDaSpLj11zfWU1pZz9CcdC6dVRR2OZKkOGawkSTFpar6Jn71wmoA/vWUcaQmOVsjSTowg40kKS7d/upadlY3MHJQBp84YmjY5UiS4pzBRpIUd8prGvnNS2sA+LfTxpOU6I8rSdJH8yeFJCnu/PblNVTWNTG+IJNzpw0JuxxJUg9gsJEkxZXSijp+/8paAK47bTyJCZGQK5Ik9QQGG0lSXPnZP1ZQ29jM4cNzOGPy4LDLkST1EAYbSVLcWLG1knvmFwPwrbMnEYk4WyNJOjQGG0lS3Lj58aW0ROGMyQXMHDkw7HIkST2IwUaSFBdeXbWd55dvIykhwjfOnBh2OZKkHsZgI0kKXUtLlJseXwrAlUcNZ3ReZsgVSZJ6GoONJCl0Dy3cxHubK8hKTeIrp4wLuxxJUg9ksJEkhaqusZn/fmo5AP9y0hgGZaaGXJEkqScy2EiSQvXHV9exubyOIdlp/NOxo8IuR5LUQxlsJEmh2VFVz6+eXwXAv58+gbTkxJArkiT1VAYbSVJofv7cKirrmzissD8fP3xo2OVIknowg40kKRRrt1fz1zfWA/CtcyaRkOBmnJKkjjPYSJJC8eMnltHUEmXuhDyOHZsbdjmSpB7OYCNJ6nZvrNnBk++VkBCBG86aFHY5kqRewGAjSepWLS1R/uux9wG4fPZwJgzOCrkiSVJvYLCRJHWrB97ZxLubgs04/+208WGXI0nqJQw2kqRuU9PQxE+fWgbAl08eS66bcUqSYsRgI0nqNv/vxTVsrainaGA6nz12ZNjlSJJ6EYONJKlbbCmv5f9eWg0EDQNSk9yMU5IUOwYbSVK3+OmTy6lrbGHWyAGcNWVw2OVIknoZg40kqcstKi7jgXc2AfDtcw4jEnEzTklSbBlsJEldKhqN8p+PBu2dP3H4UKYX5YRbkCSpVzLYSJK61BPvljB//S7SkhO4/swJYZcjSeqlDDaSpC5T19jMzU8sBeCLJ4yhMDs95IokSb2VwUaS1GX+9No6infWUtA/lS+eODrsciRJvZjBRpLUJSrrGvnVC0F756+dPoGMlKSQK5Ik9WYGG0lSl/jTa+sor21kdF4/PnHEsLDLkST1cgYbSVLMVdY18tuX1wLwr6eMIzHB9s6SpK5lsJEkxdzeszXnThsSdjmSpD7AYCNJiilnayRJYTDYSJJiytkaSVIYDDaSpJhxtkaSFBaDjSQpZpytkSSFxWAjSYoJZ2skSWEy2EiSYsLZGklSmAw2kqROc7ZGkhQ2g40kqdOcrZEkhc1gI0nqFGdrJEnxwGAjSeoUZ2skSfHAYCNJ6rCGphZuf20dAF852dkaSVJ4DDaSpA57ZulWtlc1kJeVyjnTCsMuR5LUhxlsJEkddte8DQBcOrOI5ER/pEiSwuNPIUlSh2zYUcPLK7cTicCls4rCLkeS1MclhV2AJKlnuuutYLbm+HF5FA3MCLkaSepFolFoboTmemhqaD3WQXMTtLQ+os3Q0tz6vHnP82hLcH60bfzBR3TfI9EDj8eeCtnDQv6PcegMNpKkdmtoauHe+cUAXDHb2RpJoqkBandCzc49x7pyqK+Auoq9xuVQXxkElcZaaGoNLbsfrc/jwZX39d5gc/PNN/PAAw+wbNky0tPTOeaYY/jxj3/MhAkTdn8mGo3y/e9/n//7v/9j165dHHXUUfzyl79k8uTJMS9ekhSOZ/dqGnDKpIKwy5Gk2ItGg3BSuQWqtkL1dqje9uFHzQ6o2QUNlV1XS0ISJKZCYnIw3v1IDB6RxOB5JKH1EWl9PQH4wLjt/b2PRD4wbn0vY1DX/Zm6QLuCzYsvvsiXv/xlZs2aRVNTE9/61rc4/fTTef/99+nXrx8AP/nJT/jZz37G7bffzvjx4/mv//ovTjvtNJYvX05WVlaX/CEkSd3rztamAZfMHGbTAEk9T2MdVG6Gis1QvgkqNgXjthBTWRI8WhrbeeEIpOdA+kDIGAhpOZCWDWn9g2Nq/2Ccmg3J6ZCUBslpwTEpFZLSISkleJ6YEryWmAoJfp89FJFoNBrt6Mnbtm0jPz+fF198kRNOOIFoNMqQIUP46le/yje+8Q0A6uvrKSgo4Mc//jFf/OIXD3rNiooKsrOzKS8vp3///h0tTZLURYp31nD8T54H4OWvn+T9NZLiS0NNEFLawsru417jmu2Hfr2MXMgsgMw86Nf2yN0zzhi0V5DJDmZHFDPtyQadusemvLwcgIEDBwKwdu1aSkpKOP3003d/JjU1lRNPPJHXXnttv8Gmvr6e+vr6fYqXJMWvv+1uGpBrqJHUfVqaoao0mGmpLNkzw1KxJTi2jevLD+16SenQfwhkD4X+Q4NxViFkDQ6OmQXBIymla/9cipkOB5toNMp1113Hcccdx5QpUwAoKSkBoKBg3/XWBQUFrF+/fr/Xufnmm/n+97/f0TIkSd2osbmFe+ZvBOCK2cNDrkZSrxCNBjfU7x1O2sZ7B5iqra3dug5Bcr/WwDJkT2jpPwSy9goy6QOC+0jUa3Q42FxzzTUsXryYV1555UPvRT7wf5JoNPqh19rccMMNXHfddbufV1RUUFRkhx1JikfPLt3Ktsp6cjNTOfUwmwZIOoiWlmDZV1tA2Wd52F5LxBprDu16kYRgFiWrcN8ZlrZx2zHN2xn6og4Fm2uvvZa///3vvPTSSwwbtqcF3ODBg4Fg5qawsHD366WlpR+axWmTmppKampqR8qQJHWzO+cFLZ5tGiCJhur93MOyufXm+9bZlqqtwT4rhyItpzWcFLYGlr1Dy+BgtiUz33tYdEDtCjbRaJRrr72WBx98kBdeeIFRo0bt8/6oUaMYPHgw//jHPzj88MMBaGho4MUXX+THP/5x7KqWJHW74p01vLxyGwCXzXIZmtRr7W5zvHnfwFK5OVgm1jauO8R7WYgEN9lnDQ72RGlbFtb/A/e2pHjPnjqnXcHmy1/+MnfeeScPP/wwWVlZu++pyc7OJj09nUgkwle/+lVuuukmxo0bx7hx47jpppvIyMjgiiuu6JI/gCSpe9z9VjHRaNA0YPggfwGReqS2+1nKi6F8Y/DYXwexQ90gMrX/niVg/Ye2zrYM3jPbkjk4mGVJTO7aP5dEO4PNr3/9awDmzp27z+t//OMfueqqqwD4+te/Tm1tLV/60pd2b9D59NNPu4eNJPVg9U3N3D0/WIZ2uU0DpPjVNttStg52rYey9VBWvCfIlBUf+kaS/fL2Ci2tN973HxKEl/5DvZdFcadT+9h0BfexkaT4c+/8Yq6/bzEF/VN5+esnk5Lk/TVSaBqq94SW3cd1e8YNVQe/Rsag1mVhw/Zqdzx0T/vjrMJgc0gpZN22j40kqfeLRqP8/pW1AFx1zChDjdQdanfBjjWwcw3sXA07VgfjXesObXPJzMEwYAQMGAnZRZBTFByzi4JA4/0s6oUMNpKkj/TKqu0sK6kkIyXRvWukWGqsDcLKjlWwfWUQXnasCh61Oz/63LScILjkjNjrODI45hRBcnp3/AmkuGKwkSR9pN+9HMzWXDKziOwMbwCW2q2hGrYtg9Klex7bVwb3vfARdwRkDoZBY2Dg6D3HtvCSntNNxUs9h8FGknRAK7ZW8uKKbSRE4J+OHXXwE6S+rKk+CCylS6H0/eC4bWmwfOxAUrMhdywMGtd6bH0MHA0p/bqtdKk3MNhIkg7ody+vAeCMyYNt8SztraoUNr8DmxdC6XtQuixYQhZt3v/n++VB/iTIPwzyJgaPQWOhXy5EIt1autRbGWwkSfu1rbKeh97ZDMDnjx8dcjVSiGp2toaYd/aEmYqN+/9sanZrgJm0J8jkTwoCjKQuZbCRJO3XX15fR0NzC4cPz+HIEQPCLkfqHk0NsHUJbFwAG9+CTfODG/w/JAK542HIDBg8dU+IySp0BkYKicFGkvQhtQ3N/OWN9QB8wdka9WaVJbDhDSieBxvnwZbF0Fz/4c8NHA1DjoAhhwePwmmQ6ubjUjwx2EiSPuSBdzayq6aRooHpnDF5cNjlSLHR0hLczL/hDSh+MziWrf/w59IHwNCZMGxmcBx6BGQM7P56JbWLwUaStI+Wlii/b23x/NljRpGY4LIa9VDRKOxaC2teCB5rXwo2vtxHBAomQ9FRwWPYzGB2xuVkUo9jsJEk7eO5ZaWs2V5NVloSl8wqCrscqX2qd8DaF/aEmbIN+76f3C8IL8OPhqLZMGwWpGWHUKikWDPYSJL28btXghulrzhqOJmp/phQnGusg+I3YPXzsOb54B6ZvTe9TEgOAszoucFjyOGQ6EazUm/kTyxJ0m7vbirnjTU7SUqIcNUxI8MuR/qwaDTYBHPlU7D6OVj/OjTV7vuZ/Mkw5qQgyAyfA6mZoZQqqXsZbCRJu/22dUPOc6cVUpidHnI1UqvmpmBWZvkTsPzxD7dfzhzcGmRaw0xWQShlSgqXwUaSBMCW8loeW7wFcENOxYH6Slj5jyDMrHwa6sr2vJeQDKOOh7GnwpiTIW+iN/tLMthIkgJ/m1dMU0uU2aMGMmWoN1MrBDU7gyCz9JFgmdne+8mkD4TxZ8CEs4Iw4x4ykj7AYCNJoqm5hb+9FXSP+tTRI0KuRn1K5VZY9igs/TusfRmizXveGzgGJp0L488KGgAkJIZXp6S4Z7CRJPHsslK2VtQzqF+KG3Kq69WWBbMyS+4N9pbZu4tZwRSYdD5MOg/yJ7nETNIhM9hIkrjjzWC25pJZRaQkJYRcjXqlxrqgk9mSe2HF0/suMxt65J4wM2hMeDVK6tEMNpLUx23YUcNLK7YBcPms4SFXo14lGoXiefDOX+D9h6G+Ys97eRNh6sUw9SIYMDK0EiX1HgYbSerj7pwXzNacMD6P4YMyQq5GvUJlCSy6C965A3as3PN6/2Ew9UKYegkUTHaZmaSYMthIUh9W39TMvfOLAbjyKGdr1AlNDbDiSXjnr7DqmT1NAJIz4LAL4PArYfgxkOBSR0ldw2AjSX3YU+9tZUd1AwX9UzllYn7Y5agnKiuGBbfD23+G6tI9rxcdBYd/EiZ/3NbMkrqFwUaS+rA73lgPwGWzhpOU6L+k6xC1tMCa5+Gt38OKJyDaEryeWQDTLw8CTe64cGuU1OcYbCSpj1pVWsmba3eSEIHLZheFXY56gtqyYKnZ/N/DzjV7Xh95PMz6PEw8BxKTQytPUt9msJGkPqqtxfMpkwoozE4PuRrFtR2r4Y1fw8I7obE6eC21P8y4Amb+E+RNCLc+ScJgI0l9Um1DM/cv2AjYNEAHEI3C2heDQLPiKXZvopk/GY66OmjVnNIv1BIlaW8GG0nqgx5dvJmKuiaGDUjnhHF5YZejeNJUD4vvCQJN6Xt7Xh9/Jhz9LzDqRNs0S4pLBhtJ6oPalqFdPns4CQn+kiqC+2cW/DEINFVbg9eSM2DGlXDUP0Pu2FDLk6SDMdhIUh/z3uZyFhaXkZQQ4ZKZNg3o8yo2wxu/gvm3Q0Nl8FrWEDjqi3DkZyB9QKjlSdKhMthIUh9zZ+tszRlTBpOXlRpyNQpN6TJ47X+DZWctjcFreZPg2K/AlIsgKSXc+iSpnQw2ktSHVNU38dA7mwCbBvRZO1bD8zfBu/ezuyHAiOOCQDP2NEhwPyNJPZPBRpL6kKfeLaG6oZlRuf2YM3pQ2OWoO5VtgBd/DAvvgmhz8NrEc+G4f4NhM8OtTZJiwGAjSX3IQwuD2ZqPHz6UiJ2t+oaKLfDyLbDg9j1LzsafCSd9CwqnhVqaJMWSwUaS+oitFXW8umo7ABfMGBpyNepytWXwys/gzd9AU13w2qgT4eRvQ9HsUEuTpK5gsJGkPuKRRZtpicIRw3MYPigj7HLUVZoa4K3fwUs/gdpdwWvDZsMp34FRJ4RbmyR1IYONJPURey9DUy8UjcJ7D8CzP4Bd64LX8ibCqd+H8We4qaakXs9gI0l9wMqtlby7qYKkhAjnTBsSdjmKtfWvwdPfhk0LgueZBXDSN2HGJyHRH/WS+ga/20lSH9A2WzN3Qh4D+7k/Sa+xaz08/S1Y+kjwPLlf0LZ5zjWQmhlubZLUzQw2ktTLtbREeeidzQB8zKYBvUNjLbxyG7x6W9AYIJIAR3wG5t4AWQVhVydJoTDYSFIvN3/9LjaV1ZKZmsSpk/ylt0eLRoPZmae+BeUbgtdGHg9n/RgKJodbmySFzGAjSb1c2zK0M6cMJj0lMeRq1GHblsMTX4c1LwTP+w+F0/8LJn/cxgCShMFGknq1+qZmHlu8BbAbWo/VUA0v/hhe/yW0NEFiChzzFTj+OkjpF3Z1khQ3DDaS1Iu9sHwb5bWNFPRP5ejRg8IuR+21/Al4/HooLw6ejz8LzrwJBo4Oty5JikMGG0nqxR56J1iGdv70ISQmuFypxyjfCE98A5Y9GjzPHg5n/xQmnBluXZIUxww2ktRLldc28uyyUgAucBlaz9DcBPN+A8/fBA1VkJAUtG4+8esuO5OkgzDYSFIv9eS7W2hoamF8QSaHFfYPuxwdzOaF8PdroGRJ8LzoKDj3VrudSdIhMthIUi/1YOsytAsOH0rErlnxq6keXvopvPwziDZDWg6c9gM4/FOQkBB2dZLUYxhsJKkX2lRWyxtrdgLB/TWKU5vehoe/DKXvB88nfxzO+ilk5oVblyT1QAYbSeqF/r5wMwCzRw1k2ICMkKvRhzTVBy2cX7ktmKXJyIVzboHJF4RdmST1WAYbSeqFHm7dlNO9a+LQpgXw0Jdg27Lg+ZQLg1mafrbjlqTOMNhIUi+zrKSCZSWVpCQmcPaUwrDLUZuWZnjpv+HFH0G0BfrlwTk/g8POD7sySeoVDDaS1Ms8sihYhnbihDyyM5JDrkYAVJbAA1+AtS8Fz6dcFOxLkzEw3LokqRcx2EhSLxKNRnls8RYAzp3mbE1cWP0cPHA1VG+D5H5BC+fpl4ZdlST1OgYbSepF3ttcwbodNaQmJXDqpIKwy+nbmpvghZvh5VuAKORPhotvh7zxYVcmSb2SwUaSepFHW2drTp6YT79Uv8WHpnwT3P952PBa8PzIq+DMH0FyeqhlSVJv5k89SeolotEojy0J7q85x2Vo4Vn7Mtz7GajZASmZcN7/wNSLwq5Kkno9g40k9RKLN5ZTvLOW9ORETp6YH3Y5fdNbv4cnvg4tTTB4Klz8Jxg0JuyqJKlPMNhIUi/x2JLWZWiT8slI8dt7t2puhCf/A976XfB8ykXwsV+49EySupE/+SSpF9i7G9p5LkPrXjU74Z5Pw7qXg+enfBeOuw4ikXDrkqQ+xmAjSb3AO8VlbCqrpV9KInMnuAyt25Qug7sug11rg/tpPvF/MPGcsKuSpD7JYCNJvcCji4LZmlMPKyAtOTHkavqIFU/Dff8EDZWQMxwu/xsUTA67Kknqsww2ktTDtbREebz1/ppzproMrctFo8HeNM/9FxCFEcfCJX+GfrlhVyZJfZrBRpJ6uLc37KKkoo6s1CROGJ8Xdjm9W30lPPQvsPSR4PmRV8FZP4WklFDLkiQZbCSpx2vblPM0l6F1re2r4G9XwPblkJgCZ/80CDaSpLhgsJGkHqx572VodkPrOsufhAe+APUVkFUIl/wFimaFXZUkaS8GG0nqwd5at5PSynqy0pI4fpzL0GKupQVe+gm8cHPwfPicYNPNrIJw65IkfYjBRpJ6sLa9a86YPJiUpISQq+ll6qvggath+WPB89lXw+k/9H4aSYpTBhtJ6qGamlt44t0g2JzrMrTYKtsAd10OW9+FxFQ491Y4/Mqwq5IkfQSDjST1UPPW7mR7VQM5GckcO9ZWwzGz4U24+0qo3gb98uHyu2DYzLCrkiQdhMFGknqoR1qXoZ05eTDJiS5Di4mFd8EjX4HmBhg8Ndh0M3tY2FVJkg6BwUaSeqCm5haefNduaDHT0gLPfh9evS14PvFc+MT/QUq/UMuSJB06g40k9UCvr9nBrppGBvZLYc7oQWGX07N9sEnA8V+Dk74FCc6CSVJPYrCRpB7o0UWty9CmDCbJZWgdV7kV7rwYtiwKmgR87Bcw7ZKwq5IkdYDBRpJ6mMbmFp58rwSAc6e6DK3Dtq+Ev14IZeshY1BwP03R7LCrkiR1kMFGknqY55eVUl7bSG5mCke5DK1jiufBnZdC7U4YMAo+eT8MGhN2VZKkTjDYSFIPc+e8DQBceMQwEhMiIVfTAy17DO77J2iqgyGHwxX3QmZe2FVJkjrJYCNJPUjxzhpeXLENgMtmDw+5mh7ord/B49dDtAXGnQ4X327nM0nqJQw2ktSD3P1WMdEoHDNmEKNy/YX8kEWj8Nx/wsu3BM+P+DSccysk+mNQknoLv6NLUg/R2NzC3fOLAbjiKGdrDllzI/z9K7DozuD53BvgxG9AxGV8ktSbGGwkqYd4dmkp2yrryc1M4fTDBoddTs9QXwn3fAZWPwuRRDjvtmC2RpLU6xhsJKmHaGsacNGRRaQkuXfNQVWVwh0Xw5aFkJwBF/8Jxp8edlWSpC5isJGkHqB4Zw0vrwyaBlw+uyjkanqAHavhLx/fs0fNFffCsCPDrkqS1IUMNpLUA9w1bwPRKBw/LpcRg2wa8JE2LoA7L4aaHTBgJHzyAfeokaQ+wGAjSXGusbmFe+ZvBOAKWzx/tBVPwb1XQWNN6x4190BmfthVSZK6gcFGkuLcP97fyvaqevKyUjn1sIKwy4lfi+6Gh/4Fos0w9rRgj5rUzLCrkiR1E+8+laQ4d+ebQdOAS2YOIznRb9v79faf4cEvBqFmxpVw+V2GGknqY/wJKUlxbN32al5ZtZ1IBC6b5TK0/Zr3W/j7tUAUZn0Bzv8FJCaHXZUkqZsZbCQpjt31VjBbc/y4PIoGZoRcTRx6/Zfw+NeC8Zxr4OyfQoI/2iSpL/K7vyTFqYamFu6zacCBvfwzeOqbwfi46+D0/4JIJNyaJEmhsXmAJMWpp98vYUd1A/lZqZwyyc5eu0Wj8OKP4YWbg+dzvwknft1QI0l9nMFGkuJUW9OAS2cV2TSgTTQKz/4AXvlZ8PyU78Hx14VbkyQpLhhsJCkOrd1ezWurdxCJBMFGBKHmH9+B134ePD/jJpjz5XBrkiTFDYONJMWhu+YFszVzx+cxbIBNA4hG4alvwRu/DJ6f/d8w+wvh1iRJiisGG0mKM/VNzdy3oLVpwFEjQq4mDkSj8OQN8Oavg+fn3goz/yncmiRJccdgI0lx5sl3S9hZ3cDg/mmcNCEv7HLCFY3CE1+Hef8XPD/vf+DIq0ItSZIUnww2khRn2poGXDKriKS+3DSgpSXYo2b+74EInP9zOOJTYVclSYpTBhtJiiOrSqt4c+1OEiJwWV9uGtDSAo/9Gyy4HYjABb+CGVeEXZUkKY4ZbCQpjrQ1DThpQj5DctJDriYk0Sg8+lV4+08QSYALfg3TLwu7KklSnDPYSFKcqGts5v6325oGDA+5mpBEo/DUN/eEmo//BqZdEnZVkqQeoA8v3pak+PLkuyWU1TQyJDuNuRPywy4nHC/8CN74VTA+/xeGGknSITPYSFKcaGsacOms4SQmREKuJgSv/Rxe/FEwPuuncPiV4dYjSepRDDaSFAdWbq1k3rqdJCZEuLQvNg2Y/0d4+tvB+JTvwlFXh1uPJKnHMdhIUhy4s7VpwMkT8xmcnRZyNd1s8b3w6L8F4+P+DY7/93DrkST1SAYbSQpZXWMz9y/oo00Dlj0GD34RiMKsz8Mp3wu7IklSD2WwkaSQPfVeCRV1TQzNSeeEcXlhl9N9Vj8P914F0WaYdllwX02kD95bJEmKCYONJIXsvtbZmouOHNZ3mgYUvwV/uxKaG2DSefCxX0KCP5IkSR3nTxFJCtHmslpeWbUdgAuPGBZyNd1k63twx4XQWA2jT4ILfw+JbqsmSeocg40khejBdzYRjcJRowYyfFBG2OV0vR2r4S8fh7pyKDoKLrsDklLDrkqS1AsYbCQpJNFodPcytAuP7AOzNRWb4c8XQNVWKJgCV9wNKf3CrkqS1EsYbCQpJG9v2MXa7dWkJydy9tTCsMvpWtU7glBTvgEGjoZPPQjpA8KuSpLUixhsJCkk9y3YBMBZUweTmdqL7zGpqwjuqdm+HPoPhU8/DJn5YVclSeplDDaSFIK6xmYeXbQZCLqh9VqNtXDX5bD5HcgYBJ96CHL62F49kqRuYbCRpBA89V4JlfXB3jVHjxoUdjldo6UFHvgCrH8FUvvDJx+AvPFhVyVJ6qUMNpIUgr2bBiT01r1rXv5vWPoIJKbA5X+DITPCrkiS1IsZbCSpm20p33vvmqEhV9NFlj8Bz/8wGJ97K4w8Ntx6JEm9nsFGkrrZA28He9fMHjWQEYN6YbvjbSvggauD8awvwOGfDLceSVKfYLCRpG4UjUa5v3UZWq9sGlBXDn+7AuorYMSxcObNYVckSeojDDaS1I3eKS5jTW/du6alBR74IuxYGbR1vvhPkJgcdlWSpD7CYCNJ3aitacBZU3rh3jUv/ghWPAGJqXDpXyEzL+yKJEl9iMFGkrpJXWMzj/TWvWuWPgov/jgYn/c/MPSIcOuRJPU5BhtJ6iZPv7+VyrrWvWtG96K9a0qXwYNfDMZH/TPMuDzceiRJfZLBRpK6ye69a44Y2nv2rqmvgrs/CQ1VMPJ4OP2/wq5IktRHGWwkqRuUlNfxysptQLApZ6/xxNeDZgFZQ+Di220WIEkKjcFGkrrBA+9spCUKs0f2or1rFt0NC++ASAJc+Fvolxt2RZKkPsxgI0ldLBqN7l6G1muaBmxfBY/+WzA+8Rsw8rhw65Ek9XkGG0nqYguLy1izrXXvmmm9YO+apnq477PQWA0jjoMTrg+7IkmSDDaS1NV63d41//gulCyGjEHBErSExLArkiTJYCNJXamusZm/96a9a5Y9Bm/+v2B8wa+h/5Bw65EkqZXBRpK60D9609415RvhoS8F4znXwPgzwq1HkqS9GGwkqQu1LUP7RE/fu6a5Ee77HNSVwZDD4ZTvhV2RJEn7MNhIUhcpKa/j5ba9a47o4cvQnrkRit+A1P5w0R8gKSXsiiRJ2ofBRpK6yIPvbKIlCrNGDmBkbg/eu+a9h+D1XwTjC34FA0eHWo4kSftjsJGkLhCNRrn/7V6wd832lfDwNcH4mK/ApPPCrUeSpAMw2EhSF1i0sZxVpVWkJSdw9tQeundNQzXc/SloqIQRx3pfjSQprhlsJKkL3LegGICzphSSlZYccjUdEI3CI/8K25ZCZgFc9EdI7AV78EiSei2DjSTFWENTC48s2gL04KYBb/0OltwLkUS4+HbIKgi7IkmSPpLBRpJi7KUV2yivbSQ/K5U5Y3rg3jUbF8CTNwTj074PI44Jtx5Jkg6BwUaSYuzhRZsBOG/6EBJ72t411Tvgnk9DS2PQKGDONWFXJEnSITHYSFIMVdc38Y/3SwA4f/qQkKtpp5ZmeODzULERBo6Bj/0KIj0smEmS+iyDjSTF0DNLt1LX2MLIQRlMG5Yddjnt88avYfVzkJwBl/4V0vqHXZEkSYfMYCNJMfTwwmAZ2vkzhhLpSbMdpcvg2R8E4zNvhoLDwq1HkqR2MthIUozsrG7gpRXbgB62DK25ER76Z2iuh7GnwRGfCbsiSZLazWAjSTHy+JItNLVEmTK0P2PzM8Mu59C9citsfgfScuD8n3tfjSSpRzLYSFKM/L1tGVpPmq3Zsghe/HEwPvu/oX9huPVIktRBBhtJioFNZbXMW7eTSCRo89wjNNXDg/8MLU0w6XyYelHYFUmS1GEGG0mKgUda966ZPXIghdnpIVdziJ6/CUrfh4xcOPdWl6BJkno0g40kxUDbMrSPzRgaciWHaMOb8Nr/BuPz/gf65YZbjyRJnWSwkaROWrm1kve3VJCcGOGsKYPDLufgGqqDLmjRFph+OUw6N+yKJEnqNIONJHXS31uXoZ0wLo8B/VJCruYQPPN92LkGsobAmT8KuxpJkmLCYCNJnRCNRvfalLMHNA1Y9wrM+00w/tgvID0n1HIkSYoVg40kdcLC4jI27KwhPTmR0w4rCLucj9ZQAw9fE4yPvArGnhJqOZIkxZLBRpI6oW225vTJBWSkJIVczUE8/0PYtTZYgnbaD8KuRpKkmDLYSFIHNbdEeXTxFgA+Fu/L0DYugDd+FYzPuw3SskMtR5KkWDPYSFIHvb56B9ur6hmQkczx4/LCLufAmurh4S8HXdCmXgLjzwi7IkmSYs5gI0kd9PDCTQCcNbWQ5MQ4/nb68i2wbWmwEadd0CRJvVQc/ySWpPhV19jMk++WAPCx6XG8DK3k3SDYAJz9U+g3KNx6JEnqIgYbSeqAF5aXUlnfRGF2GrNGDgy7nP1rbgqWoLU0wcRzYfLHw65IkqQuY7CRpA7YvXfN9CEkJERCruYAXv8FbFkYNAo45xaIxGmdkiTFgMFGktqpsq6RZ5eVAnG8Kef2VfDCzcH4jJsga3C49UiS1MXaHWxeeuklzjvvPIYMGUIkEuGhhx7a5/2rrrqKSCSyz+Poo4+OVb2SFLqn3ttKQ1MLY/L6cVhh/7DL+bCWFvj7tdBUB2NOhhlXhl2RJEldrt3Bprq6munTp/OLX/zigJ8588wz2bJly+7H448/3qkiJSmetHVD+9iMoUTicXnXgj/ChtcguR+ce5tL0CRJfUK7t8k+66yzOOussz7yM6mpqQwe7LIHSb3Ptsp6Xl21HQjur4k7FVvgmRuD8SnfgQEjQi1HkqTu0iX32Lzwwgvk5+czfvx4vvCFL1BaWnrAz9bX11NRUbHPQ5Li1WOLN9MShelFOYzM7Rd2OR/25DegvgKGHAGzrw67GkmSuk3Mg81ZZ53FHXfcwXPPPcctt9zCW2+9xcknn0x9ff1+P3/zzTeTnZ29+1FUVBTrkiQpZh5eFHRDi8u9a5Y/Ae8/DJFEOO9/ICEx7IokSeo27V6KdjCXXnrp7vGUKVOYOXMmI0aM4LHHHuMTn/jEhz5/ww03cN111+1+XlFRYbiRFJc27KjhnQ1lJETg3GmFYZezr/oqeOxrwXjOl6FwWrj1SJLUzWIebD6osLCQESNGsHLlyv2+n5qaSmpqaleXIUmd9sjiYLZmzphB5PdPC7maD3j+h1CxEXJGwNz/CLsaSZK6XZfvY7Njxw6Ki4spLIyzf92UpHZ6ZulWAM6bFmfL0Da9DW/+v2B87s8gJQ7v/ZEkqYu1e8amqqqKVatW7X6+du1aFi5cyMCBAxk4cCA33ngjF154IYWFhaxbt45vfvOb5Obm8vGPfzymhUtSd2puibJsSyUAM0cOCLmavTQ3wSNfgWgLTL0Yxp4adkWSJIWi3cFm/vz5nHTSSbuft90f85nPfIZf//rXLFmyhD//+c+UlZVRWFjISSedxN13301WVlbsqpakbrZ+RzW1jc2kJScwKjcz7HL2eONXULIE0nLgjJvDrkaSpNC0O9jMnTuXaDR6wPefeuqpThUkSfFoaetszYSCLBIT4mTDy13r4IXWMHP6f0JmXqjlSJIUpi6/x0aSeoOlW4I9tiYV9g+5klbRKDz279BYAyOOg8M/FXZFkiSFymAjSYcg7oLNu/fDqmcgMQXOuw0icTKLJElSSAw2knQI4irYVO+AJ1tbOh//NcgdF249kiTFAYONJB1EWU0Dm8vrAJhYGHIjlJYWeOALUL0NcifAcV8Ntx5JkuKEwUaSDuL91tmaYQPS6Z+WHG4xL98Cq5+FpDS46A+Q5AbHkiSBwUaSDqqtI1roy9DWvAgv3BSMz7kFBk8Jtx5JkuKIwUaSDiIu7q+p2AL3fy7YiHPGJ+HwT4ZXiyRJcchgI0kH0RZsDgsr2DQ3BaGmehvkT4azfxpOHZIkxTGDjSR9hMbmFlZurQJCDDbP/xesfxVSMuGSP0FKRjh1SJIUxww2kvQR1myrpqG5hczUJIYNSO/+ApY/Ca/cGozP/7mtnSVJOgCDjSR9hLZlaBMHZ5GQ0M2bYO5aDw9+MRjPvhqmfKJ7v74kST2IwUaSPkJojQOaGuDeq6CuDIYcAaf/V/d+fUmSehiDjSR9hPfDCjZPfxs2vw1pOXDx7e5XI0nSQRhsJOkj7NnDJqv7vuh7D8K83wTjj/8GBozovq8tSVIPZbCRpAMoraxje1U9kQhMGNxNwWb7Knj42mB87Fdhwpnd83UlSerhDDaSdABtszWjBvUjIyWp679gQw3c82loqIQRx8LJ3+n6rylJUi9hsJGkA9jdOGBIN91f88T1UPoe9MuDi/4Aid0QpiRJ6iUMNpJ0AG3Bpls25nznDnjnr0AELvw9ZA3u+q8pSVIvYrCRpAPY0+q5i++vKVkCj/17MD7pmzD6xK79epIk9UIGG0naj7rGZlZvqwa6uNVzzU7425XQVAtjToHjv9Z1X0uSpF7MYCNJ+7GqtIrmlig5GckM7p/WNV+kpRnu/zyUrYecEXDh7yDBb8uSJHWEP0ElaT92b8w5uD+RSKRrvsjzN8HqZyEpHS67AzIGds3XkSSpDzDYSNJ+7Lm/pouWoS19FF7+72B8/v/C4Kld83UkSeojDDaStB9d2jhg2wp48J+D8VH/AtMuif3XkCSpjzHYSNIHRKNR3t/cRTM2dRXwtytaN+E8Dk7/z9heX5KkPspgI0kfsLm8joq6JpISIowryIzdhVta4KF/gR0rIWsIXPxHSEyO3fUlSerDDDaS9AFLW2drxuZnkpqUGLsLv/IzWPYoJKbApX+BzPzYXVuSpD7OYCNJH9AljQNWPgPP/VcwPvunMGxm7K4tSZIMNpL0QUtLYtw4YOdauP9zQBSO+AwceVVsritJknYz2EjSByzdUgnEaMamoQbu/iTUlcHQI4PZGkmSFHMGG0naS01DE+t2VAMxCDbRKDzyFdj6LvTLg0v+AkmpMahSkiR9kMFGkvby7qYKolEo6J9KbmYnQ8gbv4Yl90IkES6+HbKHxqRGSZL0YQYbSdrLwuJdAMwoyunchda9Ak9/Oxif8UMYeVznridJkj6SwUaS9rKwuAyAGUUDOn6RnWvhnk9DtBmmXgJH/XNsipMkSQdksJGkvbyzoQzoxIxNXTncdRnU7IDC6XDe/0AkErP6JEnS/hlsJKnV1oo6tpTXkRCBacOy23+B5ia497OwbRlkFcLlf4OUjNgXKkmSPsRgI0mt2mZrxhdk0S81qf0XeOoGWP0sJGcEoab/kNgWKEmSDshgI0mt9txfk9P+k+f9Fub9XzD++G9gyIxYlSVJkg6BwUaSWnW4I9qqZ+GJbwTjU74Hh50f28IkSdJBGWwkCWhuibJkYzkAM4bnHPqJpcvg3quCDmjTr4Dj/q1L6pMkSR/NYCNJwMrSSqobmumXksi4/KxDO6l6O9x5CdRXwPBj4Lzb7IAmSVJIDDaSBCxsbRwwdVg2iQmHEE6a6uHuT0LZehgwEi79KySldmmNkiTpwAw2kkQ7N+aMRuGRr8KG1yG1P1x+N/Qb1KX1SZKkj2awkSTa2RHtlVth0Z0QSYSL/wj5E7u0NkmSdHAGG0l9XnV9Eyu2VgJw+MEaB7z/d3j2+8H4rB/D2FO7tjhJknRIDDaS+rzFG8tpiUJhdhoF/dMO/MHNC+HBLwbj2VfD7C90S32SJOngDDaS+rxDWobW0hyEmsYaGHMKnHFzt9QmSZIOjcFGUp93SBtzLvobbFsGaTlw0e8hMalbapMkSYfGYCOpzzvojE1jHbzQOkNz/L9D+iF0TpMkSd3KYCOpT9tSXsvWinoSEyJMHZa9/w/N/z2UF0P/od5XI0lSnDLYSOrT2jbmHF+QRUbKfpaX1VXAS/8djOf+BySnd19xkiTpkBlsJPVpB12G9vovoHYnDBoH06/otrokSVL7GGwk9WnvtAabw/cXbKpK4bVfBONTvmPDAEmS4pjBRlKf1dTcwpKN5QDM2N/GnC/9NzRWw5AjYNL53VucJElqF4ONpD5rxdYqahubyUxNYkxe5r5v7loH8/8QjE+9ESKR7i5PkiS1g8FGUp/Vdn/NtGHZJCZ8ILg8fxO0NMLok2D0id1fnCRJaheDjaQ+64Abc5a8C4vvCcanfq97i5IkSR1isJHUZx2wI9pz/wlEYfLHYcjh3V2WJEnqAIONpD6psq6RlaVVwAcaB6x9GVY8CZFEOOnb4RQnSZLazWAjqU9asrGcaBSG5qSTn5UWvNjSDE/dEIxnfhZyx4ZXoCRJaheDjaQ+6Z39LUNbdBeULIHUbJj7zVDqkiRJHWOwkdQnfej+mvoqePYHwfjE66HfoFDqkiRJHWOwkdTnRKNR3tnQ2hGt7f6aV2+Dqq0wYBTMvjq02iRJUscYbCT1OWu2V7O9qoGUpASmDcuGsmJ47efBm6f9AJJSwy1QkiS1m8FGUp/z1tqdAMwYlkNqUiI8+31oqoMRx8Gk80KuTpIkdYTBRlKfM29dEGxmjRoAG+fDknuBCJzxQ4hEwi1OkiR1SFLYBUhSd5u/Lri/ZtaIAfDUV4IXZ1wBQ2aEV5QkSeoUZ2wk9SlbK+rYsLOGhAgcVfsiFL8Jyf3g5O+EXZokSeoEZ2wk9SnzWu+vmTY4jfQX/iN48bivQv/C8IqSJEmd5oyNpD7lrdb7a65JfxrKN0D/oTDnmpCrkiRJnWWwkdSnzFu7k4FUcGLpX4IXTvkepGSEW5QkSeo0g42kPqO8tpHlWyu5NulBkpuqoXAGTL047LIkSVIMGGwk9RkL1u9kOCV8KumZ4IXTfgAJfhuUJKk38Ce6pD5j3tpdXJ90N0k0w9jTYPSJYZckSZJixGAjqc8oW/ka5ya+SZQInPb9sMuRJEkxZLCR1CfUNTRx4fbfAFA16RIomBxyRZIkKZYMNpL6hHWvP8CshGXUkULmmd8NuxxJkhRjBhtJvV9zE/lv3ATAiwMuIpI9LOSCJElSrBlsJPV+C//KwNq17Ixmsn36v4RdjSRJ6gIGG0m9W0M10eeD2Zr/bfoEM8aPCLkgSZLUFQw2knq3139JpGor61vyeTjpTCYO7h92RZIkqQsYbCT1XlWl8Or/APDTpkuZPjKPxIRIyEVJkqSuYLCR1Hu9+BNoqGJd6gQeazmKWSMHhl2RJEnqIgYbSb3TjtWw4I8A3Nx4OVESmD3KYCNJUm9lsJHUOz3/Q2hpomb4yTxVM56UpASmDcsOuypJktRFDDaSep/NC+Hd+wF4ecSXAJgxLIfUpMQQi5IkSV3JYCOp93n2+8Fx6sU8vSMfgFmjBoRYkCRJ6moGG0m9y5oXYfVzkJAMJ32Lt9btBLBxgCRJvZzBRlLvEY3CMzcG45mfZWtSIRt21pAQgSNHOGMjSVJvZrCR1Hu8/zBsfhuS+8EJ1zNvbTBbM6mwP1lpySEXJ0mSupLBRlLv0NwEz/1nMD7mGsjMdxmaJEl9iMFGUu/wzl9gxyrIGARzrgHg9dU7ADjK/WskSer1DDaSer6GGnjhR8H4hOshrT9bK+pYWVpFJAJzxgwKtz5JktTlDDaSer43/x9UlUDOcJj5TwC8snI7AFOHZpOTkRJmdZIkqRsYbCT1bDU74ZXbgvFJ34KkVABeXRUEm+PG5oZUmCRJ6k4GG0k926u3QX055E+GqRcDEI1GecVgI0lSn2KwkdRzVWyBN38TjE/5LiQkArCytIrSynrSkhM4wv1rJEnqEww2knqul34CTXVQdBSMP2P3y23318waOZC05MSwqpMkSd3IYCOpZ9q5Bt7+czA+5XsQiex+q20Z2vHjXIYmSVJfYbCR1DM9fxO0NMHYU2Hksbtfbmxu4Y01wf41x3p/jSRJfYbBRlLPU/IuLLkvGJ/y3X3eemdDGTUNzQzql8Kkwf1DKE6SJIXBYCOp53nuP4EoTP4EFE7f5622ZWjHjM0lISGyn5MlSVJvZLCR1LNseANWPAmRRDj52x96+5WV2wA4buyg7q5MkiSFyGAjqeeIRuHZHwTjwz8Jg8bs83ZFXSOLNpYDcNy4vO6uTpIkhchgI6nnWPUsrH8VElPhxG986O031+ykuSXKqNx+DM1JD6FASZIUFoONpJ6hpQWe/X4wnv0FyB76oY/sWYZmNzRJkvoag42knuH9B6FkMaRkwXHX7fcjbY0DbPMsSVLfY7CRFP+aG+G5HwbjY66Ffh9uDLClvJbV26pJiMCcMTYOkCSprzHYSIp/C++EnashIxfmfGm/H3llZTBbM21YDtnpyd1ZnSRJigMGG0nxrakeXvxJMD7+OkjN2u/H2paheX+NJEl9k8FGUnxbcDtUbISsITDzc/v9SDQa5dW2YDPOYCNJUl9ksJEUvxpq4KX/DsYnXg/Jafv92PKtlWyvaiA9OZHDh+d0X32SJCluGGwkxa95/wfVpZAzAmZ88oAfa7u/5qjRA0lNSuyu6iRJUhwx2EiKT3UV8OptwXjuDZCUcsCPen+NJEky2EiKT2/8Cmp3Qe54mHbJAT9W39TMm2t2At5fI0lSX2awkRR/anbC678Mxid9ExIOvLzsnQ1l1DY2k5uZwoSC/XdMkyRJvZ/BRlL8efV/oL4CCqbCpI995EefXboVCJahRSKR7qhOkiTFIYONpPhSuRXe/E0wPvnbkHDgb1PRaJTHl5QAcOaUwu6oTpIkxSmDjaT48sqt0FQLQ2fC+DM+8qOLNpazqayWjJRE5k7I66YCJUlSPDLYSIof5Rth/u+D8cnfhoMsLXt8yZbgoxPzSUu2zbMkSX2ZwUZS/Hjpp9DcACOPh9FzP/KjwTK0INicM9VlaJIk9XUGG0nxYecaeOevwfgQZmuWbCpn465a0pMTmTshvxsKlCRJ8cxgIyk+vPwzaGmCsafC8KMP+vHH2pahTconPcVlaJIk9XUGG0nhK98Ii/4WjE/8xkE/7jI0SZL0QQYbSeF79X+hpTG4t6Zo9kE//u6mCop31pKWnGA3NEmSBBhsJIWtqhTe/lMwPuFrh3TK4+/u6YaWkZLUVZVJkqQexGAjKVyv/xKa6oJ9a0adeNCP770M7WyXoUmSpFYGG0nhqd0Fb7XuW3PC1w7aCQ3gvc0VrN9RQ1pyAidPtBuaJEkKGGwkhefN/4OGSiiYAuPPPKRT2mZrTprgMjRJkrSHwUZSOOor4Y1fBePjrzuk2Zq9l6Gd5TI0SZK0F4ONpHDM/wPUlcGgsXDYBYd0ytItlazbUUNqUgKnuAxNkiTtxWAjqfs11sJrvwjGx/0bJBzaBpttszVzJ+TRL9VlaJIkaQ+DjaTu985foboUsotg2qWHdIrd0CRJ0kcx2EjqXs2N8Or/BONj/xUSkw/ptGUllazZXk1KUgKnTCrowgIlSVJPZLCR1L0W3w3lxdAvHw7/5CGf1jZbc+L4PDJdhiZJkj7AYCOp+7S0wCu3BuNjroHk9EM6LRqN8lhrsDnHZWiSJGk/DDaSus/yx2HHKkjLhpn/dMinrdhaxZptbcvQ7IYmSZI+zGAjqfu89r/BcebnIDXrkE974J2NAJwwLo+stEO7J0eSJPUtBhtJ3WPDm1D8JiSmwFFfPOTTGptbuH/BJgAuOnJYV1UnSZJ6OIONpO7RNlsz7VLIGnzIpz2/rJTtVfXkZqa4DE2SJB2QwUZS19u+CpY9FoyPubZdp94zP1iG9okjhpGc6LcsSZK0f/6WIKnrvf5zIArjz4K8CYd8WmlFHc8vLwXgkplFXVScJEnqDQw2krpWVSksvCsYH/uVdp16/9ubaG6JcuSIAYzNz+yC4iRJUm9hsJHUteb9HzTXw9CZMHzOIZ8WjUa5d34xAJfMtGmAJEn6aAYbSV2noRre+l0wPvYrEIkc8qlvrdvFmu3VZKQkcs60IV1UoCRJ6i0MNpK6zjt/hdpdMHA0TDy3Xafe/VYwW3PutEIyU5O6ojpJktSLGGwkdY3mJnj9F8F4zpchIfGQT62sa+TxJVsAuHSWTQMkSdLBGWwkdY2lD0PZBsgYBDOubNepjyzaQm1jM2Py+nHE8AFdVKAkSepNDDaSYi8ahVdbN+ScfTUkp7fr9LtbmwZcOquISDvuy5EkSX2XwUZS7K17GbYshKR0mPWFdp26vKSSRcVlJCVE+PjhdkOTJEmHxmAjKfZe/Z/gePiV0G9Qu069p3W25uSJ+eRlpca6MkmS1EsZbCTFVskSWPUMRBJgzjXtOrWhqYUH39kE2DRAkiS1j8FGUmy13Vtz2AUwcFS7Tn1m6VZ2VjeQn5XKiePzYl+bJEnqtQw2kmJn13p49/5gfOy/tvv0tr1rLjpyGEmJfnuSJEmHzt8cJMXOG7+CaDOMngtDZrTr1M1ltby0chsAl8x0GZokSWofg42k2KjZCW//ORgf+9V2n37fgo1EozB71EBG5vaLbW2SJKnXM9hIio15v4XGGhg8LZixaYeWlujubmiX2TRAkiR1gMFGUuc11MC83wTj474K7dxU8/U1O9i4q5as1CTOmlIY+/okSVKvZ7CR1Hnv/BVqdkDOCJj0sXaf/rfWpgHnzxhCekpirKuTJEl9gMFGUuc0N8HrPw/Gx1wLiUntOr2spoGn3isB3LtGkiR1nMFGUue8/xCUbYCMXDj8k+0+/aF3NtHQ1MKkwv5MHZod+/okSVKf0O5g89JLL3HeeecxZMgQIpEIDz300D7vR6NRbrzxRoYMGUJ6ejpz587lvffei1W9kuJJNAqv3haMj/oiJKe38/To7mVol84cRqSd9+ZIkiS1aXewqa6uZvr06fziF7/Y7/s/+clP+NnPfsYvfvEL3nrrLQYPHsxpp51GZWVlp4uVFGdWPwclSyA5A2Z9vt2nL9lUzrKSSlKSErjg8KFdUKAkSeor2rcYHjjrrLM466yz9vteNBrltttu41vf+haf+MQnAPjTn/5EQUEBd955J1/84hc7V62k+NI2W3PEZyBjYLtPv7t1tubMyYPJyUiJYWGSJKmviek9NmvXrqWkpITTTz9992upqamceOKJvPbaa/s9p76+noqKin0eknqATW/D2pcgkghzvtzu02sbmvn7ws2ATQMkSVLnxTTYlJQEnY0KCgr2eb2goGD3ex908803k52dvftRVOQvOFKP8Nr/BsepF0FO+//ePvHuFirrmygamM6c0YNiXJwkSepruqQr2gdvAI5Gowe8KfiGG26gvLx896O4uLgrSpIUS2Ub4P2Hg/Ex13boEm1NAy4+soiEBJsGSJKkzmn3PTYfZfDgwUAwc1NYuGf38NLS0g/N4rRJTU0lNTU1lmVI6mpv/gaiLTB6Lgye2u7T126vZt7anSRE4KIjh8W+PkmS1OfEdMZm1KhRDB48mH/84x+7X2toaODFF1/kmGOOieWXkhSWugp4+8/B+Oj231sDcM/8YLbmhPF5DMlpX4toSZKk/Wn3jE1VVRWrVq3a/Xzt2rUsXLiQgQMHMnz4cL761a9y0003MW7cOMaNG8dNN91ERkYGV1xxRUwLlxSSd/4K9RWQOx7Gntru05uaW7h/wUYALp3pPXWSJCk22h1s5s+fz0knnbT7+XXXXQfAZz7zGW6//Xa+/vWvU1tby5e+9CV27drFUUcdxdNPP01WVlbsqpYUjuYmePPXwfjoL0FC+yd9X1i+jdLKegb1S+GUSftfoipJktRe7Q42c+fOJRqNHvD9SCTCjTfeyI033tiZuiTFo2WPBo0D0gfC9Ms6dIm2pgGfOGIoKUld0r9EkiT1Qf5WIenQvf7L4Djr85Dc/ntjSivreH55KQCXuAxNkiTFkMFG0qEpngcb50FiShBsOuChdzbR3BLl8OE5jCtweaokSYodg42kQ9M2WzP1Eshq/70x0WiUe+YHTQMuPtLZGkmSFFsGG0kHt2s9LP17MJ7zpQ5dYmFxGatKq0hLTuDc6YUHP0GSJKkdDDaSDm73hpwnQcHkDl2ibbbmrCmF9E9LjmV1kiRJBhtJB1FXvmdDzjnXdOgStQ3NPLpoMwAXzxwWq8okSZJ2M9hI+mhv/wUaKiFvIow9pUOXeOq9Eirrmxg2IJ2jRw2KcYGSJEkGG0kfpbkpWIYGwYackUiHLnPP/GDvmouPLCIhoWPXkCRJ+igGG0kHtuxRKN8AGbkw7ZIOXaJ4Zw2vrd5BJAIXHjk0xgVKkiQFDDaSDmz+74PjkVd1aENOgPsWBE0Djh2Ty7ABGTEqTJIkaV8GG0n7t2M1rH0JiMCRn+nQJVpaoruDjU0DJElSVzLYSNq/BX8MjuNOh5zhHbrE62t2sKmslqy0JM6YPDiGxUmSJO3LYCPpwxrr4J07gvHMz3b4Mve2Ng04f/oQ0pITY1GZJEnSfhlsJH3Y0kegdif0HwpjT+vQJSrqGnni3RIALplZFMvqJEmSPsRgI+nD2pahHfFpSEzq0CUeWbSZ+qYWxhdkMm1YdgyLkyRJ+jCDjaR9bVsO61+FSGIQbDro3vmtTQOOLCLSwf1vJEmSDpXBRtK+5rfO1ow/E/oP6dAlVm6tZGFxGUkJES443L1rJElS1zPYSNqjsRYW3RmMO9E04O63gqYBJ03MJy8rNRaVSZIkfSSDjaQ93nsI6soheziMOblDl6hrbOa+t4NlaJfPtmmAJEnqHgYbSXvM/0NwPPIzkNCx9sxPvLuFsppGhuakc+L4/BgWJ0mSdGAGG0mBre/BxnmQkASHf6rDl7nzzQ0AXDqriMQEmwZIkqTuYbCRFGhrGjDhbMgq6NAlVmyt5K11u0hMiHDpLJehSZKk7mOwkQQN1bD47mDciaYBbbM1p07Kp6B/WiwqkyRJOiQGG0nw7v1QXwEDRsKouR26RF1jMw+0Ng244qgRMStNkiTpUBhsJO1ZhnbkZyGhY98WHl28hYq6JooGpnP82NwYFidJknRwBhupr9v0Nmx+GxKSYcaVHb7MnW+uB+CyWcNJsGmAJEnqZgYbqa+b//vgOPkCyMzr0CWWbqng7Q1lJCVEuHjmsNjVJkmSdIgMNlJfVrsLltwXjGd9vsOXaWsacPrkAvKzbBogSZK6n8FG6ssW3glNdVAwBYqO6tAlahqaeOidTQBcMdumAZIkKRwGG6mvammBt1qXoc36HEQ6dl/MI4s2U1nfxMhBGRwzZlAMC5QkSTp0Bhupr1r7AuxcDan9YeolHb5M2zK0y2fbNECSJIXHYCP1VW2zNdMvh9TMDl3i3U3lLNpYTkpiAhcdadMASZIUHoON1BeVb4TljwfjWZ/r8GXunBfM1pwxZTCDMlNjUZkkSVKHGGykvmjB7RBtgZHHQ96EDl2iqr6Jh3c3DRgew+IkSZLaz2Aj9TVNDbDgT8G4Ey2eH164ieqGZkbn9ePo0QNjVJwkSVLHGGykvmbp36G6FDIHw8RzOnyZu98qBoLZmkgHO6pJkiTFisFG6mvamgYceRUkJnfoEstKKli8sZzkxAgfP3xo7GqTJEnqIION1JdsfQ82vAaRxCDYdNC98zcCcMrEApsGSJKkuGCwkfqSttmaSedC/8IOXaKhqYUHW5sGXDLLFs+SJCk+GGykvqKuAhbfHYw70TTguWVb2VndQH5WKieMy4tRcZIkSZ1jsJH6isV3Q0MV5I4P2jx3UNsytE8cMYykRL+FSJKk+OBvJVJfEI3uWYY283PQwS5mWyvqeH55KQAXz3QZmiRJih8GG6kvWPcKbFsKyf1gxuUdvswDb2+iJQozRwxgTF5mDAuUJEnqHION1Be89dvgOO0SSMvu0CWi0Sj3Lgj2rnG2RpIkxRuDjdTbVWyGpY8G49lf6PBl3t6wizXbqklPTuScaUNiVJwkSVJsGGyk3m7B7RBthuHHQMHkDl/mnreCpgHnTCskMzUpRsVJkiTFhsFG6s2aGoJgA52aralpaOLRxZsBuPhIl6FJkqT4Y7CRerNlj0DVVsgcDJPO6/BlHl9SQnVDMyMHZTB71MAYFihJkhQbBhupN5v3u+B45FWQmNzhy9wzv61pQBGRDraKliRJ6koGG6m32voebHgNEpKCYNNB67ZXM2/tThIi8IkjhsauPkmSpBgy2Ei91bzWFs8Tz4X+hR2+zH0LgqYBx4/LozA7PRaVSZIkxZzBRuqN6sph8T3BuBNNA5pboruDzSUzi2JRmSRJUpcw2Ei90cK7oLEa8ibBiGM7fJmXV26jpKKOnIxkTj0sP4YFSpIkxZbBRuptolF4q7VpwOzPQydu9n/wnU0AnD99CKlJibGoTpIkqUsYbKTeZs0LsGMlpGTBtEs7fJmq+iaeeq8EgE8c4d41kiQpvhlspN6mbbZmxuWQmtXhyzz9Xgl1jS2Myu3H9GHZMSpOkiSpaxhspN6krBiWPx6MZ32+U5dqW4Z2wYyh7l0jSZLinsFG6k0W3A7RFhh1AuRN6PBltlbU8eqq7QB8/HD3rpEkSfHPYCP1Fs2N8Pafg/HMz3XqUo8s2kxLFI4cMYDhgzJiUJwkSVLXMthIvcWyR6G6FDILYOI5nbrUA2+3LkNztkaSJPUQBhupt5j/h+B4xKchMbnDl1leUsn7WypIToxw7tTCGBUnSZLUtQw2Um+wfSWsfQkiCXDEZzp1qYcWBrM1cyfkM6BfSiyqkyRJ6nIGG6k3WHB7cBx3OuQUdfgyLS1RHm7thmbTAEmS1JMYbKSerrEWFt4RjDvZNODNtTvZXF5HVloSJ0/Mj0FxkiRJ3cNgI/V07z0EtbsgeziMPaVTl3qodbbmnKmFpCUnxqA4SZKk7mGwkXq6tqYBR34GEjoeRuoam3l8yRbAbmiSJKnnMdhIPVnJEtg4DxKS4PBPdepSzy4tpbK+iaE56cweOTBGBUqSJHUPg43Uk83/Y3CcdB5kFXTqUg+2LkP72IwhJCREOluZJElStzLYSD1VfSUsvjsYz/ynTl1qZ3UDLywvBeyGJkmSeiaDjdRTLbkXGqpg0FgYeXynLvXYki00tUSZPKQ/4wqyYlSgJElS9zHYSD1RNApvtTYNmPlPEOnc0rEH394IOFsjSZJ6LoON1BNtWgBbl0BSGky/vFOXWrOtirc3lJEQgfOnD4lRgZIkSd3LYCP1RG/9PjhO/gRkdK6D2b0LgtmauRPyye+f1tnKJEmSQmGwkXqa2l3w3gPBuJNNA5qaW7i/NdhcMnNYZyuTJEkKjcFG6mmW3AdNdVAwBYbN7NSlXlyxjdLKegb2S+HkiZ1rFy1JkhQmg43U0yz6W3CccWWnmwbcM78YCJoGpCT57UCSJPVc/iYj9STbV8Km+RBJhKkXde5SVfU8uzTYu+aSmUWxqE6SJCk0BhupJ2mbrRl7KmTmd+pSD769iaaWKNOLcpgw2L1rJElSz2awkXqKlhZYfHcwnn5Zpy4VjUZ3L0OzaYAkSeoNDDZST7H+VSgvhtRsmHBWpy61sLiMlaVVpCUncJ5710iSpF7AYCP1FIvuCo6TL4Dk9E5d6p75QYvns6cU0j8tuZOFSZIkhc9gI/UEDdXw/sPBeMYVnbpUTUMTjyzaDMDFNg2QJEm9hMFG6gmWPQYNVTBgJBQd1alLPbGkhKr6JoYPzOCoUQNjU58kSVLIDDZST9C2DG365THbu+aSmcNISOjctSRJkuKFwUaKdxWbYc0LwXjapZ261Lrt1by5dieRCFx4pN3QJElS72GwkeLdknsh2gLD58DAUZ261L0LgtmaE8blUZjduQYEkiRJ8cRgI8WzaBQWti1D69zeNc0tUe5bEHRDu8SmAZIkqZcx2EjxbMsi2LYUElNh8sc7damXVm5ja0U9AzKSOfWw/BgVKEmSFB8MNlI8W/S34DjxHEjL7tSl7m1tGnDB4UNJTUrsbGWSJElxxWAjxavmxuD+Ggi6oXXCjqp6/vH+VgAuPtJlaJIkqfcx2EjxatWzULMd+uXBmJM7damHFm6msTnK1KHZHDakf4wKlCRJih8GGylete1dM/USSEzq8GWi0Sj3vNW6d80sZ2skSVLvZLCR4lFdBSx/Ihh3shva4o3lLN9aSWpSAudPHxKD4iRJkuKPwUaKR6uegeZ6GDQWCqd16lJ3tzYNOGvKYLLTk2NRnSRJUtwx2EjxaPnjwXHC2Z26TG1DM48s3Ay4d40kSerdDDZSvGluhJVPB+OJ53TqUk++t4XK+iaKBqZz9OhBMShOkiQpPhlspHiz/lWoK4eMXBg2q1OXuru1acDFRxaRkBCJRXWSJElxyWAjxZtlbcvQzoSEjm+kuX5HNW+s2UkkAhceOSxGxUmSJMUng40UT6LRve6v6dwytHvnbwTguLG5DM1J72xlkiRJcc1gI8WTkiVQXgxJ6TB6bocv09wS5b4FQbC51L1rJElSH2CwkeJJ22zNmJMhJaPDl3l55TZKKurIyUjmtMMKYlScJElS/DLYSPFk2WPBcWLn2jzf07p3zQUzhpKa1PH7dCRJknoKg40UL8qKoWQxRBJg/JkdvszO6gb+8f5WwL1rJElS32GwkeLF8ieCY9FR0C+3w5d58J1NNDZHmTK0P4cN6R+j4iRJkuKbwUaKF8tbl6FN6PgytGg0yr2ty9AudbZGkiT1IQYbKR7UlsG6V4LxxI63eV68sZxlJZWkJCVw/vShsalNkiSpBzDYSPFg5T+gpQlyJ8CgMR2+zN2tszVnTh5MdkZyrKqTJEmKewYbKR4s73w3tJqGJh5ZuBmAy9y7RpIk9TEGGylsTfWw8plgPKHjy9AeX1JCZX0TRQPTOXr0oBgVJ0mS1DMYbKSwrXsZGiohswCGHtnhy9zz1p6mAQkJkVhVJ0mS1CMYbKSwLXs8OI4/ExI69ldy9bYq5q3bSUIELjrSZWiSJKnvMdhIYYpG9+xf04luaPe0Ng2YOyGfwdlpsahMkiSpRzHYSGHa/A5UbobkfjDqxA5dorG5hfsXbATgUpsGSJKkPspgI4VpeesytLEnQ3LHZlqeW1bK9qoGcjNTOXlifgyLkyRJ6jkMNlKYVj0bHCd0vM3z3a1NAy48cijJif6VliRJfZO/BUlhqa+CLYuC8agTOnSJkvI6XlheCgTd0CRJkvoqg40Ulo3zINoM2cMhe1iHLnHfgmJaojB75EBG52XGuEBJkqSew2AjhWX9a8FxxDEdOr2lJcrdrd3QbBogSZL6OoONFJb1rwfHEXM6dPoba3ZQvLOWrNQkzp5aGMPCJEmSeh6DjRSGpnrY+FYwHnFshy7xt9amAefPGEJ6SmKsKpMkSeqRDDZSGDa/A8310C8PBo1t9+llNQ08+V4JAJfNGh7r6iRJknocg40UhvWvBsfhcyASaffpD72ziYamFg4r7M+Uof1jXJwkSVLPY7CRwrD7/pr2Nw6IRqO7l6FdOquISAeCkSRJUm9jsJG6W0szFL8ZjDsQbJZsKmdZSSUpSQlcMGNojIuTJEnqmQw2Unfb+i7UV0BqfyiY0u7T752/EYAzJw8mOyM51tVJkiT1SAYbqbu17V9TdBQktK+bWV1jMw8v3AS4d40kSdLeDDZSd9u9MWf796956r0SKuqaGJqTzpzRg2JcmCRJUs9lsJG6UzS6V7Bp//41bcvQLjpyGAkJNg2QJElqY7CRutOOVVCzHRJTYcjh7Tp1464aXl29HQiCjSRJkvYw2EjdqW3/mmGzICm1Xafev2AT0SgcM2YQRQMzuqA4SZKknstgI3Wn3fvXtO/+mpaWKPcuCPauuWSmTQMkSZI+yGAjdafd99e0b/+aN9bsYOOuWrLSkjhzyuAuKEySJKlnM9hI3aWsGMo3QCQRhs1u16n3zA9ma86fPoS05Pa1iJYkSeoLDDZSd9nQugytcDqkZh7yaRV1jTzxbgkAF7sMTZIkab8MNlJ36eAytEcWbaa+qYXxBZlMH5bdBYVJkiT1fAYbqbt0MNjc07p3zSUzi4hE3LtGkiRpfww2Uneo3g7blwfj4YfeEW3F1koWFZeRlBDhgsOHdlFxkiRJPZ/BRuoObffX5E2CjIGHfNq9rU0DTp6YT25m+/a9kSRJ6ksMNlJ36MD+NY3NLTzw9ibAvWskSZIOxmAjdYf1rwbHEcce8inPLStlR3UDeVmpzJ2Q10WFSZIk9Q4GG6mr1VdCyeJg3I77a9qWoX3i8KEkJfpXVZIk6aP425LU1YrfhGgL5IyA7ENrALCjqp7nl28D4OKZw7qyOkmSpF7BYCN1teK3gmM7ZmuefK+E5pYoU4dmMzY/q4sKkyRJ6j0MNlJXK1kSHIfMOORTHl20BYBzphV2QUGSJEm9j8FG6mptwWbw1EP6eGllHW+u3QHAOVMNNpIkSYfCYCN1pdpdUL4hGBdMOaRTnny3hJYoTC/KoWhgRhcWJ0mS1HsYbKSuVPJucMwZDuk5h3RK2zK081yGJkmSdMgMNlJX2r0Mbdqhfby8jrfW7wTgbJehSZIkHTKDjdSV2nl/zeNLthCNwpEjBjAkJ70LC5MkSepdDDZSV2pnsHlsSWs3NGdrJEmS2sVgI3WVpgbYtiwYH0Kw2VxWy4L1u4hEXIYmSZLUXgYbqatsWwYtjZCWDdlFB/34462zNbNGDGRwdlpXVydJktSrGGykrrJ344BI5KAff2RxEGzOne5sjSRJUnsZbKSu0o77a4p31rCouIyECJw5ZXAXFyZJktT7GGykrtKOYNPWNOCoUYPIz3IZmiRJUnsZbKSuEI22K9g8ungzAOe4KackSVKHGGykrlC2AerLISEZcid85EfXba/m3U0VJCZEOMtlaJIkSR1isJG6QttsTf5ESEr5yI+2LUM7ZswgBmWmdnVlkiRJvZLBRuoKe3dEO4hHF7sppyRJUmcZbKSucIj316zeVsXSLRUkJUQ4Y7LL0CRJkjoq5sHmxhtvJBKJ7PMYPNhf2NTHHGKweax1tubYsbkM6PfRS9YkSZJ0YEldcdHJkyfzzDPP7H6emJjYFV9Gik+1u6B8QzAumPKRH33y3RLAbmiSJEmd1SXBJikpyVka9V0l7wbHnOGQnnPAj20uq+X9LRVEInDKxPzuqU2SJKmX6pJ7bFauXMmQIUMYNWoUl112GWvWrDngZ+vr66moqNjnIfVoh9g44LllpQAcXpRjNzRJkqROinmwOeqoo/jzn//MU089xW9/+1tKSko45phj2LFjx34/f/PNN5Odnb37UVRUFOuSpO51iPfXtAWbUyYVdHVFkiRJvV7Mg81ZZ53FhRdeyNSpUzn11FN57LHHAPjTn/6038/fcMMNlJeX734UFxfHuiSpex1CsKltaObVVdsBOGWSy9AkSZI6q0vusdlbv379mDp1KitXrtzv+6mpqaSmugxHvURTPWxbGow/Yinaq6u2U9/UwtCcdCYUZHVTcZIkSb1Xl+9jU19fz9KlSykstOuT+oBty6ClCdJyIHvYAT/27O5laPlEIpFuKk6SJKn3inmw+drXvsaLL77I2rVrefPNN7nooouoqKjgM5/5TKy/lBR/9l6GdoDAEo1GeW7ZVgBO/v/t3Xl01fWd//HXvTd7yAIJCUs2tpAAIhBkC1qsgGWxIIxaxO0wap0BFZl6BrpMrVNLh7bUqQoFbRmnrT+ZHquiAxbEYV8CgQBCCHsCJCEkZCUhy73f3x+XXIhhCyT55pv7fJzDuZfv/d7kFc7lnLzO9/N5f5mGBgAA0CyafSnamTNnNGPGDBUWFqpz584aMWKEduzYofj4+Ob+VkDbcwsT0Q7mlulcWbWC/Bwa0TOilYIBAAC0b81ebD788MPm/pKAddzC4ID1me5laKN7RyrAl5vXAgAANIcW32MDeA3DuKViU78MjWloAAAAzYdiAzSXkmypukxy+EmRidc8paDskvadKZUk3d+XYgMAANBcKDZAc6m/WtM5SfLxu+Yp/5flXoZ2d0yYokIDWisZAABAu0exAZrLLQwOqN9f8+2k6NZIBAAA4DUoNkBzucn+mku1Tm05ViiJ/TUAAADNjWIDNJebFJsdJ4pUWeNUdKi/+ncLbcVgAAAA7R/FBmgOlRek0tPu510GXPOUrw5fWYZmu87NOwEAAHB7KDZAc8jd637smCAFhDV62TAMz/6aB5JYhgYAANDcKDZAc8je5n6MHXHNl7POletsSZX8fexK7R3ZisEAAAC8A8UGaA45292P8aOu+XL91ZrU3pEK9HO0VioAAACvQbEB7lRdtXRmt/v5dYpN/f4apqEBAAC0DIoNcKfO7pGc1VJwZymid6OXL1ys0Z6cYknSt9lfAwAA0CIoNsCdyrm8vyZupHSNaWcbsgpkGFK/rqHqGhbYyuEAAAC8A8UGuFP1gwOuswxt05HzkqT7kzq3ViIAAACvQ7EB7oTLKeXsdD+/RrExDENbjhVJkkb3ptgAAAC0FIoNcCfyD0g15ZJ/qBTd+MacR85VqLCiWoG+Dg2JD2/9fAAAAF6CYgPcifoxz7HDJXvjMc6bj7qXoQ3r0Un+Pox5BgAAaCkUG+BOePbXjLzmy1uPFUqSRnNTTgAAgBZFsQFul2FcVWxSG71cU+fSzpMXJLlvzAkAAICWQ7EBblfRMamyUHL4S90GN3p5b06xKmuciuzgp6QuISYEBAAA8B4UG+B2ZW91P8bcI/n4N3q5fhnaqF6Rstsb398GAAAAzYdiA9yu7MuDA66zv2Yz+2sAAABaDcUGuF05l/fXxDUuNmWXarXvdIkkKbUPxQYAAKClUWyA21F6RirJkWwOKXZYo5d3HC+Sy5B6Rgare3igCQEBAAC8C8UGuB31y9C6DpT8Gw8G2HJ5GRrT0AAAAFoHxQa4HfWDA64x5lm6UmxGswwNAACgVVBsgNuRc/mKzTX21+SWVOnE+Yuy26QRPSNaORgAAIB3otgATXWxSDp/2P38GsWm/mrNwJhwhQX6tmYyAAAAr0WxAZqq/mpN5yQpuPEVmfr719zLMjQAAIBWQ7EBmqq+2MSPavSSYRieYsPgAAAAgNZDsQGaqn5wQFzjYnM4v1yFFTUK9HVocFx46+YCAADwYhQboCmqy6W8/e7n8Y3319RfrRnes5P8fRytmQwAAMCrUWyApjidJhlOKTxOCotp9PLmo5fHPLMMDQAAoFVRbICm8Ix5brwMrbrOqbSTFySxvwYAAKC1UWyApsi+/uCAvTklqqp1KrKDn5K6hLRyMAAAAO9GsQFuVV21dHa3+/k1is2Wo1emodlsttZMBgAA4PUoNsCtOrtHqrskBXeWIno3ern+xpzsrwEAAGh9FBvgVtWPeY4fJX3jikxpVa32nymRxP4aAAAAM1BsgFuVvc39GD+60UvrM8/JZUi9ozqoW3hgKwcDAAAAxQa4Fc466fRO9/Nr7K/5NCNXkvTQwG6tmQoAAACXUWyAW5G/T6qpkALCpKh+DV4qrKj27K/57iCKDQAAgBkoNsCtqF+GFjdKsjf8b7P6QJ6cLkN3x4SpR2SwCeEAAABAsQFuRX2xSUht9FL9MrTvDuremokAAABwFYoNcDMu11WDAxrurzl9oVLp2cWy2aSHBnY1IRwAAAAkig1wcwWHpEslkm+w1OXuBi+t2ue+WjOyZ4SiQgNMCAcAAACJYgPcnGd/zXDJ4dPgpVWXl6FNYWgAAACAqSg2wM14bszZcH/N4fwyZZ0rl5/Dru/0ZxkaAACAmSg2wI0YxnWLTf3QgDF9OyssyLe1kwEAAOAqFBvgRoqOSRfPSw5/qfsQz2GXy7hqGRrT0AAAAMxGsQFupP5qTcw9ko+/5/CenGKdLalSsJ9DDyRHmRQOAAAA9Sg2wI1cZ8xz/TK0Bwd0UYCvo7VTAQAA4BsoNsD1GIZ06vIVm6tuzFnrdOl/D+RJYhkaAABAW0GxAa6nJEcqOyPZfdxL0S7bcqxQFy7WKCLYT6m9IkwMCAAAgHoUG+B66pehdRss+QV7DtcPDZg8sKt8HPwXAgAAaAv4rQy4Hs+Y5yv7a6pqnPr7wXxJ0ndZhgYAANBmUGyA6/EUm9GeQ19mnlNljVMxHQM1JC7cnFwAAABohGIDXEtZnnThhCSbFDfcc/hTz71ruslms5kUDgAAAN9EsQGuJefy/poud0kBYZKk0qpabTxSIIlpaAAAAG0NxQa4Fs/9a66Mef7y0DnVOg0lRndQYnSIScEAAABwLRQb4Fqucf+a1ZfvXTPxrq5mJAIAAMANUGyAb7pYJJ3PdD+PGylJKrtUq81HCyVRbAAAANoiig3wTTnb3Y+dk6TgSEnS+sxzqnG61DuKZWgAAABtEcUG+CbP/por969ZfcB975qJA7qYkQgAAAA3QbEBvil7i/vx8uCA8ku12njkvCRp4kCWoQEAALRFFBvgapdKpfwD7ueXi81XhwtUU+dSz8hg9WUZGgAAQJtEsQGulrNDMlxSp55SqPvqzNXT0LgpJwAAQNtEsQGudqrhMrSL1XXakOVehjbhLvbXAAAAtFUUG+Bq2fX3rxktyb0MrbrOpYSIIPXrGmpiMAAAANwIxQaoV10u5Wa4n1++YrPma/cytAksQwMAAGjTKDZAvdM7JcMphcdJ4bGqrKnTV4cLJEmTuCknAABAm0axAep59te4l6FtyDqvS7UuxXYKVP9uLEMDAABoyyg2QL1T9ftr3MvQmIYGAABgHRQbQJJqLkq5e9zP41N1qdbpWYY2cQDL0AAAANo6ig0gSafTJFedFNpd6pigDVnnVVnjVPfwQA2MCTM7HQAAAG6CYgNIV8Y8x6dKNttVy9C6sAwNAADAAig2gNRgf82lWqfWZ56T5N5fAwAAgLaPYgPUVklnd7ufx4/WpiPndbHGqW5hARoUG25qNAAAANwaig1wZrfkrJE6REsRvbTm63xJ3JQTAADASig2wFX7a+pchmca2ncGdDExFAAAAJqCYgPU35gzIVW7s4tVWlWrTsF+GhLX0dxcAAAAuGUUG3i3umrpzC738/jRnqs1Y/p2lsPOMjQAAACroNjAu53dI9VdkoIipc599eXlaWgPJEWbHAwAAABNQbGBd8u+vAwtfpROFlXqxPmL8rHbdF9ipLm5AAAA0CQUG3g3z/1rRnvuXTO8ZyeFBPiaGAoAAABNRbGB93LWSqfT3M/jUz37a1iGBgAAYD0UG3iv3Ayp9qIU2FFlYX2UdvKCJOmB5ChzcwEAAKDJKDbwXvX7a+JGaeORItW5DPWO6qD4iGBzcwEAAKDJKDbwXp79NVcvQ+NqDQAAgBVRbOCdnHVSzg5JUl3sKP1f1uVik8z+GgAAACui2MA75e+Xasol/zDtrYlRSWWtwoN8NSQu3OxkAAAAuA0UG3ink5vcj/Ej9WVWoSRpTGJn+Tj4LwEAAGBF/BYH73ToU/dj77H6KpNlaAAAAFZHsYH3Kc6WcvdINrvOdB2vowUV8rHbdF9iZ7OTAQAA4DZRbOB9Dn3ifoxP1dpslyTpnoROCgv0NS8TAAAA7gjFBt7n4Mfux/4PXxnzzE05AQAALI1iA+9SfErK3SvZ7KroOUE7TxZJYn8NAACA1VFs4F0OfuJ+TBitTbk21ToN9YwMVo/IYFNjAQAA4M5QbOBdrlqG9mXmOUksQwMAAGgPKDbwHhdOSnkZks0uZ9/J2pB1XpL07SSWoQEAAFgdxQbeo34aWsK9yrjgowsXaxQa4KOhCR1NjQUAAIA7R7GB97hqGdpn+/IkSd/qGyVfB/8NAAAArI7f6OAdLpyQ8vZJNocqe03QR+lnJEmPpMSYHAwAAADNgWID71A/Da3HvVp1tEbl1XWKjwjS6N6RpsYCAABA86DYwDtcXoZm9HtY/709W5L0xPB42e02M1MBAACgmVBs0P4VHZfy90s2h/aH3qtDeWXy97HrH1iGBgAA0G5QbND+1U9D63Gf3s8olyRNHthNHYP9zMsEAACAZkWxQft3eRnaxT4P6fP97mloT46MNzMRAAAAmhnFBu1b0XEp/4Bkc+ivFwepps6lu7qH6e6YMLOTAQAAoBlRbNC+1Q8N6PEt/XFPmSTpiRFxstkYGgAAANCeUGzQvl0e85wVOVY5FyoVEuCj797d3dxMAAAAaHYUG7Rfp9Okcwcku6+W5veVJD2SEqtAP4fJwQAAANDcKDZovzb9WpJ0MfkRfXa0WpI0c0ScmYkAAADQQig2aJ/y9ktH/y7Z7PrA92G5DCm1d4R6de5gdjIAAAC0AIoN2qctiyVJzuSpWva1e1DAkyMY8QwAANBeUWzQ/hQe9QwN2NzlKRVW1Cg61F9jk6PNzQUAAIAWQ7FB+7PlTUmGlDhBSw4FSJJmDIuTj4OPOwAAQHvFb3poX0pypP0fSpL2JMxS2qkL8rHb9L17GBoAAADQnlFs0L5s/Z3kqpMr4T79yzY/SdLToxLUJSzA5GAAAABoSRQbtB/l56Q9/y1JWhU6QycLL6pziL/mju1jcjAAAAC0NIoN2o8d70jOatV0GaL5e8MlST+amKyQAF9zcwEAAKDFUWzQPlRekHb9QZL0nm2aLtUaGtajk6YM6mZyMAAAALQGig3ah7R3pZoKVYQnadHJHnLYbfr3KQNks9nMTgYAAIBWQLGB9VVXSDuXSpJ+WzVJkk1Pj0xQ3y4h5uYCAABAq6HYwPrSV0hVxSoJjNWK0sHugQHjGBgAAADgTSg2sLaLRdK2tyRJv744US7Z9cOJSQplYAAAAIBXodjAupy10l+flirOqcC3u1bWpGpYQidNHdTd7GQAAABoZRQbWNfffyid2qw6n2A9UfGSXHZfvT61PwMDAAAAvBDFBtaU/r6UtlyS9JrjRR0xYvX0yAQldQk1ORgAAADMQLGB9eTslP73XyRJK/xm6M+lA9UlNICBAQAAAF6MYgNrKT0jrXxCctXqK/sIvV42Sd3DA/X/nh/BwAAAAAAv5mN2AOCW1VZJH86ULhboiOI1p/J59YoK1Z/+cZi6hgWanQ4AAAAmotjAGgxDWvWilJehYiNEs2peUa/u0Xp/1jB1CvYzOx0AAABMRrFB21d6Vlr9qpT1v6oz7Pqn2pfVPSFJ7z09VCEsPwMAAIAoNmjLXE4p7V251r8ue+1F1RoO/ahuljr0HaO3Hx+iAF+H2QkBAADQRlBs0CY5c/ep/K+zFV58QHZJ6a4+WlD7rAYMGqGl/zBQvg7mXgAAAOAKig3alJKSYp366CcacPovCpdLZUagFjlnqDjpcf08tZfuSejIDTgBAADQCMUGpqtzurTl8Fmd3fRf+lb+f2mQrVCStFYjdTTlx/rn+1LULZypZwAAALg+ig1MYRiGDuaW6bNdx+S3/7/1uHOVxtguSDapwN5ZWSk/1X3jH9d49tEAAADgFlBs0Gqq65z6+mypth8v0vqMIxpV9Ime91mjCFu5ZJPKfCNVMeSf1fXb31eUfwez4wIAAMBCKDZoMeWXarUnp0S7Tl5Q2qkL2ne6RPHObE1zbNH7ji8V6lslSaoKjpXvmHkKHTxToT7+JqcGAACAFVFs0GwMw9CRcxX6MvOc1meeU8bpErkMqYctT5Pt2/Vzx3Yl+pz1nO+MTJLjvh8osP/DkoOPIgAAAG4fv03ijtTUubTzZJHWZxboy8xzOlPsvgoTYzuv5+w7NN1vpxKNE57zDYefbL3HSYNnypE4QbIzthkAAAB3jmKDJqmsqVNGTol2Zxdrd3ax9mQXq6K6TpLUXef1gm+aHg1MV8+aw+43GJJsDqnX/dKA6bL1nSgFhpuWHwAAAO0TxQY3VFRRrbTLe2R2nyrWobwyOV2G5/VuKtQ/BqVruv8uxVUdch+skWSzS/Gp0oDpUvJ3peAIc34AAAAAeAWKDRoovFxkdpwo0s4TF5R1rrzB6/6q0eSQE3qoQ5aG1O5Rp4qjkktSlSTZpITRUv+p7jLTIcqEnwAAAADeiGLjxQzD0NmSKqVnF2v3qWLtPFmkI+cqvnmWxkaWalroYaXU7VHnC+my11ZJxfWv26T4UVL/h91lJiS6lX8KAAAAgGLjVQzD0KG8MqWdvKDd2cVKP1Ws/LJLjc4bFO2jxyJOKtXYq+5F2+Qoy5Gu7jshXaVeD7j3zfS8n2VmAAAAMB3FxgscKyjXqoxcrdqXq1NFlQ1e87HbdFfXYD0YXaoxPgfUq2SHfM/ukEprrpzk8Hdflen9gLvQRCVLNlsr/xQAAADA9VFs2qmzJVX6bF+uVmXk6lBemed4gK9NE+IMjQs7o7ttx9Wl4pAceRlSUcO9NOqYIPUeJ/UZ59434xfcqvkBAACApqDYtCNFFdVafSBPq/blatcpzyYYBdidejY2T9OD9iq+cKPsZ3Ols994s2+QFDfSXWR6j5MienFVBgAAAJZBsbG4iuo6/f3rfK3al6stxwo9o5gDbDWa1eWk/iForxKKNsl+ruTKm2wOKbqf1D3lyp/IvpKDjwMAAACsid9kLcjlMrTz5AX9Nf201hzIV1WtU5IUoko9FZml6UF7lVC8TfbiyivTy4IipaSJ7sll8amSX5B5PwAAAADQzCg2FnKmuFIfpZ/VR3vOKOeCewhAhEo1K+xr95WZ0l2yVdRemWAWGiMlP+T+EzdCsjvMCw8AAAC0IIpNG1daWasvDubpk7252nGySIYhxdjO65/80/Vo8D4lVB2QrdolVV9+Q2TilTLTdRD7ZAAAAOAVKDZt0KVap9ZnFujTjLPakHVeNU6nkm05etGermmBe5VQd9x9Yv3k5q6DrpSZzn3Nig0AAACYhmLTRtQ6Xdp+vEifZuTq7wfz5ayuUKr9oF6z79W4wP3qbBS6T6yTZLO798kkTZaSJknhsaZmBwAAAMxGsTFRZU2dNmad19pD57Q+85xCq3P1bftevW3P0MiAQ/JXrftEQ5JPoNRzjJQ8WUqcIAVHmBkdAAAAaFMoNq2sqKJa6zMLtPZgnk4eO6QhxkGl2g9rni1Tsf7nG54cHif1eVBKfNB9k0zfQHNCAwAAAG0cxaYV1DldWvN1vtZu2a7g3O0aZs/U6/ZD6uZzocF5hs0hW9wId5Hp86B7vwyb/wEAAICboti0oEu1Tn2+NV0FW/+iMdX/p7fs2ZLvldcNu6/UfYhs8alSQqpsscMl/xDzAgMAAAAWRbFpAaUlF7RrzfsKOfI3TXMdkN1mSHbJafNRXbeh8u91n7vIxAzjRpkAAABAM2ixYrNkyRL96le/Ul5envr3768333xT9957b0t9O/M5a1W8/wvlbn5fPYs2aqytxn3cJp0LH6yOI56Q38BpcgR1MjcnAAAA0A61SLFZuXKl5s6dqyVLlig1NVXLli3ThAkTdOjQIcXFxbXEt2w9NRdVe/6YSs8cVmVeloyiY/IrPamwiuPq6LqojpJkk07bu6sscboSx85SdGQPs1MDAAAA7ZrNMAyjub/o8OHDNWTIEC1dutRzLDk5WVOnTtXChQtv+N6ysjKFhYWptLRUoaGhzR2tSbKz9ipv1yr5lJxQh4vZiqw+rUhX4XXPP2+EKi3424oe/ZRSRtwvm93eimkBAACA9qUp3aDZr9jU1NQoPT1d8+fPb3B8/Pjx2rZtW6Pzq6urVV1d7fl7WVlZc0e6becPb9OIY4sbHS82OuiUuqrAN0YlQXG6FNpT9ohe6jdohCb16GxCUgAAAMC7NXuxKSwslNPpVHR0dIPj0dHRys/Pb3T+woUL9bOf/ay5YzSLsB4p2nNsjKpCEuTq1Ft+UX0U2j1JUdFdNSjYTzZGMQMAAABtQosND/jmL/2GYVyzCCxYsEDz5s3z/L2srEyxsbEtFatJ+gwcIQ381OwYAAAAAG6i2YtNZGSkHA5Ho6szBQUFja7iSJK/v7/8/f2bOwYAAAAAL9Lsu9v9/PyUkpKidevWNTi+bt06jRo1qrm/HQAAAAC0zFK0efPm6cknn9TQoUM1cuRILV++XDk5OXrhhRda4tsBAAAA8HItUmwee+wxFRUV6fXXX1deXp4GDBig1atXKz4+viW+HQAAAAAv1yL3sbkTbek+NgAAAADM05RuwB0kAQAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5VFsAAAAAFgexQYAAACA5fmYHeCbDMOQJJWVlZmcBAAAAICZ6jtBfUe4kTZXbMrLyyVJsbGxJicBAAAA0BaUl5crLCzshufYjFupP63I5XIpNzdXISEhstlsZse5obKyMsXGxur06dMKDQ01Ow7aET5baAl8rtBS+GyhpfDZgmEYKi8vV7du3WS333gXTZu7YmO32xUTE2N2jCYJDQ3lPxtaBJ8ttAQ+V2gpfLbQUvhsebebXampx/AAAAAAAJZHsQEAAABgeRSbO+Dv76+f/vSn8vf3NzsK2hk+W2gJfK7QUvhsoaXw2UJTtLnhAQAAAADQVFyxAQAAAGB5FBsAAAAAlkexAQAAAGB5FBsAAAAAlkexuU1LlixRjx49FBAQoJSUFG3evNnsSLC4hQsX6p577lFISIiioqI0depUZWVlmR0L7czChQtls9k0d+5cs6OgHTh79qyeeOIJRUREKCgoSIMGDVJ6errZsWBxdXV1+vGPf6wePXooMDBQPXv21Ouvvy6Xy2V2NLRxFJvbsHLlSs2dO1c/+tGPtHfvXt17772aMGGCcnJyzI4GC9u4caNmz56tHTt2aN26daqrq9P48eN18eJFs6Ohndi1a5eWL1+ugQMHmh0F7UBxcbFSU1Pl6+urNWvW6NChQ/rNb36j8PBws6PB4v7jP/5Dv//97/X2228rMzNTixYt0q9+9Su99dZbZkdDG8e459swfPhwDRkyREuXLvUcS05O1tSpU7Vw4UITk6E9OX/+vKKiorRx40bdd999ZseBxVVUVGjIkCFasmSJfv7zn2vQoEF68803zY4FC5s/f762bt3KigU0u8mTJys6Olp/+MMfPMemT5+uoKAg/elPfzIxGdo6rtg0UU1NjdLT0zV+/PgGx8ePH69t27aZlArtUWlpqSSpU6dOJidBezB79mxNmjRJY8eONTsK2olVq1Zp6NCheuSRRxQVFaXBgwfr3XffNTsW2oHRo0dr/fr1OnLkiCRp37592rJliyZOnGhyMrR1PmYHsJrCwkI5nU5FR0c3OB4dHa38/HyTUqG9MQxD8+bN0+jRozVgwACz48DiPvzwQ+3Zs0e7du0yOwrakRMnTmjp0qWaN2+efvjDHyotLU0vvfSS/P399dRTT5kdDxb2r//6ryotLVVSUpIcDoecTqfeeOMNzZgxw+xoaOMoNrfJZrM1+LthGI2OAbdrzpw52r9/v7Zs2WJ2FFjc6dOn9fLLL2vt2rUKCAgwOw7aEZfLpaFDh+oXv/iFJGnw4ME6ePCgli5dSrHBHVm5cqX+/Oc/64MPPlD//v2VkZGhuXPnqlu3bnr66afNjoc2jGLTRJGRkXI4HI2uzhQUFDS6igPcjhdffFGrVq3Spk2bFBMTY3YcWFx6eroKCgqUkpLiOeZ0OrVp0ya9/fbbqq6ulsPhMDEhrKpr167q169fg2PJycn66KOPTEqE9uLVV1/V/Pnz9b3vfU+SdNdddyk7O1sLFy6k2OCG2GPTRH5+fkpJSdG6desaHF+3bp1GjRplUiq0B4ZhaM6cOfrb3/6mr776Sj169DA7EtqBBx54QAcOHFBGRobnz9ChQzVz5kxlZGRQanDbUlNTG42kP3LkiOLj401KhPaisrJSdnvDX1EdDgfjnnFTXLG5DfPmzdOTTz6poUOHauTIkVq+fLlycnL0wgsvmB0NFjZ79mx98MEH+vTTTxUSEuK5KhgWFqbAwECT08GqQkJCGu3TCg4OVkREBPu3cEdeeeUVjRo1Sr/4xS/06KOPKi0tTcuXL9fy5cvNjgaLe+ihh/TGG28oLi5O/fv31969e7V48WLNmjXL7Gho4xj3fJuWLFmiRYsWKS8vTwMGDNBvf/tbRvLijlxvj9aKFSv0zDPPtG4YtGtjxoxh3DOaxeeff64FCxbo6NGj6tGjh+bNm6fnnnvO7FiwuPLycv3kJz/Rxx9/rIKCAnXr1k0zZszQv/3bv8nPz8/seGjDKDYAAAAALI89NgAAAAAsj2IDAAAAwPIoNgAAAAAsj2IDAAAAwPIoNgAAAAAsj2IDAAAAwPIoNgAAAAAsj2IDAF5mzJgxmjt3rtkxAABoVhQbAAAAAJZHsQEAtCk1NTVmR2ikLWYCADREsQEAL1ZcXKynnnpKHTt2VFBQkCZMmKCjR482OOfdd99VbGysgoKC9PDDD2vx4sUKDw+/pa//2muvadCgQVq2bJnnazzyyCMqKSnxnPPMM89o6tSpWrhwobp166bExERJ0tmzZ/XYY4+pY8eOioiI0JQpU3Tq1CnP+zZs2KBhw4YpODhY4eHhSk1NVXZ2tiRp3759uv/++xUSEqLQ0FClpKRo9+7dDTJd7c0331RCQsIdZwIAmIdiAwBe7JlnntHu3bu1atUqbd++XYZhaOLEiaqtrZUkbd26VS+88IJefvllZWRkaNy4cXrjjTea9D2OHTum//mf/9Fnn32mL774QhkZGZo9e3aDc9avX6/MzEytW7dOn3/+uSorK3X//ferQ4cO2rRpk7Zs2aIOHTroO9/5jmpqalRXV6epU6fqW9/6lvbv36/t27fr+eefl81mkyTNnDlTMTEx2rVrl9LT0zV//nz5+vo2KXdTMwEAzOVjdgAAgDmOHj2qVatWaevWrRo1apQk6S9/+YtiY2P1ySef6JFHHtFbb72lCRMm6Ac/+IEkKTExUdu2bdPnn39+y9/n0qVLev/99xUTEyNJeuuttzRp0iT95je/UZcuXSRJwcHBeu+99+Tn5ydJ+uMf/yi73a733nvPU1ZWrFih8PBwbdiwQUOHDlVpaakmT56sXr16SZKSk5M93zMnJ0evvvqqkpKSJEl9+vRp8r9PUzONHz++yd8DANB8uGIDAF4qMzNTPj4+Gj58uOdYRESE+vbtq8zMTElSVlaWhg0b1uB93/z7zcTFxXlKjSSNHDlSLpdLWVlZnmN33XWXp0BIUnp6uo4dO6aQkBB16NBBHTp0UKdOnXTp0iUdP35cnTp10jPPPKMHH3xQDz30kP7zP/9TeXl5nvfPmzdPzz77rMaOHatf/vKXOn78eJMy304mAIC5KDYA4KUMw7ju8forElc/v9n7blX917v66wYHBzc4x+VyKSUlRRkZGQ3+HDlyRI8//rgk99WS7du3a9SoUVq5cqUSExO1Y8cOSe59NAcPHtSkSZP01VdfqV+/fvr4448lSXa7vdHPUL/07mq3kwkAYB6KDQB4qX79+qmurk47d+70HCsqKtKRI0c8y7qSkpKUlpbW4H31m/BvVU5OjnJzcz1/3759u+x2u2dD/rUMGTJER48eVVRUlHr37t3gT1hYmOe8wYMHa8GCBdq2bZsGDBigDz74wPNaYmKiXnnlFa1du1bTpk3TihUrJEmdO3dWfn5+g3KTkZFx05/jVjMBAMxBsQEAL9WnTx9NmTJFzz33nLZs2aJ9+/bpiSeeUPfu3TVlyhRJ0osvvqjVq1dr8eLFOnr0qJYtW6Y1a9Y0uopzIwEBAXr66ae1b98+bd68WS+99JIeffRRz/6aa5k5c6YiIyM1ZcoUbd68WSdPntTGjRv18ssv68yZMzp58qQWLFig7du3Kzs7W2vXrvUUsqqqKs2ZM0cbNmxQdna2tm7dql27dnnK2pgxY3T+/HktWrRIx48f1zvvvKM1a9bc9Oe4WSYAgLkoNgDgxVasWKGUlBRNnjxZI0eOlGEYWr16tWeCWGpqqn7/+99r8eLFuvvuu/XFF1/olVdeUUBAwC1/j969e2vatGmaOHGixo8frwEDBmjJkiU3fE9QUJA2bdqkuLg4TZs2TcnJyZo1a5aqqqoUGhqqoKAgHT58WNOnT1diYqKef/55zZkzR9///vflcDhUVFSkp556SomJiXr00Uc1YcIE/exnP5PkHjKwZMkSvfPOO7r77ruVlpbmGY5wJ5kAAOayGXe6WBoA4FWee+45HT58WJs3b77pua+99po++eSTW1rqBQDAnWDcMwDghn79619r3LhxCg4O1po1a/T+++/f9IoLAACtjWIDALihtLQ0LVq0SOXl5erZs6d+97vf6dlnn5Uk9e/fX9nZ2dd837Jly1ozJgDAy7EUDQBw27Kzs685KlmSoqOjFRIS0sqJAADeimIDAAAAwPKYigYAAADA8ig2AAAAACyPYgMAAADA8ig2AAAAACyPYgMAAADA8ig2AAAAACyPYgMAAADA8ig2AAAAACzv/wNXrrl2bMpvFgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1000x1200 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[0, :].to_list(),\n",
    "              'bv_pred':y_pred[0, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[0, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact'], figsize=(10,12));"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ed93545d",
   "metadata": {},
   "source": [
    "Feature importance:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "8d6724b9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "pc_35    9.920031e+06\n",
       "pc_34    5.565515e+06\n",
       "pc_33    4.061165e+06\n",
       "pc_26    3.115999e+06\n",
       "pc_32    2.022171e+06\n",
       "pc_31    1.883059e+06\n",
       "pc_88    1.728465e+06\n",
       "pc_19    1.606785e+06\n",
       "pc_29    1.570292e+06\n",
       "pc_87    1.321934e+06\n",
       "pc_92    1.319392e+06\n",
       "pc_96    1.271971e+06\n",
       "pc_99    1.154558e+06\n",
       "pc_93    1.097378e+06\n",
       "pc_24    1.036412e+06\n",
       "pc_91    9.843024e+05\n",
       "pc_95    9.446993e+05\n",
       "pc_27    9.338211e+05\n",
       "pc_28    8.475343e+05\n",
       "pc_94    7.772646e+05\n",
       "dtype: float64"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feature_importance = pd.DataFrame(lr.coef_, columns = X_prep.columns).mean(axis=0).abs().sort_values(ascending=False)\n",
    "feature_importance.head(20)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e319e2e1",
   "metadata": {},
   "source": [
    "# Model optimization"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bbdf138",
   "metadata": {},
   "source": [
    "## Linear regression with regularization"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "34a0587f",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.linear_model import Ridge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "c3e8c5f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "estimator = Ridge(random_state=8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "16f35b4a",
   "metadata": {},
   "outputs": [],
   "source": [
    "params = {\n",
    "    'alpha': [1e-6, 1e-5, 0.0001, 0.001, 0.01, 0.1, 1, 5, 10, 20],\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "79c09af1",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = GridSearchCV(\n",
    "    estimator=estimator,\n",
    "    param_grid=params,\n",
    "    scoring='neg_mean_absolute_percentage_error',\n",
    "    n_jobs=-1,\n",
    "    cv=10,\n",
    "    verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "701e83a2",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 10 folds for each of 10 candidates, totalling 100 fits\n",
      "CPU times: user 96.8 ms, sys: 8.27 ms, total: 105 ms\n",
      "Wall time: 363 ms\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "%%chime\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "72f658a9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'alpha': 10}"
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "3d197ef0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.526113026880459"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "397542e2",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "b33c9679",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4843865655647991"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_absolute_percentage_error(y_val, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "91bee7fd",
   "metadata": {},
   "source": [
    "Some improvement compared to ordinary linear regression."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "210d4e16",
   "metadata": {},
   "source": [
    "Example curve"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "f1b4a03e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x1200 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[0, :].to_list(),\n",
    "              'bv_pred':y_pred[0, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[0, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact'], figsize=(10,12));"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d6adf22f",
   "metadata": {},
   "source": [
    "# KNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "1448b99d",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.neighbors import KNeighborsRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "051a7a22",
   "metadata": {},
   "outputs": [],
   "source": [
    "estimator = KNeighborsRegressor(metric='minkowski', n_jobs=-1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "9235e4f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "params = {\n",
    "    'n_neighbors': list(range(2,25)),\n",
    "    'weights': ['uniform', 'distance'],\n",
    "    'p': [1, 2, 3]\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "id": "5dd87d46",
   "metadata": {},
   "outputs": [],
   "source": [
    "model = GridSearchCV(\n",
    "    estimator=estimator,\n",
    "    param_grid=params,\n",
    "    scoring='neg_mean_absolute_percentage_error',\n",
    "    cv=10,\n",
    "    verbose=3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "id": "8cc78748",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Fitting 10 folds for each of 138 candidates, totalling 1380 fits\n",
      "[CV 1/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.600 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.808 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.662 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.560 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.421 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.961 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.456 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.966 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.424 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=2, p=1, weights=uniform;, score=-0.817 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=2, p=1, weights=distance;, score=-0.604 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=2, p=1, weights=distance;, score=-0.802 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=2, p=1, weights=distance;, score=-0.662 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=2, p=1, weights=distance;, score=-0.559 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=2, p=1, weights=distance;, score=-0.420 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=2, p=1, weights=distance;, score=-0.957 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=2, p=1, weights=distance;, score=-0.449 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=2, p=1, weights=distance;, score=-0.958 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=2, p=1, weights=distance;, score=-0.424 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=2, p=1, weights=distance;, score=-0.797 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.607 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.861 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.680 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.563 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.405 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=2, p=2, weights=uniform;, score=-1.089 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.422 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.867 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.394 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=2, p=2, weights=uniform;, score=-0.551 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=2, p=2, weights=distance;, score=-0.604 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=2, p=2, weights=distance;, score=-0.859 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=2, p=2, weights=distance;, score=-0.676 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=2, p=2, weights=distance;, score=-0.563 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=2, p=2, weights=distance;, score=-0.403 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=2, p=2, weights=distance;, score=-1.077 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=2, p=2, weights=distance;, score=-0.421 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=2, p=2, weights=distance;, score=-0.863 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=2, p=2, weights=distance;, score=-0.391 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=2, p=2, weights=distance;, score=-0.553 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.670 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.729 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.748 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.641 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.408 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=2, p=3, weights=uniform;, score=-1.021 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.492 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.889 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.482 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=2, p=3, weights=uniform;, score=-0.533 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=2, p=3, weights=distance;, score=-0.664 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=2, p=3, weights=distance;, score=-0.725 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=2, p=3, weights=distance;, score=-0.741 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=2, p=3, weights=distance;, score=-0.640 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=2, p=3, weights=distance;, score=-0.408 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=2, p=3, weights=distance;, score=-1.008 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=2, p=3, weights=distance;, score=-0.489 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=2, p=3, weights=distance;, score=-0.890 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=2, p=3, weights=distance;, score=-0.472 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=2, p=3, weights=distance;, score=-0.534 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.584 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.789 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.598 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.548 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.389 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.978 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.403 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.884 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.456 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=3, p=1, weights=uniform;, score=-0.721 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=3, p=1, weights=distance;, score=-0.586 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=3, p=1, weights=distance;, score=-0.784 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=3, p=1, weights=distance;, score=-0.598 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=3, p=1, weights=distance;, score=-0.547 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=3, p=1, weights=distance;, score=-0.390 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=3, p=1, weights=distance;, score=-0.973 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=3, p=1, weights=distance;, score=-0.400 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=3, p=1, weights=distance;, score=-0.880 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=3, p=1, weights=distance;, score=-0.453 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=3, p=1, weights=distance;, score=-0.712 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.539 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.876 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.680 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.587 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.428 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.939 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.449 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.881 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.476 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=3, p=2, weights=uniform;, score=-0.525 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=3, p=2, weights=distance;, score=-0.541 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=3, p=2, weights=distance;, score=-0.873 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=3, p=2, weights=distance;, score=-0.673 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=3, p=2, weights=distance;, score=-0.584 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=3, p=2, weights=distance;, score=-0.422 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=3, p=2, weights=distance;, score=-0.943 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=3, p=2, weights=distance;, score=-0.446 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=3, p=2, weights=distance;, score=-0.875 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=3, p=2, weights=distance;, score=-0.467 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=3, p=2, weights=distance;, score=-0.528 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.643 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.729 total time=   0.1s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 3/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.664 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.598 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.406 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.944 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.456 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.878 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.489 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=3, p=3, weights=uniform;, score=-0.573 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=3, p=3, weights=distance;, score=-0.638 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=3, p=3, weights=distance;, score=-0.727 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=3, p=3, weights=distance;, score=-0.659 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=3, p=3, weights=distance;, score=-0.595 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=3, p=3, weights=distance;, score=-0.401 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=3, p=3, weights=distance;, score=-0.943 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=3, p=3, weights=distance;, score=-0.453 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=3, p=3, weights=distance;, score=-0.875 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=3, p=3, weights=distance;, score=-0.481 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=3, p=3, weights=distance;, score=-0.570 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.581 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.791 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.642 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.524 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.379 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.903 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.426 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.894 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.449 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=4, p=1, weights=uniform;, score=-0.654 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=4, p=1, weights=distance;, score=-0.583 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=4, p=1, weights=distance;, score=-0.786 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=4, p=1, weights=distance;, score=-0.637 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=4, p=1, weights=distance;, score=-0.523 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=4, p=1, weights=distance;, score=-0.379 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=4, p=1, weights=distance;, score=-0.910 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=4, p=1, weights=distance;, score=-0.421 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=4, p=1, weights=distance;, score=-0.888 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=4, p=1, weights=distance;, score=-0.447 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=4, p=1, weights=distance;, score=-0.650 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.607 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.817 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.671 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.607 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.408 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.887 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.425 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.865 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.528 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=4, p=2, weights=uniform;, score=-0.510 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=4, p=2, weights=distance;, score=-0.600 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=4, p=2, weights=distance;, score=-0.817 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=4, p=2, weights=distance;, score=-0.663 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=4, p=2, weights=distance;, score=-0.602 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=4, p=2, weights=distance;, score=-0.406 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=4, p=2, weights=distance;, score=-0.890 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=4, p=2, weights=distance;, score=-0.422 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=4, p=2, weights=distance;, score=-0.858 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=4, p=2, weights=distance;, score=-0.518 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=4, p=2, weights=distance;, score=-0.510 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.615 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.764 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.641 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.593 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.392 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.908 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.449 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.902 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.521 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=4, p=3, weights=uniform;, score=-0.615 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=4, p=3, weights=distance;, score=-0.614 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=4, p=3, weights=distance;, score=-0.760 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=4, p=3, weights=distance;, score=-0.639 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=4, p=3, weights=distance;, score=-0.589 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=4, p=3, weights=distance;, score=-0.389 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=4, p=3, weights=distance;, score=-0.909 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=4, p=3, weights=distance;, score=-0.446 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=4, p=3, weights=distance;, score=-0.898 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=4, p=3, weights=distance;, score=-0.512 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=4, p=3, weights=distance;, score=-0.610 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.633 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.804 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.646 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.508 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.410 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.841 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.422 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.897 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.477 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=5, p=1, weights=uniform;, score=-0.685 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=5, p=1, weights=distance;, score=-0.626 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=5, p=1, weights=distance;, score=-0.799 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=5, p=1, weights=distance;, score=-0.643 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=5, p=1, weights=distance;, score=-0.508 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=5, p=1, weights=distance;, score=-0.407 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=5, p=1, weights=distance;, score=-0.855 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=5, p=1, weights=distance;, score=-0.417 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=5, p=1, weights=distance;, score=-0.892 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=5, p=1, weights=distance;, score=-0.471 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=5, p=1, weights=distance;, score=-0.678 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.626 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.821 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.681 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 4/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.592 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.408 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.931 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.422 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.881 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.497 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=5, p=2, weights=uniform;, score=-0.604 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=5, p=2, weights=distance;, score=-0.616 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=5, p=2, weights=distance;, score=-0.816 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=5, p=2, weights=distance;, score=-0.674 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=5, p=2, weights=distance;, score=-0.587 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=5, p=2, weights=distance;, score=-0.403 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=5, p=2, weights=distance;, score=-0.929 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=5, p=2, weights=distance;, score=-0.418 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=5, p=2, weights=distance;, score=-0.874 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=5, p=2, weights=distance;, score=-0.490 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=5, p=2, weights=distance;, score=-0.598 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.627 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.790 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.666 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.600 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.429 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.928 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.434 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.914 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.538 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=5, p=3, weights=uniform;, score=-0.661 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=5, p=3, weights=distance;, score=-0.625 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=5, p=3, weights=distance;, score=-0.783 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=5, p=3, weights=distance;, score=-0.661 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=5, p=3, weights=distance;, score=-0.595 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=5, p=3, weights=distance;, score=-0.425 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=5, p=3, weights=distance;, score=-0.927 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=5, p=3, weights=distance;, score=-0.431 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=5, p=3, weights=distance;, score=-0.907 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=5, p=3, weights=distance;, score=-0.530 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=5, p=3, weights=distance;, score=-0.649 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.632 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.821 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.650 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.546 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.409 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.856 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.437 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.875 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.478 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=6, p=1, weights=uniform;, score=-0.737 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=6, p=1, weights=distance;, score=-0.626 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=6, p=1, weights=distance;, score=-0.816 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=6, p=1, weights=distance;, score=-0.647 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=6, p=1, weights=distance;, score=-0.543 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=6, p=1, weights=distance;, score=-0.405 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=6, p=1, weights=distance;, score=-0.868 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=6, p=1, weights=distance;, score=-0.430 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=6, p=1, weights=distance;, score=-0.871 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=6, p=1, weights=distance;, score=-0.472 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=6, p=1, weights=distance;, score=-0.726 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.582 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.791 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.647 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.602 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.388 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.937 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.422 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.900 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.495 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=6, p=2, weights=uniform;, score=-0.623 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=6, p=2, weights=distance;, score=-0.578 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=6, p=2, weights=distance;, score=-0.789 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=6, p=2, weights=distance;, score=-0.642 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=6, p=2, weights=distance;, score=-0.596 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=6, p=2, weights=distance;, score=-0.384 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=6, p=2, weights=distance;, score=-0.933 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=6, p=2, weights=distance;, score=-0.417 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=6, p=2, weights=distance;, score=-0.892 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=6, p=2, weights=distance;, score=-0.489 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=6, p=2, weights=distance;, score=-0.616 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.658 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.771 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.694 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.600 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.433 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.960 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.421 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.888 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.565 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=6, p=3, weights=uniform;, score=-0.640 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=6, p=3, weights=distance;, score=-0.652 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=6, p=3, weights=distance;, score=-0.766 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=6, p=3, weights=distance;, score=-0.686 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=6, p=3, weights=distance;, score=-0.595 