diff --git a/Yapiki_publ/Public_solution_KI_YP.ipynb b/Yapiki_publ/Public_solution_KI_YP.ipynb
new file mode 100644
index 0000000..196a42e
--- /dev/null
+++ b/Yapiki_publ/Public_solution_KI_YP.ipynb
@@ -0,0 +1,3330 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "id": "78b262fa"
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import typing\n",
+    "import torch\n",
+    "\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
+    "from lightautoml.automl.presets.tabular_presets import TabularUtilizedAutoML\n",
+    "from lightautoml.tasks import Task\n",
+    "\n",
+    "import phik\n",
+    "from phik.report import plot_correlation_matrix\n",
+    "from phik import report"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "id": "5114ddf7"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((279792, 77), (2974, 76))"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_data = pd.read_csv('data/train.csv')\n",
+    "test_data = pd.read_csv('data/test.csv')\n",
+    "train_data.shape, test_data.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## EDA analisys"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Анализ отчет pandas_profiling (! big size file) https://drive.google.com/file/d/1xQl3LvpX9J0G6gJoaBjzRcBFKZi6QZXz/view?usp=sharing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for col in train_data.select_dtypes(include=np.number).columns:\n",
+    "    train_data[col] = pd.to_numeric(train_data[col], downcast = 'unsigned')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "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>lat</th>\n",
+       "      <th>lng</th>\n",
+       "      <th>osm_amenity_points_in_0.001</th>\n",
+       "      <th>osm_amenity_points_in_0.005</th>\n",
+       "      <th>osm_amenity_points_in_0.0075</th>\n",
+       "      <th>osm_amenity_points_in_0.01</th>\n",
+       "      <th>osm_building_points_in_0.001</th>\n",
+       "      <th>osm_building_points_in_0.005</th>\n",
+       "      <th>osm_building_points_in_0.0075</th>\n",
+       "      <th>osm_building_points_in_0.01</th>\n",
+       "      <th>...</th>\n",
+       "      <th>reform_count_of_houses_500</th>\n",
+       "      <th>reform_house_population_1000</th>\n",
+       "      <th>reform_house_population_500</th>\n",
+       "      <th>reform_mean_floor_count_1000</th>\n",
+       "      <th>reform_mean_floor_count_500</th>\n",
+       "      <th>reform_mean_year_building_1000</th>\n",
+       "      <th>reform_mean_year_building_500</th>\n",
+       "      <th>total_square</th>\n",
+       "      <th>realty_type</th>\n",
+       "      <th>price_type</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>count</th>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>265196.000000</td>\n",
+       "      <td>252558.000000</td>\n",
+       "      <td>263084.000000</td>\n",
+       "      <td>249624.000000</td>\n",
+       "      <td>263553.000000</td>\n",
+       "      <td>250155.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "      <td>279792.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>mean</th>\n",
+       "      <td>54.364078</td>\n",
+       "      <td>47.763540</td>\n",
+       "      <td>2.709084</td>\n",
+       "      <td>40.605146</td>\n",
+       "      <td>81.596171</td>\n",
+       "      <td>133.285458</td>\n",
+       "      <td>0.037442</td>\n",
+       "      <td>0.885701</td>\n",
+       "      <td>2.046467</td>\n",
+       "      <td>3.748163</td>\n",
+       "      <td>...</td>\n",
+       "      <td>30.110661</td>\n",
+       "      <td>2042.541716</td>\n",
+       "      <td>644.610557</td>\n",
+       "      <td>7.051233</td>\n",
+       "      <td>7.360464</td>\n",
+       "      <td>1967.532599</td>\n",
+       "      <td>1967.988580</td>\n",
+       "      <td>507.833604</td>\n",
+       "      <td>54.974088</td>\n",
+       "      <td>0.016058</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>std</th>\n",
+       "      <td>4.245713</td>\n",
+       "      <td>17.044625</td>\n",
+       "      <td>4.202451</td>\n",
+       "      <td>53.293388</td>\n",
+       "      <td>105.193169</td>\n",
+       "      <td>172.290136</td>\n",
+       "      <td>0.391014</td>\n",
+       "      <td>6.858338</td>\n",
+       "      <td>14.801566</td>\n",
+       "      <td>25.679859</td>\n",
+       "      <td>...</td>\n",
+       "      <td>27.686234</td>\n",
+       "      <td>1359.884747</td>\n",
+       "      <td>445.699329</td>\n",
+       "      <td>3.542084</td>\n",
+       "      <td>4.231369</td>\n",
+       "      <td>45.807699</td>\n",
+       "      <td>54.110015</td>\n",
+       "      <td>1704.251771</td>\n",
+       "      <td>47.856417</td>\n",
+       "      <td>0.125700</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>min</th>\n",
+       "      <td>42.651897</td>\n",
+       "      <td>19.892178</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>5.100000</td>\n",
+       "      <td>10.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25%</th>\n",
+       "      <td>53.226600</td>\n",
+       "      <td>37.582988</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>7.000000</td>\n",
+       "      <td>16.000000</td>\n",
+       "      <td>28.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>10.000000</td>\n",
+       "      <td>932.000000</td>\n",
+       "      <td>290.000000</td>\n",
+       "      <td>4.591837</td>\n",
+       "      <td>4.619959</td>\n",
+       "      <td>1960.070000</td>\n",
+       "      <td>1959.890097</td>\n",
+       "      <td>65.900000</td>\n",
+       "      <td>10.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>50%</th>\n",
+       "      <td>55.679090</td>\n",
+       "      <td>39.702435</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>22.000000</td>\n",
+       "      <td>46.000000</td>\n",
+       "      <td>77.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>25.000000</td>\n",
+       "      <td>1949.000000</td>\n",
+       "      <td>602.000000</td>\n",
+       "      <td>6.368932</td>\n",
+       "      <td>6.395349</td>\n",
+       "      <td>1970.890411</td>\n",
+       "      <td>1971.647059</td>\n",
+       "      <td>128.737034</td>\n",
+       "      <td>10.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>75%</th>\n",
+       "      <td>56.306976</td>\n",
+       "      <td>55.957523</td>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>51.000000</td>\n",
+       "      <td>101.000000</td>\n",
+       "      <td>164.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>2.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>43.000000</td>\n",
+       "      <td>2978.000000</td>\n",
+       "      <td>936.000000</td>\n",
+       "      <td>8.698925</td>\n",
+       "      <td>9.100000</td>\n",
+       "      <td>1983.701754</td>\n",
+       "      <td>1986.950000</td>\n",
+       "      <td>336.000000</td>\n",
+       "      <td>110.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>max</th>\n",
+       "      <td>69.500740</td>\n",
+       "      <td>151.777000</td>\n",
+       "      <td>46.000000</td>\n",
+       "      <td>468.000000</td>\n",
+       "      <td>851.000000</td>\n",
+       "      <td>1392.000000</td>\n",
+       "      <td>30.000000</td>\n",
+       "      <td>586.000000</td>\n",
+       "      <td>949.000000</td>\n",
+       "      <td>1162.000000</td>\n",
+       "      <td>...</td>\n",
+       "      <td>289.000000</td>\n",
+       "      <td>18392.000000</td>\n",
+       "      <td>6105.000000</td>\n",
+       "      <td>53.717949</td>\n",
+       "      <td>221.666667</td>\n",
+       "      <td>2019.000000</td>\n",
+       "      <td>2020.000000</td>\n",
+       "      <td>40000.000000</td>\n",
+       "      <td>110.000000</td>\n",
+       "      <td>1.000000</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>8 rows × 70 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 lat            lng  osm_amenity_points_in_0.001  \\\n",
+       "count  279792.000000  279792.000000                279792.000000   \n",
+       "mean       54.364078      47.763540                     2.709084   \n",
+       "std         4.245713      17.044625                     4.202451   \n",
+       "min        42.651897      19.892178                     0.000000   \n",
+       "25%        53.226600      37.582988                     0.000000   \n",
+       "50%        55.679090      39.702435                     1.000000   \n",
+       "75%        56.306976      55.957523                     4.000000   \n",
+       "max        69.500740     151.777000                    46.000000   \n",
+       "\n",
+       "       osm_amenity_points_in_0.005  osm_amenity_points_in_0.0075  \\\n",
+       "count                279792.000000                 279792.000000   \n",
+       "mean                     40.605146                     81.596171   \n",
+       "std                      53.293388                    105.193169   \n",
+       "min                       0.000000                      0.000000   \n",
+       "25%                       7.000000                     16.000000   \n",
+       "50%                      22.000000                     46.000000   \n",
+       "75%                      51.000000                    101.000000   \n",
+       "max                     468.000000                    851.000000   \n",
+       "\n",
+       "       osm_amenity_points_in_0.01  osm_building_points_in_0.001  \\\n",
+       "count               279792.000000                 279792.000000   \n",
+       "mean                   133.285458                      0.037442   \n",
+       "std                    172.290136                      0.391014   \n",
+       "min                      0.000000                      0.000000   \n",
+       "25%                     28.000000                      0.000000   \n",
+       "50%                     77.000000                      0.000000   \n",
+       "75%                    164.000000                      0.000000   \n",
+       "max                   1392.000000                     30.000000   \n",
+       "\n",
+       "       osm_building_points_in_0.005  osm_building_points_in_0.0075  \\\n",
+       "count                 279792.000000                  279792.000000   \n",
+       "mean                       0.885701                       2.046467   \n",
+       "std                        6.858338                      14.801566   \n",
+       "min                        0.000000                       0.000000   \n",
+       "25%                        0.000000                       0.000000   \n",
+       "50%                        0.000000                       0.000000   \n",
+       "75%                        0.000000                       1.000000   \n",
+       "max                      586.000000                     949.000000   \n",
+       "\n",
+       "       osm_building_points_in_0.01  ...  reform_count_of_houses_500  \\\n",
+       "count                279792.000000  ...               279792.000000   \n",
+       "mean                      3.748163  ...                   30.110661   \n",
+       "std                      25.679859  ...                   27.686234   \n",
+       "min                       0.000000  ...                    0.000000   \n",
+       "25%                       0.000000  ...                   10.000000   \n",
+       "50%                       0.000000  ...                   25.000000   \n",
+       "75%                       2.000000  ...                   43.000000   \n",
+       "max                    1162.000000  ...                  289.000000   \n",
+       "\n",
+       "       reform_house_population_1000  reform_house_population_500  \\\n",
+       "count                 265196.000000                252558.000000   \n",
+       "mean                    2042.541716                   644.610557   \n",
+       "std                     1359.884747                   445.699329   \n",
+       "min                        0.000000                     0.000000   \n",
+       "25%                      932.000000                   290.000000   \n",
+       "50%                     1949.000000                   602.000000   \n",
+       "75%                     2978.000000                   936.000000   \n",
+       "max                    18392.000000                  6105.000000   \n",
+       "\n",
+       "       reform_mean_floor_count_1000  reform_mean_floor_count_500  \\\n",
+       "count                 263084.000000                249624.000000   \n",
+       "mean                       7.051233                     7.360464   \n",
+       "std                        3.542084                     4.231369   \n",
+       "min                        0.000000                     0.000000   \n",
+       "25%                        4.591837                     4.619959   \n",