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=6, p=3, weights=distance;, score=-0.429 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=6, p=3, weights=distance;, score=-0.955 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=6, p=3, weights=distance;, score=-0.419 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=6, p=3, weights=distance;, score=-0.882 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=6, p=3, weights=distance;, score=-0.555 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=6, p=3, weights=distance;, score=-0.631 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.628 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.802 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.655 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.583 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.406 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.859 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.444 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.869 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.504 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=7, p=1, weights=uniform;, score=-0.724 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=7, p=1, weights=distance;, score=-0.622 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=7, p=1, weights=distance;, score=-0.797 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=7, p=1, weights=distance;, score=-0.651 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=7, p=1, weights=distance;, score=-0.575 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=7, p=1, weights=distance;, score=-0.403 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=7, p=1, weights=distance;, score=-0.869 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 7/10] END n_neighbors=7, p=1, weights=distance;, score=-0.436 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=7, p=1, weights=distance;, score=-0.865 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=7, p=1, weights=distance;, score=-0.498 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=7, p=1, weights=distance;, score=-0.716 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.603 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.811 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.676 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.614 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.373 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.953 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.404 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.939 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.501 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=7, p=2, weights=uniform;, score=-0.642 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=7, p=2, weights=distance;, score=-0.597 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=7, p=2, weights=distance;, score=-0.806 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=7, p=2, weights=distance;, score=-0.668 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=7, p=2, weights=distance;, score=-0.605 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=7, p=2, weights=distance;, score=-0.371 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=7, p=2, weights=distance;, score=-0.947 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=7, p=2, weights=distance;, score=-0.402 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=7, p=2, weights=distance;, score=-0.928 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=7, p=2, weights=distance;, score=-0.495 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=7, p=2, weights=distance;, score=-0.633 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.697 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.796 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.699 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.618 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.434 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.958 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.410 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.932 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.555 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=7, p=3, weights=uniform;, score=-0.661 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=7, p=3, weights=distance;, score=-0.690 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=7, p=3, weights=distance;, score=-0.789 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=7, p=3, weights=distance;, score=-0.691 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=7, p=3, weights=distance;, score=-0.612 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=7, p=3, weights=distance;, score=-0.430 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=7, p=3, weights=distance;, score=-0.952 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=7, p=3, weights=distance;, score=-0.408 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=7, p=3, weights=distance;, score=-0.921 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=7, p=3, weights=distance;, score=-0.546 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=7, p=3, weights=distance;, score=-0.650 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.615 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.795 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.654 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.597 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.402 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.863 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.442 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.878 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.514 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=8, p=1, weights=uniform;, score=-0.734 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=8, p=1, weights=distance;, score=-0.611 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=8, p=1, weights=distance;, score=-0.791 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=8, p=1, weights=distance;, score=-0.650 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=8, p=1, weights=distance;, score=-0.589 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=8, p=1, weights=distance;, score=-0.399 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=8, p=1, weights=distance;, score=-0.870 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=8, p=1, weights=distance;, score=-0.435 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=8, p=1, weights=distance;, score=-0.874 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=8, p=1, weights=distance;, score=-0.507 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=8, p=1, weights=distance;, score=-0.726 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.610 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.810 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.668 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.615 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.381 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.926 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.398 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.954 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.520 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=8, p=2, weights=uniform;, score=-0.649 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=8, p=2, weights=distance;, score=-0.604 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=8, p=2, weights=distance;, score=-0.804 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=8, p=2, weights=distance;, score=-0.660 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=8, p=2, weights=distance;, score=-0.607 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=8, p=2, weights=distance;, score=-0.379 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=8, p=2, weights=distance;, score=-0.922 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=8, p=2, weights=distance;, score=-0.396 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=8, p=2, weights=distance;, score=-0.944 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=8, p=2, weights=distance;, score=-0.513 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=8, p=2, weights=distance;, score=-0.640 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.678 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.807 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.736 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.646 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.423 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.979 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.432 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.938 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.564 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=8, p=3, weights=uniform;, score=-0.653 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=8, p=3, weights=distance;, score=-0.673 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=8, p=3, weights=distance;, score=-0.798 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=8, p=3, weights=distance;, score=-0.725 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=8, p=3, weights=distance;, score=-0.638 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=8, p=3, weights=distance;, score=-0.420 total time=   0.1s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 6/10] END n_neighbors=8, p=3, weights=distance;, score=-0.971 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=8, p=3, weights=distance;, score=-0.427 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=8, p=3, weights=distance;, score=-0.928 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=8, p=3, weights=distance;, score=-0.556 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=8, p=3, weights=distance;, score=-0.645 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.629 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.788 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.664 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.628 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.399 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.872 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.434 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.926 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.506 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=9, p=1, weights=uniform;, score=-0.739 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=9, p=1, weights=distance;, score=-0.623 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=9, p=1, weights=distance;, score=-0.786 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=9, p=1, weights=distance;, score=-0.660 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=9, p=1, weights=distance;, score=-0.617 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=9, p=1, weights=distance;, score=-0.396 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=9, p=1, weights=distance;, score=-0.876 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=9, p=1, weights=distance;, score=-0.428 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=9, p=1, weights=distance;, score=-0.918 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=9, p=1, weights=distance;, score=-0.501 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=9, p=1, weights=distance;, score=-0.732 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.633 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.801 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.691 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.591 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.395 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.930 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.415 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.972 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.537 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=9, p=2, weights=uniform;, score=-0.676 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=9, p=2, weights=distance;, score=-0.624 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=9, p=2, weights=distance;, score=-0.796 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=9, p=2, weights=distance;, score=-0.682 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=9, p=2, weights=distance;, score=-0.586 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=9, p=2, weights=distance;, score=-0.392 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=9, p=2, weights=distance;, score=-0.926 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=9, p=2, weights=distance;, score=-0.410 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=9, p=2, weights=distance;, score=-0.960 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=9, p=2, weights=distance;, score=-0.529 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=9, p=2, weights=distance;, score=-0.665 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.688 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.797 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.732 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.654 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.408 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.990 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.444 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.942 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.591 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=9, p=3, weights=uniform;, score=-0.658 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=9, p=3, weights=distance;, score=-0.680 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=9, p=3, weights=distance;, score=-0.789 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=9, p=3, weights=distance;, score=-0.723 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=9, p=3, weights=distance;, score=-0.646 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=9, p=3, weights=distance;, score=-0.406 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=9, p=3, weights=distance;, score=-0.983 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=9, p=3, weights=distance;, score=-0.438 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=9, p=3, weights=distance;, score=-0.931 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=9, p=3, weights=distance;, score=-0.580 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=9, p=3, weights=distance;, score=-0.649 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.591 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.782 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.669 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.641 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.412 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.875 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.443 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.924 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.499 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=10, p=1, weights=uniform;, score=-0.735 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=10, p=1, weights=distance;, score=-0.591 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=10, p=1, weights=distance;, score=-0.780 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=10, p=1, weights=distance;, score=-0.664 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=10, p=1, weights=distance;, score=-0.629 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=10, p=1, weights=distance;, score=-0.406 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=10, p=1, weights=distance;, score=-0.878 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=10, p=1, weights=distance;, score=-0.436 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=10, p=1, weights=distance;, score=-0.917 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=10, p=1, weights=distance;, score=-0.494 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=10, p=1, weights=distance;, score=-0.729 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.690 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.791 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.715 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.595 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.412 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.947 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.417 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.995 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.559 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=10, p=2, weights=uniform;, score=-0.669 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=10, p=2, weights=distance;, score=-0.676 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=10, p=2, weights=distance;, score=-0.788 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=10, p=2, weights=distance;, score=-0.706 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=10, p=2, weights=distance;, score=-0.591 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=10, p=2, weights=distance;, score=-0.407 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=10, p=2, weights=distance;, score=-0.940 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 7/10] END n_neighbors=10, p=2, weights=distance;, score=-0.412 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=10, p=2, weights=distance;, score=-0.983 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=10, p=2, weights=distance;, score=-0.549 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=10, p=2, weights=distance;, score=-0.660 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.683 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.813 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.746 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.663 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.411 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=10, p=3, weights=uniform;, score=-1.009 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.452 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.936 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.591 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=10, p=3, weights=uniform;, score=-0.696 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=10, p=3, weights=distance;, score=-0.676 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=10, p=3, weights=distance;, score=-0.804 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=10, p=3, weights=distance;, score=-0.737 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=10, p=3, weights=distance;, score=-0.654 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=10, p=3, weights=distance;, score=-0.408 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=10, p=3, weights=distance;, score=-0.999 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=10, p=3, weights=distance;, score=-0.446 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=10, p=3, weights=distance;, score=-0.926 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=10, p=3, weights=distance;, score=-0.580 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=10, p=3, weights=distance;, score=-0.684 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.592 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.776 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.678 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.660 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.420 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.876 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.439 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.927 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.518 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=11, p=1, weights=uniform;, score=-0.715 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=11, p=1, weights=distance;, score=-0.592 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=11, p=1, weights=distance;, score=-0.775 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=11, p=1, weights=distance;, score=-0.671 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=11, p=1, weights=distance;, score=-0.647 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=11, p=1, weights=distance;, score=-0.413 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=11, p=1, weights=distance;, score=-0.879 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=11, p=1, weights=distance;, score=-0.433 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=11, p=1, weights=distance;, score=-0.919 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=11, p=1, weights=distance;, score=-0.511 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=11, p=1, weights=distance;, score=-0.712 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.693 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.789 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.718 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.577 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.412 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.957 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.429 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.978 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.574 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=11, p=2, weights=uniform;, score=-0.678 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=11, p=2, weights=distance;, score=-0.680 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=11, p=2, weights=distance;, score=-0.785 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=11, p=2, weights=distance;, score=-0.710 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=11, p=2, weights=distance;, score=-0.574 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=11, p=2, weights=distance;, score=-0.406 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=11, p=2, weights=distance;, score=-0.950 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=11, p=2, weights=distance;, score=-0.423 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=11, p=2, weights=distance;, score=-0.968 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=11, p=2, weights=distance;, score=-0.564 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=11, p=2, weights=distance;, score=-0.668 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.697 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.810 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.755 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.653 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.407 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=11, p=3, weights=uniform;, score=-1.004 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.445 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.988 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.574 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=11, p=3, weights=uniform;, score=-0.668 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=11, p=3, weights=distance;, score=-0.690 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=11, p=3, weights=distance;, score=-0.803 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=11, p=3, weights=distance;, score=-0.745 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=11, p=3, weights=distance;, score=-0.646 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=11, p=3, weights=distance;, score=-0.405 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=11, p=3, weights=distance;, score=-0.995 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=11, p=3, weights=distance;, score=-0.440 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=11, p=3, weights=distance;, score=-0.975 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=11, p=3, weights=distance;, score=-0.566 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=11, p=3, weights=distance;, score=-0.660 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.592 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.796 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.690 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.664 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.425 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.878 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.444 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.901 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.535 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=12, p=1, weights=uniform;, score=-0.717 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=12, p=1, weights=distance;, score=-0.590 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=12, p=1, weights=distance;, score=-0.792 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=12, p=1, weights=distance;, score=-0.683 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=12, p=1, weights=distance;, score=-0.650 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=12, p=1, weights=distance;, score=-0.418 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=12, p=1, weights=distance;, score=-0.881 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=12, p=1, weights=distance;, score=-0.438 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=12, p=1, weights=distance;, score=-0.896 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=12, p=1, weights=distance;, score=-0.528 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=12, p=1, weights=distance;, score=-0.714 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.700 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.786 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 3/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.728 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.608 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.430 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.961 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.433 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.991 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.565 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=12, p=2, weights=uniform;, score=-0.732 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=12, p=2, weights=distance;, score=-0.687 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=12, p=2, weights=distance;, score=-0.783 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=12, p=2, weights=distance;, score=-0.719 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=12, p=2, weights=distance;, score=-0.603 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=12, p=2, weights=distance;, score=-0.423 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=12, p=2, weights=distance;, score=-0.953 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=12, p=2, weights=distance;, score=-0.427 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=12, p=2, weights=distance;, score=-0.980 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=12, p=2, weights=distance;, score=-0.557 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=12, p=2, weights=distance;, score=-0.716 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.710 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.830 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.766 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.655 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.410 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=12, p=3, weights=uniform;, score=-1.034 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.453 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=12, p=3, weights=uniform;, score=-1.015 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.585 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=12, p=3, weights=uniform;, score=-0.679 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=12, p=3, weights=distance;, score=-0.702 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=12, p=3, weights=distance;, score=-0.821 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=12, p=3, weights=distance;, score=-0.757 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=12, p=3, weights=distance;, score=-0.648 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=12, p=3, weights=distance;, score=-0.407 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=12, p=3, weights=distance;, score=-1.023 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=12, p=3, weights=distance;, score=-0.447 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=12, p=3, weights=distance;, score=-1.002 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=12, p=3, weights=distance;, score=-0.576 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=12, p=3, weights=distance;, score=-0.669 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.608 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.762 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.709 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.650 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.424 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.869 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.444 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.910 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.536 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=13, p=1, weights=uniform;, score=-0.730 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=13, p=1, weights=distance;, score=-0.604 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=13, p=1, weights=distance;, score=-0.763 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=13, p=1, weights=distance;, score=-0.701 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=13, p=1, weights=distance;, score=-0.639 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=13, p=1, weights=distance;, score=-0.417 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=13, p=1, weights=distance;, score=-0.871 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=13, p=1, weights=distance;, score=-0.438 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=13, p=1, weights=distance;, score=-0.905 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=13, p=1, weights=distance;, score=-0.529 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=13, p=1, weights=distance;, score=-0.726 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.683 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.793 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.772 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.616 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.425 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.965 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.442 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=13, p=2, weights=uniform;, score=-1.036 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.566 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=13, p=2, weights=uniform;, score=-0.732 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=13, p=2, weights=distance;, score=-0.672 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=13, p=2, weights=distance;, score=-0.789 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=13, p=2, weights=distance;, score=-0.761 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=13, p=2, weights=distance;, score=-0.610 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=13, p=2, weights=distance;, score=-0.418 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=13, p=2, weights=distance;, score=-0.956 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=13, p=2, weights=distance;, score=-0.435 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=13, p=2, weights=distance;, score=-1.021 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=13, p=2, weights=distance;, score=-0.558 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=13, p=2, weights=distance;, score=-0.717 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.711 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.817 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.783 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.650 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.398 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=13, p=3, weights=uniform;, score=-1.019 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.460 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=13, p=3, weights=uniform;, score=-1.069 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.587 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=13, p=3, weights=uniform;, score=-0.727 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=13, p=3, weights=distance;, score=-0.703 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=13, p=3, weights=distance;, score=-0.810 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=13, p=3, weights=distance;, score=-0.772 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=13, p=3, weights=distance;, score=-0.644 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=13, p=3, weights=distance;, score=-0.397 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=13, p=3, weights=distance;, score=-1.010 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=13, p=3, weights=distance;, score=-0.453 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=13, p=3, weights=distance;, score=-1.052 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=13, p=3, weights=distance;, score=-0.579 total time=   0.1s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 10/10] END n_neighbors=13, p=3, weights=distance;, score=-0.712 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.617 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.766 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.704 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.667 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.438 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.896 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.440 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.922 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.557 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=14, p=1, weights=uniform;, score=-0.748 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=14, p=1, weights=distance;, score=-0.612 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=14, p=1, weights=distance;, score=-0.766 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=14, p=1, weights=distance;, score=-0.696 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=14, p=1, weights=distance;, score=-0.655 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=14, p=1, weights=distance;, score=-0.431 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=14, p=1, weights=distance;, score=-0.896 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=14, p=1, weights=distance;, score=-0.434 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=14, p=1, weights=distance;, score=-0.915 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=14, p=1, weights=distance;, score=-0.548 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=14, p=1, weights=distance;, score=-0.741 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.673 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.802 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.787 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.622 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.415 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.972 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.443 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=14, p=2, weights=uniform;, score=-1.045 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.573 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=14, p=2, weights=uniform;, score=-0.720 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=14, p=2, weights=distance;, score=-0.664 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=14, p=2, weights=distance;, score=-0.797 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=14, p=2, weights=distance;, score=-0.775 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=14, p=2, weights=distance;, score=-0.616 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=14, p=2, weights=distance;, score=-0.411 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=14, p=2, weights=distance;, score=-0.962 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=14, p=2, weights=distance;, score=-0.437 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=14, p=2, weights=distance;, score=-1.030 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=14, p=2, weights=distance;, score=-0.565 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=14, p=2, weights=distance;, score=-0.708 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.702 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.817 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.781 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.671 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.406 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=14, p=3, weights=uniform;, score=-1.007 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.467 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=14, p=3, weights=uniform;, score=-1.084 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.596 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=14, p=3, weights=uniform;, score=-0.725 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=14, p=3, weights=distance;, score=-0.695 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=14, p=3, weights=distance;, score=-0.811 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=14, p=3, weights=distance;, score=-0.770 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=14, p=3, weights=distance;, score=-0.663 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=14, p=3, weights=distance;, score=-0.403 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=14, p=3, weights=distance;, score=-0.999 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=14, p=3, weights=distance;, score=-0.460 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=14, p=3, weights=distance;, score=-1.067 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=14, p=3, weights=distance;, score=-0.587 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=14, p=3, weights=distance;, score=-0.712 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.633 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.774 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.709 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.684 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.446 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.895 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.444 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.940 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.562 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=15, p=1, weights=uniform;, score=-0.758 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=15, p=1, weights=distance;, score=-0.626 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=15, p=1, weights=distance;, score=-0.773 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=15, p=1, weights=distance;, score=-0.702 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=15, p=1, weights=distance;, score=-0.672 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=15, p=1, weights=distance;, score=-0.438 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=15, p=1, weights=distance;, score=-0.895 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=15, p=1, weights=distance;, score=-0.438 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=15, p=1, weights=distance;, score=-0.931 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=15, p=1, weights=distance;, score=-0.553 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=15, p=1, weights=distance;, score=-0.750 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.680 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.780 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.782 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.649 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.417 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.977 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.452 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=15, p=2, weights=uniform;, score=-1.036 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.578 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=15, p=2, weights=uniform;, score=-0.715 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=15, p=2, weights=distance;, score=-0.670 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=15, p=2, weights=distance;, score=-0.779 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=15, p=2, weights=distance;, score=-0.772 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=15, p=2, weights=distance;, score=-0.641 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=15, p=2, weights=distance;, score=-0.412 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=15, p=2, weights=distance;, score=-0.968 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=15, p=2, weights=distance;, score=-0.445 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=15, p=2, weights=distance;, score=-1.023 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=15, p=2, weights=distance;, score=-0.570 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=15, p=2, weights=distance;, score=-0.704 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.711 total time=   0.1s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 2/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.816 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.792 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.666 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.413 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=15, p=3, weights=uniform;, score=-1.014 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.469 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=15, p=3, weights=uniform;, score=-1.116 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.605 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=15, p=3, weights=uniform;, score=-0.716 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=15, p=3, weights=distance;, score=-0.703 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=15, p=3, weights=distance;, score=-0.811 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=15, p=3, weights=distance;, score=-0.781 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=15, p=3, weights=distance;, score=-0.659 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=15, p=3, weights=distance;, score=-0.410 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=15, p=3, weights=distance;, score=-1.007 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=15, p=3, weights=distance;, score=-0.462 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=15, p=3, weights=distance;, score=-1.098 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=15, p=3, weights=distance;, score=-0.596 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=15, p=3, weights=distance;, score=-0.706 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.634 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.768 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.715 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.694 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.438 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.895 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.443 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.951 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.563 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=16, p=1, weights=uniform;, score=-0.770 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=16, p=1, weights=distance;, score=-0.627 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=16, p=1, weights=distance;, score=-0.768 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=16, p=1, weights=distance;, score=-0.708 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=16, p=1, weights=distance;, score=-0.681 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=16, p=1, weights=distance;, score=-0.432 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=16, p=1, weights=distance;, score=-0.894 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=16, p=1, weights=distance;, score=-0.437 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=16, p=1, weights=distance;, score=-0.942 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=16, p=1, weights=distance;, score=-0.554 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=16, p=1, weights=distance;, score=-0.762 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.668 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.787 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.794 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.654 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.425 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.960 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.458 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=16, p=2, weights=uniform;, score=-1.049 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.587 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=16, p=2, weights=uniform;, score=-0.739 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=16, p=2, weights=distance;, score=-0.661 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=16, p=2, weights=distance;, score=-0.785 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=16, p=2, weights=distance;, score=-0.783 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=16, p=2, weights=distance;, score=-0.646 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=16, p=2, weights=distance;, score=-0.420 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=16, p=2, weights=distance;, score=-0.954 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=16, p=2, weights=distance;, score=-0.450 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=16, p=2, weights=distance;, score=-1.034 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=16, p=2, weights=distance;, score=-0.578 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=16, p=2, weights=distance;, score=-0.725 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.712 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.835 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.818 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.688 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.414 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.994 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.462 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=16, p=3, weights=uniform;, score=-1.138 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.615 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=16, p=3, weights=uniform;, score=-0.709 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=16, p=3, weights=distance;, score=-0.704 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=16, p=3, weights=distance;, score=-0.828 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=16, p=3, weights=distance;, score=-0.803 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=16, p=3, weights=distance;, score=-0.680 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=16, p=3, weights=distance;, score=-0.411 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=16, p=3, weights=distance;, score=-0.990 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=16, p=3, weights=distance;, score=-0.456 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=16, p=3, weights=distance;, score=-1.119 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=16, p=3, weights=distance;, score=-0.606 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=16, p=3, weights=distance;, score=-0.701 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.645 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.760 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.710 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.695 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.436 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.885 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.443 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.963 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.554 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=17, p=1, weights=uniform;, score=-0.791 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=17, p=1, weights=distance;, score=-0.637 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=17, p=1, weights=distance;, score=-0.760 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=17, p=1, weights=distance;, score=-0.704 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=17, p=1, weights=distance;, score=-0.682 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=17, p=1, weights=distance;, score=-0.431 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=17, p=1, weights=distance;, score=-0.885 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=17, p=1, weights=distance;, score=-0.437 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=17, p=1, weights=distance;, score=-0.953 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=17, p=1, weights=distance;, score=-0.546 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 10/10] END n_neighbors=17, p=1, weights=distance;, score=-0.780 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.665 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.800 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.809 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.668 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.438 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.959 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.469 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=17, p=2, weights=uniform;, score=-1.061 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.596 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=17, p=2, weights=uniform;, score=-0.736 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=17, p=2, weights=distance;, score=-0.658 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=17, p=2, weights=distance;, score=-0.797 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=17, p=2, weights=distance;, score=-0.797 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=17, p=2, weights=distance;, score=-0.659 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=17, p=2, weights=distance;, score=-0.432 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=17, p=2, weights=distance;, score=-0.954 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=17, p=2, weights=distance;, score=-0.460 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=17, p=2, weights=distance;, score=-1.045 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=17, p=2, weights=distance;, score=-0.586 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=17, p=2, weights=distance;, score=-0.723 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.708 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.840 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.823 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.680 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.419 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=17, p=3, weights=uniform;, score=-1.007 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.465 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=17, p=3, weights=uniform;, score=-1.150 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.614 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=17, p=3, weights=uniform;, score=-0.737 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=17, p=3, weights=distance;, score=-0.702 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=17, p=3, weights=distance;, score=-0.832 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=17, p=3, weights=distance;, score=-0.808 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=17, p=3, weights=distance;, score=-0.672 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=17, p=3, weights=distance;, score=-0.416 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=17, p=3, weights=distance;, score=-1.000 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=17, p=3, weights=distance;, score=-0.459 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=17, p=3, weights=distance;, score=-1.130 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=17, p=3, weights=distance;, score=-0.605 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=17, p=3, weights=distance;, score=-0.726 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.646 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.766 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.721 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.703 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.448 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.876 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.443 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.956 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.570 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=18, p=1, weights=uniform;, score=-0.790 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=18, p=1, weights=distance;, score=-0.638 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=18, p=1, weights=distance;, score=-0.765 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=18, p=1, weights=distance;, score=-0.714 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=18, p=1, weights=distance;, score=-0.691 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=18, p=1, weights=distance;, score=-0.441 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=18, p=1, weights=distance;, score=-0.878 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=18, p=1, weights=distance;, score=-0.437 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=18, p=1, weights=distance;, score=-0.947 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=18, p=1, weights=distance;, score=-0.562 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=18, p=1, weights=distance;, score=-0.779 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.666 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.813 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.804 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.685 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.434 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.957 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.467 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=18, p=2, weights=uniform;, score=-1.069 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.611 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=18, p=2, weights=uniform;, score=-0.728 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=18, p=2, weights=distance;, score=-0.659 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=18, p=2, weights=distance;, score=-0.808 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=18, p=2, weights=distance;, score=-0.793 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=18, p=2, weights=distance;, score=-0.675 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=18, p=2, weights=distance;, score=-0.429 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=18, p=2, weights=distance;, score=-0.952 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=18, p=2, weights=distance;, score=-0.459 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=18, p=2, weights=distance;, score=-1.054 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=18, p=2, weights=distance;, score=-0.600 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=18, p=2, weights=distance;, score=-0.717 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.695 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.860 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.833 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.674 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.415 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.993 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.476 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=18, p=3, weights=uniform;, score=-1.156 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.621 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=18, p=3, weights=uniform;, score=-0.751 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=18, p=3, weights=distance;, score=-0.690 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=18, p=3, weights=distance;, score=-0.850 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=18, p=3, weights=distance;, score=-0.819 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=18, p=3, weights=distance;, score=-0.668 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=18, p=3, weights=distance;, score=-0.412 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=18, p=3, weights=distance;, score=-0.989 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=18, p=3, weights=distance;, score=-0.470 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=18, p=3, weights=distance;, score=-1.137 total time=   0.1s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 9/10] END n_neighbors=18, p=3, weights=distance;, score=-0.612 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=18, p=3, weights=distance;, score=-0.739 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.641 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.766 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.719 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.695 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.441 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.885 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.439 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.950 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.588 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=19, p=1, weights=uniform;, score=-0.798 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=19, p=1, weights=distance;, score=-0.634 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=19, p=1, weights=distance;, score=-0.765 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=19, p=1, weights=distance;, score=-0.712 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=19, p=1, weights=distance;, score=-0.684 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=19, p=1, weights=distance;, score=-0.435 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=19, p=1, weights=distance;, score=-0.885 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=19, p=1, weights=distance;, score=-0.434 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=19, p=1, weights=distance;, score=-0.942 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=19, p=1, weights=distance;, score=-0.578 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=19, p=1, weights=distance;, score=-0.787 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.689 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.829 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.816 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.701 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.434 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.953 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.471 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=19, p=2, weights=uniform;, score=-1.064 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.617 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=19, p=2, weights=uniform;, score=-0.719 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=19, p=2, weights=distance;, score=-0.680 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=19, p=2, weights=distance;, score=-0.823 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=19, p=2, weights=distance;, score=-0.804 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=19, p=2, weights=distance;, score=-0.690 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=19, p=2, weights=distance;, score=-0.429 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=19, p=2, weights=distance;, score=-0.948 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=19, p=2, weights=distance;, score=-0.463 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=19, p=2, weights=distance;, score=-1.050 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=19, p=2, weights=distance;, score=-0.607 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=19, p=2, weights=distance;, score=-0.709 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.698 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.865 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.840 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.674 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.416 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=19, p=3, weights=uniform;, score=-1.006 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.478 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=19, p=3, weights=uniform;, score=-1.160 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.626 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=19, p=3, weights=uniform;, score=-0.742 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=19, p=3, weights=distance;, score=-0.694 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=19, p=3, weights=distance;, score=-0.855 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=19, p=3, weights=distance;, score=-0.826 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=19, p=3, weights=distance;, score=-0.667 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=19, p=3, weights=distance;, score=-0.412 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=19, p=3, weights=distance;, score=-1.000 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=19, p=3, weights=distance;, score=-0.470 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=19, p=3, weights=distance;, score=-1.142 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=19, p=3, weights=distance;, score=-0.616 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=19, p=3, weights=distance;, score=-0.732 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.637 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.771 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.724 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.692 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.439 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.893 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.435 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.961 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.602 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=20, p=1, weights=uniform;, score=-0.798 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=20, p=1, weights=distance;, score=-0.630 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=20, p=1, weights=distance;, score=-0.770 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=20, p=1, weights=distance;, score=-0.718 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=20, p=1, weights=distance;, score=-0.682 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=20, p=1, weights=distance;, score=-0.434 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=20, p=1, weights=distance;, score=-0.892 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=20, p=1, weights=distance;, score=-0.430 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=20, p=1, weights=distance;, score=-0.952 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=20, p=1, weights=distance;, score=-0.591 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=20, p=1, weights=distance;, score=-0.787 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.693 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.829 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.828 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.683 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.430 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.959 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.470 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=20, p=2, weights=uniform;, score=-1.069 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.617 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=20, p=2, weights=uniform;, score=-0.721 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=20, p=2, weights=distance;, score=-0.684 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=20, p=2, weights=distance;, score=-0.823 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=20, p=2, weights=distance;, score=-0.815 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=20, p=2, weights=distance;, score=-0.675 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=20, p=2, weights=distance;, score=-0.425 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=20, p=2, weights=distance;, score=-0.954 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=20, p=2, weights=distance;, score=-0.463 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=20, p=2, weights=distance;, score=-1.055 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=20, p=2, weights=distance;, score=-0.606 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=20, p=2, weights=distance;, score=-0.712 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 1/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.702 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.865 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.852 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.684 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.425 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=20, p=3, weights=uniform;, score=-1.006 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.483 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=20, p=3, weights=uniform;, score=-1.169 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.635 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=20, p=3, weights=uniform;, score=-0.743 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=20, p=3, weights=distance;, score=-0.697 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=20, p=3, weights=distance;, score=-0.855 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=20, p=3, weights=distance;, score=-0.838 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=20, p=3, weights=distance;, score=-0.677 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=20, p=3, weights=distance;, score=-0.421 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=20, p=3, weights=distance;, score=-1.000 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=20, p=3, weights=distance;, score=-0.475 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=20, p=3, weights=distance;, score=-1.151 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=20, p=3, weights=distance;, score=-0.626 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=20, p=3, weights=distance;, score=-0.733 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.635 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.783 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.730 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.692 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.433 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.890 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.428 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.973 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.600 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=21, p=1, weights=uniform;, score=-0.784 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=21, p=1, weights=distance;, score=-0.629 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=21, p=1, weights=distance;, score=-0.780 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=21, p=1, weights=distance;, score=-0.723 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=21, p=1, weights=distance;, score=-0.682 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=21, p=1, weights=distance;, score=-0.428 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=21, p=1, weights=distance;, score=-0.889 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=21, p=1, weights=distance;, score=-0.424 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=21, p=1, weights=distance;, score=-0.963 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=21, p=1, weights=distance;, score=-0.590 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=21, p=1, weights=distance;, score=-0.775 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.698 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.845 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.835 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.698 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.424 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.965 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.469 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=21, p=2, weights=uniform;, score=-1.084 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.623 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=21, p=2, weights=uniform;, score=-0.723 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=21, p=2, weights=distance;, score=-0.689 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=21, p=2, weights=distance;, score=-0.839 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=21, p=2, weights=distance;, score=-0.821 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=21, p=2, weights=distance;, score=-0.688 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=21, p=2, weights=distance;, score=-0.420 