+       "50%                        6.368932                     6.395349   \n",
+       "75%                        8.698925                     9.100000   \n",
+       "max                       53.717949                   221.666667   \n",
+       "\n",
+       "       reform_mean_year_building_1000  reform_mean_year_building_500  \\\n",
+       "count                   263553.000000                  250155.000000   \n",
+       "mean                      1967.532599                    1967.988580   \n",
+       "std                         45.807699                      54.110015   \n",
+       "min                          1.000000                       1.000000   \n",
+       "25%                       1960.070000                    1959.890097   \n",
+       "50%                       1970.890411                    1971.647059   \n",
+       "75%                       1983.701754                    1986.950000   \n",
+       "max                       2019.000000                    2020.000000   \n",
+       "\n",
+       "        total_square    realty_type     price_type  \n",
+       "count  279792.000000  279792.000000  279792.000000  \n",
+       "mean      507.833604      54.974088       0.016058  \n",
+       "std      1704.251771      47.856417       0.125700  \n",
+       "min         5.100000      10.000000       0.000000  \n",
+       "25%        65.900000      10.000000       0.000000  \n",
+       "50%       128.737034      10.000000       0.000000  \n",
+       "75%       336.000000     110.000000       0.000000  \n",
+       "max     40000.000000     110.000000       1.000000  \n",
+       "\n",
+       "[8 rows x 70 columns]"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_data.describe()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def check_features(df):\n",
+    "    return pd.DataFrame({'unique_values': df.nunique(),'type': df.dtypes,'pct_missing': df.isna().sum()/len(df) * 100}).sort_values(by = 'pct_missing', ascending=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "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>floor</th>\n",
+       "      <th>reform_mean_floor_count_500</th>\n",
+       "      <th>reform_mean_year_building_500</th>\n",
+       "      <th>reform_house_population_500</th>\n",
+       "      <th>reform_mean_floor_count_1000</th>\n",
+       "      <th>reform_mean_year_building_1000</th>\n",
+       "      <th>reform_house_population_1000</th>\n",
+       "      <th>street</th>\n",
+       "      <th>osm_city_nearest_population</th>\n",
+       "      <th>region</th>\n",
+       "      <th>...</th>\n",
+       "      <th>osm_finance_points_in_0.005</th>\n",
+       "      <th>osm_finance_points_in_0.001</th>\n",
+       "      <th>osm_culture_points_in_0.01</th>\n",
+       "      <th>osm_culture_points_in_0.0075</th>\n",
+       "      <th>osm_culture_points_in_0.005</th>\n",
+       "      <th>osm_culture_points_in_0.001</th>\n",
+       "      <th>osm_crossing_points_in_0.01</th>\n",
+       "      <th>osm_crossing_points_in_0.0075</th>\n",
+       "      <th>osm_crossing_points_in_0.005</th>\n",
+       "      <th>price_type</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>unique_values</th>\n",
+       "      <td>206</td>\n",
+       "      <td>17121</td>\n",
+       "      <td>43143</td>\n",
+       "      <td>2366</td>\n",
+       "      <td>49017</td>\n",
+       "      <td>76044</td>\n",
+       "      <td>6206</td>\n",
+       "      <td>28841</td>\n",
+       "      <td>169</td>\n",
+       "      <td>49</td>\n",
+       "      <td>...</td>\n",
+       "      <td>29</td>\n",
+       "      <td>7</td>\n",
+       "      <td>216</td>\n",
+       "      <td>159</td>\n",
+       "      <td>111</td>\n",
+       "      <td>16</td>\n",
+       "      <td>268</td>\n",
+       "      <td>191</td>\n",
+       "      <td>108</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>type</th>\n",
+       "      <td>object</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>object</td>\n",
+       "      <td>float64</td>\n",
+       "      <td>object</td>\n",
+       "      <td>...</td>\n",
+       "      <td>uint8</td>\n",
+       "      <td>uint8</td>\n",
+       "      <td>uint16</td>\n",
+       "      <td>uint16</td>\n",
+       "      <td>uint8</td>\n",
+       "      <td>uint8</td>\n",
+       "      <td>uint16</td>\n",
+       "      <td>uint8</td>\n",
+       "      <td>uint8</td>\n",
+       "      <td>uint8</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>pct_missing</th>\n",
+       "      <td>62.9886</td>\n",
+       "      <td>10.7823</td>\n",
+       "      <td>10.5925</td>\n",
+       "      <td>9.73366</td>\n",
+       "      <td>5.97158</td>\n",
+       "      <td>5.80395</td>\n",
+       "      <td>5.21673</td>\n",
+       "      <td>0.573998</td>\n",
+       "      <td>0.0196575</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>3 rows × 77 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                 floor reform_mean_floor_count_500  \\\n",
+       "unique_values      206                       17121   \n",
+       "type            object                     float64   \n",
+       "pct_missing    62.9886                     10.7823   \n",
+       "\n",
+       "              reform_mean_year_building_500 reform_house_population_500  \\\n",
+       "unique_values                         43143                        2366   \n",
+       "type                                float64                     float64   \n",
+       "pct_missing                         10.5925                     9.73366   \n",
+       "\n",
+       "              reform_mean_floor_count_1000 reform_mean_year_building_1000  \\\n",
+       "unique_values                        49017                          76044   \n",
+       "type                               float64                        float64   \n",
+       "pct_missing                        5.97158                        5.80395   \n",
+       "\n",
+       "              reform_house_population_1000    street  \\\n",
+       "unique_values                         6206     28841   \n",
+       "type                               float64    object   \n",
+       "pct_missing                        5.21673  0.573998   \n",
+       "\n",
+       "              osm_city_nearest_population  region  ...  \\\n",
+       "unique_values                         169      49  ...   \n",
+       "type                              float64  object  ...   \n",
+       "pct_missing                     0.0196575       0  ...   \n",
+       "\n",
+       "              osm_finance_points_in_0.005 osm_finance_points_in_0.001  \\\n",
+       "unique_values                          29                           7   \n",
+       "type                                uint8                       uint8   \n",
+       "pct_missing                             0                           0   \n",
+       "\n",
+       "              osm_culture_points_in_0.01 osm_culture_points_in_0.0075  \\\n",
+       "unique_values                        216                          159   \n",
+       "type                              uint16                       uint16   \n",
+       "pct_missing                            0                            0   \n",
+       "\n",
+       "              osm_culture_points_in_0.005 osm_culture_points_in_0.001  \\\n",
+       "unique_values                         111                          16   \n",
+       "type                                uint8                       uint8   \n",
+       "pct_missing                             0                           0   \n",
+       "\n",
+       "              osm_crossing_points_in_0.01 osm_crossing_points_in_0.0075  \\\n",
+       "unique_values                         268                           191   \n",
+       "type                               uint16                         uint8   \n",
+       "pct_missing                             0                             0   \n",
+       "\n",
+       "              osm_crossing_points_in_0.005 price_type  \n",
+       "unique_values                          108          2  \n",
+       "type                                 uint8      uint8  \n",
+       "pct_missing                              0          0  \n",
+       "\n",
+       "[3 rows x 77 columns]"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "check_features(train_data).T"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([nan, 3.0, 4.0, -1.0, 1.0, 14.0, 2.0, 8.0, -2.0, 6.0, 10.0, 5.0,\n",
+       "       16.0, 19.0, 7.0, 9.0, 58.0, 24.0, 18.0, 26.0, 17.0, 48.0, 11.0,\n",
+       "       -3.0, 15.0, 22.0, 60.0, 12.0, 21.0, 35.0, 28.0, 38.0, 39.0, 13.0,\n",
+       "       81.0, 44.0, 82.0, 25.0, 45.0, 47.0, 23.0, 37.0, 29.0, 113.0, 78.0,\n",
+       "       42.0, 69.0, 27.0, 46.0, 53.0, 80.0, 70.0, 76.0, 64.0, 30.0, 73.0,\n",
+       "       77.0, 52.0, 67.0, 65.0, 20.0, 40.0, 49.0, 75.0, 93.0, 94.0, 91.0,\n",
+       "       72.0, 79.0, 84.0, 92.0, 33.0, 66.0, 90.0, 31.0, 36.0, 61.0, 71.0,\n",
+       "       68.0, 51.0, 97.0, 43.0, 95.0, 85.0, 50.0, 0.0, 62.0, 54.0, 74.0,\n",
+       "       57.0, 41.0, 34.0, 59.0, 56.0, 123.0, 55.0, 83.0, '27.0', '1.0',\n",
+       "       '5.0', '-1.0', '67.0', '2.0', '0.0', '4.0', '6.0', '3.0', '15.0',\n",
+       "       '10.0', '11.0', '30.0', '12.0', '-2.0', '14.0', '36.0', '8.0',\n",
+       "       '50.0', '17.0', '19.0', '37.0', '68.0', '7.0', '42.0', '9.0',\n",
+       "       '16.0', '20.0', '53.0', '91.0', '84.0', '38.0', '21.0', '48.0',\n",
+       "       '22.0', '23.0', '1', '18.0', 'подвал, 1', '2', 'подвал',\n",
+       "       'цоколь, 1', '1,2,антресоль', 'цоколь', '4', '5', 'тех.этаж (6)',\n",
+       "       '3', 'Подвал', 'Цоколь', '10', 'фактически на уровне 1 этажа', '6',\n",
+       "       '1,2,3', '1, подвал', '1,2,3,4', '1,2', '1,2,3,4,5', '5, мансарда',\n",
+       "       '1-й, подвал', '12', '15', '13', '1, подвал, антресоль', 'мезонин',\n",
+       "       'подвал, 1-3', '8', '7', '1 (Цокольный этаж)',\n",
+       "       '3, Мансарда (4 эт)', 'подвал,1', '1, антресоль', '1-3',\n",
+       "       'мансарда (4эт)', '1, 2.', '9', 'подвал , 1 ', '1, 2',\n",
+       "       'подвал, 1,2,3', '1 + подвал (без отделки)', 'мансарда', '2,3',\n",
+       "       '4, 5', '1-й, 2-й', '18', '1 этаж, подвал', '1, цоколь',\n",
+       "       'подвал, 1-7, техэтаж', '3 (антресоль)', '1, 2, 3',\n",
+       "       'Цоколь, 1,2(мансарда)', 'подвал, 3. 4 этаж', 'подвал, 1-4 этаж',\n",
+       "       'подва, 1.2 этаж', '2, 3', '-1', '1.2', '11', '36', '7,8',\n",
+       "       '1 этаж', '1-й', '3 этаж', '4 этаж', '5 этаж', 'подвал,1,2,3,4,5',\n",
+       "       '29', 'подвал, цоколь, 1 этаж', '3, мансарда'], dtype=object)"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_data['floor'].unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Вручную обработали столбец с этажами\n",
+    "for df in [train_data, test_data]:\n",
+    "    df.replace('1', 1, inplace=True)\n",
+    "    df.replace('1.0', 1, inplace=True)\n",
+    "\n",
+    "train_data['floor'] = train_data.apply(lambda row: 1 if row['floor'] == 1 else 0, axis=1)\n",
+    "test_data['floor'] = test_data.apply(lambda row: 1 if row['floor'] == 1 else 0, axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# вручную удалила повторяющиеся признаки с разным метражом, оставив только значение \"in 0.01\" для osm и \"1000\" для reform, чтобы матрица корреляции помещалась на экране\n",
+    "columns_for_pearson = [\n",
+    "                       'per_square_meter_price', \n",
+    "                       'city', 'floor',\n",
+    "                       'osm_amenity_points_in_0.01', \n",
+    "                       'osm_building_points_in_0.01', \n",
+    "                       'osm_catering_points_in_0.01', \n",
+    "                       'osm_city_closest_dist', \n",
+    "                       'osm_city_nearest_name', \n",
+    "                       'osm_city_nearest_population',\n",
+    "                       'osm_crossing_closest_dist', \n",
+    "                       'osm_crossing_points_in_0.01', \n",
+    "                       'osm_culture_points_in_0.01',\n",
+    "                       'osm_healthcare_points_in_0.01', \n",
+    "                       'osm_historic_points_in_0.01', \n",
+    "                       'osm_hotels_points_in_0.01',\n",
+    "                       'osm_leisure_points_in_0.01', \n",
+    "                       'osm_offices_points_in_0.01', \n",
+    "                       'osm_shops_points_in_0.01', \n",
+    "                       'osm_subway_closest_dist',\n",
+    "                       'osm_train_stop_closest_dist', \n",
+    "                       'osm_train_stop_points_in_0.01', \n",
+    "                       'osm_transport_stop_closest_dist',\n",
+    "                       'osm_transport_stop_points_in_0.01', \n",
+    "                       'reform_count_of_houses_1000', \n",
+    "                       'reform_house_population_1000',\n",
+    "                       'reform_mean_floor_count_1000', \n",
+    "                       'reform_mean_year_building_1000', \n",
+    "                       'region', \n",
+    "                       'total_square', \n",
+    "                       'street', \n",
+    "                       'date', \n",
+    "                       'realty_type', \n",
+    "                       'price_type']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "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>feature</th>\n",
+       "      <th>pearson</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>per_square_meter_price</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>osm_city_nearest_population</td>\n",
+       "      <td>0.55</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>osm_amenity_points_in_0.01</td>\n",
+       "      <td>0.48</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>osm_healthcare_points_in_0.01</td>\n",
+       "      <td>0.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>osm_catering_points_in_0.01</td>\n",
+       "      <td>0.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>osm_leisure_points_in_0.01</td>\n",
+       "      <td>0.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>osm_shops_points_in_0.01</td>\n",
+       "      <td>0.44</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>osm_transport_stop_points_in_0.01</td>\n",
+       "      <td>0.43</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>osm_crossing_points_in_0.01</td>\n",
+       "      <td>0.43</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>osm_offices_points_in_0.01</td>\n",
+       "      <td>0.42</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                              feature  pearson\n",
+       "0              per_square_meter_price     1.00\n",
+       "6         osm_city_nearest_population     0.55\n",
+       "2          osm_amenity_points_in_0.01     0.48\n",
+       "10      osm_healthcare_points_in_0.01     0.46\n",
+       "4         osm_catering_points_in_0.01     0.46\n",
+       "13         osm_leisure_points_in_0.01     0.46\n",
+       "15           osm_shops_points_in_0.01     0.44\n",
+       "20  osm_transport_stop_points_in_0.01     0.43\n",
+       "8         osm_crossing_points_in_0.01     0.43\n",
+       "14         osm_offices_points_in_0.01     0.42"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Находим признаки, имеющие максимальное значение коэффициента корреляции Пирсона с целевой переменной. \n",
+    "# В качестве отсечки выбрано значение 0.4 по модулю\n",
+    "pearson = train_data[columns_for_pearson].corr().round(2)\n",
+    "pearson_max_corr = (\n",
+    "    pearson['per_square_meter_price'].to_frame().reset_index()\n",
+    "    .rename(columns={'per_square_meter_price':'pearson', 'index':'feature'})\n",
+    "    .sort_values(by='pearson', ascending=False)\n",
+    "    .query('pearson > 0.4 or pearson < -0.4')\n",
+    "    )\n",
+    "pearson_max_corr"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# fig, ax = plt.subplots(figsize=(20, 20))\n",
+    "# sns.heatmap(train_data[columns_for_pearson].corr().round(2), annot=True, square=True, cmap='mako')\n",
+    "# ax.set_title(label = 'МАТРИЦА КОРРЕЛЯЦИИ ПРИЗНАКОВ $r$', fontdict={'fontsize': 15, 'fontweight': 'bold'})\n",
+    "# plt.show();"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Высокая взаимная корреляция (> 0.8) у следующих переменных:\n",
+    "- amenity и catering, healthcare, office, shop\n",
+    "- catering и shop\n",
+    "- office и shop, catering\n",
+    "- healthcare и catering, office, shop,\n",
+    "- transport и crossing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# убрали city и street(закодирована)\n",
+    "\n",
+    "columns_for_phik = [\n",
+    "  'per_square_meter_price',\n",
+    " 'floor',\n",
+    " 'osm_amenity_points_in_0.01',\n",
+    " 'osm_building_points_in_0.01',\n",
+    " 'osm_catering_points_in_0.01',\n",
+    " 'osm_city_closest_dist',\n",
+    " 'osm_city_nearest_name',\n",
+    " 'osm_city_nearest_population',\n",
+    " 'osm_crossing_closest_dist',\n",
+    " 'osm_crossing_points_in_0.01',\n",
+    " 'osm_culture_points_in_0.01',\n",
+    " 'osm_healthcare_points_in_0.01',\n",
+    " 'osm_historic_points_in_0.01',\n",
+    " 'osm_hotels_points_in_0.01',\n",
+    " 'osm_leisure_points_in_0.01',\n",
+    " 'osm_offices_points_in_0.01',\n",
+    " 'osm_shops_points_in_0.01',\n",
+    " 'osm_subway_closest_dist',\n",
+    " 'osm_train_stop_closest_dist',\n",
+    " 'osm_train_stop_points_in_0.01',\n",
+    " 'osm_transport_stop_closest_dist',\n",
+    " 'osm_transport_stop_points_in_0.01',\n",
+    " 'reform_count_of_houses_1000',\n",
+    " 'reform_house_population_1000',\n",
+    " 'reform_mean_floor_count_1000',\n",
+    " 'reform_mean_year_building_1000',\n",
+    " 'region',\n",
+    " 'total_square',\n",
+    " 'date',\n",
+    " 'realty_type',\n",
+    " 'price_type']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "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>per_square_meter_price</th>\n",
+       "      <th>floor</th>\n",
+       "      <th>osm_amenity_points_in_0.01</th>\n",
+       "      <th>osm_building_points_in_0.01</th>\n",
+       "      <th>osm_catering_points_in_0.01</th>\n",
+       "      <th>osm_city_closest_dist</th>\n",
+       "      <th>osm_city_nearest_name</th>\n",
+       "      <th>osm_city_nearest_population</th>\n",
+       "      <th>osm_crossing_closest_dist</th>\n",
+       "      <th>osm_crossing_points_in_0.01</th>\n",
+       "      <th>...</th>\n",
+       "      <th>osm_transport_stop_points_in_0.01</th>\n",
+       "      <th>reform_count_of_houses_1000</th>\n",
+       "      <th>reform_house_population_1000</th>\n",
+       "      <th>reform_mean_floor_count_1000</th>\n",
+       "      <th>reform_mean_year_building_1000</th>\n",
+       "      <th>region</th>\n",
+       "      <th>total_square</th>\n",
+       "      <th>date</th>\n",
+       "      <th>realty_type</th>\n",
+       "      <th>price_type</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>per_square_meter_price</th>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.46</td>\n",
+       "      <td>0.16</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.05</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>floor</th>\n",
+       "      <td>0.18</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.10</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_amenity_points_in_0.01</th>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.96</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>0.49</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.82</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.69</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.62</td>\n",
+       "      <td>0.25</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.45</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.22</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_building_points_in_0.01</th>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_catering_points_in_0.01</th>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.96</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.51</td>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.60</td>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_city_closest_dist</th>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.73</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_city_nearest_name</th>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.51</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>0.64</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.62</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.59</td>\n",
+       "      <td>0.44</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.37</td>\n",
+       "      <td>0.30</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_city_nearest_population</th>\n",
+       "      <td>0.55</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.49</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.60</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.49</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.24</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.97</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_crossing_closest_dist</th>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.73</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_crossing_points_in_0.01</th>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.82</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.64</td>\n",
+       "      <td>0.60</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.77</td>\n",
+       "      <td>0.67</td>\n",
+       "      <td>0.59</td>\n",
+       "      <td>0.41</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.09</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_culture_points_in_0.01</th>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.61</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.60</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.46</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.62</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.34</td>\n",
+       "      <td>0.37</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.39</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.04</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_healthcare_points_in_0.01</th>\n",
+       "      <td>0.46</td>\n",
+       "      <td>0.10</td>\n",
+       "      <td>0.85</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.80</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>0.49</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.81</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.68</td>\n",
+       "      <td>0.53</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.46</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.04</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_historic_points_in_0.01</th>\n",
+       "      <td>0.38</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.75</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.73</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.45</td>\n",
+       "      <td>0.35</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.76</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.33</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.05</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_hotels_points_in_0.01</th>\n",
+       "      <td>0.37</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.44</td>\n",
+       "      <td>0.42</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.71</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.50</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.36</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.21</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_leisure_points_in_0.01</th>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.10</td>\n",
+       "      <td>0.72</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.68</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.50</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.71</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.58</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>0.39</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.09</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_offices_points_in_0.01</th>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.89</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.87</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.76</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.61</td>\n",
+       "      <td>0.56</td>\n",
+       "      <td>0.59</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_shops_points_in_0.01</th>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.96</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.92</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.49</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.79</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.67</td>\n",
+       "      <td>0.64</td>\n",
+       "      <td>0.65</td>\n",
+       "      <td>0.25</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.20</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_subway_closest_dist</th>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.41</td>\n",