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=21, p=2, weights=distance;, score=-0.960 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=21, p=2, weights=distance;, score=-0.463 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=21, p=2, weights=distance;, score=-1.068 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=21, p=2, weights=distance;, score=-0.612 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=21, p=2, weights=distance;, score=-0.714 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.711 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.863 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.873 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.704 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.430 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=21, p=3, weights=uniform;, score=-1.010 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.498 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=21, p=3, weights=uniform;, score=-1.197 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.650 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=21, p=3, weights=uniform;, score=-0.736 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=21, p=3, weights=distance;, score=-0.705 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=21, p=3, weights=distance;, score=-0.854 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=21, p=3, weights=distance;, score=-0.857 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=21, p=3, weights=distance;, score=-0.695 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=21, p=3, weights=distance;, score=-0.426 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=21, p=3, weights=distance;, score=-1.005 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=21, p=3, weights=distance;, score=-0.489 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=21, p=3, weights=distance;, score=-1.177 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=21, p=3, weights=distance;, score=-0.638 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=21, p=3, weights=distance;, score=-0.728 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.631 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.777 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.721 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.695 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.434 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.890 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.430 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.983 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.602 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=22, p=1, weights=uniform;, score=-0.804 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=22, p=1, weights=distance;, score=-0.625 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=22, p=1, weights=distance;, score=-0.775 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=22, p=1, weights=distance;, score=-0.715 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=22, p=1, weights=distance;, score=-0.685 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=22, p=1, weights=distance;, score=-0.429 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=22, p=1, weights=distance;, score=-0.890 total time=   0.0s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 7/10] END n_neighbors=22, p=1, weights=distance;, score=-0.425 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=22, p=1, weights=distance;, score=-0.972 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=22, p=1, weights=distance;, score=-0.591 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=22, p=1, weights=distance;, score=-0.793 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.687 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.835 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.838 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.707 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.418 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.952 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.471 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=22, p=2, weights=uniform;, score=-1.097 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.626 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=22, p=2, weights=uniform;, score=-0.733 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=22, p=2, weights=distance;, score=-0.679 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=22, p=2, weights=distance;, score=-0.829 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=22, p=2, weights=distance;, score=-0.825 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=22, p=2, weights=distance;, score=-0.697 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=22, p=2, weights=distance;, score=-0.415 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=22, p=2, weights=distance;, score=-0.948 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=22, p=2, weights=distance;, score=-0.464 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=22, p=2, weights=distance;, score=-1.080 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=22, p=2, weights=distance;, score=-0.615 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=22, p=2, weights=distance;, score=-0.722 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.730 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.859 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.875 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.709 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.429 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=22, p=3, weights=uniform;, score=-1.010 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.497 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=22, p=3, weights=uniform;, score=-1.194 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.671 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=22, p=3, weights=uniform;, score=-0.747 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=22, p=3, weights=distance;, score=-0.722 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=22, p=3, weights=distance;, score=-0.851 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=22, p=3, weights=distance;, score=-0.860 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=22, p=3, weights=distance;, score=-0.700 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=22, p=3, weights=distance;, score=-0.425 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=22, p=3, weights=distance;, score=-1.005 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=22, p=3, weights=distance;, score=-0.488 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=22, p=3, weights=distance;, score=-1.175 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=22, p=3, weights=distance;, score=-0.658 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=22, p=3, weights=distance;, score=-0.737 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.643 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.808 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.728 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.690 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.434 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.881 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.434 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.980 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.607 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=23, p=1, weights=uniform;, score=-0.798 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=23, p=1, weights=distance;, score=-0.636 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=23, p=1, weights=distance;, score=-0.802 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=23, p=1, weights=distance;, score=-0.722 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=23, p=1, weights=distance;, score=-0.681 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=23, p=1, weights=distance;, score=-0.429 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=23, p=1, weights=distance;, score=-0.882 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=23, p=1, weights=distance;, score=-0.430 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=23, p=1, weights=distance;, score=-0.970 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=23, p=1, weights=distance;, score=-0.596 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=23, p=1, weights=distance;, score=-0.788 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.678 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.847 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.828 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.704 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.429 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.964 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.485 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=23, p=2, weights=uniform;, score=-1.106 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.634 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=23, p=2, weights=uniform;, score=-0.745 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=23, p=2, weights=distance;, score=-0.672 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=23, p=2, weights=distance;, score=-0.840 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=23, p=2, weights=distance;, score=-0.816 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=23, p=2, weights=distance;, score=-0.694 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=23, p=2, weights=distance;, score=-0.425 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=23, p=2, weights=distance;, score=-0.959 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=23, p=2, weights=distance;, score=-0.477 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=23, p=2, weights=distance;, score=-1.089 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=23, p=2, weights=distance;, score=-0.622 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=23, p=2, weights=distance;, score=-0.733 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.737 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.864 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.887 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.704 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.437 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=23, p=3, weights=uniform;, score=-1.003 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.502 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=23, p=3, weights=uniform;, score=-1.229 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.679 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=23, p=3, weights=uniform;, score=-0.762 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=23, p=3, weights=distance;, score=-0.728 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=23, p=3, weights=distance;, score=-0.856 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=23, p=3, weights=distance;, score=-0.871 total time=   0.1s\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[CV 4/10] END n_neighbors=23, p=3, weights=distance;, score=-0.696 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=23, p=3, weights=distance;, score=-0.432 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=23, p=3, weights=distance;, score=-0.998 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=23, p=3, weights=distance;, score=-0.493 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=23, p=3, weights=distance;, score=-1.207 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=23, p=3, weights=distance;, score=-0.666 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=23, p=3, weights=distance;, score=-0.751 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.645 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.812 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.734 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.695 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.437 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.880 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.435 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.980 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.607 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=24, p=1, weights=uniform;, score=-0.797 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=24, p=1, weights=distance;, score=-0.638 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=24, p=1, weights=distance;, score=-0.806 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=24, p=1, weights=distance;, score=-0.727 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=24, p=1, weights=distance;, score=-0.686 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=24, p=1, weights=distance;, score=-0.432 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=24, p=1, weights=distance;, score=-0.881 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=24, p=1, weights=distance;, score=-0.431 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=24, p=1, weights=distance;, score=-0.971 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=24, p=1, weights=distance;, score=-0.596 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=24, p=1, weights=distance;, score=-0.788 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.685 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.851 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.824 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.699 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.427 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.964 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.494 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=24, p=2, weights=uniform;, score=-1.119 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.634 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=24, p=2, weights=uniform;, score=-0.748 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=24, p=2, weights=distance;, score=-0.678 total time=   0.0s\n",
      "[CV 2/10] END n_neighbors=24, p=2, weights=distance;, score=-0.844 total time=   0.0s\n",
      "[CV 3/10] END n_neighbors=24, p=2, weights=distance;, score=-0.813 total time=   0.0s\n",
      "[CV 4/10] END n_neighbors=24, p=2, weights=distance;, score=-0.690 total time=   0.0s\n",
      "[CV 5/10] END n_neighbors=24, p=2, weights=distance;, score=-0.423 total time=   0.0s\n",
      "[CV 6/10] END n_neighbors=24, p=2, weights=distance;, score=-0.959 total time=   0.0s\n",
      "[CV 7/10] END n_neighbors=24, p=2, weights=distance;, score=-0.486 total time=   0.0s\n",
      "[CV 8/10] END n_neighbors=24, p=2, weights=distance;, score=-1.102 total time=   0.0s\n",
      "[CV 9/10] END n_neighbors=24, p=2, weights=distance;, score=-0.623 total time=   0.0s\n",
      "[CV 10/10] END n_neighbors=24, p=2, weights=distance;, score=-0.737 total time=   0.0s\n",
      "[CV 1/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.739 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.865 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.892 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.710 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.435 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=24, p=3, weights=uniform;, score=-1.015 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.502 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=24, p=3, weights=uniform;, score=-1.245 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.684 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=24, p=3, weights=uniform;, score=-0.756 total time=   0.1s\n",
      "[CV 1/10] END n_neighbors=24, p=3, weights=distance;, score=-0.730 total time=   0.1s\n",
      "[CV 2/10] END n_neighbors=24, p=3, weights=distance;, score=-0.857 total time=   0.1s\n",
      "[CV 3/10] END n_neighbors=24, p=3, weights=distance;, score=-0.875 total time=   0.1s\n",
      "[CV 4/10] END n_neighbors=24, p=3, weights=distance;, score=-0.701 total time=   0.1s\n",
      "[CV 5/10] END n_neighbors=24, p=3, weights=distance;, score=-0.431 total time=   0.1s\n",
      "[CV 6/10] END n_neighbors=24, p=3, weights=distance;, score=-1.009 total time=   0.1s\n",
      "[CV 7/10] END n_neighbors=24, p=3, weights=distance;, score=-0.494 total time=   0.1s\n",
      "[CV 8/10] END n_neighbors=24, p=3, weights=distance;, score=-1.223 total time=   0.1s\n",
      "[CV 9/10] END n_neighbors=24, p=3, weights=distance;, score=-0.670 total time=   0.1s\n",
      "[CV 10/10] END n_neighbors=24, p=3, weights=distance;, score=-0.747 total time=   0.1s\n",
      "CPU times: user 2min 21s, sys: 6.23 s, total: 2min 28s\n",
      "Wall time: 39.3 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "%%chime\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "id": "59f07fa2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'n_neighbors': 4, 'p': 1, 'weights': 'distance'}"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.best_params_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "id": "839ee0c1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.6224380152274456"
      ]
     },
     "execution_count": 51,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.best_score_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "id": "47a22851",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = model.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "9b51b1ab",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.44704195562371907"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_absolute_percentage_error(y_val, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "dd03625a",
   "metadata": {},
   "source": [
    "Minor improvement over linear regression on the test set, though cross-validation results are much worse."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "11b59332",
   "metadata": {},
   "source": [
    "# Random forest\n",
    "Using Optuna to select the best hyperparameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "0043ee64",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import RandomForestRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "3f1b679c",
   "metadata": {},
   "outputs": [],
   "source": [
    "def objective(trial):\n",
    "    bootstrap = trial.suggest_categorical('bootstrap', [True, False])\n",
    "    if bootstrap:\n",
    "        max_samples = trial.suggest_float('max_samples', 0.3, 1.0, log=False)\n",
    "    else:\n",
    "        max_samples = None\n",
    "    params = {\n",
    "        'n_estimators': trial.suggest_int('n_estimators', 10, 1000, log=True),\n",
    "        'max_features': trial.suggest_categorical('max_features', ['sqrt', 'log2', None]),\n",
    "        'max_depth': trial.suggest_int('max_depth', 2, 100, log=True),\n",
    "        'min_samples_split': trial.suggest_int('min_samples_split', 2, 20)\n",
    "    }\n",
    "\n",
    "    regressor = RandomForestRegressor(random_state=8, \n",
    "                                          bootstrap=bootstrap,\n",
    "                                          max_samples=max_samples,\n",
    "                                          **params)\n",
    "    cv_scores = cross_val_score(regressor, \n",
    "                                X_train, y_train, \n",
    "                                scoring='neg_mean_absolute_percentage_error', \n",
    "                                cv=10)\n",
    "    return cv_scores.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "c4b993e7",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 11:02:19,395]\u001b[0m A new study created in memory with name: no-name-94f02845-c189-4dab-80c7-970c6bc65f9e\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "study = optuna.create_study(\n",
    "    pruner=optuna.pruners.HyperbandPruner(),\n",
    "    direction='maximize'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "7c0d3e5d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 11:02:39,046]\u001b[0m Trial 0 finished with value: -0.5876777164229214 and parameters: {'bootstrap': False, 'n_estimators': 246, 'max_features': 'sqrt', 'max_depth': 9, 'min_samples_split': 18}. Best is trial 0 with value: -0.5876777164229214.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:03,774]\u001b[0m Trial 1 finished with value: -0.5705400642812224 and parameters: {'bootstrap': False, 'n_estimators': 265, 'max_features': 'sqrt', 'max_depth': 21, 'min_samples_split': 9}. Best is trial 1 with value: -0.5705400642812224.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:06,917]\u001b[0m Trial 2 finished with value: -0.7259445720188499 and parameters: {'bootstrap': True, 'max_samples': 0.6586428661400694, 'n_estimators': 114, 'max_features': 'sqrt', 'max_depth': 3, 'min_samples_split': 2}. Best is trial 1 with value: -0.5705400642812224.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:10,638]\u001b[0m Trial 3 finished with value: -0.6726902586226899 and parameters: {'bootstrap': False, 'n_estimators': 82, 'max_features': 'log2', 'max_depth': 6, 'min_samples_split': 3}. Best is trial 1 with value: -0.5705400642812224.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:14,616]\u001b[0m Trial 4 finished with value: -0.5536083260778721 and parameters: {'bootstrap': False, 'n_estimators': 39, 'max_features': 'sqrt', 'max_depth': 37, 'min_samples_split': 6}. Best is trial 4 with value: -0.5536083260778721.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:15,916]\u001b[0m Trial 5 finished with value: -0.5917395647279191 and parameters: {'bootstrap': False, 'n_estimators': 19, 'max_features': 'log2', 'max_depth': 85, 'min_samples_split': 8}. Best is trial 4 with value: -0.5536083260778721.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:16,646]\u001b[0m Trial 6 finished with value: -0.5747685036493543 and parameters: {'bootstrap': True, 'max_samples': 0.8736213538937809, 'n_estimators': 13, 'max_features': 'sqrt', 'max_depth': 45, 'min_samples_split': 16}. Best is trial 4 with value: -0.5536083260778721.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:55,899]\u001b[0m Trial 7 finished with value: -0.35475664730002554 and parameters: {'bootstrap': True, 'max_samples': 0.8934028746381759, 'n_estimators': 166, 'max_features': None, 'max_depth': 4, 'min_samples_split': 15}. Best is trial 7 with value: -0.35475664730002554.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:57,960]\u001b[0m Trial 8 finished with value: -0.6052016566225692 and parameters: {'bootstrap': True, 'max_samples': 0.6344327095809816, 'n_estimators': 45, 'max_features': 'sqrt', 'max_depth': 61, 'min_samples_split': 11}. Best is trial 7 with value: -0.35475664730002554.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:03:59,054]\u001b[0m Trial 9 finished with value: -0.7369840392174323 and parameters: {'bootstrap': True, 'max_samples': 0.6403623016418806, 'n_estimators': 38, 'max_features': 'sqrt', 'max_depth': 3, 'min_samples_split': 4}. Best is trial 7 with value: -0.35475664730002554.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:05:50,206]\u001b[0m Trial 10 finished with value: -0.4352903674936249 and parameters: {'bootstrap': True, 'max_samples': 0.9536848734263486, 'n_estimators': 838, 'max_features': None, 'max_depth': 2, 'min_samples_split': 15}. Best is trial 7 with value: -0.35475664730002554.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:08:01,823]\u001b[0m Trial 11 finished with value: -0.4354286591509074 and parameters: {'bootstrap': True, 'max_samples': 0.9609461495524269, 'n_estimators': 987, 'max_features': None, 'max_depth': 2, 'min_samples_split': 15}. Best is trial 7 with value: -0.35475664730002554.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:12:31,172]\u001b[0m Trial 12 finished with value: -0.3435172829433039 and parameters: {'bootstrap': True, 'max_samples': 0.9680526401077758, 'n_estimators': 936, 'max_features': None, 'max_depth': 5, 'min_samples_split': 14}. Best is trial 12 with value: -0.3435172829433039.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:14:20,077]\u001b[0m Trial 13 finished with value: -0.34995700221618575 and parameters: {'bootstrap': True, 'max_samples': 0.8213225286944713, 'n_estimators': 435, 'max_features': None, 'max_depth': 6, 'min_samples_split': 20}. Best is trial 12 with value: -0.3435172829433039.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:16:22,657]\u001b[0m Trial 14 finished with value: -0.34806541587380135 and parameters: {'bootstrap': True, 'max_samples': 0.8034090060181, 'n_estimators': 481, 'max_features': None, 'max_depth': 11, 'min_samples_split': 19}. Best is trial 12 with value: -0.3435172829433039.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:17:26,353]\u001b[0m Trial 15 finished with value: -0.3518080062392515 and parameters: {'bootstrap': True, 'max_samples': 0.3605365893178673, 'n_estimators': 472, 'max_features': None, 'max_depth': 14, 'min_samples_split': 12}. Best is trial 12 with value: -0.3435172829433039.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:20:04,279]\u001b[0m Trial 16 finished with value: -0.3455755567025579 and parameters: {'bootstrap': True, 'max_samples': 0.9904532436518116, 'n_estimators': 529, 'max_features': None, 'max_depth': 14, 'min_samples_split': 20}. Best is trial 12 with value: -0.3435172829433039.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:25:32,758]\u001b[0m Trial 17 finished with value: -0.33636143886386766 and parameters: {'bootstrap': True, 'max_samples': 0.9493626555647624, 'n_estimators': 949, 'max_features': None, 'max_depth': 21, 'min_samples_split': 12}. Best is trial 17 with value: -0.33636143886386766.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:26:06,582]\u001b[0m Trial 18 finished with value: -0.6817632987692238 and parameters: {'bootstrap': True, 'max_samples': 0.7741666603721412, 'n_estimators': 968, 'max_features': 'log2', 'max_depth': 25, 'min_samples_split': 12}. Best is trial 17 with value: -0.33636143886386766.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:27:47,529]\u001b[0m Trial 19 finished with value: -0.333780221492587 and parameters: {'bootstrap': True, 'max_samples': 0.996175875970005, 'n_estimators': 265, 'max_features': None, 'max_depth': 20, 'min_samples_split': 10}. Best is trial 19 with value: -0.333780221492587.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:29:36,826]\u001b[0m Trial 20 finished with value: -0.33337054482077527 and parameters: {'bootstrap': True, 'max_samples': 0.9972744849510295, 'n_estimators': 279, 'max_features': None, 'max_depth': 22, 'min_samples_split': 9}. Best is trial 20 with value: -0.33337054482077527.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:31:18,973]\u001b[0m Trial 21 finished with value: -0.33425866139684557 and parameters: {'bootstrap': True, 'max_samples': 0.9060460640663691, 'n_estimators': 281, 'max_features': None, 'max_depth': 23, 'min_samples_split': 9}. Best is trial 20 with value: -0.33337054482077527.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:32:54,474]\u001b[0m Trial 22 finished with value: -0.3327831820892127 and parameters: {'bootstrap': True, 'max_samples': 0.9974779972680141, 'n_estimators': 244, 'max_features': None, 'max_depth': 30, 'min_samples_split': 9}. Best is trial 22 with value: -0.3327831820892127.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:34:06,813]\u001b[0m Trial 23 finished with value: -0.33016595344169836 and parameters: {'bootstrap': True, 'max_samples': 0.9762097908079214, 'n_estimators': 177, 'max_features': None, 'max_depth': 35, 'min_samples_split': 7}. Best is trial 23 with value: -0.33016595344169836.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:35:14,314]\u001b[0m Trial 24 finished with value: -0.328213432913118 and parameters: {'bootstrap': True, 'max_samples': 0.9947451872788506, 'n_estimators': 158, 'max_features': None, 'max_depth': 35, 'min_samples_split': 6}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:36:14,443]\u001b[0m Trial 25 finished with value: -0.3304274077946899 and parameters: {'bootstrap': True, 'max_samples': 0.8851724383648284, 'n_estimators': 153, 'max_features': None, 'max_depth': 37, 'min_samples_split': 6}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:36:20,026]\u001b[0m Trial 26 finished with value: -0.659139843274177 and parameters: {'bootstrap': True, 'max_samples': 0.8872829018614634, 'n_estimators': 128, 'max_features': 'log2', 'max_depth': 46, 'min_samples_split': 6}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:37:19,721]\u001b[0m Trial 27 finished with value: -0.35280389875343743 and parameters: {'bootstrap': False, 'n_estimators': 82, 'max_features': None, 'max_depth': 99, 'min_samples_split': 6}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:38:26,168]\u001b[0m Trial 28 finished with value: -0.32999184324606745 and parameters: {'bootstrap': True, 'max_samples': 0.8490115072953405, 'n_estimators': 169, 'max_features': None, 'max_depth': 71, 'min_samples_split': 5}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 11:40:43,409]\u001b[0m Trial 29 finished with value: -0.3484061786000631 and parameters: {'bootstrap': False, 'n_estimators': 176, 'max_features': None, 'max_depth': 66, 'min_samples_split': 4}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:40:47,414]\u001b[0m Trial 30 finished with value: -0.6650205986069666 and parameters: {'bootstrap': True, 'max_samples': 0.8296207362466665, 'n_estimators': 92, 'max_features': 'log2', 'max_depth': 64, 'min_samples_split': 5}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:41:49,606]\u001b[0m Trial 31 finished with value: -0.331150547014117 and parameters: {'bootstrap': True, 'max_samples': 0.9125527764212737, 'n_estimators': 160, 'max_features': None, 'max_depth': 41, 'min_samples_split': 7}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:43:08,683]\u001b[0m Trial 32 finished with value: -0.33060153678613874 and parameters: {'bootstrap': True, 'max_samples': 0.9219704342284601, 'n_estimators': 201, 'max_features': None, 'max_depth': 30, 'min_samples_split': 7}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:43:58,145]\u001b[0m Trial 33 finished with value: -0.33106156298653755 and parameters: {'bootstrap': True, 'max_samples': 0.8602996956470115, 'n_estimators': 114, 'max_features': None, 'max_depth': 48, 'min_samples_split': 3}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:46:01,111]\u001b[0m Trial 34 finished with value: -0.3485747982132241 and parameters: {'bootstrap': False, 'n_estimators': 144, 'max_features': None, 'max_depth': 34, 'min_samples_split': 2}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:47:29,431]\u001b[0m Trial 35 finished with value: -0.32833620869614155 and parameters: {'bootstrap': True, 'max_samples': 0.9204198337018239, 'n_estimators': 210, 'max_features': None, 'max_depth': 54, 'min_samples_split': 5}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:50:18,649]\u001b[0m Trial 36 finished with value: -0.34864533050566526 and parameters: {'bootstrap': False, 'n_estimators': 216, 'max_features': None, 'max_depth': 83, 'min_samples_split': 4}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:50:25,710]\u001b[0m Trial 37 finished with value: -0.5873316275595316 and parameters: {'bootstrap': True, 'max_samples': 0.9359790442682652, 'n_estimators': 109, 'max_features': 'sqrt', 'max_depth': 54, 'min_samples_split': 7}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:50:42,004]\u001b[0m Trial 38 finished with value: -0.6596140218910447 and parameters: {'bootstrap': True, 'max_samples': 0.9375568352184497, 'n_estimators': 350, 'max_features': 'log2', 'max_depth': 75, 'min_samples_split': 5}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:53:32,851]\u001b[0m Trial 39 finished with value: -0.34877841015616984 and parameters: {'bootstrap': False, 'n_estimators': 200, 'max_features': None, 'max_depth': 55, 'min_samples_split': 2}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:53:37,263]\u001b[0m Trial 40 finished with value: -0.5991476673889481 and parameters: {'bootstrap': True, 'max_samples': 0.7455935593202612, 'n_estimators': 84, 'max_features': 'sqrt', 'max_depth': 100, 'min_samples_split': 8}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:54:29,074]\u001b[0m Trial 41 finished with value: -0.33155523599556636 and parameters: {'bootstrap': True, 'max_samples': 0.8642639142402812, 'n_estimators': 130, 'max_features': None, 'max_depth': 39, 'min_samples_split': 5}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:55:33,525]\u001b[0m Trial 42 finished with value: -0.3303553328759078 and parameters: {'bootstrap': True, 'max_samples': 0.9244990629417561, 'n_estimators': 159, 'max_features': None, 'max_depth': 50, 'min_samples_split': 6}. Best is trial 24 with value: -0.328213432913118.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:56:58,814]\u001b[0m Trial 43 finished with value: -0.3265529878313387 and parameters: {'bootstrap': True, 'max_samples': 0.9317252186241477, 'n_estimators': 184, 'max_features': None, 'max_depth': 72, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 11:58:36,216]\u001b[0m Trial 44 finished with value: -0.3284478994524077 and parameters: {'bootstrap': True, 'max_samples': 0.9485301619576867, 'n_estimators': 208, 'max_features': None, 'max_depth': 73, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:01:02,490]\u001b[0m Trial 45 finished with value: -0.3282951655209901 and parameters: {'bootstrap': True, 'max_samples': 0.8575951427691717, 'n_estimators': 338, 'max_features': None, 'max_depth': 74, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:01:27,640]\u001b[0m Trial 46 finished with value: -0.5857290323176692 and parameters: {'bootstrap': True, 'max_samples': 0.8983339060452878, 'n_estimators': 371, 'max_features': 'sqrt', 'max_depth': 60, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:03:48,096]\u001b[0m Trial 47 finished with value: -0.32914939427017537 and parameters: {'bootstrap': True, 'max_samples': 0.8616503290289994, 'n_estimators': 323, 'max_features': None, 'max_depth': 80, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:05:47,724]\u001b[0m Trial 48 finished with value: -0.32823466041830296 and parameters: {'bootstrap': True, 'max_samples': 0.9474735560594137, 'n_estimators': 242, 'max_features': None, 'max_depth': 69, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:10:43,220]\u001b[0m Trial 49 finished with value: -0.3272508380699507 and parameters: {'bootstrap': True, 'max_samples': 0.9039986502289786, 'n_estimators': 620, 'max_features': None, 'max_depth': 59, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:11:36,070]\u001b[0m Trial 50 finished with value: -0.6468740219297768 and parameters: {'bootstrap': False, 'n_estimators': 656, 'max_features': 'log2', 'max_depth': 88, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:14:27,629]\u001b[0m Trial 51 finished with value: -0.3291996809214818 and parameters: {'bootstrap': True, 'max_samples': 0.9099884936744042, 'n_estimators': 396, 'max_features': None, 'max_depth': 61, 'min_samples_split': 4}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:17:05,288]\u001b[0m Trial 52 finished with value: -0.3282265179471378 and parameters: {'bootstrap': True, 'max_samples': 0.9580050975556482, 'n_estimators': 317, 'max_features': None, 'max_depth': 53, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:22:24,929]\u001b[0m Trial 53 finished with value: -0.3276444413929435 and parameters: {'bootstrap': True, 'max_samples': 0.9640571794004396, 'n_estimators': 641, 'max_features': None, 'max_depth': 45, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:27:07,839]\u001b[0m Trial 54 finished with value: -0.32702907021804284 and parameters: {'bootstrap': True, 'max_samples': 0.956136168234229, 'n_estimators': 571, 'max_features': None, 'max_depth': 46, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:32:17,705]\u001b[0m Trial 55 finished with value: -0.32714487197917047 and parameters: {'bootstrap': True, 'max_samples': 0.9672627690842183, 'n_estimators': 619, 'max_features': None, 'max_depth': 50, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:36:59,707]\u001b[0m Trial 56 finished with value: -0.32825431383063075 and parameters: {'bootstrap': True, 'max_samples': 0.9645432996353762, 'n_estimators': 627, 'max_features': None, 'max_depth': 49, 'min_samples_split': 4}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:37:56,691]\u001b[0m Trial 57 finished with value: -0.5833172451864931 and parameters: {'bootstrap': True, 'max_samples': 0.9750956321015101, 'n_estimators': 762, 'max_features': 'sqrt', 'max_depth': 45, 'min_samples_split': 2}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 12:42:49,225]\u001b[0m Trial 58 finished with value: -0.3274078838030285 and parameters: {'bootstrap': True, 'max_samples': 0.9950673883059369, 'n_estimators': 606, 'max_features': None, 'max_depth': 40, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:45:41,351]\u001b[0m Trial 59 finished with value: -0.3421931365845122 and parameters: {'bootstrap': True, 'max_samples': 0.9590075351185137, 'n_estimators': 553, 'max_features': None, 'max_depth': 42, 'min_samples_split': 17}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:48:51,611]\u001b[0m Trial 60 finished with value: -0.3279996956316401 and parameters: {'bootstrap': True, 'max_samples': 0.8855145869851797, 'n_estimators': 449, 'max_features': None, 'max_depth': 29, 'min_samples_split': 4}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:52:04,520]\u001b[0m Trial 61 finished with value: -0.32796213094119864 and parameters: {'bootstrap': True, 'max_samples': 0.8958180146752438, 'n_estimators': 430, 'max_features': None, 'max_depth': 43, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 12:57:31,969]\u001b[0m Trial 62 finished with value: -0.3272743786921157 and parameters: {'bootstrap': True, 'max_samples': 0.9345529474973715, 'n_estimators': 709, 'max_features': None, 'max_depth': 40, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:03:59,363]\u001b[0m Trial 63 finished with value: -0.32679097598296863 and parameters: {'bootstrap': True, 'max_samples': 0.9712683861536543, 'n_estimators': 816, 'max_features': None, 'max_depth': 57, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:09:49,130]\u001b[0m Trial 64 finished with value: -0.3280285306649555 and parameters: {'bootstrap': True, 'max_samples': 0.9966711614917731, 'n_estimators': 758, 'max_features': None, 'max_depth': 58, 'min_samples_split': 4}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:16:03,657]\u001b[0m Trial 65 finished with value: -0.32708777826953717 and parameters: {'bootstrap': True, 'max_samples': 0.9331264566598733, 'n_estimators': 815, 'max_features': None, 'max_depth': 62, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:22:27,680]\u001b[0m Trial 66 finished with value: -0.32751904920834224 and parameters: {'bootstrap': True, 'max_samples': 0.9283543810905117, 'n_estimators': 837, 'max_features': None, 'max_depth': 62, 'min_samples_split': 3}. Best is trial 43 with value: -0.3265529878313387.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:26:47,926]\u001b[0m Trial 67 finished with value: -0.3263629279563265 and parameters: {'bootstrap': True, 'max_samples': 0.937470690076186, 'n_estimators': 534, 'max_features': None, 'max_depth': 90, 'min_samples_split': 2}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:27:13,250]\u001b[0m Trial 68 finished with value: -0.6624450566549736 and parameters: {'bootstrap': True, 'max_samples': 0.8888124421768893, 'n_estimators': 506, 'max_features': 'log2', 'max_depth': 87, 'min_samples_split': 2}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:31:59,956]\u001b[0m Trial 69 finished with value: -0.33780018474072443 and parameters: {'bootstrap': True, 'max_samples': 0.9728804565586455, 'n_estimators': 850, 'max_features': None, 'max_depth': 66, 'min_samples_split': 14}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:35:43,289]\u001b[0m Trial 70 finished with value: -0.3303404005617644 and parameters: {'bootstrap': True, 'max_samples': 0.831238643143267, 'n_estimators': 555, 'max_features': None, 'max_depth': 94, 'min_samples_split': 4}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:41:21,249]\u001b[0m Trial 71 finished with value: -0.32756268965582436 and parameters: {'bootstrap': True, 'max_samples': 0.9420301521903259, 'n_estimators': 724, 'max_features': None, 'max_depth': 82, 'min_samples_split': 3}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:48:59,860]\u001b[0m Trial 72 finished with value: -0.3273305977083141 and parameters: {'bootstrap': True, 'max_samples': 0.9184964655233862, 'n_estimators': 953, 'max_features': None, 'max_depth': 70, 'min_samples_split': 2}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:52:56,537]\u001b[0m Trial 73 finished with value: -0.3277849478364976 and parameters: {'bootstrap': True, 'max_samples': 0.9741263405798926, 'n_estimators': 499, 'max_features': None, 'max_depth': 51, 'min_samples_split': 3}. Best is trial 67 with value: -0.3263629279563265.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 13:58:42,215]\u001b[0m Trial 74 finished with value: -0.32634522526992826 and parameters: {'bootstrap': True, 'max_samples': 0.9366972545422723, 'n_estimators': 705, 'max_features': None, 'max_depth': 80, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:06:56,261]\u001b[0m Trial 75 finished with value: -0.3484430424636799 and parameters: {'bootstrap': False, 'n_estimators': 579, 'max_features': None, 'max_depth': 93, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:12:43,061]\u001b[0m Trial 76 finished with value: -0.32860921965110274 and parameters: {'bootstrap': True, 'max_samples': 0.9058581669788629, 'n_estimators': 809, 'max_features': None, 'max_depth': 79, 'min_samples_split': 4}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:17:13,597]\u001b[0m Trial 77 finished with value: -0.329543403643512 and parameters: {'bootstrap': True, 'max_samples': 0.8781953608909475, 'n_estimators': 671, 'max_features': None, 'max_depth': 58, 'min_samples_split': 5}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:18:28,077]\u001b[0m Trial 78 finished with value: -0.5845181140554645 and parameters: {'bootstrap': True, 'max_samples': 0.9783324196728648, 'n_estimators': 994, 'max_features': 'sqrt', 'max_depth': 99, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:22:27,300]\u001b[0m Trial 79 finished with value: -0.327143798321721 and parameters: {'bootstrap': True, 'max_samples': 0.9432865146470454, 'n_estimators': 488, 'max_features': None, 'max_depth': 68, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:22:46,543]\u001b[0m Trial 80 finished with value: -0.6629174928502551 and parameters: {'bootstrap': True, 'max_samples': 0.9448899070762418, 'n_estimators': 408, 'max_features': 'log2', 'max_depth': 80, 'min_samples_split': 4}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:26:41,301]\u001b[0m Trial 81 finished with value: -0.327715680237858 and parameters: {'bootstrap': True, 'max_samples': 0.9162428250393271, 'n_estimators': 488, 'max_features': None, 'max_depth': 67, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:31:04,904]\u001b[0m Trial 82 finished with value: -0.32796364200969697 and parameters: {'bootstrap': True, 'max_samples': 0.9509612587483951, 'n_estimators': 564, 'max_features': None, 'max_depth': 73, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:36:49,859]\u001b[0m Trial 83 finished with value: -0.32676620901145703 and parameters: {'bootstrap': True, 'max_samples': 0.9743556383593446, 'n_estimators': 687, 'max_features': None, 'max_depth': 58, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:43:27,805]\u001b[0m Trial 84 finished with value: -0.3267537614593886 and parameters: {'bootstrap': True, 'max_samples': 0.9758154856187053, 'n_estimators': 837, 'max_features': None, 'max_depth': 87, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 14:50:31,500]\u001b[0m Trial 85 finished with value: -0.3267155751311821 and parameters: {'bootstrap': True, 'max_samples': 0.9832559637517837, 'n_estimators': 887, 'max_features': None, 'max_depth': 88, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 15:01:10,787]\u001b[0m Trial 86 finished with value: -0.3509757505614734 and parameters: {'bootstrap': False, 'n_estimators': 854, 'max_features': None, 'max_depth': 90, 'min_samples_split': 5}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:08:17,443]\u001b[0m Trial 87 finished with value: -0.3269574157718286 and parameters: {'bootstrap': True, 'max_samples': 0.9998457151509972, 'n_estimators': 883, 'max_features': None, 'max_depth': 87, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:13:46,079]\u001b[0m Trial 88 finished with value: -0.32826425710108964 and parameters: {'bootstrap': True, 'max_samples': 0.998683782906586, 'n_estimators': 709, 'max_features': None, 'max_depth': 82, 'min_samples_split': 4}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:21:27,440]\u001b[0m Trial 89 finished with value: -0.3272068051057532 and parameters: {'bootstrap': True, 'max_samples': 0.9810994889112197, 'n_estimators': 965, 'max_features': None, 'max_depth': 99, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:26:56,552]\u001b[0m Trial 90 finished with value: -0.33469325810237666 and parameters: {'bootstrap': True, 'max_samples': 0.9808637255041198, 'n_estimators': 898, 'max_features': None, 'max_depth': 77, 'min_samples_split': 11}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:32:53,283]\u001b[0m Trial 91 finished with value: -0.3271194970931076 and parameters: {'bootstrap': True, 'max_samples': 0.9321834451242237, 'n_estimators': 774, 'max_features': None, 'max_depth': 87, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:39:50,680]\u001b[0m Trial 92 finished with value: -0.3267484477375979 and parameters: {'bootstrap': True, 'max_samples': 0.9827866589773789, 'n_estimators': 871, 'max_features': None, 'max_depth': 75, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:46:16,775]\u001b[0m Trial 93 finished with value: -0.3288947874050967 and parameters: {'bootstrap': True, 'max_samples': 0.958799470605588, 'n_estimators': 895, 'max_features': None, 'max_depth': 75, 'min_samples_split': 5}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:51:42,868]\u001b[0m Trial 94 finished with value: -0.32825807139867574 and parameters: {'bootstrap': True, 'max_samples': 0.9989231838219709, 'n_estimators': 706, 'max_features': None, 'max_depth': 89, 'min_samples_split': 4}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:56:59,032]\u001b[0m Trial 95 finished with value: -0.3273186316187211 and parameters: {'bootstrap': True, 'max_samples': 0.979915115039899, 'n_estimators': 664, 'max_features': None, 'max_depth': 56, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 15:58:04,810]\u001b[0m Trial 96 finished with value: -0.5860712951613122 and parameters: {'bootstrap': True, 'max_samples': 0.9598048677692722, 'n_estimators': 889, 'max_features': 'sqrt', 'max_depth': 66, 'min_samples_split': 2}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 16:04:08,295]\u001b[0m Trial 97 finished with value: -0.3266021142129159 and parameters: {'bootstrap': True, 'max_samples': 0.9793014594896522, 'n_estimators': 762, 'max_features': None, 'max_depth': 72, 'min_samples_split': 3}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 16:11:37,875]\u001b[0m Trial 98 finished with value: -0.327777120986933 and parameters: {'bootstrap': True, 'max_samples': 0.9844429152527908, 'n_estimators': 986, 'max_features': None, 'max_depth': 76, 'min_samples_split': 4}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 16:21:30,756]\u001b[0m Trial 99 finished with value: -0.35098553899384566 and parameters: {'bootstrap': False, 'n_estimators': 792, 'max_features': None, 'max_depth': 92, 'min_samples_split': 5}. Best is trial 74 with value: -0.32634522526992826.\u001b[0m\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 5h 18min 27s, sys: 10.1 s, total: 5h 18min 37s\n",
      "Wall time: 5h 19min 10s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "%%chime\n",
    "study.optimize(objective, n_trials=100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "b142b94e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'bootstrap': True,\n",
       " 'max_samples': 0.9366972545422723,\n",
       " 'n_estimators': 705,\n",
       " 'max_features': None,\n",
       " 'max_depth': 80,\n",
       " 'min_samples_split': 2}"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "study.best_params"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "a98952b3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-0.32634522526992826"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "study.best_value"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "0b1d7a0e",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_11131/3324289224.py:1: ExperimentalWarning: plot_optimization_history is experimental (supported from v2.2.0). The interface can change in the future.\n",
      "  plot_optimization_history(study)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<AxesSubplot: title={'center': 'Optimization History Plot'}, xlabel='Trial', ylabel='Objective Value'>"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_optimization_history(study)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "ab9f4634",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_11131/2122237422.py:1: ExperimentalWarning: plot_param_importances is experimental (supported from v2.2.0). The interface can change in the future.\n",
      "  plot_param_importances(study);\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_param_importances(study);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "3df86a5f",
   "metadata": {},
   "outputs": [],
   "source": [
    "best_regressor = RandomForestRegressor(random_state=8, **study.best_params)\\\n",
    "    .fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "67e75c0c",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = best_regressor.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "99cfe3b1",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.31682153721513423"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_absolute_percentage_error(y_val, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b5b79b22",
   "metadata": {},
   "source": [
    "Some curve examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "ae28ab8e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[0, :].to_list(),\n",
    "              'bv_pred':y_pred[0, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[0, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "1faadf8f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[1, :].to_list(),\n",
    "              'bv_pred':y_pred[1, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[1, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "8bdbb2af",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[2, :].to_list(),\n",
    "              'bv_pred':y_pred[2, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[2, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "1aeb1988",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAh8AAAGzCAYAAACPa3XZAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjYuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8o6BhiAAAACXBIWXMAAA9hAAAPYQGoP6dpAABiy0lEQVR4nO3dd3hUZd7/8feZzCSkkUISEkiQ0HsvFhawN1ZEERs2bCuuuro+/HaXdRd3sfDsWp7VdddVWNuKFEFQUVk7iIKCiBiKdCGEFNLrzJz798dANFJMQjIl+byuK1cyM2fO+c6dYfLhnLtYxhiDiIiIiJ84Al2AiIiItC4KHyIiIuJXCh8iIiLiVwofIiIi4lcKHyIiIuJXCh8iIiLiVwofIiIi4lcKHyIiIuJXCh8iIiLiVwofIiIi4lfOQBdwLIWFhXg8nkCX0WjJycnk5eUFuoyQojZrHLVbw6nNGkft1nCtqc2cTicJCQn127aZa2k0j8eD2+0OdBmNYlkW4HsNWjqnftRmjaN2azi1WeOo3RpObXZsuuwiIiIifqXwISIiIn6l8CEiIiJ+pfAhIiIifhW0HU6Px+PxUFFREegyjquyspKamppAl+F3xhicTifR0dGBLkVERIJUyIUPj8dDeXk5sbGxOBzBe+LG5XKF7GidE1VeXk51dTURERGBLkVERIJQ8P71PoaKioqgDx6tXVRUFNXV1YEuQ0REglRI/gVX8Ahuh8e2i4iIHI3+iouIiIhfKXyIiIiIXyl8+MnEiRP5wx/+EOgymkRLei0iIuJ/Ch8iIiLiVyE31FaaRk1NDeHh4YEuQ0SkxTK2jfF4MO4ajNcLtv39l/nhzwZs76Hv9g++H/r58Hf7Bz/Xfh3ltm0A86P7f/RlWVhDTglY2yh8+JHX62X69OksWrQIh8PBtddey7Rp03j44Yf55JNPeOONN+psf9ZZZ3Heeedx7733Hne/v/rVrygpKaFfv34899xzVFdXM378eGbOnFkbMCZOnEjPnj1xuVwsXLiQnj178uqrr7J161b+/Oc/89lnnxEVFcXo0aO5//77SUxMBHxDm3/zm9/w1ltvERMTw6233to8jSMiUg/G7YbqSqiuqvtVUw3uGky17zvuGvC4we32ffe4wev9/rvXA14v5tD37788viBw+Lb9o9Bw+LbX6/tDXxsqvEduA+wNcHsdkyucsKcWBuzwIR8+jDG+N10ghEc0aFjpggULuOKKK3j99dfZsGED06ZNIz09nQkTJvDkk0+ya9cuOnfuDMCWLVvYtGkTTz/9dL32vXLlSiIiIliwYAHfffcd99xzD4mJifzmN7+pc/xrr72W1157DYADBw5w6aWXctVVV/HHP/6RqqoqHnjgAW699VYWLFgAwJ///GdWrVrF7NmzSU5O5uGHH2bDhg306dOn3q9bROQwYwxUlkNpCZSVQFkpprwUDn9VlENlBaayHCrKoLISqioOfVWCxxPol9B0LAc4Dn1Z1qHvP7htWeAIO/TdAqy6j1kOsA7t5/B9tfu16t7/wy8scLkC+MJbQPigphr7l5MCcmjHk/Mhok29t+/QoQP3338/lmXRrVs3Nm/ezDPPPMPVV19N7969Wbx4MXfffTcAixYtYtCgQXTt2rVe+3a5XDz66KNERkbSs2dP7r33XmbOnMm0adNq50Xp3Lkzv//972uf85e//IX+/fvz29/+tva+Rx55hOHDh7N9+3ZSU1N55ZVXePzxxxk9ejQAjz/+OMOGDav3axaR1sEY4wsTB/OgIA9TVADFhVB8EFNcCEWFUFbsCx3eJggQThe0aQMRkRAecegr3PfdFYHlcvm2cYX7/tA6nRB2+Cvs0O2w72+HOX1/6MPCsMKcEObw3T50ny8k1P1uHBY2YdhhDryWAxsHtsOBbTmwLQtjhdEuOYUD+QV4DbX325aFbSwMFl5jaq+o2Id+9hrju8IC2LbxfT98n/n+Z9scfszX/rXPOcq2hu/vO3TVhUtP/LfQ+F9fAI/d6gwZMqTOmZKhQ4fy9NNP4/V6ueSSS3jllVe4++67McawZMkSbrrppnrvu0+fPkRGRtbZd3l5OdnZ2aSnpwMwcODAOs/ZsGEDq1atonv37kfsb/fu3VRVVVFTU1MnbCQkJNQ7EIlIy2LcNZh9uzEHsjF5+yHvgO97fq4vdLgbsJ5VRCTExEJMW4iOxYqJhaiYQ19REBkNkdFYkVF420RR6YykwhlBhSOCKoeTauOgymPXflV7DDVemxqvocZrcHtt3LbBYxvcXt93rwGvXfdnr6fu/bYxeGxfAPAe2s42xnc1pfaPvhfbeDH1eqEHGtnazSs8zOLSvu0CdvzQDx/hEb4zEAE6dlO5+OKLefDBB/n666+pqqoiOzub8ePHn/B+fxh2fhhOwJeUzz77bH73u98d8bz27duzY8eOEz6+iIQe4/HAgX2Y73bC3l2YnL2w/zv25h+o7ctwTHGJkJgECe2w4hJ8t+MTsdom4I1tS1lEW4pc0ZR4LIqrvJTWeCmp9lJ66Ku8xku526a8xEt5vk2520uVxwCVh75Ch8MCh2Ud+v7Dn4/13fez9aP7LHw/W5ZFWO3VEwsHHLntoZ+/fw44fvDz4cedjsDORB3y4cOyrAZd+gikdevWHXE7MzOTsLAwOnTowMknn8yiRYuoqqriZz/7GcnJyfXed1ZWFpWVlbUBY926dURHR5OWlnbM5/Tr149ly5aRkZGB03nkWyEzMxOXy8XatWvp2LEjAEVFRezYsYOTTz653rWJSPAythey92B2bIWdWzF7tkP2nmP3rYiMhvYdsJJT4dCXldQeb0Iy+eFx5FYbcsvd5Jd7OFjpoaDCzcFiDwdzPJRUe7FNIVDYqFpdDotIl4NIl4M2Tt9XpNMiwukgIsxBuNMiIswiPMyBK8zC5bBwOixcYb7vYQ7fH2/fd999Dgc4Ld9jh/8ohx16XtixgoKj7u0fbnd4P74QYZGWlsb+/ft9l6WkVsiHj1CSnZ3NjBkzmDx5Mhs3bmTOnDl1JuuaMGECjz76KDU1NcyYMaNB+3a73dx7773cdddd7N27l0ceeYQbbrjhuOvgXH/99bz88stMnTqV2267jcTERHbt2sWSJUv4y1/+QnR0NFdccQUzZ84kISGB5ORkZs2apbV1REKYqa6C7Zsx336D+TYLdm3zjR75sTaRkN4ZK70zdOiElZZB+4FD2VhQwd6SavaV1JBdWkN2SQ3Zm93kVxRjm+J61RAbEUZ8mzDaRvi+YiPCaBvhJDbCQUx4GFEuB9HhYUS7wogOdxDl8n25wvTZ01IofPjRxIkTqaqqYty4cYSFhTFlyhQmT55c+/i4ceO47777cDgcnHfeeQ3a96hRo8jMzOSSSy6hpqaG8ePHc8899xz3Oampqbz22ms8+OCDXH311VRXV5Oens7YsWNrA8Z9991HeXk5N9xwQ+1Q29LS0oa/eBEJCOPxwI7NmG++xGz5GnZ96xse+kMRkZDZHSuzB1bnbpDRBXd8EruK3Ww/WMWuomp276lmz9dZlNd4j34gfGcmkqNdtI9xkRTlpF2Uk3ZRLhIjnSRGOomPdNI2Iizgp/wl8CwTpOeC8vLycLvdR9xfUlJC27ZtA1BRw7hcrqPW3xwOz/MxZ84cvxyvPhr6e9LpycZRuzVca2gzczAPs+ELzDfrYPMG3xDVH0pIwurRF3r0xeraG9LSyauw+Sa3gi35lWw7WMXOwio8R+ne4XRAWmw4HduG0zE2nA5tw+kQG077GBcJkU4cWtW6Vmt4r/2Qy+Wqd3cBnfkQEQlxxhjY/x3my88wX34Gu7fV3SCmLVafwdBnIFaPfpDUntxyN1/lVPDN7gq+WbOTvIoj+3jERoTRPbENnRMiyExow7Du6YRXl+DU1Q85QQofIeBoQ2EPe+mll/xYiYgEE5OXg1n9IWb1R5Cz7/sHLAu69sLqNxSr3xDI6EKFx/D1gQrW7yxn/ac72F9a98ysw4JuiW3onRxJ93aR9EhqQ0q0q3bEnGVZpCXHsH9/aav4X7w0L4WPELB8+fJjPpaamsrIkSP9WI2IBJKpKMOsWYFZ/SFs2/T9A04n9B6ENWgk1qARWG0TyCmt4fN9Zaz5YC/fHKjA+4PMEGZBz6RI+rWPom9KFD2TIol06ZSG+IfCRwjIzMwMdAkiEmBm93bMR2/5QkfNocm8LAf0HoA1cizW4JOhTSQ7C6v5dGcpn323gz3FdSf96hDrYnBaNAPTounfPoooV5j/X4gICh8iIkHLeDyYz1dgPngTdm79/oGOJ2GdegbWiNEQl8i2g1Ws2lzKqj37ySn7/nKKw4K+KVEM7xjDiPQY0mK1krUEB4UPEZEgY2qqMZ+8i3l7kW/acoAwJ9bQ07DGng/depNT5uajnSV8tGsH2T/ovxEeZjGkQzSnZMQyrEMMMRE6uyHBR+FDRCRImKpK36WV5a9BSZHvzrbxWGeMw/rZ2VS0acvHu0p4/53dbC2oqn1eeJjF8I4xnNYpliEdYtR3Q4KewoeISIAZjwezcjlm6VwoPTRLaGIy1nmXwqlnsLnYZvnGIj7Zk0vNoV6jDgsGpkYzpnNbRmbEqP+GhBSFDxGRADHGwPrV2Iue/36obEoa1gWTqBzyMz7YU8Zby7PZW/J9x9FOceGc3S2e0Se1JT5SH+ESmvTO9ZOJEyfSp08f/vSnPzXL/h955BFeeOEF8vPzmT17doOnZxcR/zJ7d2K//DR8m+W7I6Yt1kVX8t2Asby1vZQPlu48tJortHFajDqpLed0i6dHuzZ1VqsWCUUKHy3At99+y6OPPsrs2bMZMmQIcXFxJ7zPefPmMWPGDDZt2vTTG4tIvZmqSszrr2DeXeJbnt4VDmeN56shF/Da9nK+evu72m3T24ZzYc8Exma21WUVaVEaFD4WL17MmjVr2LdvH+Hh4fTo0YPJkyfToUOH2m3+/ve/89FHH9V5Xvfu3XnggQeapmI5wq5duwA499xz9T8ikSBm1q/Gnvs0HMwHwD3kNFaNuprX9rjZ/YlvVIvDghHpMVzYI4H+7aP0b1papAaFj6ysLM4991y6du2K1+vllVdeYebMmTz66KO0adOmdrtBgwYxderU7w/i1AkWAK/Xy/Tp01m0aBEOh4Nrr72WadOm8fDDD/PJJ5/wxhtv1Nn+rLPO4rzzzuPee+895j4feeQRHn30UQDS09MB2LdvH+vXr+fhhx9m48aNeDwe+vbty4wZM+jfv3/tc4uLi3nggQd45513KC0tpXPnzvz2t78lOjq6dkXcjh07AnDPPffw61//uknbQ6S1MGUl2C89BWtXAVCV1JF3z76VJUUxFGwoA3yXVs7uFs/PeybQPkbzcUjL1qBUMH369Dq3p06dyk033cSOHTvo06fP9zt1OomPj2+SAn+KMYZqb2DWGYgIsxr0v5IFCxZwxRVX8Prrr7NhwwamTZtGeno6EyZM4Mknn2TXrl107twZgC1btrBp0yaefvrp4+7zF7/4Benp6dxzzz18+eWXtfeXlZVx2WWX8ec//xmAp59+mmuuuYaVK1cSExODbdtMnjyZ8vJynnjiCU466SS2bt1KWFgYw4YN4/777+evf/0rH3/8MQDR0dENbB0RATCbvsKe8xgUHaQ8PJq3Rk/hDcdJlOy3AQ8JbcIY1yuR87rFa04OaTVO6JRERUUFADExMXXuz8rK4qabbiI6OprevXtz5ZVXHrMfgtvtrrP0vGVZREZG1v78U6q9hsvnbf3J7ZrDvMt70MZZ//DRoUMH7r//fizLolu3bmzevJlnnnmGq6++mt69e7N48WLuvvtuABYtWsSgQYPo2rXrcfcZHR1d27YpKSm1948aNarOdrNmzaJPnz58+umnnH322axYsYL169fz4Ycf1h7jpJNOqt0+NjYWy7Lq7LOhGhLMfrh4ldSf2q3h/NVmxu3Gfu1FzDuLKXe2YUm/S1nWfiS+xWNtUmNcXNq3HWd0icMVFvzzcui91nBqs2NrdPgwxvD888/Tq1cvOnXqVHv/4MGDOeWUU0hKSiI3N5d58+bxpz/9iYcffhiXy3XEfhYvXszChQtrb2dmZjJr1iySk5OPetzKyso6+/FiN/YlnDCX04XrOJP5/LBOy7IYNmwY4eHfn04dMWIETz/9NA6Hg4kTJzJ37lymTZuGMYalS5dyyy23HLXNfiwsLOyI4+Xl5TFr1ixWrlxJXl4eXq+XyspKcnJycLlcbNq0iQ4dOtCrV6+j7vPwpbL6HP9owsPDSUtLa/DzUlNTG3W81k7t1nDN2WbufXso+MtvKNu9izc7nc7SLmdThhO80CUpmhtGnsRZvVJwOoI/dPyY3msNpzY7UqPDx+zZs9mzZ88RQ0dPPfXU2p87depE165dmTp1KuvWrTvq6qsTJkxg3LhxtbcPJ8S8vDw8Hs8R29fU1NQ5U+IwhnmX92jsyzghDuPB7T56onW5XHXqNMZg23ad+7xeL+A7+3PRRRcxc+ZM1q1bR1VVFfv27WPcuHF1tj+WH+7nsDvuuIOCggJmzJhBeno64eHhXHTRRVRVVeF2uwkPD8cYc8z9H277+hz/aGpqati/f3+9t7csi9TUVHJycrRcdwOo3RquudvMXr+a6jn/xzsJA3j15CsodvnODHeKi+CqgUmcnBGLwzLkHTjQ5MduTnqvNVxrazOn03nMEwdHbNuYA8yZM4e1a9dy//33065du+Num5CQQHJy8jH/ELlcrmP+77o+vyzLshp06SOQ1q1bd8TtzMxMwsLC6NChAyeffDKLFi2iqqqKn/3sZ/X+JR7N6tWrefDBBznzzDMBXyfUgwcP1j7eu3dv9u/fz/bt2496aSc8PLw21DRWY/6xGWNaxT/SpqZ2a7imbjNje/G+NpeP133LywNuJ69NIgCpMS6uHJDEz05qS5jDqj12qNJ7reHUZkdqUPgwxjBnzhzWrFnDjBkz6tUfoLS0lIKCAhISEhpdZEuRnZ3NjBkzmDx5Mhs3bmTOnDn84Q9/qH18woQJPProo9TU1DBjxowTOlbnzp159dVXGThwIKWlpcycObPOiKRTTjmFkSNHcsstt/DHP/6Rzp07s23bNizL4vTTTyc9PZ3y8nJWrFhB3759iYyMrO2LIyJ12aXFrH1hLi85e7Cr9zAAEiPDuKJ/Mmd2jcPpCI3/IIn4S4MuOM6ePZsVK1Zw1113ERkZSVFREUVFRdTU+Kb+raqq4oUXXmDr1q3k5ubyzTffMGvWLGJjYxkxYkSzvIBQMnHiRKqqqhg3bhzTp09nypQpTJ48ufbxcePGUVhYSGVl5QnPUProo49SXFzMueeey5133smUKVNISkqqs80zzzzDwIEDmTp1KqeffjoPPPBA7dmO4cOHc80113DbbbfRv39/nnrqqROqR6Sl2rl1F394+TNmxo9lV0wHohw21wxK5p8XdeXc7vEKHiJHYZkGnAuaNGnSUe+fOnUqY8eOpaamhr/85S/s3LmT8vJyEhIS6Nu3L5dffvkRf/h+Sl5e3lH7G5SUlNC2bdsG7SsQftzno7Vp6O/JsizS0tLYv3+/Tk82gNqt4ZqqzYqqPPzng028WxCGbTlw2R4u7BTBxJO7ENsCh8zqvdZwra3NXC5X8/T5mD9//nEfDw8PP2IuEBGRlsTtNby59SDzvjxAhXGBBadW7OS6i0aS2j4x0OWJhARNPRoCunfvfszHXnrppaOOIhKRprcuu4xnvzjAvlI34KBL6V5ujNhH3+uvwmrksHSR1kjhIwQsX778mI9p/LhI8ztQVsPstbms3uubCj2uppTJO97ijFP6EHb+tZpESqSBFD5CQGZmZqBLEGmVqj02r2YVsOibg7htg8PYXLh3JZP2fUTs9bdjDT31p3ciIkdQ+BAR+RFjDJ9+V8qctbnk+eZDZ0DZHm7Mmk8GFTju+j1Wtz4/sRcROZaQDB+2beMIwWmJW4vW0KtbWq49xdU888UBNuT41q5KjoDrNi3ilD2fYSUm4/jVLKy0jABXKRLaQi58REVFUVpaSmxsrAJIkKqoqCAiIiLQZYg0SIXby7yvC3h980G8BlwOiwntPUx47SEiKksgvTOOu/6IFX/8WZ1F5KeFXPhwOp1ER0dTVlYW6FKOKzw8vHbytdbEGIPT6VT4kJBhjGHF7lLmrMulsNJ3iWVEegxT2mST8tws8LihZ38cU3+HFRUd4GpFWoaQCx/gCyDBPNFYa5tYRiRU7Smq5ukvDrDxgO8SS2qMi5uHtWfIrtWY2U+AsWHQyThuuRfLFf4TexOR+grJ8CEiciLKqj08+8UB3thyENtAeJjFxL7tmNAnEef7r2PmzwbAOvVMrGt/iRXW8mYsFQkkhQ8RaTVsY/hgRzEvLdrGwQrf8gcj02O4cWgKKdEuzNK5mDdeAcA6ezzWxBuw1LdMpMkpfIhIq/BtQSX/+vwAWwuqAOgYG85Nw1IY0iHGt+T5wucwyxcDYF08GeuCyzR5mEgzUfgQkRbtYKWHF9fn8f6OYgAinQ5uPi2TMR1cOB1gbBsz91+YD5cBYF1xM44zfx7IkkVaPIUPEWmR3F6bpZsLmb+xgCqPDcDYzLZcNziFfl07sX//fmyvB/PC3zGfvAuWhTX5Nhyjzwtw5SItn8KHiLQoxhg+2VPKi+vzyCnz9evo3q4NNw9rT8+kyNpLKcbrxcx+HLPmI7AcWDfcheOU0wNZukirofAhIi3GN7kV/HtdLt8e6teREOnkukHJjMlsi+MH/TeM14s95zFf8AgLw3HTr7GGjQpU2SKtjsKHiIS8vcXVvLA+r3bV2TZOiwm92zG+dyKRrrqjVYzt5eBjMzCrDwWPW6ZhDTklEGWLtFoKHyISsgoq3LzydT7vbi/GNuCw4Oyu8Vw5IImEyCM/3oztxTz3BBWfvg8OB45b/kfBQyQAFD5EJOSU1XhZ9E0Br28ppMbrm0V4ZHoM1wxKJiPu6FP7G9vGPP8k5tP3wRF2KHic6s+yReQQhQ8RCRmVbps3txSyeFMBZTW+ESy9kyO5bnAyvZOjjvk8Y9uYl57CrHoPHA7aTXuA4m59tfyBSIAofIhI0Kv22Lz9bRGvflNAcbUXgIy4cK4dlMzwjjHHnQzMGIN55V+YFcvBcuC46ddE/ewsivfv91f5IvIjCh8iErRqvDb/3VbMwm8KOHhoxdnUGBdXDkjiZye1Jcxx/BlIfTOX/hvzwTLfPB433IVjxGh/lC4ix6HwISJBp9pj8862IhZlHaxd5j45ysnl/ZM4vUsczp8IHYeZJf/BLH8NAGvyVM3jIRIkFD5EJGhUeWze2lrI4k0HKa7yXV5JinJyad92nN01DldY/Rd5s9+cj3lzPgDWlbfgGH1us9QsIg2n8CEiAVfjtXnn2yIWflNA0aHQkRLt4rJ+7Tg9Mw5XWMMWeLPfXYJ57SUArIk34DhjXJPXLCKNp/AhIgHj9hre21HE/I0FFFT4Lq+0j3ExqV87xmbW//LKD9krlmPmzQbAuugqHOdOaNKaReTEKXyIiN/ZxvDxrhLmbsivXX+lXZSTy/slcWbXxoUOAHvNx5gX/w6Adc4ErHGXN1nNItJ0FD5ExG+MMXyxr5wXv8pjd1E1AHFtwrisbzvO7R5PeAP6dByx76/WYOY8BsZgjTkPa+L1xx2CKyKBo/AhIn7xTW4FL3yZx+b8SgCiXQ4m9Enk570SaeNsfOgAMJu+wv7nLPB6sU4ei3XVLxQ8RIKYwoeINKtdhVW8uD6PL7LLAQgPsxjXM4FL+rQjNiLshPdvtm/G/vsD4HHD4JOxrr8Ly3FiYUZEmpfCh4g0iwNlNbz8VT4f7SrB4Fv07Zxu8Uzq1452Ua4mOYbZuxP7b/dDdRX0GYTj5v/BCjvxQCMizUvhQ0SaVFm1lwXfFPDGlkI8tm/tlNM6xTJ5YDId2oY32XHMgWzsx/4IFeXQtReOqb/DcjVNqBGR5qXwISJNwu01vP1tIfO+zqf00KJvA1KjuG5QCt3atWnSY5mCPOxH74OSIsjIxHHnH7AimvYYItJ8FD5E5IQYY/j0u1JeXJ9Hdqlv2GxGXDg3DE5hSIfoJu/4aUqLsR/7AxzMg/YdcfzqfqyomCY9hog0L4UPEWm0rNwKnvsyly35VQDEtwnjqgHJnNU17icXfWsMU12N/eRMOLAPEpNx3PMnrLbxTX4cEWleCh8i0mB7S6p54cs8Vu8tAyAizOLiPolc3DuRKFfzdPg0thf72b/Cji0QFeM745GY3CzHEpHmpfAhIvVWVuPlla/zWbalEK/xjWA5u2s8VwxIIjGy+T5OjDGYuc/A+tXgdOH45e+x0tKb7Xgi0rwUPkTkJ3ltw3s7inlpfR7F1b6F34Z3jOa6wSlkxEU0+/HNO4swHy4Dy8Jx0z1Y3fs0+zFFpPkofIjIcWXlVvDMFwfYUeibDj29bTg3DWvP4LRovxzfXvMx5tXnAbAum4I19DS/HFdEmo/Ch4gcVW6Zm+e+zOWTPaWAbzr0KwYkcUGPhEYv/NZQZvtmzL//DwDrzJ/jOHu8X44rIs1L4UNE6qh02yzKKuC1TQep8Ros4OxucVw9MJn4Nv77yDAFedhPPeibNn3gCKxJU/x2bBFpXgofIgL4OnV+sqeU2WtzOVjpAaBf+yhuGppCZoJ/J/AyVZW+IbUlRZDeGcdNv8ZyaNp0kZZC4UNE2FdSw78+z2F9TgUA7WNc3DA4hZMzYvy+OqyxbexnH4G9O6FtPI5f3ofVJtKvNYhI81L4EGnFqj02C78pYFHWQTy2weWwmNivHZf0SSQ8LDArw5rFL8JXa3xDaqf+Dqud5vIQaWkUPkRaqfX7y/nHmhxyynxTog9Oi+bW4e1Ji226xd8ayv58BebtVwGwrr8Tq2uvgNUiIs1H4UOklSmu8jBnbS4f7ioBoF2kkxuHpXBqRqzfL7H8kMnLwbzwJADW+RNxjBwTsFpEpHkpfIi0EsYY3t9RzL/X5VJaY2MBF/RMYPLApGabEr3etXnc2E//L1RVQvc+WOOvDmg9ItK8FD5EWoH9pTU8tTqHDQd8HUozEyKYOiKVHknB0ZHTLH4Rdm+D6FjfyJYwjWwRackUPkRaMK9tWLL5IHM35FPjNYSHWVw5IImLeiX6baKwn2I2fI5Z/hoAjuvv1GJxIq2AwodIC7XjYBVPfLa/dlr0galRTB2RSmoAO5T+mCkswP7BDKbWoJEBrkhE/EHhQ6SFMcawdHMhz3+Zi9dATLiDKUNSOKNLXEA7lP6YsW3sOY9BWQl06oJ16fWBLklE/EThQ6QFKav28rfP9rN6bxkAp2TE8IvhqcQ343L3jWU+WAabN0B4BI6b/wfL5Qp0SSLiJw36RFq8eDFr1qxh3759hIeH06NHDyZPnkyHDh1qtzHGsGDBAt577z3Kysro3r07N954IxkZGU1evIh879uCSv53RTa55W6cDosbh6Zwfvf4oDrbcZjJ2YdZ9BwA1mU3YKV2DGxBIuJXDZrCMCsri3PPPZcHHniA3//+99i2zcyZM6mqqqrdZsmSJbz55ptMmTKFhx56iPj4eGbOnEllZWWTFy8ivsC/bGshv1m+h9xyN+1jXMw65yQu6JEQnMHD68X+9+NQUwN9BmGNOT/QJYmInzUofEyfPp2xY8eSkZFB586dmTp1Kvn5+ezYsQM49CG4bBkTJkxg5MiRdOrUidtvv53q6mpWrlzZLC9ApDWrdNvc92YW/1yTg8c2nJwRw6Pnd6ZbO/8uBNcQZvli2LEFIqNwXHdHUAYkEWleJ7R4Q0WFb86AmJgYAHJzcykqKmLgwIG127hcLvr06cOWLVtO5FAi8iN7iqu59+2dvLPpAGEWTBmSwm9+1pGY8OCdI8Ps3YVZ8jIA1hU3a1itSCvV6F5oxhief/55evXqRadOnQAoKioCIC4urs62cXFx5OfnH3U/brcbt9tde9uyLCIjI2t/DkWH6w7V+gNBbdYwK3aV8LdPs6n2GlJiIvj1aWn0Tg6OCcOOxXjc2HMeB68Ha9BIHKeeGZDft95rjaN2azi12bE1OnzMnj2bPXv28Kc//emIx37c0MaYY+5n8eLFLFy4sPZ2ZmYms2bNIjk59P9HlJqaGugSQo7a7Pi8tuGpFdt5Yc0+AEaclMCfL+xLYnTwzN1xLMVzn6Xkux042saR+uv7CUtMCmg9eq81jtqt4dRmR2pU+JgzZw5r167l/vvvp127drX3x8fHA74zIAkJCbX3l5SUHHE25LAJEyYwbty42tuHg0teXh4ej6cx5QWcZVmkpqaSk5Nz3OAl31Ob/bSyGi+PrNzH2uxyAC7t245rBqWQGB0e9O1msr/D+8qzvhuX30xutRv27w9ILXqvNY7areFaW5s5nc56nzhoUPgwxjBnzhzWrFnDjBkzSElJqfN4SkoK8fHxbNiwgczMTAA8Hg9ZWVlcffXRF4pyuVy4jjG+P9R/WcaYkH8N/qY2O7q9xdU88NFeskvdhIdZ3HFyGqM7t+XwScZgbjdj29gvPAEeD/QfBsN/FhS1BnObBTO1W8OpzY7UoPAxe/ZsVq5cybRp04iMjKzt4xEVFUV4eDiWZXHBBRewePFi0tLSSE1NZfHixURERDBq1KjmqF+kxVv9XSmPrdpPpccmOcrJ78ak0yUxeEez/Jj5+B3Ytgki2uC4+jZd/xaRhoWP5cuXAzBjxow690+dOpWxY8cCMH78eGpqanj22WcpLy+nW7duTJ8+vbYTqYjUj20Mr3ydz7yvCwDomxLJtJ91JL5N8M1WeiymsADz6nMAWBOuwWoX+n25ROTENehTbP78+T+5jWVZTJo0iUmTJjW6KJHWrqzGy+Orsvl8n69/x4U9E5gyJCVoVqKtD2MM9sv/hKpKyOyBdfoFgS5JRIJE6PwXSqSV+K64mgd/0L/jthGpnNHl6B22g9q6T2H9aggLw3HtL7EcwTv/iIj4l8KHSBD5JreCBz7aS3mNr3/Hb0anB/Vspcdiykux5z4NgHXepVjpnQNbkIgEFYUPkSDx6XelPLIyG7dt6JkUyfQxHYkLof4dP2Tm/guKCyE1HetCXYIVkbpC85NNpIV5a2sh//riALaBEekx3HtaByKcJ7T6QcCYLz/DrP4ILAeOG+7CcgX/BGgi4l8KHyIBZIzh5Q35zN/oG9FyTrc4fjE8lbAQ6lj6Q6asBPulpwCwzp2A1aVngCsSkWCk8CESIDVemyc/y+GjXSUAXNG/HVf0TwrpeTDM3H9BSRGkZWBddGWgyxGRIKXwIRIARZUeHvx4L1vyq3BY8IvhqZzbPT7QZZ0Qs+5TzJqPdblFRH6SwoeIn+0srGLmh3vJr/AQHe5g2qiODEqLDnRZJ8SU/uByy3mXYGX2CHBFIhLMFD5E/Oiz70p5bFU2VR5Dh9hwfj82nY5tQ/sMgfF6sZ/5C5QWQ4dOWD/X5RYROT6FDxE/eXNLIc98cQADDEyNYtqojsREhP7EW+bV52DTVxAegePmX2MdY6FIEZHDFD5E/OC74mpmr/UFjwt6xHPj0PYhNVX6sdiffoD57xIAHFN+hZWeGeCKRCQUKHyINDNjDM98cQCvgeEdo7l1eGqgS2oSZte3mBeeBMC6YBLW0NMCXJGIhIrQnMVIJIR89l0ZX+VU4HJY3Di0faDLaRKmpBD7qYfA44YBw7HGXxXokkQkhCh8iDSjao/N7LUHAJjQJ5G02NDuXApg3G7sf8yCwnxI7YjjxnuwHPooEZH60yeGSDOav7GAvAoPKdFOJvZtF+hyTpgxBvPik7AtCyKjcNw+HSsqtIcJi4j/KXyINJNP9pSw8BvftOlThrYP2bVafsgsW4D59ANwOHDcMg0rNT3QJYlICAr9T0ORILQlv5LHV+0H4Oc9EzglIzbAFZ04+/OVmNdeAsC68hasfkMCXJGIhCqFD5EmdqCshgc+3EuN1zC8Yww3DEkJdEknzOzYgvn34wBYZ12EY+wFgS1IREKawodIEyqr8fKnD/ZSXO2lS0IEvz6tQ8iuUHuYKcjFfnImuGt8I1suuyHQJYlIiFP4EGkiHtsw6+N97C2poV2Uk9+PTSfSFdr/xExFOfbf/uSbOj09E8fN92I5Qn9WVhEJrND+ZBQJIs9+cYANBypo43Rw39h02kWF9jTjxuPBfvp/IXsPxCXiuOP3WG0iA12WiLQACh8iTWD5tiLe+rYIC/j1aWlkJrQJdEknxBiDmfsvyPrSt2bLHb/HSkwOdFki0kIofIicoE15FTz9eQ4AVw1MYkR66I9sMf99DfPx22BZvsXiTuoW6JJEpAVR+BA5AQUVbmZ9vA+PDadkxHJZS5hI7MvPMAufA8C6bArWoJMDW5CItDgKHyKNVOO1eejjfRRWeTkpPoK7TknDskJ8ZMue7djP/hWMwRp7AdZZFwW6JBFpgRQ+RBrBGMM/1hzg24IqYsMd/G50x9Af2VJagv33B6GmBvoNwbri5pAPUyISnEL701IkQN7+toj3dxTjsODeUR1JDfEF44zXi/2v/4WDeZCS5htSG6YhtSLSPBQ+RBpoc14lzx5aqfaagckMSgv9hdXMq8/B5g0Q0QbH1OlYUTGBLklEWjCFD5EGKKr0MGvF9x1MJ/RJDHRJJ8xe/RHmv0sAcNzwK6yOnQJckYi0dAofIvXktQ1/WbmPg5Ue0tuGc+cpqSHfJ8Ls2YF54QkArAsuwxp6aoArEpHWQOFDpJ6e/zKXjbmVRDod/HZ0R6Jcod0nwpQUYT91uIPpUKzxVwW6JBFpJRQ+ROph1Z4SlmwuBOCuU9JIj4sIcEUnxnjc2P98GApyfR1Mb/q11mwREb9R+BD5Cbllbp5c7ZvBdELvRE7pFNozmBpjMC8/Dd9mQWQUjl/ehxWtDqYi4j8KHyLH4bUNj3ySTXmNTY92bZg8KPTXNzHvv4lZsRwsB46b/wcrLT3QJYlIK6PwIXIcczfkszm/kiiXg3tHdcDpCPEOplnrMfOfBcCaeB1W/6EBrkhEWiOFD5Fj2JBTzsJvCgC4fWQq7WNCfCKxA9nYT/8v2DbWKWdgnX1xoEsSkVZK4UPkKIqrPDy6aj8GOLtrHKNOahvokk6IqSjHfnImVJRBl55Y10wN+WHCIhK6FD5EfsQYw98+3U/hofk8bh7WPtAlnRBje7Gf+Svk7IWEJBxTf4flCu2zOCIS2hQ+RH5k2dYivsgux+Ww+J9RHYhwhvY/E7PoBdi4FsLDcdw+HSsuIdAliUgrF9qfqiJNbE9xNc99mQvAdYOT6ZzQJsAVnRh71fuYdxYDYF1/F9ZJXQNckYiIwodILbfX5tFPsqnxGoakRTOuZ2ifITDbN2NefBIA68JJOIb/LMAViYj4KHyIHPLSV/nsLKymbUQYd56SFtIdMk1JEfY/HgKPBwaNxLpIU6eLSPBQ+BAB1u8v57VNBwG44+RUEiKdAa6o8Ywx2P/5BxQXQloGjhvvxnLon7qIBA99IkmrV1Lt5f8+3Q/Aed3jGZEe4tOnr/kY1n0KYWG+NVvaRAW6JBGROhQ+pNWbs/YABys9dGwbzpQhKYEu54SYooO+dVsA68LLsTp1CXBFIiJHUviQVm1ddhkf7CzBwrdabSgPqzXGYL/4d99EYid1wzp/YqBLEhE5qtD9pBU5QZVum3+s8a1WO65nAj2TIgNc0Ykxq96HDZ+D04njhl9hOUO334qItGwKH9Jqvbwhj9xyD8lRTq4eGNqr1ZqCXMy8ZwCwLroaq2OnAFckInJsCh/SKm3Nr+SNLYUA3DYilUhX6P5TMF4v3tmPQWWFb92Wcy8OdEkiIscVup+4Io3ksQ1Prs7BNjCmc1uGdowJdEknpHTxS7B1I0S0OTSsNizQJYmIHJfCh7Q6i7MK2F3km0zspqEhPrpl9zaKX/wHANYVN2OldAhwRSIiP0090qRVyS1zM39jAQA3Dk2hbZvQ/Sdgqquxn3kEPB6swadgnXZWoEsSEamXBn/yZmVlsXTpUnbu3ElhYSH33nsvI0aMqH3873//Ox999FGd53Tv3p0HHnjgxKsVOUHPr8+lxmvolxLJmM5tA13OCTGv/hty9uJITMK69nYI4engRaR1aXD4qK6upnPnzpx++uk88sgjR91m0KBBTJ069fuDaMifBIGs3ApW7i7FAm4c2j601275ei3mg2UAJP7qjxTFxmGMCXBVIiL10+BUMHjwYAYPHnz8nTqdxMfHN7YmkSZnG8Oza3MBOLtbHF0S2wS4osYzVRW+ycQA64xxRA49haL9+wNclYhI/TXLKYmsrCxuuukmoqOj6d27N1deeSVxcXFH3dbtduN2u2tvW5ZFZGRk7c+h6HDdoVp/IDR3m32wo5jtB6uIcjmYPCglpH839uKXoDAfklMJm3g9oPdaQ+jfZ+Oo3RpObXZsTR4+Bg8ezCmnnEJSUhK5ubnMmzePP/3pTzz88MO4XK4jtl+8eDELFy6svZ2ZmcmsWbNITg7tSZ8AUlNTA11CyGmONiuv8fCfxdsBuOnULvTOzGjyY/hLddZX5H7wJgDJd91Hm5M6A3qvNYbarHHUbg2nNjtSk4ePU089tfbnTp060bVrV6ZOncq6desYOXLkEdtPmDCBcePG1d4+nBDz8vLweDxNXZ5fWJZFamoqOTk5ug5fT83ZZs9/mUtBeQ1psS7GdHCyP0QvURi3G+9jM8AYrFPPpDC1E1ZOjt5rDaR/n42jdmu41tZmTqez3icOmr0naEJCAsnJycf8wHe5XEc9IwKE/C/LGBPyr8HfmrrNckprWLLpIAA3DEnB6Qjd95X91kLI/g5i47Auu6HO69B7reHUZo2jdms4tdmRmn2SsdLSUgoKCkhISGjuQ4kc4aWv8vDYhgGpUYwI4ZlMTfYezJvzAbCuvAUrJrSHCYtI69bgMx9VVVXk5OTU3s7NzWXXrl3ExMQQExPD/PnzOfnkk4mPjycvL4+5c+cSGxtbZy4QEX/YfrCKFbtLAbhhcOh2MjW2F/uFJ8HrgQHDsYaNCnRJIiInpMHhY/v27dx///21t1944QUAxowZw80338x3333Hxx9/THl5OQkJCfTt25df/epXtSNYRPzlhfV5AIzu3Da0h9a+/yZs3wwRkTiu/kXIhigRkcMaHD769u3L/Pnzj/n49OnTT6ggkaawIaec9fvLcTrg6gFJgS6n0UxuNmaxL+Bbl92AlRj6o8BERLSwnLQ4xpjasx7ndosnNTY8wBU1jrFt7Of+BjU10GsA1uhzA12SiEiTUPiQFmfVd6V8W1BFG6fFpH4hfNbjg2XwbRZEtMFx3R263CIiLYbCh7QoXtvw0vp8AMb3TiQ+MjTXFTK5+zGLngfAmng9VlL7AFckItJ0FD6kRXl3ezHZpTW0jQjj4t6JgS6nUYxt+0a31FRDz/5Yo88LdEkiIk1K4UNajBqvzStf+856TOrXjihXWIArahzz0duw5WsIj/BdbnHon6mItCz6VJMW4/0dxRys9NAuysl53eMDXU6jmMKC7y+3XHIdVrLWhBCRlkfhQ1oEr21YlOWbRn1C70RcYaH51rZfeQaqKiGzB9bpFwS6HBGRZhGan9AiP7JidwkHytzERYRxTrf4QJfTKOarNbBuFTgcOK69XZdbRKTF0qebhDzbGBZ+UwDARb0SiXCG3tvaVFdhv/w0ANbZF2OlZwa4IhGR5hN6n9IiP7J6bxnfFdcQ7XJwfo/4QJfTKGbpXDiYB+1SsH5+RaDLERFpVgofEtKMMSzc6DvrcUGPBKLDQ2+Ei9mzA/PuEgDf2i0RobsOjYhIfSh8SEhbn1PBtoNVRIRZ/LxXQqDLaTBje7FfegpsG2voaVj9hwW6JBGRZqfwISFt4UbfvB7ndI8nrk3ozWZq3n8Ddm6FyCisK24KdDkiIn6h8CEha1NuBRtzK3E6CMnZTE32Hsyrh1asveQ6rPh2Aa5IRMQ/FD4kZC3a5JvXY2xmHElRrgBX0zDG48ae/Sh43NBvKNYYTaEuIq2HwoeEpL0l1azZW4YFTOgTgmc9Xp8He3ZAdKxWrBWRVkfhQ0LSkkNnPUakx5DeNiLA1TSM2b4Z89ZCABzXTMWKD73wJCJyIhQ+JOQUVXr4YEcJEHp9PUxVJfacx8DYWCePxRp6WqBLEhHxO4UPCTlvbi3EbRt6tGtD7+TIQJfTIGbBvyF3PyQkYV15S6DLEREJCIUPCSlVHpu3thYCcHGfxJDqK2G+/gLz8dsAOG64CysqJsAViYgEhsKHhJT3thdTWmOTGuPi5PTYQJdTb8YY7Ln/AsA66yKs3gMDXJGISOAofEjI8NqGpZt9HU0v6pVImCN0znqwfTPk5UBEJNbFkwNdjYhIQCl8SMj4bG8pOWVuYsMdnNk1LtDlNIhZ/REA1uCTtXaLiLR6Ch8SEowxvJblO+txfo8E2jhD561rPB7MFysBsEaOCXA1IiKBFzqf4NKqbS2oYmtBFU6HxYU9QmwBuawvoawEYuNAfT1ERBQ+JDS8sdk3wmV057bER4bWAnK1l1xGjMYKCwtwNSIigafwIUGvoMLNJ3t8k4qN6xlaZz1MVSVm/WoArJFjA1uMiEiQUPiQoPf2t0V4DfRJjqRrYmh11jTrP4OaakjpAJ27BbocEZGgoPAhQc3ttXnn2yIg9M56AJhP3gN8HU1DaUI0EZHmpPAhQW3F7lKKq720i3IyMiN0JhUDMFu/gc0bICwM69QzAl2OiEjQUPiQoGWM4Y0tvo6mF/RIwBlCk4oZY7BfexEA67SzsZLaB7giEZHgofAhQWtzfiXbD1YRHmZxTohNKsY3X8K3WeB0YY27PNDViIgEFYUPCVqHz3qM7tyWtm1CZ3it76zHSwBYp1+AldAuwBWJiAQXhQ8JSvkVblbtKQVCsKPpl5/B7m2+dVzOnxjoakREgo7ChwSld74twjbQLyWSzITQGV5rbO/3Zz3O+jlWbIhdLhIR8QOFDwk6Xtvw7vZiwLeOSygxaz6G/d9BVAzWORcHuhwRkaCk8CFB54vsMg5WeoiLCGNkeugMrzUeD2bpXACs8y7BiooJcEUiIsFJ4UOCzn+3FQFwepc4XGEhNLx21XuQlwNt47HOGBfockREgpbChwSV/HI3a7PLATinW3xgi2kA43Fj3pwPgHX+pVgRodNPRUTE3xQ+JKi8u/37jqYd24YHupx6MyvfhYN5EJeINfq8QJcjIhLUFD4kaHhtw3+3FwFwdiid9XC7McsWAGCdPxErPCLAFYmIBDeFDwkaq3cfJK/cQ0y4g1M7hVBH05X/hcJ8iG+HNfqcQJcjIhL0FD4kaLz2VTYAYzPjCA8Ljbemcddglh3q63HBZViu0LlUJCISKKHxCS8tXmGlh4+35wMh1tH04+VQdBASk7BGnR3ockREQoLChwSF97YX4bUNvZIiOSk+NPpMmJpqzFsLAbDOvwzL5QpwRSIioUHhQwLONoblh+b2OKd7fEBraQjz8dtQfBASk7FGnRXockREQobChwTc5rxKcsrcRIeHMeqktoEup15MRTlm2aGzHhdehuXUWQ8RkfpS+JCA+3BnCQCn90imjTM03pLmzflQWgypHbFO1VkPEZGGCI1Pemmx3F7DJ3t84eP8PqkBrqZ+TG425r3XAXBMuhHL6QxwRSIioUXhQwJqXXYZZTU2iZFOhmaExgq29oJ/g9cD/YZg9R8W6HJEREKOwocE1Ie7fGc9RnduS5gj+BeRM5u+gvWrweHAcdmUQJcjIhKSGny+OCsri6VLl7Jz504KCwu59957GTFiRO3jxhgWLFjAe++9R1lZGd27d+fGG28kIyOjSQuX0Fde4+XzvWWAb2KxYGdsL/a8ZwGwxl6A1aFTYAsSEQlRDT7zUV1dTefOnZky5ej/61uyZAlvvvkmU6ZM4aGHHiI+Pp6ZM2dSWVl5wsVKy/Lpd6W4bUNGXDiZCcE/t4dZ+V/YtxuiYrB+fkWgyxERCVkNDh+DBw/miiuuYOTIkUc8Zoxh2bJlTJgwgZEjR9KpUyduv/12qqurWblyZZMULC3H4VEuYzvHYVnBfcnFVJRjXvsPANZFV2LFhMaQYBGRYNSkfT5yc3MpKipi4MCBtfe5XC769OnDli1bmvJQEuLyK9xsPFAB+Pp7BDvz6nOHhtamY405P9DliIiEtCYdI1hUVARAXFzd6/dxcXHk5+cf9Tlutxu3211727IsIiMja38ORYfrDtX6/WHFrlIM0Cclkvax4UHdZnbWeszH7wDgmDwVRxBNox7M7Ras1GaNo3ZrOLXZsTXLBAU/bmhjzDG3Xbx4MQsXLqy9nZmZyaxZs0hOTm6O0vwqNTU05q0IhE/e+Q6A8YM6kZaWVnt/sLWZXVFOzktPARAz7jISTj8nwBUdXbC1WyhQmzWO2q3h1GZHatLwER8fD/jOgCQkfD9nQ0lJyRFnQw6bMGEC48aNq719OLjk5eXh8Xiasjy/sSyL1NRUcnJyjhu8WqtdhVV8m1eG02HRP86wf//+oG0z73/+gcndD0kpVJ53GVX79we6pDqCtd2CmdqscdRuDdfa2szpdNb7xEGTho+UlBTi4+PZsGEDmZmZAHg8HrKysrj66quP+hyXy4XrGKexQ/2XZYwJ+dfQHD7aWQzA0A7RRIc76rRRMLWZ2fI15oNlADiuvQMi2gRNbT8WTO0WKtRmjaN2azi12ZEaHD6qqqrIycmpvZ2bm8uuXbuIiYkhKSmJCy64gMWLF5OWlkZqaiqLFy8mIiKCUaNGNWnhEro+3+eb2yOYF5Ez1VXYzz8BgDX6PKzeA3/iGSIiUl8NDh/bt2/n/vvvr739wgsvADBmzBhuv/12xo8fT01NDc8++yzl5eV069aN6dOn13YildYtt8zNnuIaHBYMSYsOdDnHZBa/CHk5kJiENfH6QJcjItKiNDh89O3bl/nz5x/zccuymDRpEpMmTTqhwqRlWpvtO+vRMymSmIiwAFdzdCZr/fcLx13zS6zIqABXJCLSsmhtF/GrtdnlgK+/RzAy5WXY//4/AKyx52P1GxLYgkREWiCFD/GbGq/NhpzD4SMmwNUcnfnPP6CoAFI6YE28IdDliIi0SAof4jff5FZS7TUkRDqDci0Xe/VHmM9X+FasvekerIg2gS5JRKRFUvgQv1l7aJTL0A7RQTfjnzmYh/nPPwGwLrwcK7NHgCsSEWm5FD7Ebw53Nh0WZJdcjG1jz3kcKsshswfWheosLSLSnBQ+xC/2l9aQXeomzIKBacE1esS8/zps+RrCI3DceA9WWHCOwhERaSkUPsQvDp/16JMSRZQreP64m+w9mFd9c9VYl03Bat8hwBWJiLR8Ch/iF2v3Bd8QW+Px+C63eNzQbwjWmPMCXZKISKug8CHNrtpj8/WBCgCGdgye/h5m2XzYvQ2iYnBce0fQdYIVEWmpFD6k2X19oAK3bUiJdpLRNjzQ5QBgdn2LedM3U6911a1YCe0CXJGISOuh8CHN7otDQ2yHdIgJirMLpqYae/ZjYNtYw0ZhjRgd6JJERFoVhQ9pVsaYoJtS3Sx+EXL2QlwC1tW/CIpAJCLSmih8SLPaV1JDbrkbp8NiQGrgw4fZuvH7ReOu/SVWTNsAVyQi0voofEiz+irH19G0T3IkbZyBfbuZ6irs5/4GxmCNOhtrwPCA1iMi0lopfEiz2nDAd8llQGrgJxYzrz4PeTmQkIR12ZRAlyMi0mopfEiz8dqmdohtoC+5mM0bMB+8CYDjujuwogJ/CUhEpLVS+JBms6OwivIamyiXg26JgVsh1lRV+i63ANboc7H6Dg5YLSIiovAhzejrQ/09+qZEEeYI3IgS8+pzUJAL7VKwLrshYHWIiIiPwoc0m68OXXIZGMD+HmbTV5gP3wIOXW5pE/i+JyIirZ3ChzQLt9cmKzew/T1MZcX3l1vGnIfVe2BA6hARkboUPqRZbMmvosZriGsTRqe4wEypbhbMgYN5kNQea6Iut4iIBAuFD2kWtUNs20cFZAZRs3EdZsVyABzX34XVJtLvNYiIyNEpfEiz2JATuEsupqIM+/knALDO/DlWz35+r0FERI5N4UOaXKXbZmt+JRCYzqZm3mwoKoCUNKwJ1/r9+CIicnwKH9LkvsmtwGsgJdpF+xj/9vcwX32OWfUeWBaOG+7Ciojw6/FFROSnKXxIk/t+VlP/nvUw5WXYL/4dAOvs8Vjd+vj1+CIiUj8KH9LkvsrxdTYd6Of+HmbBbCg+CKkdscZf7ddji4hI/Sl8SJMqqfKws7Aa8I108RezcR3mk0OXW667Eytcl1tERIKVwoc0qcOXXE6KiyA+0umXY5rKCuwXnwQOjW7p1tsvxxURkcZR+JAmteFQ+Ojvx/4e5tXn4GA+JKdiXTzZb8cVEZHGUfiQJrXhUH8Pf3U2NZs3YD56GwDHNbdjRQRu9VwREakfhQ9pMrllbrJL3Tgs6JfS/OHDVFdhv3Docstord0iIhIqFD6kyRyeUr17u0iiw8Oa/Xjm1ecgLwcSkrAmXt/sxxMRkaah8CFN5qtDU6r7Y1ZTs+FzzAfLAHBcdwdWpP9nUhURkcZR+JAmYYyp7e/R3PN7mJJC7Of+Bhwa3dJ3cLMeT0REmpbChzSJPcU1FFV5CQ+z6JnUfJ0+jTHYzz0BpcXQ8SSsS69rtmOJiEjzUPiQJnF4VtO+KVG4wprvbWU+XAZffwFOF46bfo3l8u/aMSIicuIUPqRJ+GOIrcneg1nwbwCsiddjpXdutmOJiEjzUfiQE+axDV8fqARgUDP19zA11djPPALuGug7GOuMcc1yHBERaX4KH3LCvi2opMpjExsRRueE5llTxcx7FvbuhJi2OK6/C8uymuU4IiLS/BQ+5IQdHmI7oH0UjmYIBfZnH2A+fse3aNzNv8aKT2zyY4iIiP8ofMgJ+2p/8w2xNdl7MC8+BYA17nKsPhpWKyIS6hQ+5IRUum22Fvj6ezR1Z1NTVYn9z1lQUw29B2KNu7xJ9y8iIoGh8CEnJCu3Ao8NKdEuUmNcTbZfYwzmpadg/3cQn+gbVuto/inbRUSk+Sl8yAnZcOD7KdWbshOo+ehtzOqPwOHAccs0rLbxTbZvEREJLIUPOSFf1c7v0XT9Pcz2zZhXngHAuuRarO59mmzfIiISeAof0mjFVR52FlYDTdffwxQXYv/zYfB6YOipWOdMaJL9iohI8FD4kEZbm+0769ElIYL4Ns4T3p/xePD+82EoOghpGTiuv1PzeYiItEAKH9Joa/aWAjAiPaZJ9lf07GPwbRZERuGY+jusNs03VbuIiASOwoc0So3X5stD83sM7xh7wvuzP32fstfnAeCYcjdWascT3qeIiAQnhQ9plI0HKqjyGBIjnXRNPLEp1c2eHdgv/B0A6+dXYA0a2RQliohIkFL4kEZZs7cMgOEdY06oX4YpL8P+x0PgrqHNsFNx/PzKpipRRESC1In3EvyR+fPns3Dhwjr3xcXF8cwzzzT1oSRAjDGs2ecLHyfS38PYNvbsRyH/ACS1J/HeP5NbVoExpqlKFRGRINTk4QMgIyOD++67r/a2w6ETLC3JzsJqCio8RIRZJzTE1iybD19/Aa5wwqb+lrDYOCiraMJKRUQkGDVL+HA4HMTHxzfHriUIHL7kMigtmvCwxgVLs3EtZulcAKzJt2F16tpk9YmISHBrlvCRk5PDrbfeitPppHv37lx55ZW0b9/+qNu63W7cbnftbcuyiIyMrP05FB2uO1Tr/ymHL7mMzIht1Gs0+Qewn3kEjMEacz5hp53V4tusuajdGk5t1jhqt4ZTmx2bZZr4AvuXX35JdXU1HTp0oKioiEWLFrFv3z4effRRYmOPHJL54z4imZmZzJo1qylLkiZ0oLSKcf9chQW8PXUUidHhDXq+8XrInXYLNZs3EN6jLyn/+wyWq2H7EBGR0Nbk4ePHqqqquOOOOxg/fjzjxo074vFjnfnIy8vD4/E0Z2nNxrIsUlNTycnJaXGdJ9/aWsg/1uTQKymS/z2vc4Ofb78xD/u1lyAymrAZf8NqlwK07DZrTmq3hlObNY7areFaW5s5nU6Sk5Prt20z10KbNm3o1KkT+/fvP+rjLpcLl+voS7GH+i/LGBPyr+HHDs9qOjw9psGvzez6Fvv1Q/08rroVEpOP2EdLbDN/ULs1nNqscdRuDac2O1KzD0Nxu93s27ePhISE5j6UNLNKt82GHN9olBEdGzbE1lRX+4bVer1Yw0ZhjRzTHCWKiEgIaPIzHy+88ALDhg0jKSmJ4uJiXn31VSorKxkzRn9sQt36nHLctiE1xkVGXAP7erz6HOTsg7hE3+gWdcASEWm1mjx8HDx4kP/7v/+jpKSEtm3b0r17dx544IF6XweS4PXDSy4NCQ9m4zrMB28C4LjhLqzoE18LRkREQleTh49f/epXTb1LCQLVHptP9/iG2J6SXv/wYMrLsJ/7GwDWGeOw+g5ulvpERCR0aOpRqZfVe8uo9NikRLvonRJZ7+eZRS9A8UFI7Yh1yXXNWKGIiIQKhQ+plw92FAMwNrMtjnpecjHbN2M+fhsAx+TbsSJObPVbERFpGRQ+5CcVVLhZn1MOwBld4ur1HOPxYL/4dwCs087E6tmv2eoTEZHQovAhP+njXSXYBnolRZIWW79RLua9pbBvN8TEYl16QzNXKCIioUThQ47LGMMHO0qABpz1yD+AWfoyANbEKVixbZutPhERCT0KH3JcOwur2V1cjcthcdpJPz3KxRiD/fLTUFMDPfphnXqGH6oUEZFQovAhx/X+oY6mI9JjiAkP++knrPsUvv4Cwpw4Jk/VZGIiInIEhQ85Jo9t+HhX/S+5mOpq7PnPAmCddwlWWnqz1iciIqFJ4UOOaV12GcXVXuLahDE4LfontzfvvAoH8yExGeuCy/xQoYiIhCKFDzmmD3b6znqM6dyWMMfxL5+YglzM24sAcFx2A1a45vQQEZGjU/iQoyqt9rJmr2869Xpdcln4HLh9nUwZelozVyciIqFM4UOO6s0thXhsQ2ZCBJkJbY67rdmyEfPFSrAcOK64WZ1MRUTkuBQ+5Ahl1V6Wbj4IwMS+7Y67rbG92K88A4A1+hysjMxmr09EREKbwoccYcnmg5S7bU6Ki+DUTsef28Os+C/s3QlR0VjjJ/upQhERCWUKH1JHabWX1zcXAnD5gHbHXUTOlJdiXnsRAOuiqzWTqYiI1IvCh9SxZNNBKj02neMjOCXjJ856LJgDZaXQoRPWmPP8VKGIiIQ6hQ+pVVLt5fUtvrMeV/RPOv5Zj01fYT55DwDHNbdjOZ1+qVFEREKfwofUWrLpIFUem8yECEZmxBxzO1NTjf3SUwBYY8/H6tbbTxWKiEhLoPAhABRXeXhji2+Ey5U/ddbjzfmQux/iE7EmXOuvEkVEpIVQ+BAAFmUdpMpj6JoYwYj045z12LsL886hmUyvvBUr6qenXRcREfkhhQ9h+8Gq2nk9ruyffMxJwoztxX7hSfB6YdDJWENO8WeZIiLSQih8tHJur83jq7KxDZzWKZbhxzvr8cFbsHMrtInEcdWtfqxSRERaEoWPVu6VrwvYU1xDXJswfjG8/TG3M9/txCz8NwDWJddhJRx/5lMREZFjUfhoxbbkV7IoqwCA20ak0rbN0YfLmsoK7H/OAo8b+g/TnB4iInJCFD5aqWqPzd8+3Y9tYEzntsecUMwYg3nx75CbDYlJOKb8Csuht42IiDSe/oq0Ui9vyGdvSQ0JkU5uHnacyy0fv4P5fAWEheG4ZRpWjKZQFxGRE6Pw0Qqt31/Okk2+0S2/HJlKbETYUbcze7ZjDq9YO+FarK69/FajiIi0XAofrcyuwipmrdiHAc7qGsewjkcf3WLKS7Gf/l9fP48Bw7HOHu/fQkVEpMVS+GhFCirc/PnDvVS4bfqmRB5zdIspL8N+9D7fLKaJSThuuEv9PEREpMnoL0orUeH28ucP95Jf4aFj23B+OzodV9iRv35TUYb92B9gzw6IjcNx5wz18xARkSal8NEKeGzDX1Zks7Owmrg2Yfzx9PSj9vMwFeXYj/0Rdm+DmLY4fj0Tq2OnAFQsIiItmcJHC+e1DU+tzmHd/nLCwyzuG5tO+5jwI7YzlRXYj/8Rdn0LMbE4fv1nrI4nBaBiERFp6Y4+q5S0CDVem0c/yebT78pwWHDvqA50bxd5xHYmZx/207Ng7y6IjsVxz0ys9Ez/FywiIq2CwkcLVVbj5cGP9vJNbiVOh8U9p6YxMv3IicTsz1dgnn8Sqit9fTx+NQMrQ8FDRESaj8JHC5Rf4eZP7+9ld3E1US4HvxvTkf7to+tsY9xuzPzZmA+X+e7o0Q/HzfdixScGoGIREWlNFD5amC35lfzvin3kV3hIiHTyx9PTyUxoU2cbs2c79gt/93UsBawLLsO66CqssKNPNiYiItKUFD5aiGqPzcsb8lm6+SC2gY5tw/nj6XU7l5qSQsxr/8Gs/C8Y4+tYOuUerP5DA1i5iIi0NgofLcCm3Ar+9lkO2aU1gG+huJuHta8dTmvcbsz7r2PemAdVlQBYw3+GNfEGrMSkgNUtIiKtk8JHCMstc7Pgm3z+u60YAyRGOrltRHtGHOpYaqoqMSv/i/nvEjiY53vSSd1wXHETVrc+gStcRERaNYWPEHSgrIaF3xTw/o5iPLbvvjO7xDFlaAox4WGYkiLM+29gPlgGFWW+DeISsCZcg3XKGZoqXUREAkrhI0TYxrApt5L3dhTz4c5ivMZ3/4DUKK7sn0TvBBds/Bzv6g/hq899C8IBpKRhnTMB65TTscIjAla/iIjIYQofQcwYw/aD1azYXcKK3SUUVHhqHxuYGsXlvePpU7gd8/ZS7LWfQEX590/O7IHjvEtg0Egsh0axiIhI8FD4CDKVbpsNOeWszS5nbXYZ+T8IHFEuB6ckh3FWzS56Zq2CRRuwa6q/f3J8O6wRo7FGjoGMTCzLCsArEBEROT6FjwCr8dpsza9iY24F3xyoICuvEo9tah8PtwzDXCX8rDCLwVs/Jry4oO4O4hOx+g/DGjEaevTVWQ4REQl6Ch9+Vu2x2ZJfydcHKth4oIKtBVV1wgZAe6oYUrqdIbs/p9/Bb4mw3d8/GBYGmT2x+g/F6j8M0jvrDIeIiIQUhY9mVuH2sjW/iqw835mNLflVuH8UNuLtSvqW7KZP7iYGFG6jQ2UetXEivh1W117QpSdWl57QqYs6joqISEhT+GhiZTVevsmtZHtWKZ/vzGNXUTU/yhokuEvpd3Ab/Yq207doB2mV+d+HjfYdsYadA936YPXoC+1SdGZDRERaFIWPE1TtsdmU57uM8lVOOdsLqrB/tE1K5UF6leyid9FO+hdt94UNhwPSMrAGDYBOmVgZXSGjM1ZUTEBeh4iIiL8ofDSQ22uTlVfJ1zkVbMyt4Nv8Sjw/OrPRsSKX/oXb6Fu0g17Fu2jnLvWd0TipK4y+GKtzd8joghWhyyciItL6KHzUQ1GVh7X7yvh8Xxlf7i+n6kdpo11VEf2KttO/aBsDCreRFOUiasBQqoaOhE5X+Ya9tokMUPUiIiLBReHjGKo9Np9+V8q724vYeKCSH8aN+OoSBhZ+W9tno31sOI6e/eGUn2H1+AVWUnvadejA/v37McYc8xgiIiKtUbOFj3feeYelS5dSVFREeno6119/Pb17926uwzUJYwzbDlbx7vZiPt5ZTMUPznB0Ld3L0IJNDCvYRBdnFWG9+sMpp2H1vA2rXXKd/aiDqIiIyLE1S/hYtWoVzz33HDfddBM9e/bk3Xff5cEHH+Sxxx4jKSn4lnAvqvTw4a5i3ttezJ7imtr7UyoPckbOF4wt3EhKl85Ypw7E6j3B139DAUNERKRRmiV8vPHGG5xxxhmceeaZAFx//fV89dVXLF++nKuuuqo5DtlgZdVevtxfxsdbclmb78F7aLBruNfNyPyNnLn/c/rFQdjY87GG36rOoSIiIk2kycOHx+Nhx44dXHzxxXXuHzBgAFu2bGnqw9Wbp7qGbRu3sm5vCV+WhrGNWGzr8NLyFt1LdnPG/i8YVbaNmP6DsCbchpXZPWD1ioiItFRNHj5KSkqwbZu4uLg698fFxVFUVHTE9m63G7f7++nDLcsiMjKy9uemUlBUxv/b7AQSOTyjV0Z5DkMLt3JGZAmdemRiXXCFb86NE1wf5XDdujRTf2qzxlG7NZzarHHUbg2nNju2ZutwerTGPtp9ixcvZuHChbW3MzMzmTVrFsnJyUdseyLS0tLouewVkh0eRiTAyZnt6Nh9GK6MiViu8CY91mGpqanNst+WTG3WOGq3hlObNY7areHUZkdq8vDRtm1bHA7HEWc5iouLjzgbAjBhwgTGjRtXe/twQMnLy8Pj8Ryx/Yn4y5QxdW4XAOQXHHXbE2FZFqmpqeTk5GiobT2pzRpH7dZwarPGUbs1XGtrM6fTWe8TB00ePpxOJ126dGHDhg2MGDGi9v4NGzYwfPjwI7Z3uVy4XK6j7ivUf1nGmJB/Df6mNmsctVvDqc0aR+3WcGqzIzXLZZdx48bxxBNP0KVLF3r06MG7775Lfn4+Z599dnMcTkREREJIs4SPU089ldLSUl599VUKCwvJyMjgt7/9bZP34xAREZHQ02wdTs8991zOPffc5tq9iIiIhCjHT28iIiIi0nQUPkRERMSvFD5ERETErxQ+RERExK8UPkRERMSvFD5ERETErxQ+RERExK8UPkRERMSvFD5ERETErxQ+RERExK+abXr1E+V0Bm1p9dYSXoO/qc0aR+3WcGqzxlG7NVxrabOGvE7LaJ1fERER8SNddmkGlZWV/L//9/+orKwMdCkhQ23WOGq3hlObNY7areHUZsem8NEMjDHs3LkTnVSqP7VZ46jdGk5t1jhqt4ZTmx2bwoeIiIj4lcKHiIiI+JXCRzNwuVxMnDgRl8sV6FJChtqscdRuDac2axy1W8OpzY5No11ERETEr3TmQ0RERPxK4UNERET8SuFDRERE/Kp1zPnqR++88w5Lly6lqKiI9PR0rr/+enr37h3osoLW4sWLWbNmDfv27SM8PJwePXowefJkOnToEOjSQsbixYuZO3cuF1xwAddff32gywlqBw8e5KWXXmL9+vXU1NSQlpbGbbfdRpcuXQJdWlDyer0sWLCAFStWUFRUREJCAmPHjuWSSy7B4dD/XQ/Lyspi6dKl7Ny5k8LCQu69915GjBhR+7gxhgULFvDee+9RVlZG9+7dufHGG8nIyAhg1YGld08TWrVqFc899xyXXHIJs2bNonfv3jz44IPk5+cHurSglZWVxbnnnssDDzzA73//e2zbZubMmVRVVQW6tJCwbds23n33XU466aRAlxL0ysrKuO+++3A6nfzud7/j0Ucf5dprryUqKirQpQWtJUuW8N///pcbb7yRxx57jMmTJ7N06VLefvvtQJcWVKqrq+ncuTNTpkw56uNLlizhzTffZMqUKTz00EPEx8czc+bMVj3zqcJHE3rjjTc444wzOPPMM2vPeiQlJbF8+fJAlxa0pk+fztixY8nIyKBz585MnTqV/Px8duzYEejSgl5VVRVPPPEEt956K9HR0YEuJ+gtWbKEdu3aMXXqVLp160ZKSgr9+/cnNTU10KUFra1btzJs2DCGDBlCSkoKJ598MgMGDGD79u2BLi2oDB48mCuuuIKRI0ce8ZgxhmXLljFhwgRGjhxJp06duP3226murmblypUBqDY4KHw0EY/Hw44dOxg4cGCd+wcMGMCWLVsCVFXoqaioACAmJibAlQS/Z599lsGDBzNgwIBAlxISvvjiC7p06cKjjz7KTTfdxLRp03j33XcDXVZQ69WrFxs3biQ7OxuAXbt2sWXLFgYPHhzgykJHbm4uRUVFdf42uFwu+vTp06r/NqjPRxMpKSnBtm3i4uLq3B8XF0dRUVFgigoxxhief/55evXqRadOnQJdTlD75JNP2LlzJw899FCgSwkZubm5/Pe//+XCCy9kwoQJbNu2jX//+9+4XC7GjBkT6PKC0vjx46moqODuu+/G4XBg2zZXXHEFo0aNCnRpIePw5//R/ja05kvyCh9NzLKset0nR5o9ezZ79uzhT3/6U6BLCWr5+fk899xzTJ8+nfDw8ECXEzJs26Zr165cddVVAGRmZvLdd9+xfPlyhY9jWLVqFStWrODOO+8kIyODXbt28dxzz9V2PJX6+/HfgdY+v6fCRxNp27YtDofjiLMcxcXFRyReOdKcOXNYu3Yt999/P+3atQt0OUFtx44dFBcX85vf/Kb2Ptu22bRpE2+//TYvv/yyRiIcRUJCAunp6XXuS09PZ/Xq1QGqKPi99NJLjB8/ntNOOw2ATp06kZeXx2uvvabwUU/x8fEAtaOFDispKWnVfxsUPpqI0+mkS5cubNiwoc4Qqw0bNjB8+PAAVhbcjDHMmTOHNWvWMGPGDFJSUgJdUtDr378/f/3rX+vc949//IMOHTowfvx4BY9j6NmzZ23fhcOys7NJTk4OUEXBr7q6+oj3k8PhaPX/a2+IlJQU4uPj2bBhA5mZmYCvj2BWVhZXX311gKsLHIWPJjRu3DieeOIJunTpQo8ePXj33XfJz8/n7LPPDnRpQWv27NmsXLmSadOmERkZWXvmKCoqSpcUjiEyMvKIPjERERHExsaqr8xxXHjhhdx3330sWrSIU089lW3btvHee+9xyy23BLq0oDV06FAWLVpEUlIS6enp7Nq1izfeeIPTTz890KUFlaqqKnJycmpv5+bmsmvXLmJiYkhKSuKCCy5g8eLFpKWlkZqayuLFi4mIiGjVfWe0sFwTOzzJWGFhIRkZGVx33XX06dMn0GUFrUmTJh31/qlTp+q0bgPMmDGDzp07a5Kxn7B27VpefvllcnJySElJ4cILL+Sss84KdFlBq7Kyknnz5rFmzRqKi4tJTEzktNNOY+LEiTid+r/rYd988w3333//EfePGTOG22+/vXaSsXfffZfy8nK6devGjTfe2Kr/s6DwISIiIn6li8MiIiLiVwofIiIi4lcKHyIiIuJXCh8iIiLiVwofIiIi4lcKHyIiIuJXCh8iIiLiVwofIiIi4lcKHyIh4MMPP2TSpEnk5uYGuhQRkROm8CEiIiJ+pfAhIs3Otm3cbnegy2iQmpoard4q0ky0MpBIiHr//fd56623yM7OJjw8nD59+nDllVeSnp5eZ7t3332X119/nby8PNq3b8+ll17KV199RVZWFn//+9/rfbwZM2ZQWlrKTTfdxEsvvVS7aufpp5/OpEmTapdez83N5Ze//CVXX301Ho+H999/n4KCAn7zm98waNAgtm/fzsKFC9m8eTM1NTV07NiRiy++mFNPPbX2WNXV1cybN4/Vq1dTVFREeHg47du3Z9y4cbUrgR44cIC5c+eyadMmSktLiY6OJiMjg2uvvZbOnTsDvoULJ06ceMQChrfffjt9+vTh9ttvB3yXtZ566immT5/OJ598wtq1ayktLeWll14iPDycVatW8eabb7Jnzx4AevXqxVVXXVW7RLqINIzCh0gIWrx4MXPnzuW0007jyiuvpKysjAULFvD73/+ehx56iLS0NMAXPP71r38xcuRIrrvuOioqKliwYAEej6dRxy0qKuLxxx/n4osvZtKkSaxbt45FixZRXl7OjTfeWGfbt956i7S0NK655hqioqJITU1l48aNPPjgg3Tv3p2bb76ZqKgoVq1axeOPP05NTU3tSsbPP/88K1as4PLLLyczM5Pq6mr27NlDWVlZ7f4feughbNvm6quvJikpidLSUrZs2UJ5eXnjGhX4xz/+wZAhQ7jjjjuoqqrC6XSyaNEi5s2bx9ixY7n00kvxeDwsXbqUP/zhDzz00ENHhD0R+WkKHyIhpry8nFdffZXBgwdz11131d7fp08f7rrrLhYsWMCdd96JbdvMnz+f7t278+tf/7p2u169enHHHXeQmJjY4GOXlpYybdo0hg0bBsDAgQOpqalh+fLljB8/nqSkpNptXS4X06dPr7P0+kMPPURGRgZ/+MMfCAsLA2DQoEGUlJQwd+5cRo8ejcPhYMuWLQwYMIBx48bVPnfIkCF16sjOzub6669n9OjRtfePHDmywa/ph/r168ctt9xSezs/P58FCxZw7rnnMmXKlNr7BwwYwJ133smCBQu4++67T+iYIq2R+nyIhJitW7fWOUtwWFJSEv369ePrr78GIDs7m6KiIk455ZQjtuvVq1ejjh0ZGVkbPA4bNWoUxhiysrLq3D9s2LA6wSMnJ4d9+/bVXjbxer21X0OGDKGwsJDs7GwAunXrxvr16/nPf/7DN998Q01NTZ19x8TE0L59e5YuXcobb7zBzp07sW27Ua/ph04++eQ6t7/66iu8Xi9jxoypU6/L5aJPnz5HvGYRqR+d+RAJMaWlpQAkJCQc8VhCQkLtpYnD3+Pi4o7YLi4urlHDdo+2r/j4+DrH+2EtP1RUVATAiy++yIsvvnjU/R9+bTfccAPt2rVj1apVLFmyBJfLxcCBA7nmmmtIS0vDsiz+8Ic/sHDhQpYsWcILL7xATEwMo0aN4sorryQyMrLBr+2Hr+Ww4uJiAH77298edXvLshp1HJHWTuFDJMTExsYCUFhYeMRjhYWFtY/HxMQA3/8B/aHDQaChjrevw8c7lrZt2wJw8cUXH/PySIcOHQBo06YNkyZNYtKkSRQVFdWeBZk1axaPP/44AMnJydx2222A7yzPp59+Wtuf5fClE5fLddT+LYdDzo/9OEwcbst77rmH5OTk474+Eak/hQ+RENOjRw/Cw8NZsWJFnUsqBQUFbNy4sfYPe4cOHYiPj+fTTz+t03ciPz+fLVu2NKrPR2VlJV988UWdSy8rV67Esiz69Olz3Od26NCBtLQ0du/ezVVXXVXvY8bHxzN27Fh27drFsmXLqK6uJiIi4oh9X3rppaxevZqdO3fW3p+cnMzu3bvrbLtx40aqqqrqdeyBAwcSFhbGgQMHjrgkIyKNp/AhEmKio6O59NJLmTt3Lk8++SSnnXYapaWlLFy4EJfLxWWXXQaAw+Fg0qRJ/Otf/+KRRx7h9NNPrx3tkpCQ0KhLBrGxsTzzzDPk5+eTlpbGl19+yXvvvcc555xTp7Ppsdx888089NBDPPDAA4wZM4bExETKysrYt28fO3fu5J577gHgd7/7HUOGDOGkk04iOjqaffv2sWLFCnr06EFERAS7d+9mzpw5nHzyyaSlpeF0Otm4cSO7d+/m4osvrj3e6NGjmTdvHvPmzaNPnz7s3buXt99+m6ioqHq93pSUFCZNmsQrr7zCgQMHGDRoEDExMRQVFbFt27baMzQi0jAKHyIhaMKECcTFxfHWW2+xatWq2nk+rrrqqtphtgBnnXUWAEuXLuWvf/0rycnJXHzxxXz++ecUFBQ0+Ljx8fHceOONvPjii+zZs4eYmBgmTJhQ7z/A/fr148EHH2TRokU8//zzlJWVERsbS3p6ep2zOP369WPt2rW8+eab1NTUkJiYyOjRo7nkkktq62jfvj3Lly8nPz8fy7Jo37491157Leeff37tfi666CIqKir48MMPef311+nWrRt33303f/nLX+r9midMmEB6ejrLli3jk08+wePxEB8fT9euXTn77LPrvR8R+Z5lNIWfSKtSXl7OXXfdxfDhw7n11lvr/bzDk4w98sgjzVidiLQGOvMh0oIVFRWxaNEi+vbtS2xsLHl5ebz55ptUVlZywQUXBLo8EWmlFD5EWjCn00lubi6ffvopZWVlRERE1M4umpGRAfjWXTneCVDLsmqnThcRaQq67CLSys2YMeO4k2UlJyc3aA0YEZGfovAh0splZ2dTWVl5zMddLhedOnXyY0Ui0tIpfIiIiIhf6UKuiIiI+JXCh4iIiPiVwoeIiIj4lcKHiIiI+JXCh4iIiPiVwoeIiIj4lcKHiIiI+JXCh4iIiPjV/wf5h0AvgfCepQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[3, :].to_list(),\n",
    "              'bv_pred':y_pred[3, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[3, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "86dfeb20",
   "metadata": {},
   "source": [
    "Significant improvement over linear regression"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01cbdb07",
   "metadata": {},
   "source": [
    "## AdaBoost\n",
    "AdaBoost does not support multi-output regression so I use MultiOutputRegressor."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "2bfec1fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.ensemble import AdaBoostRegressor\n",
    "from sklearn.tree import DecisionTreeRegressor\n",
    "from sklearn.multioutput import MultiOutputRegressor"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "40b7e6fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "def objective(trial):\n",
    "    tree_params = {\n",
    "        'max_depth': trial.suggest_int('max_tree', 10, 1000, log=True)\n",
    "    }\n",
    "\n",
    "    ada_params = {\n",
    "        'n_estimators': trial.suggest_int('n_estimators', 10, 1000, log=True),\n",
    "        'learning_rate': trial.suggest_float('lr', 0.01, 10, log=True)\n",
    "    }\n",
    "    tree = DecisionTreeRegressor(random_state=8, **tree_params)\n",
    "    ada = AdaBoostRegressor(estimator=tree, loss='linear', random_state=8, **ada_params)\n",
    "    regressor = MultiOutputRegressor(estimator=ada, n_jobs=-1)\n",
    "    cv_scores = cross_val_score(regressor, \n",
    "                                X_train, y_train, \n",
    "                                scoring='neg_mean_absolute_percentage_error', \n",
    "                                cv=10)\n",
    "    return cv_scores.mean()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "74a07185",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 18:35:31,265]\u001b[0m A new study created in memory with name: no-name-fdfd3758-acfd-4479-b555-f923f29cd8f6\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "study = optuna.create_study(\n",
    "    pruner=optuna.pruners.HyperbandPruner(),\n",
    "    direction='maximize'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "95a5afea",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-07 18:43:31,750]\u001b[0m Trial 0 finished with value: -0.3182286006237014 and parameters: {'max_tree': 247, 'n_estimators': 94, 'lr': 0.042383775358325264}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:44:00,381]\u001b[0m Trial 1 finished with value: -1.1341342166201198 and parameters: {'max_tree': 112, 'n_estimators': 27, 'lr': 3.750384725158504}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:45:19,615]\u001b[0m Trial 2 finished with value: -0.3271534479997142 and parameters: {'max_tree': 67, 'n_estimators': 15, 'lr': 0.03785958063599961}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:47:56,023]\u001b[0m Trial 3 finished with value: -0.32159939875094967 and parameters: {'max_tree': 33, 'n_estimators': 30, 'lr': 0.012211095931713819}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:49:25,177]\u001b[0m Trial 4 finished with value: -0.3252296858003392 and parameters: {'max_tree': 70, 'n_estimators': 17, 'lr': 0.07450643663618428}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:52:30,085]\u001b[0m Trial 5 finished with value: -0.31942080542887324 and parameters: {'max_tree': 10, 'n_estimators': 38, 'lr': 0.0113504635388689}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:55:05,225]\u001b[0m Trial 6 finished with value: -1.0349297171046667 and parameters: {'max_tree': 139, 'n_estimators': 206, 'lr': 3.9595468590428835}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 18:56:19,890]\u001b[0m Trial 7 finished with value: -0.3290123779648501 and parameters: {'max_tree': 720, 'n_estimators': 14, 'lr': 0.032545428337243026}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 19:07:40,754]\u001b[0m Trial 8 finished with value: -0.32145431393284907 and parameters: {'max_tree': 166, 'n_estimators': 151, 'lr': 0.485212223200024}. Best is trial 0 with value: -0.3182286006237014.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 19:29:07,179]\u001b[0m Trial 9 finished with value: -0.3141605738440897 and parameters: {'max_tree': 10, 'n_estimators': 272, 'lr': 0.01974826191547239}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 20:24:45,328]\u001b[0m Trial 10 finished with value: -0.3199772182583618 and parameters: {'max_tree': 11, 'n_estimators': 744, 'lr': 0.1860820312391713}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 20:31:40,843]\u001b[0m Trial 11 finished with value: -0.31658093329350045 and parameters: {'max_tree': 297, 'n_estimators': 83, 'lr': 0.09721620184564288}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 20:55:43,789]\u001b[0m Trial 12 finished with value: -0.3212063311135927 and parameters: {'max_tree': 419, 'n_estimators': 312, 'lr': 0.2714401139127073}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 21:02:00,800]\u001b[0m Trial 13 finished with value: -0.3158491423122318 and parameters: {'max_tree': 987, 'n_estimators': 76, 'lr': 0.11358111279882295}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 21:30:21,188]\u001b[0m Trial 14 finished with value: -0.32769466813127435 and parameters: {'max_tree': 800, 'n_estimators': 414, 'lr': 0.7917573802330143}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 21:35:55,556]\u001b[0m Trial 15 finished with value: -0.3180665427159077 and parameters: {'max_tree': 998, 'n_estimators': 65, 'lr': 0.018522279699636875}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 21:48:24,325]\u001b[0m Trial 16 finished with value: -0.317289584301509 and parameters: {'max_tree': 27, 'n_estimators': 154, 'lr': 0.10813571002255758}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 23:08:20,285]\u001b[0m Trial 17 finished with value: -0.3175797158994448 and parameters: {'max_tree': 341, 'n_estimators': 993, 'lr': 0.029500630441816056}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 23:12:42,094]\u001b[0m Trial 18 finished with value: -0.31944562170379726 and parameters: {'max_tree': 510, 'n_estimators': 51, 'lr': 0.06290102399137232}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 23:21:16,946]\u001b[0m Trial 19 finished with value: -0.3180506943980051 and parameters: {'max_tree': 184, 'n_estimators': 106, 'lr': 0.17004024910644883}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-07 23:46:14,437]\u001b[0m Trial 20 finished with value: -0.3154539021301363 and parameters: {'max_tree': 492, 'n_estimators': 299, 'lr': 0.020688313087407564}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 00:12:20,027]\u001b[0m Trial 21 finished with value: -0.31667787949931037 and parameters: {'max_tree': 634, 'n_estimators': 312, 'lr': 0.01913942239370763}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 00:29:14,619]\u001b[0m Trial 22 finished with value: -0.3175691254599429 and parameters: {'max_tree': 492, 'n_estimators': 201, 'lr': 0.021177302107472883}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 01:00:17,106]\u001b[0m Trial 23 finished with value: -0.31664933018509867 and parameters: {'max_tree': 901, 'n_estimators': 383, 'lr': 0.051511022272641316}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 01:09:43,236]\u001b[0m Trial 24 finished with value: -0.31578476772720665 and parameters: {'max_tree': 239, 'n_estimators': 110, 'lr': 0.010094586400760924}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 01:56:19,100]\u001b[0m Trial 25 finished with value: -0.31637614340913345 and parameters: {'max_tree': 245, 'n_estimators': 559, 'lr': 0.011696519649151268}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 02:14:13,211]\u001b[0m Trial 26 finished with value: -0.3154045351504885 and parameters: {'max_tree': 384, 'n_estimators': 211, 'lr': 0.010849276048406457}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 02:33:34,932]\u001b[0m Trial 27 finished with value: -0.31665918556955186 and parameters: {'max_tree': 379, 'n_estimators': 231, 'lr': 0.024958301730564826}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 03:16:03,050]\u001b[0m Trial 28 finished with value: -0.31674448445618775 and parameters: {'max_tree': 569, 'n_estimators': 513, 'lr': 0.016474735592140993}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 03:38:04,810]\u001b[0m Trial 29 finished with value: -0.31647201724729446 and parameters: {'max_tree': 387, 'n_estimators': 269, 'lr': 0.049409122489888324}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 03:50:02,842]\u001b[0m Trial 30 finished with value: -0.3164411053694011 and parameters: {'max_tree': 241, 'n_estimators': 142, 'lr': 0.034527522251498646}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 03:59:28,012]\u001b[0m Trial 31 finished with value: -0.31594212356732226 and parameters: {'max_tree': 279, 'n_estimators': 110, 'lr': 0.011777577848526784}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 04:14:52,096]\u001b[0m Trial 32 finished with value: -0.31597974053380357 and parameters: {'max_tree': 208, 'n_estimators': 181, 'lr': 0.017159640525334995}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 04:24:46,461]\u001b[0m Trial 33 finished with value: -0.3165699956411435 and parameters: {'max_tree': 121, 'n_estimators': 117, 'lr': 0.026463176160253888}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 04:46:22,439]\u001b[0m Trial 34 finished with value: -0.31711100997071806 and parameters: {'max_tree': 314, 'n_estimators': 263, 'lr': 0.04524516001515101}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 05:01:21,637]\u001b[0m Trial 35 finished with value: -0.31575019556851325 and parameters: {'max_tree': 80, 'n_estimators': 176, 'lr': 0.010935712798745273}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 05:30:12,147]\u001b[0m Trial 36 finished with value: -0.31643993607485055 and parameters: {'max_tree': 105, 'n_estimators': 344, 'lr': 0.016542768712566495}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[32m[I 2023-03-08 05:49:27,048]\u001b[0m Trial 37 finished with value: -0.3152974258802068 and parameters: {'max_tree': 69, 'n_estimators': 227, 'lr': 0.01045366680251343}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 06:09:08,121]\u001b[0m Trial 38 finished with value: -0.31603452424957795 and parameters: {'max_tree': 57, 'n_estimators': 237, 'lr': 0.031221904795785238}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 06:47:54,166]\u001b[0m Trial 39 finished with value: -0.31572134728001117 and parameters: {'max_tree': 49, 'n_estimators': 465, 'lr': 0.014697316148549537}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 07:12:29,855]\u001b[0m Trial 40 finished with value: -0.3170867746577496 and parameters: {'max_tree': 92, 'n_estimators': 299, 'lr': 0.03741309483604211}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 07:49:11,992]\u001b[0m Trial 41 finished with value: -0.3158299018736809 and parameters: {'max_tree': 151, 'n_estimators': 440, 'lr': 0.01478537367096431}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 08:09:16,124]\u001b[0m Trial 42 finished with value: -0.3150720582083415 and parameters: {'max_tree': 40, 'n_estimators': 239, 'lr': 0.02114280365621077}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 08:27:26,460]\u001b[0m Trial 43 finished with value: -0.31623313149227666 and parameters: {'max_tree': 20, 'n_estimators': 216, 'lr': 0.021443898435521212}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 08:56:31,046]\u001b[0m Trial 44 finished with value: -0.3159383695514696 and parameters: {'max_tree': 45, 'n_estimators': 351, 'lr': 0.025066785365654785}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 09:16:56,908]\u001b[0m Trial 45 finished with value: -0.31526715668168553 and parameters: {'max_tree': 68, 'n_estimators': 241, 'lr': 0.010197753962329054}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 09:30:06,898]\u001b[0m Trial 46 finished with value: -0.31702475224140014 and parameters: {'max_tree': 70, 'n_estimators': 155, 'lr': 0.013900285633207547}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 09:50:52,626]\u001b[0m Trial 47 finished with value: -0.31551913041456064 and parameters: {'max_tree': 124, 'n_estimators': 245, 'lr': 0.010258355266547652}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 10:06:37,298]\u001b[0m Trial 48 finished with value: -0.31607553376151654 and parameters: {'max_tree': 89, 'n_estimators': 189, 'lr': 0.03758049125817355}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 10:18:21,889]\u001b[0m Trial 49 finished with value: -0.3155267398150672 and parameters: {'max_tree': 12, 'n_estimators': 141, 'lr': 0.013938866524000715}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[32m[I 2023-03-08 11:07:50,797]\u001b[0m Trial 50 finished with value: -0.31660061628524516 and parameters: {'max_tree': 33, 'n_estimators': 603, 'lr': 0.024264576867751422}. Best is trial 9 with value: -0.3141605738440897.\u001b[0m\n",
      "\u001b[33m[W 2023-03-08 11:14:02,233]\u001b[0m Trial 51 failed with parameters: {'max_tree': 61, 'n_estimators': 266, 'lr': 0.01003724598479266} because of the following error: KeyboardInterrupt().\u001b[0m\n",
      "Traceback (most recent call last):\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/optuna/study/_optimize.py\", line 200, in _run_trial\n",
      "    value_or_values = func(trial)\n",
      "  File \"/tmp/ipykernel_3740/1984333302.py\", line 13, in objective\n",
      "    cv_scores = cross_val_score(regressor,\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/model_selection/_validation.py\", line 515, in cross_val_score\n",
      "    cv_results = cross_validate(\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/model_selection/_validation.py\", line 266, in cross_validate\n",
      "    results = parallel(\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/utils/parallel.py\", line 63, in __call__\n",
      "    return super().__call__(iterable_with_config)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 1051, in __call__\n",
      "    while self.dispatch_one_batch(iterator):\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 864, in dispatch_one_batch\n",
      "    self._dispatch(tasks)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 782, in _dispatch\n",
      "    job = self._backend.apply_async(batch, callback=cb)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/_parallel_backends.py\", line 208, in apply_async\n",
      "    result = ImmediateResult(func)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/_parallel_backends.py\", line 572, in __init__\n",
      "    self.results = batch()\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 263, in __call__\n",
      "    return [func(*args, **kwargs)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 263, in <listcomp>\n",
      "    return [func(*args, **kwargs)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/utils/parallel.py\", line 123, in __call__\n",
      "    return self.function(*args, **kwargs)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/model_selection/_validation.py\", line 686, in _fit_and_score\n",
      "    estimator.fit(X_train, y_train, **fit_params)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/multioutput.py\", line 216, in fit\n",
      "    self.estimators_ = Parallel(n_jobs=self.n_jobs)(\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/utils/parallel.py\", line 63, in __call__\n",
      "    return super().__call__(iterable_with_config)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 1061, in __call__\n",
      "    self.retrieve()\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py\", line 938, in retrieve\n",
      "    self._output.extend(job.get(timeout=self.timeout))\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/_parallel_backends.py\", line 542, in wrap_future_result\n",
      "    return future.result(timeout=timeout)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/concurrent/futures/_base.py\", line 453, in result\n",
      "    self._condition.wait(timeout)\n",
      "  File \"/home/denis/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/threading.py\", line 320, in wait\n",
      "    waiter.acquire()\n",
      "KeyboardInterrupt\n",
      "\u001b[33m[W 2023-03-08 11:14:02,251]\u001b[0m Trial 51 failed with value None.\u001b[0m\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "File \u001b[0;32m<timed eval>:1\u001b[0m\n",