+       "      <td>0.99</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.32</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.91</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>0.04</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_train_stop_closest_dist</th>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.73</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.79</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.43</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_train_stop_points_in_0.01</th>\n",
+       "      <td>0.27</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.33</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.34</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.32</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.46</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.25</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.26</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.03</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_transport_stop_closest_dist</th>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.73</td>\n",
+       "      <td>0.25</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.88</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>osm_transport_stop_points_in_0.01</th>\n",
+       "      <td>0.46</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.69</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.62</td>\n",
+       "      <td>0.49</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.77</td>\n",
+       "      <td>...</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.45</td>\n",
+       "      <td>0.33</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.07</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>reform_count_of_houses_1000</th>\n",
+       "      <td>0.16</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.63</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.57</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.67</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>0.38</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.43</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>reform_house_population_1000</th>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.10</td>\n",
+       "      <td>0.62</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.60</td>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.48</td>\n",
+       "      <td>0.24</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.59</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.45</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.36</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.16</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>reform_mean_floor_count_1000</th>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.15</td>\n",
+       "      <td>0.25</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.59</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.41</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.33</td>\n",
+       "      <td>0.38</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.05</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>reform_mean_year_building_1000</th>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.44</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.37</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>region</th>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.23</td>\n",
+       "      <td>0.45</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>0.40</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.97</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.55</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.52</td>\n",
+       "      <td>0.43</td>\n",
+       "      <td>0.36</td>\n",
+       "      <td>0.47</td>\n",
+       "      <td>0.37</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.27</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>total_square</th>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.12</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.01</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <td>0.11</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.08</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.17</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.10</td>\n",
+       "      <td>0.02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>realty_type</th>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.18</td>\n",
+       "      <td>0.03</td>\n",
+       "      <td>0.19</td>\n",
+       "      <td>0.06</td>\n",
+       "      <td>0.37</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.31</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.14</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.28</td>\n",
+       "      <td>0.04</td>\n",
+       "      <td>0.10</td>\n",
+       "      <td>1.00</td>\n",
+       "      <td>0.02</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>price_type</th>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.22</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.20</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.30</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.09</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.07</td>\n",
+       "      <td>0.13</td>\n",
+       "      <td>0.16</td>\n",
+       "      <td>0.05</td>\n",
+       "      <td>0.00</td>\n",
+       "      <td>0.27</td>\n",
+       "      <td>0.01</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>0.02</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>31 rows × 31 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                   per_square_meter_price  floor  \\\n",
+       "per_square_meter_price                               1.00   0.18   \n",
+       "floor                                                0.18   1.00   \n",
+       "osm_amenity_points_in_0.01                           0.48   0.07   \n",
+       "osm_building_points_in_0.01                          0.02   0.01   \n",
+       "osm_catering_points_in_0.01                          0.48   0.06   \n",
+       "osm_city_closest_dist                                0.05   0.08   \n",
+       "osm_city_nearest_name                                0.57   0.28   \n",
+       "osm_city_nearest_population                          0.55   0.15   \n",
+       "osm_crossing_closest_dist                            0.00   0.01   \n",
+       "osm_crossing_points_in_0.01                          0.57   0.14   \n",
+       "osm_culture_points_in_0.01                           0.31   0.04   \n",
+       "osm_healthcare_points_in_0.01                        0.46   0.10   \n",
+       "osm_historic_points_in_0.01                          0.38   0.05   \n",
+       "osm_hotels_points_in_0.01                            0.37   0.06   \n",
+       "osm_leisure_points_in_0.01                           0.47   0.10   \n",
+       "osm_offices_points_in_0.01                           0.47   0.08   \n",
+       "osm_shops_points_in_0.01                             0.47   0.07   \n",
+       "osm_subway_closest_dist                              0.18   0.09   \n",
+       "osm_train_stop_closest_dist                          0.02   0.02   \n",
+       "osm_train_stop_points_in_0.01                        0.27   0.02   \n",
+       "osm_transport_stop_closest_dist                      0.00   0.01   \n",
+       "osm_transport_stop_points_in_0.01                    0.46   0.12   \n",
+       "reform_count_of_houses_1000                          0.16   0.03   \n",
+       "reform_house_population_1000                         0.19   0.10   \n",
+       "reform_mean_floor_count_1000                         0.23   0.15   \n",
+       "reform_mean_year_building_1000                       0.03   0.00   \n",
+       "region                                               0.52   0.23   \n",
+       "total_square                                         0.02   0.01   \n",
+       "date                                                 0.11   0.22   \n",
+       "realty_type                                          0.18   0.04   \n",
+       "price_type                                           0.05   0.00   \n",
+       "\n",
+       "                                   osm_amenity_points_in_0.01  \\\n",
+       "per_square_meter_price                                   0.48   \n",
+       "floor                                                    0.07   \n",
+       "osm_amenity_points_in_0.01                               1.00   \n",
+       "osm_building_points_in_0.01                              0.02   \n",
+       "osm_catering_points_in_0.01                              0.96   \n",
+       "osm_city_closest_dist                                    0.07   \n",
+       "osm_city_nearest_name                                    0.56   \n",
+       "osm_city_nearest_population                              0.49   \n",
+       "osm_crossing_closest_dist                                0.00   \n",
+       "osm_crossing_points_in_0.01                              0.82   \n",
+       "osm_culture_points_in_0.01                               0.61   \n",
+       "osm_healthcare_points_in_0.01                            0.85   \n",
+       "osm_historic_points_in_0.01                              0.75   \n",
+       "osm_hotels_points_in_0.01                                0.88   \n",
+       "osm_leisure_points_in_0.01                               0.72   \n",
+       "osm_offices_points_in_0.01                               0.89   \n",
+       "osm_shops_points_in_0.01                                 0.96   \n",
+       "osm_subway_closest_dist                                  0.14   \n",
+       "osm_train_stop_closest_dist                              0.03   \n",
+       "osm_train_stop_points_in_0.01                            0.33   \n",
+       "osm_transport_stop_closest_dist                          0.00   \n",
+       "osm_transport_stop_points_in_0.01                        0.69   \n",
+       "reform_count_of_houses_1000                              0.63   \n",
+       "reform_house_population_1000                             0.62   \n",
+       "reform_mean_floor_count_1000                             0.25   \n",
+       "reform_mean_year_building_1000                           0.04   \n",
+       "region                                                   0.45   \n",
+       "total_square                                             0.05   \n",
+       "date                                                     0.07   \n",
+       "realty_type                                              0.18   \n",
+       "price_type                                               0.22   \n",
+       "\n",
+       "                                   osm_building_points_in_0.01  \\\n",
+       "per_square_meter_price                                    0.02   \n",
+       "floor                                                     0.01   \n",
+       "osm_amenity_points_in_0.01                                0.02   \n",
+       "osm_building_points_in_0.01                               1.00   \n",
+       "osm_catering_points_in_0.01                               0.02   \n",
+       "osm_city_closest_dist                                     0.00   \n",
+       "osm_city_nearest_name                                     0.28   \n",
+       "osm_city_nearest_population                               0.17   \n",
+       "osm_crossing_closest_dist                                 0.00   \n",
+       "osm_crossing_points_in_0.01                               0.11   \n",
+       "osm_culture_points_in_0.01                                0.00   \n",
+       "osm_healthcare_points_in_0.01                             0.02   \n",
+       "osm_historic_points_in_0.01                               0.01   \n",
+       "osm_hotels_points_in_0.01                                 0.00   \n",
+       "osm_leisure_points_in_0.01                                0.03   \n",
+       "osm_offices_points_in_0.01                                0.02   \n",
+       "osm_shops_points_in_0.01                                  0.02   \n",
+       "osm_subway_closest_dist                                   0.12   \n",
+       "osm_train_stop_closest_dist                               0.00   \n",
+       "osm_train_stop_points_in_0.01                             0.00   \n",
+       "osm_transport_stop_closest_dist                           0.00   \n",
+       "osm_transport_stop_points_in_0.01                         0.04   \n",
+       "reform_count_of_houses_1000                               0.03   \n",
+       "reform_house_population_1000                              0.03   \n",
+       "reform_mean_floor_count_1000                              0.03   \n",
+       "reform_mean_year_building_1000                            0.00   \n",
+       "region                                                    0.22   \n",
+       "total_square                                              0.00   \n",
+       "date                                                      0.01   \n",
+       "realty_type                                               0.03   \n",
+       "price_type                                                0.01   \n",
+       "\n",
+       "                                   osm_catering_points_in_0.01  \\\n",
+       "per_square_meter_price                                    0.48   \n",
+       "floor                                                     0.06   \n",
+       "osm_amenity_points_in_0.01                                0.96   \n",
+       "osm_building_points_in_0.01                               0.02   \n",
+       "osm_catering_points_in_0.01                               1.00   \n",
+       "osm_city_closest_dist                                     0.05   \n",
+       "osm_city_nearest_name                                     0.51   \n",
+       "osm_city_nearest_population                               0.47   \n",
+       "osm_crossing_closest_dist                                 0.00   \n",
+       "osm_crossing_points_in_0.01                               0.80   \n",
+       "osm_culture_points_in_0.01                                0.60   \n",
+       "osm_healthcare_points_in_0.01                             0.80   \n",
+       "osm_historic_points_in_0.01                               0.73   \n",
+       "osm_hotels_points_in_0.01                                 0.88   \n",
+       "osm_leisure_points_in_0.01                                0.68   \n",
+       "osm_offices_points_in_0.01                                0.87   \n",
+       "osm_shops_points_in_0.01                                  0.92   \n",
+       "osm_subway_closest_dist                                   0.12   \n",
+       "osm_train_stop_closest_dist                               0.02   \n",
+       "osm_train_stop_points_in_0.01                             0.34   \n",
+       "osm_transport_stop_closest_dist                           0.00   \n",
+       "osm_transport_stop_points_in_0.01                         0.63   \n",
+       "reform_count_of_houses_1000                               0.57   \n",
+       "reform_house_population_1000                              0.60   \n",
+       "reform_mean_floor_count_1000                              0.23   \n",
+       "reform_mean_year_building_1000                            0.03   \n",
+       "region                                                    0.40   \n",
+       "total_square                                              0.05   \n",
+       "date                                                      0.07   \n",
+       "realty_type                                               0.19   \n",
+       "price_type                                                0.20   \n",
+       "\n",
+       "                                   osm_city_closest_dist  \\\n",
+       "per_square_meter_price                              0.05   \n",
+       "floor                                               0.08   \n",
+       "osm_amenity_points_in_0.01                          0.07   \n",
+       "osm_building_points_in_0.01                         0.00   \n",
+       "osm_catering_points_in_0.01                         0.05   \n",
+       "osm_city_closest_dist                               1.00   \n",
+       "osm_city_nearest_name                               0.80   \n",
+       "osm_city_nearest_population                         0.11   \n",
+       "osm_crossing_closest_dist                           0.73   \n",
+       "osm_crossing_points_in_0.01                         0.22   \n",
+       "osm_culture_points_in_0.01                          0.01   \n",
+       "osm_healthcare_points_in_0.01                       0.07   \n",
+       "osm_historic_points_in_0.01                         0.04   \n",
+       "osm_hotels_points_in_0.01                           0.03   \n",
+       "osm_leisure_points_in_0.01                          0.07   \n",
+       "osm_offices_points_in_0.01                          0.05   \n",
+       "osm_shops_points_in_0.01                            0.07   \n",
+       "osm_subway_closest_dist                             0.41   \n",
+       "osm_train_stop_closest_dist                         0.73   \n",
+       "osm_train_stop_points_in_0.01                       0.01   \n",
+       "osm_transport_stop_closest_dist                     0.73   \n",
+       "osm_transport_stop_points_in_0.01                   0.15   \n",
+       "reform_count_of_houses_1000                         0.09   \n",
+       "reform_house_population_1000                        0.11   \n",
+       "reform_mean_floor_count_1000                        0.13   \n",
+       "reform_mean_year_building_1000                      0.00   \n",
+       "region                                              0.40   \n",
+       "total_square                                        0.00   \n",
+       "date                                                0.02   \n",
+       "realty_type                                         0.06   \n",
+       "price_type                                          0.01   \n",
+       "\n",
+       "                                   osm_city_nearest_name  \\\n",
+       "per_square_meter_price                              0.57   \n",
+       "floor                                               0.28   \n",
+       "osm_amenity_points_in_0.01                          0.56   \n",
+       "osm_building_points_in_0.01                         0.28   \n",
+       "osm_catering_points_in_0.01                         0.51   \n",
+       "osm_city_closest_dist                               0.80   \n",
+       "osm_city_nearest_name                               1.00   \n",
+       "osm_city_nearest_population                         1.00   \n",
+       "osm_crossing_closest_dist                           0.42   \n",
+       "osm_crossing_points_in_0.01                         0.64   \n",
+       "osm_culture_points_in_0.01                          0.46   \n",
+       "osm_healthcare_points_in_0.01                       0.56   \n",
+       "osm_historic_points_in_0.01                         0.45   \n",
+       "osm_hotels_points_in_0.01                           0.44   \n",
+       "osm_leisure_points_in_0.01                          0.57   \n",
+       "osm_offices_points_in_0.01                          0.57   \n",
+       "osm_shops_points_in_0.01                            0.57   \n",
+       "osm_subway_closest_dist                             0.99   \n",
+       "osm_train_stop_closest_dist                         0.88   \n",
+       "osm_train_stop_points_in_0.01                       0.32   \n",
+       "osm_transport_stop_closest_dist                     0.25   \n",
+       "osm_transport_stop_points_in_0.01                   0.62   \n",
+       "reform_count_of_houses_1000                         0.55   \n",
+       "reform_house_population_1000                        0.48   \n",
+       "reform_mean_floor_count_1000                        0.59   \n",
+       "reform_mean_year_building_1000                      0.44   \n",
+       "region                                              1.00   \n",
+       "total_square                                        0.12   \n",
+       "date                                                0.22   \n",
+       "realty_type                                         0.37   \n",
+       "price_type                                          0.30   \n",
+       "\n",
+       "                                   osm_city_nearest_population  \\\n",
+       "per_square_meter_price                                    0.55   \n",
+       "floor                                                     0.15   \n",
+       "osm_amenity_points_in_0.01                                0.49   \n",
+       "osm_building_points_in_0.01                               0.17   \n",
+       "osm_catering_points_in_0.01                               0.47   \n",
+       "osm_city_closest_dist                                     0.11   \n",
+       "osm_city_nearest_name                                     1.00   \n",
+       "osm_city_nearest_population                               1.00   \n",
+       "osm_crossing_closest_dist                                 0.00   \n",
+       "osm_crossing_points_in_0.01                               0.60   \n",
+       "osm_culture_points_in_0.01                                0.22   \n",
+       "osm_healthcare_points_in_0.01                             0.49   \n",
+       "osm_historic_points_in_0.01                               0.35   \n",
+       "osm_hotels_points_in_0.01                                 0.42   \n",
+       "osm_leisure_points_in_0.01                                0.50   \n",
+       "osm_offices_points_in_0.01                                0.52   \n",
+       "osm_shops_points_in_0.01                                  0.49   \n",
+       "osm_subway_closest_dist                                   0.31   \n",
+       "osm_train_stop_closest_dist                               0.03   \n",
+       "osm_train_stop_points_in_0.01                             0.29   \n",
+       "osm_transport_stop_closest_dist                           0.01   \n",
+       "osm_transport_stop_points_in_0.01                         0.49   \n",
+       "reform_count_of_houses_1000                               0.20   \n",
+       "reform_house_population_1000                              0.24   \n",
+       "reform_mean_floor_count_1000                              0.31   \n",
+       "reform_mean_year_building_1000                            0.05   \n",
+       "region                                                    0.97   \n",
+       "total_square                                              0.07   \n",
+       "date                                                      0.14   \n",
+       "realty_type                                               0.14   \n",
+       "price_type                                                0.07   \n",
+       "\n",
+       "                                   osm_crossing_closest_dist  \\\n",
+       "per_square_meter_price                                  0.00   \n",
+       "floor                                                   0.01   \n",
+       "osm_amenity_points_in_0.01                              0.00   \n",
+       "osm_building_points_in_0.01                             0.00   \n",
+       "osm_catering_points_in_0.01                             0.00   \n",
+       "osm_city_closest_dist                                   0.73   \n",
+       "osm_city_nearest_name                                   0.42   \n",
+       "osm_city_nearest_population                             0.00   \n",
+       "osm_crossing_closest_dist                               1.00   \n",
+       "osm_crossing_points_in_0.01                             0.00   \n",
+       "osm_culture_points_in_0.01                              0.00   \n",
+       "osm_healthcare_points_in_0.01                           0.00   \n",
+       "osm_historic_points_in_0.01                             0.00   \n",
+       "osm_hotels_points_in_0.01                               0.00   \n",
+       "osm_leisure_points_in_0.01                              0.00   \n",
+       "osm_offices_points_in_0.01                              0.00   \n",
+       "osm_shops_points_in_0.01                                0.00   \n",
+       "osm_subway_closest_dist                                 0.32   \n",
+       "osm_train_stop_closest_dist                             0.79   \n",
+       "osm_train_stop_points_in_0.01                           0.00   \n",
+       "osm_transport_stop_closest_dist                         0.88   \n",
+       "osm_transport_stop_points_in_0.01                       0.02   \n",
+       "reform_count_of_houses_1000                             0.01   \n",
+       "reform_house_population_1000                            0.00   \n",
+       "reform_mean_floor_count_1000                            0.01   \n",
+       "reform_mean_year_building_1000                          0.00   \n",
+       "region                                                  0.07   \n",
+       "total_square                                            0.00   \n",
+       "date                                                    0.00   \n",
+       "realty_type                                             0.01   \n",
+       "price_type                                              0.00   \n",
+       "\n",
+       "                                   osm_crossing_points_in_0.01  ...  \\\n",
+       "per_square_meter_price                                    0.57  ...   \n",
+       "floor                                                     0.14  ...   \n",
+       "osm_amenity_points_in_0.01                                0.82  ...   \n",
+       "osm_building_points_in_0.01                               0.11  ...   \n",
+       "osm_catering_points_in_0.01                               0.80  ...   \n",
+       "osm_city_closest_dist                                     0.22  ...   \n",
+       "osm_city_nearest_name                                     0.64  ...   \n",
+       "osm_city_nearest_population                               0.60  ...   \n",
+       "osm_crossing_closest_dist                                 0.00  ...   \n",
+       "osm_crossing_points_in_0.01                               1.00  ...   \n",
+       "osm_culture_points_in_0.01                                0.62  ...   \n",
+       "osm_healthcare_points_in_0.01                             0.81  ...   \n",
+       "osm_historic_points_in_0.01                               0.76  ...   \n",
+       "osm_hotels_points_in_0.01                                 0.71  ...   \n",
+       "osm_leisure_points_in_0.01                                0.71  ...   \n",
+       "osm_offices_points_in_0.01                                0.76  ...   \n",
+       "osm_shops_points_in_0.01                                  0.79  ...   \n",
+       "osm_subway_closest_dist                                   0.20  ...   \n",
+       "osm_train_stop_closest_dist                               0.09  ...   \n",
+       "osm_train_stop_points_in_0.01                             0.46  ...   \n",
+       "osm_transport_stop_closest_dist                           0.00  ...   \n",
+       "osm_transport_stop_points_in_0.01                         0.77  ...   \n",
+       "reform_count_of_houses_1000                               0.67  ...   \n",
+       "reform_house_population_1000                              0.59  ...   \n",
+       "reform_mean_floor_count_1000                              0.41  ...   \n",
+       "reform_mean_year_building_1000                            0.17  ...   \n",
+       "region                                                    0.55  ...   \n",
+       "total_square                                              0.18  ...   \n",
+       "date                                                      0.17  ...   \n",
+       "realty_type                                               0.31  ...   \n",
+       "price_type                                                0.09  ...   \n",
+       "\n",
+       "                                   osm_transport_stop_points_in_0.01  \\\n",
+       "per_square_meter_price                                          0.46   \n",
+       "floor                                                           0.12   \n",
+       "osm_amenity_points_in_0.01                                      0.69   \n",
+       "osm_building_points_in_0.01                                     0.04   \n",
+       "osm_catering_points_in_0.01                                     0.63   \n",
+       "osm_city_closest_dist                                           0.15   \n",
+       "osm_city_nearest_name                                           0.62   \n",
+       "osm_city_nearest_population                                     0.49   \n",
+       "osm_crossing_closest_dist                                       0.02   \n",
+       "osm_crossing_points_in_0.01                                     0.77   \n",
+       "osm_culture_points_in_0.01                                      0.34   \n",
+       "osm_healthcare_points_in_0.01                                   0.68   \n",
+       "osm_historic_points_in_0.01                                     0.52   \n",
+       "osm_hotels_points_in_0.01                                       0.50   \n",
+       "osm_leisure_points_in_0.01                                      0.58   \n",
+       "osm_offices_points_in_0.01                                      0.61   \n",
+       "osm_shops_points_in_0.01                                        0.67   \n",
+       "osm_subway_closest_dist                                         0.18   \n",
+       "osm_train_stop_closest_dist                                     0.06   \n",
+       "osm_train_stop_points_in_0.01                                   0.25   \n",
+       "osm_transport_stop_closest_dist                                 0.02   \n",
+       "osm_transport_stop_points_in_0.01                               1.00   \n",
+       "reform_count_of_houses_1000                                     0.52   \n",
+       "reform_house_population_1000                                    0.45   \n",
+       "reform_mean_floor_count_1000                                    0.33   \n",
+       "reform_mean_year_building_1000                                  0.05   \n",
+       "region                                                          0.52   \n",
+       "total_square                                                    0.05   \n",
+       "date                                                            0.08   \n",
+       "realty_type                                                     0.20   \n",
+       "price_type                                                      0.07   \n",
+       "\n",
+       "                                   reform_count_of_houses_1000  \\\n",
+       "per_square_meter_price                                    0.16   \n",
+       "floor                                                     0.03   \n",
+       "osm_amenity_points_in_0.01                                0.63   \n",
+       "osm_building_points_in_0.01                               0.03   \n",
+       "osm_catering_points_in_0.01                               0.57   \n",
+       "osm_city_closest_dist                                     0.09   \n",
+       "osm_city_nearest_name                                     0.55   \n",
+       "osm_city_nearest_population                               0.20   \n",
+       "osm_crossing_closest_dist                                 0.01   \n",
+       "osm_crossing_points_in_0.01                               0.67   \n",
+       "osm_culture_points_in_0.01                                0.37   \n",
+       "osm_healthcare_points_in_0.01                             0.53   \n",
+       "osm_historic_points_in_0.01                               0.52   \n",
+       "osm_hotels_points_in_0.01                                 0.52   \n",
+       "osm_leisure_points_in_0.01                                0.40   \n",
+       "osm_offices_points_in_0.01                                0.56   \n",
+       "osm_shops_points_in_0.01                                  0.64   \n",
+       "osm_subway_closest_dist                                   0.12   \n",
+       "osm_train_stop_closest_dist                               0.03   \n",
+       "osm_train_stop_points_in_0.01                             0.12   \n",
+       "osm_transport_stop_closest_dist                           0.01   \n",
+       "osm_transport_stop_points_in_0.01                         0.52   \n",
+       "reform_count_of_houses_1000                               1.00   \n",
+       "reform_house_population_1000                              0.55   \n",
+       "reform_mean_floor_count_1000                              0.38   \n",
+       "reform_mean_year_building_1000                            0.06   \n",
+       "region                                                    0.43   \n",
+       "total_square                                              0.05   \n",
+       "date                                                      0.03   \n",
+       "realty_type                                               0.13   \n",
+       "price_type                                                0.13   \n",
+       "\n",
+       "                                   reform_house_population_1000  \\\n",
+       "per_square_meter_price                                     0.19   \n",
+       "floor                                                      0.10   \n",
+       "osm_amenity_points_in_0.01                                 0.62   \n",
+       "osm_building_points_in_0.01                                0.03   \n",
+       "osm_catering_points_in_0.01                                0.60   \n",
+       "osm_city_closest_dist                                      0.11   \n",
+       "osm_city_nearest_name                                      0.48   \n",
+       "osm_city_nearest_population                                0.24   \n",
+       "osm_crossing_closest_dist                                  0.00   \n",
+       "osm_crossing_points_in_0.01                                0.59   \n",
+       "osm_culture_points_in_0.01                                 0.15   \n",
+       "osm_healthcare_points_in_0.01                              0.42   \n",
+       "osm_historic_points_in_0.01                                0.19   \n",
+       "osm_hotels_points_in_0.01                                  0.56   \n",
+       "osm_leisure_points_in_0.01                                 0.39   \n",
+       "osm_offices_points_in_0.01                                 0.59   \n",
+       "osm_shops_points_in_0.01                                   0.65   \n",
+       "osm_subway_closest_dist                                    0.09   \n",
+       "osm_train_stop_closest_dist                                0.05   \n",
+       "osm_train_stop_points_in_0.01                              0.13   \n",
+       "osm_transport_stop_closest_dist                            0.01   \n",
+       "osm_transport_stop_points_in_0.01                          0.45   \n",
+       "reform_count_of_houses_1000                                0.55   \n",
+       "reform_house_population_1000                               1.00   \n",
+       "reform_mean_floor_count_1000                               0.31   \n",
+       "reform_mean_year_building_1000                             0.04   \n",
+       "region                                                     0.36   \n",
+       "total_square                                               0.02   \n",
+       "date                                                       0.04   \n",
+       "realty_type                                                0.20   \n",
+       "price_type                                                 0.16   \n",
+       "\n",
+       "                                   reform_mean_floor_count_1000  \\\n",
+       "per_square_meter_price                                     0.23   \n",
+       "floor                                                      0.15   \n",
+       "osm_amenity_points_in_0.01                                 0.25   \n",
+       "osm_building_points_in_0.01                                0.03   \n",
+       "osm_catering_points_in_0.01                                0.23   \n",
+       "osm_city_closest_dist                                      0.13   \n",
+       "osm_city_nearest_name                                      0.59   \n",
+       "osm_city_nearest_population                                0.31   \n",
+       "osm_crossing_closest_dist                                  0.01   \n",
+       "osm_crossing_points_in_0.01                                0.41   \n",
+       "osm_culture_points_in_0.01                                 0.12   \n",
+       "osm_healthcare_points_in_0.01                              0.23   \n",
+       "osm_historic_points_in_0.01                                0.19   \n",
+       "osm_hotels_points_in_0.01                                  0.17   \n",
+       "osm_leisure_points_in_0.01                                 0.27   \n",
+       "osm_offices_points_in_0.01                                 0.27   \n",
+       "osm_shops_points_in_0.01                                   0.25   \n",
+       "osm_subway_closest_dist                                    0.15   \n",
+       "osm_train_stop_closest_dist                                0.07   \n",
+       "osm_train_stop_points_in_0.01                              0.12   \n",
+       "osm_transport_stop_closest_dist                            0.02   \n",
+       "osm_transport_stop_points_in_0.01                          0.33   \n",
+       "reform_count_of_houses_1000                                0.38   \n",
+       "reform_house_population_1000                               0.31   \n",
+       "reform_mean_floor_count_1000                               1.00   \n",
+       "reform_mean_year_building_1000                             0.08   \n",
+       "region                                                     0.47   \n",
+       "total_square                                               0.02   \n",
+       "date                                                       0.06   \n",
+       "realty_type                                                0.14   \n",
+       "price_type                                                 0.05   \n",