      "File \u001b[0;32m~/.local/lib/python3.10/site-packages/IPython/core/interactiveshell.py:2417\u001b[0m, in \u001b[0;36mInteractiveShell.run_cell_magic\u001b[0;34m(self, magic_name, line, cell)\u001b[0m\n\u001b[1;32m   2415\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbuiltin_trap:\n\u001b[1;32m   2416\u001b[0m     args \u001b[38;5;241m=\u001b[39m (magic_arg_s, cell)\n\u001b[0;32m-> 2417\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2418\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m result\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/chime.py:302\u001b[0m, in \u001b[0;36mChimeMagics.chime\u001b[0;34m(self, line, cell, local_ns)\u001b[0m\n\u001b[1;32m    300\u001b[0m     run(line)\n\u001b[1;32m    301\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 302\u001b[0m     \u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcell\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/chime.py:293\u001b[0m, in \u001b[0;36mChimeMagics.chime.<locals>.run\u001b[0;34m(code)\u001b[0m\n\u001b[1;32m    291\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mrun\u001b[39m(code):\n\u001b[1;32m    292\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 293\u001b[0m         \u001b[43mexec\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcode\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mlocal_ns\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    294\u001b[0m         success()\n\u001b[1;32m    295\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m<string>:1\u001b[0m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/optuna/study/study.py:425\u001b[0m, in \u001b[0;36mStudy.optimize\u001b[0;34m(self, func, n_trials, timeout, n_jobs, catch, callbacks, gc_after_trial, show_progress_bar)\u001b[0m\n\u001b[1;32m    321\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21moptimize\u001b[39m(\n\u001b[1;32m    322\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m    323\u001b[0m     func: ObjectiveFuncType,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    330\u001b[0m     show_progress_bar: \u001b[38;5;28mbool\u001b[39m \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[1;32m    331\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    332\u001b[0m     \u001b[38;5;124;03m\"\"\"Optimize an objective function.\u001b[39;00m\n\u001b[1;32m    333\u001b[0m \n\u001b[1;32m    334\u001b[0m \u001b[38;5;124;03m    Optimization is done by choosing a suitable set of hyperparameter values from a given\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    422\u001b[0m \u001b[38;5;124;03m            If nested invocation of this method occurs.\u001b[39;00m\n\u001b[1;32m    423\u001b[0m \u001b[38;5;124;03m    \"\"\"\u001b[39;00m\n\u001b[0;32m--> 425\u001b[0m     \u001b[43m_optimize\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    426\u001b[0m \u001b[43m        \u001b[49m\u001b[43mstudy\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m    427\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfunc\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    428\u001b[0m \u001b[43m        \u001b[49m\u001b[43mn_trials\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_trials\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    429\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    430\u001b[0m \u001b[43m        \u001b[49m\u001b[43mn_jobs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_jobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    431\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcatch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mtuple\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcatch\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43misinstance\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mcatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mIterable\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[43mcatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    432\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    433\u001b[0m \u001b[43m        \u001b[49m\u001b[43mgc_after_trial\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgc_after_trial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    434\u001b[0m \u001b[43m        \u001b[49m\u001b[43mshow_progress_bar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mshow_progress_bar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    435\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/optuna/study/_optimize.py:66\u001b[0m, in \u001b[0;36m_optimize\u001b[0;34m(study, func, n_trials, timeout, n_jobs, catch, callbacks, gc_after_trial, show_progress_bar)\u001b[0m\n\u001b[1;32m     64\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m     65\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m n_jobs \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m---> 66\u001b[0m         \u001b[43m_optimize_sequential\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m     67\u001b[0m \u001b[43m            \u001b[49m\u001b[43mstudy\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     68\u001b[0m \u001b[43m            \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     69\u001b[0m \u001b[43m            \u001b[49m\u001b[43mn_trials\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     70\u001b[0m \u001b[43m            \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     71\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcatch\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     72\u001b[0m \u001b[43m            \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     73\u001b[0m \u001b[43m            \u001b[49m\u001b[43mgc_after_trial\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     74\u001b[0m \u001b[43m            \u001b[49m\u001b[43mreseed_sampler_rng\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m     75\u001b[0m \u001b[43m            \u001b[49m\u001b[43mtime_start\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m     76\u001b[0m \u001b[43m            \u001b[49m\u001b[43mprogress_bar\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mprogress_bar\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m     77\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     78\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m     79\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m n_jobs \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m:\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/optuna/study/_optimize.py:163\u001b[0m, in \u001b[0;36m_optimize_sequential\u001b[0;34m(study, func, n_trials, timeout, catch, callbacks, gc_after_trial, reseed_sampler_rng, time_start, progress_bar)\u001b[0m\n\u001b[1;32m    160\u001b[0m         \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m    162\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 163\u001b[0m     frozen_trial \u001b[38;5;241m=\u001b[39m \u001b[43m_run_trial\u001b[49m\u001b[43m(\u001b[49m\u001b[43mstudy\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcatch\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    164\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n\u001b[1;32m    165\u001b[0m     \u001b[38;5;66;03m# The following line mitigates memory problems that can be occurred in some\u001b[39;00m\n\u001b[1;32m    166\u001b[0m     \u001b[38;5;66;03m# environments (e.g., services that use computing containers such as GitHub Actions).\u001b[39;00m\n\u001b[1;32m    167\u001b[0m     \u001b[38;5;66;03m# Please refer to the following PR for further details:\u001b[39;00m\n\u001b[1;32m    168\u001b[0m     \u001b[38;5;66;03m# https://github.com/optuna/optuna/pull/325.\u001b[39;00m\n\u001b[1;32m    169\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m gc_after_trial:\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/optuna/study/_optimize.py:251\u001b[0m, in \u001b[0;36m_run_trial\u001b[0;34m(study, func, catch)\u001b[0m\n\u001b[1;32m    244\u001b[0m         \u001b[38;5;28;01massert\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mShould not reach.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    246\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\n\u001b[1;32m    247\u001b[0m     frozen_trial\u001b[38;5;241m.\u001b[39mstate \u001b[38;5;241m==\u001b[39m TrialState\u001b[38;5;241m.\u001b[39mFAIL\n\u001b[1;32m    248\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m func_err \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    249\u001b[0m     \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(func_err, catch)\n\u001b[1;32m    250\u001b[0m ):\n\u001b[0;32m--> 251\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m func_err\n\u001b[1;32m    252\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m frozen_trial\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/optuna/study/_optimize.py:200\u001b[0m, in \u001b[0;36m_run_trial\u001b[0;34m(study, func, catch)\u001b[0m\n\u001b[1;32m    198\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m get_heartbeat_thread(trial\u001b[38;5;241m.\u001b[39m_trial_id, study\u001b[38;5;241m.\u001b[39m_storage):\n\u001b[1;32m    199\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 200\u001b[0m         value_or_values \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtrial\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    201\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m exceptions\u001b[38;5;241m.\u001b[39mTrialPruned \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    202\u001b[0m         \u001b[38;5;66;03m# TODO(mamu): Handle multi-objective cases.\u001b[39;00m\n\u001b[1;32m    203\u001b[0m         state \u001b[38;5;241m=\u001b[39m TrialState\u001b[38;5;241m.\u001b[39mPRUNED\n",
      "Cell \u001b[0;32mIn[22], line 13\u001b[0m, in \u001b[0;36mobjective\u001b[0;34m(trial)\u001b[0m\n\u001b[1;32m     11\u001b[0m ada \u001b[38;5;241m=\u001b[39m AdaBoostRegressor(estimator\u001b[38;5;241m=\u001b[39mtree, loss\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mlinear\u001b[39m\u001b[38;5;124m'\u001b[39m, random_state\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m8\u001b[39m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mada_params)\n\u001b[1;32m     12\u001b[0m regressor \u001b[38;5;241m=\u001b[39m MultiOutputRegressor(estimator\u001b[38;5;241m=\u001b[39mada, n_jobs\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m)\n\u001b[0;32m---> 13\u001b[0m cv_scores \u001b[38;5;241m=\u001b[39m \u001b[43mcross_val_score\u001b[49m\u001b[43m(\u001b[49m\u001b[43mregressor\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m     14\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m     15\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mscoring\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mneg_mean_absolute_percentage_error\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\n\u001b[1;32m     16\u001b[0m \u001b[43m                            \u001b[49m\u001b[43mcv\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m10\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m     17\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cv_scores\u001b[38;5;241m.\u001b[39mmean()\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/model_selection/_validation.py:515\u001b[0m, in \u001b[0;36mcross_val_score\u001b[0;34m(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, error_score)\u001b[0m\n\u001b[1;32m    512\u001b[0m \u001b[38;5;66;03m# To ensure multimetric format is not supported\u001b[39;00m\n\u001b[1;32m    513\u001b[0m scorer \u001b[38;5;241m=\u001b[39m check_scoring(estimator, scoring\u001b[38;5;241m=\u001b[39mscoring)\n\u001b[0;32m--> 515\u001b[0m cv_results \u001b[38;5;241m=\u001b[39m \u001b[43mcross_validate\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    516\u001b[0m \u001b[43m    \u001b[49m\u001b[43mestimator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mestimator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    517\u001b[0m \u001b[43m    \u001b[49m\u001b[43mX\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    518\u001b[0m \u001b[43m    \u001b[49m\u001b[43my\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    519\u001b[0m \u001b[43m    \u001b[49m\u001b[43mgroups\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mgroups\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    520\u001b[0m \u001b[43m    \u001b[49m\u001b[43mscoring\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mscore\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mscorer\u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    521\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcv\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcv\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    522\u001b[0m \u001b[43m    \u001b[49m\u001b[43mn_jobs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mn_jobs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    523\u001b[0m \u001b[43m    \u001b[49m\u001b[43mverbose\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    524\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfit_params\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfit_params\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    525\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpre_dispatch\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpre_dispatch\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    526\u001b[0m \u001b[43m    \u001b[49m\u001b[43merror_score\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merror_score\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    527\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    528\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m cv_results[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtest_score\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/model_selection/_validation.py:266\u001b[0m, in \u001b[0;36mcross_validate\u001b[0;34m(estimator, X, y, groups, scoring, cv, n_jobs, verbose, fit_params, pre_dispatch, return_train_score, return_estimator, error_score)\u001b[0m\n\u001b[1;32m    263\u001b[0m \u001b[38;5;66;03m# We clone the estimator to make sure that all the folds are\u001b[39;00m\n\u001b[1;32m    264\u001b[0m \u001b[38;5;66;03m# independent, and that it is pickle-able.\u001b[39;00m\n\u001b[1;32m    265\u001b[0m parallel \u001b[38;5;241m=\u001b[39m Parallel(n_jobs\u001b[38;5;241m=\u001b[39mn_jobs, verbose\u001b[38;5;241m=\u001b[39mverbose, pre_dispatch\u001b[38;5;241m=\u001b[39mpre_dispatch)\n\u001b[0;32m--> 266\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[43mparallel\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    267\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdelayed\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_fit_and_score\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    268\u001b[0m \u001b[43m        \u001b[49m\u001b[43mclone\u001b[49m\u001b[43m(\u001b[49m\u001b[43mestimator\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    269\u001b[0m \u001b[43m        \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    270\u001b[0m \u001b[43m        \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    271\u001b[0m \u001b[43m        \u001b[49m\u001b[43mscorers\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    272\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtrain\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    273\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtest\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    274\u001b[0m \u001b[43m        \u001b[49m\u001b[43mverbose\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    275\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    276\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfit_params\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    277\u001b[0m \u001b[43m        \u001b[49m\u001b[43mreturn_train_score\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_train_score\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    278\u001b[0m \u001b[43m        \u001b[49m\u001b[43mreturn_times\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    279\u001b[0m \u001b[43m        \u001b[49m\u001b[43mreturn_estimator\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_estimator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    280\u001b[0m \u001b[43m        \u001b[49m\u001b[43merror_score\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43merror_score\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    281\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    282\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mtrain\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtest\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mcv\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mgroups\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    283\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    285\u001b[0m _warn_or_raise_about_fit_failures(results, error_score)\n\u001b[1;32m    287\u001b[0m \u001b[38;5;66;03m# For callabe scoring, the return type is only know after calling. If the\u001b[39;00m\n\u001b[1;32m    288\u001b[0m \u001b[38;5;66;03m# return type is a dictionary, the error scores can now be inserted with\u001b[39;00m\n\u001b[1;32m    289\u001b[0m \u001b[38;5;66;03m# the correct key.\u001b[39;00m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/utils/parallel.py:63\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m     58\u001b[0m config \u001b[38;5;241m=\u001b[39m get_config()\n\u001b[1;32m     59\u001b[0m iterable_with_config \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m     60\u001b[0m     (_with_config(delayed_func, config), args, kwargs)\n\u001b[1;32m     61\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m delayed_func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m iterable\n\u001b[1;32m     62\u001b[0m )\n\u001b[0;32m---> 63\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43miterable_with_config\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:1051\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m   1048\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdispatch_one_batch(iterator):\n\u001b[1;32m   1049\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iterating \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_original_iterator \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1051\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdispatch_one_batch\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m:\n\u001b[1;32m   1052\u001b[0m     \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[1;32m   1054\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m pre_dispatch \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mall\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mor\u001b[39;00m n_jobs \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m   1055\u001b[0m     \u001b[38;5;66;03m# The iterable was consumed all at once by the above for loop.\u001b[39;00m\n\u001b[1;32m   1056\u001b[0m     \u001b[38;5;66;03m# No need to wait for async callbacks to trigger to\u001b[39;00m\n\u001b[1;32m   1057\u001b[0m     \u001b[38;5;66;03m# consumption.\u001b[39;00m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:864\u001b[0m, in \u001b[0;36mParallel.dispatch_one_batch\u001b[0;34m(self, iterator)\u001b[0m\n\u001b[1;32m    862\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m    863\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 864\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_dispatch\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtasks\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    865\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mTrue\u001b[39;00m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:782\u001b[0m, in \u001b[0;36mParallel._dispatch\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    780\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock:\n\u001b[1;32m    781\u001b[0m     job_idx \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlen\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jobs)\n\u001b[0;32m--> 782\u001b[0m     job \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_backend\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mapply_async\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbatch\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallback\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcb\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    783\u001b[0m     \u001b[38;5;66;03m# A job can complete so quickly than its callback is\u001b[39;00m\n\u001b[1;32m    784\u001b[0m     \u001b[38;5;66;03m# called before we get here, causing self._jobs to\u001b[39;00m\n\u001b[1;32m    785\u001b[0m     \u001b[38;5;66;03m# grow. To ensure correct results ordering, .insert is\u001b[39;00m\n\u001b[1;32m    786\u001b[0m     \u001b[38;5;66;03m# used (rather than .append) in the following line\u001b[39;00m\n\u001b[1;32m    787\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jobs\u001b[38;5;241m.\u001b[39minsert(job_idx, job)\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/_parallel_backends.py:208\u001b[0m, in \u001b[0;36mSequentialBackend.apply_async\u001b[0;34m(self, func, callback)\u001b[0m\n\u001b[1;32m    206\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mapply_async\u001b[39m(\u001b[38;5;28mself\u001b[39m, func, callback\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[1;32m    207\u001b[0m     \u001b[38;5;124;03m\"\"\"Schedule a func to be run\"\"\"\u001b[39;00m\n\u001b[0;32m--> 208\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[43mImmediateResult\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfunc\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    209\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m callback:\n\u001b[1;32m    210\u001b[0m         callback(result)\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/_parallel_backends.py:572\u001b[0m, in \u001b[0;36mImmediateResult.__init__\u001b[0;34m(self, batch)\u001b[0m\n\u001b[1;32m    569\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__init__\u001b[39m(\u001b[38;5;28mself\u001b[39m, batch):\n\u001b[1;32m    570\u001b[0m     \u001b[38;5;66;03m# Don't delay the application, to avoid keeping the input\u001b[39;00m\n\u001b[1;32m    571\u001b[0m     \u001b[38;5;66;03m# arguments in memory\u001b[39;00m\n\u001b[0;32m--> 572\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mresults \u001b[38;5;241m=\u001b[39m \u001b[43mbatch\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:263\u001b[0m, in \u001b[0;36mBatchedCalls.__call__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    259\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m    260\u001b[0m     \u001b[38;5;66;03m# Set the default nested backend to self._backend but do not set the\u001b[39;00m\n\u001b[1;32m    261\u001b[0m     \u001b[38;5;66;03m# change the default number of processes to -1\u001b[39;00m\n\u001b[1;32m    262\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m parallel_backend(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backend, n_jobs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_n_jobs):\n\u001b[0;32m--> 263\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m [func(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    264\u001b[0m                 \u001b[38;5;28;01mfor\u001b[39;00m func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mitems]\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:263\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m    259\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m__call__\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m    260\u001b[0m     \u001b[38;5;66;03m# Set the default nested backend to self._backend but do not set the\u001b[39;00m\n\u001b[1;32m    261\u001b[0m     \u001b[38;5;66;03m# change the default number of processes to -1\u001b[39;00m\n\u001b[1;32m    262\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m parallel_backend(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backend, n_jobs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_n_jobs):\n\u001b[0;32m--> 263\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m [\u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    264\u001b[0m                 \u001b[38;5;28;01mfor\u001b[39;00m func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mitems]\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/utils/parallel.py:123\u001b[0m, in \u001b[0;36m_FuncWrapper.__call__\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    121\u001b[0m     config \u001b[38;5;241m=\u001b[39m {}\n\u001b[1;32m    122\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m config_context(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mconfig):\n\u001b[0;32m--> 123\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunction\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/model_selection/_validation.py:686\u001b[0m, in \u001b[0;36m_fit_and_score\u001b[0;34m(estimator, X, y, scorer, train, test, verbose, parameters, fit_params, return_train_score, return_parameters, return_n_test_samples, return_times, return_estimator, split_progress, candidate_progress, error_score)\u001b[0m\n\u001b[1;32m    684\u001b[0m         estimator\u001b[38;5;241m.\u001b[39mfit(X_train, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfit_params)\n\u001b[1;32m    685\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m--> 686\u001b[0m         \u001b[43mestimator\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my_train\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfit_params\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    688\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[1;32m    689\u001b[0m     \u001b[38;5;66;03m# Note fit time as time until error\u001b[39;00m\n\u001b[1;32m    690\u001b[0m     fit_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime() \u001b[38;5;241m-\u001b[39m start_time\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/multioutput.py:216\u001b[0m, in \u001b[0;36m_MultiOutputEstimator.fit\u001b[0;34m(self, X, y, sample_weight, **fit_params)\u001b[0m\n\u001b[1;32m    212\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mUnderlying estimator does not support sample weights.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    214\u001b[0m fit_params_validated \u001b[38;5;241m=\u001b[39m _check_fit_params(X, fit_params)\n\u001b[0;32m--> 216\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mestimators_ \u001b[38;5;241m=\u001b[39m \u001b[43mParallel\u001b[49m\u001b[43m(\u001b[49m\u001b[43mn_jobs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mn_jobs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    217\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdelayed\u001b[49m\u001b[43m(\u001b[49m\u001b[43m_fit_estimator\u001b[49m\u001b[43m)\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    218\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mestimator\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mX\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43my\u001b[49m\u001b[43m[\u001b[49m\u001b[43m:\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mi\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43msample_weight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mfit_params_validated\u001b[49m\n\u001b[1;32m    219\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    220\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mi\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mrange\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43my\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mshape\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    221\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    223\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mhasattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mestimators_[\u001b[38;5;241m0\u001b[39m], \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mn_features_in_\u001b[39m\u001b[38;5;124m\"\u001b[39m):\n\u001b[1;32m    224\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mn_features_in_ \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mestimators_[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39mn_features_in_\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/sklearn/utils/parallel.py:63\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m     58\u001b[0m config \u001b[38;5;241m=\u001b[39m get_config()\n\u001b[1;32m     59\u001b[0m iterable_with_config \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m     60\u001b[0m     (_with_config(delayed_func, config), args, kwargs)\n\u001b[1;32m     61\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m delayed_func, args, kwargs \u001b[38;5;129;01min\u001b[39;00m iterable\n\u001b[1;32m     62\u001b[0m )\n\u001b[0;32m---> 63\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43miterable_with_config\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:1061\u001b[0m, in \u001b[0;36mParallel.__call__\u001b[0;34m(self, iterable)\u001b[0m\n\u001b[1;32m   1058\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_iterating \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m   1060\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backend\u001b[38;5;241m.\u001b[39mretrieval_context():\n\u001b[0;32m-> 1061\u001b[0m     \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mretrieve\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1062\u001b[0m \u001b[38;5;66;03m# Make sure that we get a last message telling us we are done\u001b[39;00m\n\u001b[1;32m   1063\u001b[0m elapsed_time \u001b[38;5;241m=\u001b[39m time\u001b[38;5;241m.\u001b[39mtime() \u001b[38;5;241m-\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_start_time\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/parallel.py:938\u001b[0m, in \u001b[0;36mParallel.retrieve\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    936\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    937\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backend, \u001b[38;5;124m'\u001b[39m\u001b[38;5;124msupports_timeout\u001b[39m\u001b[38;5;124m'\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m):\n\u001b[0;32m--> 938\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output\u001b[38;5;241m.\u001b[39mextend(\u001b[43mjob\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[1;32m    939\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    940\u001b[0m         \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_output\u001b[38;5;241m.\u001b[39mextend(job\u001b[38;5;241m.\u001b[39mget())\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/site-packages/joblib/_parallel_backends.py:542\u001b[0m, in \u001b[0;36mLokyBackend.wrap_future_result\u001b[0;34m(future, timeout)\u001b[0m\n\u001b[1;32m    539\u001b[0m \u001b[38;5;124;03m\"\"\"Wrapper for Future.result to implement the same behaviour as\u001b[39;00m\n\u001b[1;32m    540\u001b[0m \u001b[38;5;124;03mAsyncResults.get from multiprocessing.\"\"\"\u001b[39;00m\n\u001b[1;32m    541\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 542\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfuture\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mresult\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    543\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m CfTimeoutError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    544\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mTimeoutError\u001b[39;00m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/concurrent/futures/_base.py:453\u001b[0m, in \u001b[0;36mFuture.result\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    450\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;241m==\u001b[39m FINISHED:\n\u001b[1;32m    451\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m__get_result()\n\u001b[0;32m--> 453\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_condition\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwait\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtimeout\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    455\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_state \u001b[38;5;129;01min\u001b[39;00m [CANCELLED, CANCELLED_AND_NOTIFIED]:\n\u001b[1;32m    456\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m CancelledError()\n",
      "File \u001b[0;32m~/MyCode/NonGit/Tests/Aramco/env/lib/python3.10/threading.py:320\u001b[0m, in \u001b[0;36mCondition.wait\u001b[0;34m(self, timeout)\u001b[0m\n\u001b[1;32m    318\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:    \u001b[38;5;66;03m# restore state no matter what (e.g., KeyboardInterrupt)\u001b[39;00m\n\u001b[1;32m    319\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m timeout \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m--> 320\u001b[0m         \u001b[43mwaiter\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43macquire\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    321\u001b[0m         gotit \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m    322\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "%%time\n",
    "%%chime\n",
    "study.optimize(objective, n_trials=100)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36cf2bfc",
   "metadata": {},
   "source": [
    "Interrupted as it took too long and the best value was achieved at trial 9:\n",
    "\n",
    "Trial 9 finished with value: -0.3141605738440897 and parameters: {'max_tree': 10, 'n_estimators': 272, 'lr': 0.01974826191547239}. Best is trial 9 with value: -0.3141605738440897."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "e2968614",
   "metadata": {},
   "outputs": [],
   "source": [
    "tree = DecisionTreeRegressor(random_state=8,\n",
    "                             max_depth=10)\n",
    "ada = AdaBoostRegressor(estimator=tree, \n",
    "                        loss='linear', \n",
    "                        random_state=8,\n",
    "                        n_estimators=272,\n",
    "                        learning_rate=0.01974826191547239\n",
    "                       )\n",
    "best_regressor = MultiOutputRegressor(estimator=ada, n_jobs=-1)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "960a5967",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputRegressor(estimator=AdaBoostRegressor(estimator=DecisionTreeRegressor(max_depth=10,\n",
       "                                                                                 random_state=8),\n",
       "                                                 learning_rate=0.01974826191547239,\n",
       "                                                 n_estimators=272,\n",
       "                                                 random_state=8),\n",
       "                     n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MultiOutputRegressor</label><div class=\"sk-toggleable__content\"><pre>MultiOutputRegressor(estimator=AdaBoostRegressor(estimator=DecisionTreeRegressor(max_depth=10,\n",
       "                                                                                 random_state=8),\n",
       "                                                 learning_rate=0.01974826191547239,\n",
       "                                                 n_estimators=272,\n",
       "                                                 random_state=8),\n",
       "                     n_jobs=-1)</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: AdaBoostRegressor</label><div class=\"sk-toggleable__content\"><pre>AdaBoostRegressor(estimator=DecisionTreeRegressor(max_depth=10, random_state=8),\n",
       "                  learning_rate=0.01974826191547239, n_estimators=272,\n",
       "                  random_state=8)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor(max_depth=10, random_state=8)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeRegressor</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeRegressor(max_depth=10, random_state=8)</pre></div></div></div></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "MultiOutputRegressor(estimator=AdaBoostRegressor(estimator=DecisionTreeRegressor(max_depth=10,\n",
       "                                                                                 random_state=8),\n",
       "                                                 learning_rate=0.01974826191547239,\n",
       "                                                 n_estimators=272,\n",
       "                                                 random_state=8),\n",
       "                     n_jobs=-1)"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "best_regressor.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "31a665f9",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_pred = best_regressor.predict(X_val)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "6027b2ac",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.2982196152206533"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mean_absolute_percentage_error(y_val, y_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7594bfdb",
   "metadata": {},
   "source": [
    "Some curve examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "7166e8a3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[0, :].to_list(),\n",
    "              'bv_pred':y_pred[0, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[0, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "b8ba61d5",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[1, :].to_list(),\n",
    "              'bv_pred':y_pred[1, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[1, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "3ef7e9b3",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[2, :].to_list(),\n",
    "              'bv_pred':y_pred[2, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[2, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "890b413b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pd.DataFrame({'log_pressure': X_val.filter(regex='pc_').iloc[3, :].to_list(),\n",
    "              'bv_pred':y_pred[3, :].tolist(),\n",
    "              'bv_fact': y_val.iloc[3, :].to_list()}) \\\n",
    "    .plot.line(x='log_pressure', y=['bv_pred', 'bv_fact']);"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df67d92b",
   "metadata": {},
   "source": [
    "# Conclusion\n",
    "- This approach could be closer to real MICP experiments conducted with the purpose to determine volume-vs-pressure curves\n",
    "- Whan needs to be improved: curve smoothing and constraining as injected volume should increase with pressure"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}