+       "\n",
+       "                                   reform_mean_year_building_1000  region  \\\n",
+       "per_square_meter_price                                       0.03    0.52   \n",
+       "floor                                                        0.00    0.23   \n",
+       "osm_amenity_points_in_0.01                                   0.04    0.45   \n",
+       "osm_building_points_in_0.01                                  0.00    0.22   \n",
+       "osm_catering_points_in_0.01                                  0.03    0.40   \n",
+       "osm_city_closest_dist                                        0.00    0.40   \n",
+       "osm_city_nearest_name                                        0.44    1.00   \n",
+       "osm_city_nearest_population                                  0.05    0.97   \n",
+       "osm_crossing_closest_dist                                    0.00    0.07   \n",
+       "osm_crossing_points_in_0.01                                  0.17    0.55   \n",
+       "osm_culture_points_in_0.01                                   0.00    0.39   \n",
+       "osm_healthcare_points_in_0.01                                0.05    0.46   \n",
+       "osm_historic_points_in_0.01                                  0.04    0.33   \n",
+       "osm_hotels_points_in_0.01                                    0.01    0.36   \n",
+       "osm_leisure_points_in_0.01                                   0.05    0.48   \n",
+       "osm_offices_points_in_0.01                                   0.04    0.47   \n",
+       "osm_shops_points_in_0.01                                     0.06    0.47   \n",
+       "osm_subway_closest_dist                                      0.04    0.91   \n",
+       "osm_train_stop_closest_dist                                  0.00    0.43   \n",
+       "osm_train_stop_points_in_0.01                                0.05    0.26   \n",
+       "osm_transport_stop_closest_dist                              0.00    0.14   \n",
+       "osm_transport_stop_points_in_0.01                            0.05    0.52   \n",
+       "reform_count_of_houses_1000                                  0.06    0.43   \n",
+       "reform_house_population_1000                                 0.04    0.36   \n",
+       "reform_mean_floor_count_1000                                 0.08    0.47   \n",
+       "reform_mean_year_building_1000                               1.00    0.37   \n",
+       "region                                                       0.37    1.00   \n",
+       "total_square                                                 0.00    0.08   \n",
+       "date                                                         0.02    0.17   \n",
+       "realty_type                                                  0.02    0.28   \n",
+       "price_type                                                   0.00    0.27   \n",
+       "\n",
+       "                                   total_square  date  realty_type  price_type  \n",
+       "per_square_meter_price                     0.02  0.11         0.18        0.05  \n",
+       "floor                                      0.01  0.22         0.04        0.00  \n",
+       "osm_amenity_points_in_0.01                 0.05  0.07         0.18        0.22  \n",
+       "osm_building_points_in_0.01                0.00  0.01         0.03        0.01  \n",
+       "osm_catering_points_in_0.01                0.05  0.07         0.19        0.20  \n",
+       "osm_city_closest_dist                      0.00  0.02         0.06        0.01  \n",
+       "osm_city_nearest_name                      0.12  0.22         0.37        0.30  \n",
+       "osm_city_nearest_population                0.07  0.14         0.14        0.07  \n",
+       "osm_crossing_closest_dist                  0.00  0.00         0.01        0.00  \n",
+       "osm_crossing_points_in_0.01                0.18  0.17         0.31        0.09  \n",
+       "osm_culture_points_in_0.01                 0.04  0.03         0.07        0.04  \n",
+       "osm_healthcare_points_in_0.01              0.06  0.07         0.13        0.04  \n",
+       "osm_historic_points_in_0.01                0.08  0.05         0.14        0.05  \n",
+       "osm_hotels_points_in_0.01                  0.05  0.05         0.08        0.21  \n",
+       "osm_leisure_points_in_0.01                 0.06  0.08         0.14        0.09  \n",
+       "osm_offices_points_in_0.01                 0.05  0.07         0.19        0.20  \n",
+       "osm_shops_points_in_0.01                   0.03  0.07         0.17        0.20  \n",
+       "osm_subway_closest_dist                    0.03  0.06         0.09        0.04  \n",
+       "osm_train_stop_closest_dist                0.00  0.01         0.02        0.00  \n",
+       "osm_train_stop_points_in_0.01              0.04  0.04         0.11        0.03  \n",
+       "osm_transport_stop_closest_dist            0.00  0.00         0.02        0.00  \n",
+       "osm_transport_stop_points_in_0.01          0.05  0.08         0.20        0.07  \n",
+       "reform_count_of_houses_1000                0.05  0.03         0.13        0.13  \n",
+       "reform_house_population_1000               0.02  0.04         0.20        0.16  \n",
+       "reform_mean_floor_count_1000               0.02  0.06         0.14        0.05  \n",
+       "reform_mean_year_building_1000             0.00  0.02         0.02        0.00  \n",
+       "region                                     0.08  0.17         0.28        0.27  \n",
+       "total_square                               1.00  0.02         0.04        0.01  \n",
+       "date                                       0.02  1.00         0.10        0.02  \n",
+       "realty_type                                0.04  0.10         1.00        0.02  \n",
+       "price_type                                 0.01  0.02         0.02        1.00  \n",
+       "\n",
+       "[31 rows x 31 columns]"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# считаем корреляцию phik - она позволяет находитб взаимосвязи в том числе между категориальными переменными. \n",
+    "# направление взаимосвязи не видно, только абсолютное значение. Чем ближе к единице, тем лучше\n",
+    "\n",
+    "# выделяем интервальные переменные\n",
+    "interval_cols = ['osm_amenity_points_in_0.01', 'osm_building_points_in_0.01',\n",
+    "       'osm_catering_points_in_0.01', 'osm_city_closest_dist',\n",
+    "       'osm_city_nearest_population','osm_crossing_closest_dist', 'osm_crossing_points_in_0.001', 'osm_culture_points_in_0.01',\n",
+    "       'osm_healthcare_points_in_0.01', 'osm_historic_points_in_0.01', 'osm_hotels_points_in_0.01',\n",
+    "       'osm_leisure_points_in_0.01', 'osm_offices_points_in_0.01',\n",
+    "       'osm_shops_points_in_0.01', 'osm_subway_closest_dist',\n",
+    "       'osm_train_stop_closest_dist', 'osm_train_stop_points_in_0.01',\n",
+    "       'osm_transport_stop_closest_dist', 'osm_transport_stop_points_in_0.01', 'per_square_meter_price',\n",
+    "       'reform_count_of_houses_1000', 'reform_house_population_1000', \n",
+    "       'reform_mean_floor_count_1000', 'reform_mean_year_building_1000',\n",
+    "      'total_square', 'realty_type', 'price_type', 'many_floors',\n",
+    "      'city', 'street']\n",
+    "\n",
+    "# строим матрицу корреляции\n",
+    "phik_overview = train_data[columns_for_phik].phik_matrix(interval_cols=interval_cols)\n",
+    "\n",
+    "phik_overview.round(2)\n",
+    "\n",
+    "# визуализируем с помощью тепловой карты\n",
+    "# fig, ax = plt.subplots(figsize=(20, 20))\n",
+    "# sns.heatmap(phik_overview.round(2), annot=True, square=True, cmap='mako')\n",
+    "# ax.set_title(label = 'МАТРИЦА КОРРЕЛЯЦИИ ПРИЗНАКОВ $\\phi_K$', fontdict={'fontsize': 15, 'fontweight': 'bold'})\n",
+    "\n",
+    "# plt.tight_layout()\n",
+    "# plt.show();"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "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>feature</th>\n",
+       "      <th>phik</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>per_square_meter_price</td>\n",
+       "      <td>1.00</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>osm_crossing_points_in_0.01</td>\n",
+       "      <td>0.57</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>osm_city_nearest_name</td>\n",
+       "      <td>0.57</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>osm_city_nearest_population</td>\n",
+       "      <td>0.55</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>region</td>\n",
+       "      <td>0.52</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>osm_amenity_points_in_0.01</td>\n",
+       "      <td>0.48</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>osm_catering_points_in_0.01</td>\n",
+       "      <td>0.48</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>osm_leisure_points_in_0.01</td>\n",
+       "      <td>0.47</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>osm_offices_points_in_0.01</td>\n",
+       "      <td>0.47</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>osm_shops_points_in_0.01</td>\n",
+       "      <td>0.47</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>osm_healthcare_points_in_0.01</td>\n",
+       "      <td>0.46</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>osm_transport_stop_points_in_0.01</td>\n",
+       "      <td>0.46</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                              feature  phik\n",
+       "0              per_square_meter_price  1.00\n",
+       "9         osm_crossing_points_in_0.01  0.57\n",
+       "6               osm_city_nearest_name  0.57\n",
+       "7         osm_city_nearest_population  0.55\n",
+       "26                             region  0.52\n",
+       "2          osm_amenity_points_in_0.01  0.48\n",
+       "4         osm_catering_points_in_0.01  0.48\n",
+       "14         osm_leisure_points_in_0.01  0.47\n",
+       "15         osm_offices_points_in_0.01  0.47\n",
+       "16           osm_shops_points_in_0.01  0.47\n",
+       "11      osm_healthcare_points_in_0.01  0.46\n",
+       "21  osm_transport_stop_points_in_0.01  0.46"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Формируем список переменных с максимальным коэффициентов корреляции phik с целевой переменной \n",
+    "phik_max_corr = (\n",
+    "    phik_overview['per_square_meter_price'].to_frame().reset_index()\n",
+    "    .rename(columns={'per_square_meter_price':'phik', 'index':'feature'})\n",
+    "    .sort_values(by='phik', ascending=False)\n",
+    "    .query('phik > 0.4')\n",
+    "    .round(2)\n",
+    "    )\n",
+    "phik_max_corr\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Матрица корреляции phik показала максимальную взаимосвязь целевой переменной с пременными:\n",
+    "- количество пешеходных переходов в радиусе 1 км\n",
+    "- название ближайшего города\n",
+    "- население ближайшего города\n",
+    "- регион\n",
+    "- количество в радиусе 1 км точек кейтеринга, досуга, офисов, магазинов, медучреждений, остановок общественного транспорта и объектов связаннных с удобством\n",
+    "\n",
+    "Также обнаружены новые взаимосвязи переменных между собой, которые не были видны на матрице корреляции Пирсона:\n",
+    "- этаж и price_type\n",
+    "- название близлежащего города и население ближайшего города, расстояние до ближайшего метро, остановки общественного транспорта, регион\n",
+    "- регион и расстояние до ближайшего метро"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Modelling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# add features\n",
+    "city_population = pd.read_csv('city_population.csv')\n",
+    "zarplaty = pd.read_excel('zarplaty.xlsx')\n",
+    "\n",
+    "def city_type(row):\n",
+    "    if row >=1000000:\n",
+    "        return \"1Million\"\n",
+    "    elif  (row<1000000)&(row >200000):\n",
+    "        return \"Medium\"\n",
+    "    elif  (row <=200000):\n",
+    "        return \"Small\"\n",
+    "    \n",
+    "def floor_type(row):\n",
+    "    if ('1' in str(row))&(row!=-1):\n",
+    "        return 1\n",
+    "    else:\n",
+    "        return 0\n",
+    "    \n",
+    "def add_features(df):\n",
+    "    df['age'] = round(2021 - df['reform_mean_year_building_500'])\n",
+    "    df.city = df.city.apply(lambda x: x.lower())\n",
+    "    \n",
+    "    city_population_clean = city_population.groupby('settlement').agg({'population':'sum'}).reset_index()\n",
+    "    city_population_clean.columns = ['city', 'city_population']\n",
+    "    city_population_clean['city_population']\n",
+    "    city_population_clean.city = city_population_clean.city.apply(lambda x: x.lower())\n",
+    "    df = df.merge(city_population_clean, on = 'city', how='left')\n",
+    "    \n",
+    "    for col in df.select_dtypes(include=np.number).columns:\n",
+    "        df[col] = pd.to_numeric(df[col], downcast = 'unsigned')\n",
+    "    \n",
+    "    df['city_type'] = df['city_population'].apply(lambda x: city_type(x))\n",
+    "    df.loc[df.city  == 'москва', 'city_type'] = \"Capital\"\n",
+    "    df.loc[df.city  == 'санкт-Петербург', 'city_type'] = \"Capital\"\n",
+    "    \n",
+    "    df = df.merge(zarplaty, on = 'region', how='left')\n",
+    "    df['zarplata'] = pd.to_numeric(df['zarplata'], downcast = 'unsigned')\n",
+    "    df['floor_type'] = df['floor'].apply(lambda x: floor_type(x))\n",
+    "    \n",
+    "    return df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data = add_features(train_data)\n",
+    "test_data = add_features(test_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((279967, 82), (2974, 81))"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_data.shape, test_data.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "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>city</th>\n",
+       "      <th>floor</th>\n",
+       "      <th>id</th>\n",
+       "      <th>lat</th>\n",
+       "      <th>lng</th>\n",
+       "      <th>osm_amenity_points_in_0.001</th>\n",
+       "      <th>osm_amenity_points_in_0.005</th>\n",
+       "      <th>osm_amenity_points_in_0.0075</th>\n",
+       "      <th>osm_amenity_points_in_0.01</th>\n",
+       "      <th>osm_building_points_in_0.001</th>\n",
+       "      <th>...</th>\n",
+       "      <th>total_square</th>\n",
+       "      <th>street</th>\n",
+       "      <th>date</th>\n",
+       "      <th>realty_type</th>\n",
+       "      <th>price_type</th>\n",
+       "      <th>age</th>\n",
+       "      <th>city_population</th>\n",
+       "      <th>city_type</th>\n",
+       "      <th>zarplata</th>\n",
+       "      <th>floor_type</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>пермь</td>\n",
+       "      <td>0</td>\n",
+       "      <td>COL_0</td>\n",
+       "      <td>57.998207</td>\n",
+       "      <td>56.292797</td>\n",
+       "      <td>4</td>\n",
+       "      <td>19</td>\n",
+       "      <td>35</td>\n",
+       "      <td>52</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>32.0</td>\n",
+       "      <td>S27289</td>\n",
+       "      <td>2020-01-05</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>1048011.0</td>\n",
+       "      <td>1Million</td>\n",
+       "      <td>41958.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>шатура</td>\n",
+       "      <td>0</td>\n",
+       "      <td>COL_1</td>\n",
+       "      <td>55.574284</td>\n",
+       "      <td>39.543835</td>\n",
+       "      <td>3</td>\n",
+       "      <td>24</td>\n",
+       "      <td>37</td>\n",
+       "      <td>59</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>280.0</td>\n",
+       "      <td>S17052</td>\n",
+       "      <td>2020-01-05</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>64.0</td>\n",
+       "      <td>32885.0</td>\n",
+       "      <td>Small</td>\n",
+       "      <td>58066.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ярославль</td>\n",
+       "      <td>0</td>\n",
+       "      <td>COL_2</td>\n",
+       "      <td>57.619140</td>\n",
+       "      <td>39.850525</td>\n",
+       "      <td>1</td>\n",
+       "      <td>30</td>\n",
+       "      <td>67</td>\n",
+       "      <td>128</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>297.4</td>\n",
+       "      <td>S16913</td>\n",
+       "      <td>2020-01-05</td>\n",
+       "      <td>110</td>\n",
+       "      <td>0</td>\n",
+       "      <td>48.0</td>\n",
+       "      <td>604128.0</td>\n",
+       "      <td>Medium</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>новокузнецк</td>\n",
+       "      <td>0</td>\n",
+       "      <td>COL_3</td>\n",
+       "      <td>53.897083</td>\n",
+       "      <td>87.108604</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "      <td>21</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>190.0</td>\n",
+       "      <td>S10148</td>\n",
+       "      <td>2020-01-05</td>\n",
+       "      <td>110</td>\n",
+       "      <td>0</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>551919.0</td>\n",
+       "      <td>Medium</td>\n",
+       "      <td>43429.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>москва</td>\n",
+       "      <td>0</td>\n",
+       "      <td>COL_4</td>\n",
+       "      <td>55.802590</td>\n",
+       "      <td>37.487110</td>\n",
+       "      <td>1</td>\n",
+       "      <td>23</td>\n",
+       "      <td>64</td>\n",
+       "      <td>153</td>\n",
+       "      <td>0</td>\n",
+       "      <td>...</td>\n",
+       "      <td>60.2</td>\n",
+       "      <td>S1338</td>\n",
+       "      <td>2020-01-05</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>60.0</td>\n",
+       "      <td>12380691.0</td>\n",
+       "      <td>Capital</td>\n",
+       "      <td>100070.0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 82 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          city  floor     id        lat        lng  \\\n",
+       "0        пермь      0  COL_0  57.998207  56.292797   \n",
+       "1       шатура      0  COL_1  55.574284  39.543835   \n",
+       "2    ярославль      0  COL_2  57.619140  39.850525   \n",
+       "3  новокузнецк      0  COL_3  53.897083  87.108604   \n",
+       "4       москва      0  COL_4  55.802590  37.487110   \n",
+       "\n",
+       "   osm_amenity_points_in_0.001  osm_amenity_points_in_0.005  \\\n",
+       "0                            4                           19   \n",
+       "1                            3                           24   \n",
+       "2                            1                           30   \n",
+       "3                            0                            0   \n",
+       "4                            1                           23   \n",
+       "\n",
+       "   osm_amenity_points_in_0.0075  osm_amenity_points_in_0.01  \\\n",
+       "0                            35                          52   \n",
+       "1                            37                          59   \n",
+       "2                            67                         128   \n",
+       "3                             5                          21   \n",
+       "4                            64                         153   \n",
+       "\n",
+       "   osm_building_points_in_0.001  ...  total_square  street        date  \\\n",
+       "0                             0  ...          32.0  S27289  2020-01-05   \n",
+       "1                             0  ...         280.0  S17052  2020-01-05   \n",
+       "2                             0  ...         297.4  S16913  2020-01-05   \n",
+       "3                             0  ...         190.0  S10148  2020-01-05   \n",
+       "4                             0  ...          60.2   S1338  2020-01-05   \n",
+       "\n",
+       "   realty_type  price_type   age  city_population  city_type  zarplata  \\\n",
+       "0           10           0  60.0        1048011.0   1Million   41958.0   \n",
+       "1           10           0  64.0          32885.0      Small   58066.0   \n",
+       "2          110           0  48.0         604128.0     Medium       NaN   \n",
+       "3          110           0   7.0         551919.0     Medium   43429.0   \n",
+       "4           10           0  60.0       12380691.0    Capital  100070.0   \n",
+       "\n",
+       "   floor_type  \n",
+       "0           0  \n",
+       "1           0  \n",
+       "2           0  \n",
+       "3           0  \n",
+       "4           0  \n",
+       "\n",
+       "[5 rows x 82 columns]"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_data.head()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data = train_data.query('price_type == 1')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_data.replace('1', 1, inplace=True)\n",
+    "train_data.replace('1.0', 1, inplace=True)\n",
+    "test_data.replace('1', 1, inplace=True)\n",
+    "test_data.replace('1.0', 1, inplace=True)\n",
+    "\n",
+    "train_data['floor'] = train_data.apply(lambda row: 1 if row['floor'] == 1 else 0, axis=1)\n",
+    "test_data['floor'] = test_data.apply(lambda row: 1 if row['floor'] == 1 else 0, axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "metadata": {
+    "id": "811f6b6d"
+   },
+   "outputs": [],
+   "source": [
+    "N_THREADS = 4 # threads cnt for lgbm and linear models\n",
+    "N_FOLDS = 5 # folds cnt for AutoML\n",
+    "RANDOM_STATE = 42 # fixed random state for various reasons\n",
+    "#TEST_SIZE = 0.1 # Test size for metric check\n",
+    "TIMEOUT = 100 # Time in seconds for automl run USE TIMEOUT = 1700 for perfect score\n",
+    "\n",
+    "np.random.seed(RANDOM_STATE)\n",
+    "torch.set_num_threads(N_THREADS)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {
+    "id": "e6d51e72"
+   },
+   "outputs": [],
+   "source": [
+    "# train_df, test_df = train_test_split(train_data, \n",
+    "#                                      test_size=TEST_SIZE, \n",
+    "#                                      random_state=RANDOM_STATE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "THRESHOLD = 0.15\n",
+    "NEGATIVE_WEIGHT = 1.1\n",
+    "\n",
+    "def deviation_metric_one_sample(y_true: typing.Union[float, int], y_pred: typing.Union[float, int]) -> float:\n",
+    "    \"\"\"\n",
+    "    Реализация кастомной метрики для хакатона.\n",
+    "\n",
+    "    :param y_true: float, реальная цена\n",
+    "    :param y_pred: float, предсказанная цена\n",
+    "    :return: float, значение метрики\n",
+    "    \"\"\"\n",
+    "    deviation = (y_pred - y_true) / np.maximum(1e-8, y_true)\n",
+    "    if np.abs(deviation) <= THRESHOLD:\n",
+    "        return 0\n",
+    "    elif deviation <= - 4 * THRESHOLD:\n",
+    "        return 9 * NEGATIVE_WEIGHT\n",
+    "    elif deviation < -THRESHOLD:\n",
+    "        return NEGATIVE_WEIGHT * ((deviation / THRESHOLD) + 1) ** 2\n",
+    "    elif deviation < 4 * THRESHOLD:\n",
+    "        return ((deviation / THRESHOLD) - 1) ** 2\n",
+    "    else:\n",
+    "        return 9\n",
+    "\n",
+    "\n",
+    "def deviation_metric(y_true: np.array, y_pred: np.array) -> float:\n",
+    "    return np.array([deviation_metric_one_sample(y_true[n], y_pred[n]) for n in range(len(y_true))]).mean()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {
+    "id": "11901a60"
+   },
+   "outputs": [],
+   "source": [
+    "task = Task('reg', loss = 'rmsle', metric = deviation_metric)\n",
+    "\n",
+    "roles = {\n",
+    "    'target': 'per_square_meter_price',\n",
+    "    'drop': 'id'\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 800
+    },
+    "id": "c77216e8",
+    "outputId": "ae6a7952-b341-40ed-f000-00f38639be74"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Current random state: {'reader_params': {'random_state': 42}, 'general_params': {'return_all_predictions': False}}\n",
+      "Found reader_params in kwargs, need to combine\n",
+      "Merged variant for reader_params = {'n_jobs': 4, 'cv': 5, 'random_state': 42}\n",
+      "Start automl preset with listed constraints:\n",
+      "- time: 100.0 seconds\n",
+      "- cpus: 4 cores\n",
+      "- memory: 16 gb\n",
+      "\n",
+      "Train data shape: (4493, 82)\n",
+      "Feats was rejected during automatic roles guess: []\n",
+      "\n",
+      "\n",
+      "Layer 1 ...\n",
+      "Train process start. Time left 89.13144850730896 secs\n",
+      "Start fitting Lvl_0_Pipe_0_Mod_0_LinearL2 ...\n",
+      "\n",
+      "===== Start working with fold 0 for Lvl_0_Pipe_0_Mod_0_LinearL2 =====\n",
+      "\n",
+      "Linear model: C = 1e-05 score = [-3.7152774]\n",
+      "Linear model: C = 5e-05 score = [-3.7152774]\n",
+      "Linear model: C = 0.0001 score = [-3.7152774]\n",
+      "\n",
+      "===== Start working with fold 1 for Lvl_0_Pipe_0_Mod_0_LinearL2 =====\n",
+      "\n",
+      "Linear model: C = 1e-05 score = [-3.3165922]\n",
+      "Linear model: C = 5e-05 score = [-3.3165922]\n",
+      "Linear model: C = 0.0001 score = [-3.3165922]\n",
+      "\n",
+      "===== Start working with fold 2 for Lvl_0_Pipe_0_Mod_0_LinearL2 =====\n",
+      "\n",
+      "Linear model: C = 1e-05 score = [-3.6910217]\n",
+      "Linear model: C = 5e-05 score = [-3.6910217]\n",
+      "Linear model: C = 0.0001 score = [-3.6910217]\n",
+      "\n",
+      "===== Start working with fold 3 for Lvl_0_Pipe_0_Mod_0_LinearL2 =====\n",
+      "\n",
+      "Linear model: C = 1e-05 score = [-3.6205108]\n",
+      "Linear model: C = 5e-05 score = [-3.6205108]\n",
+      "Linear model: C = 0.0001 score = [-3.6205108]\n",
+      "\n",
+      "===== Start working with fold 4 for Lvl_0_Pipe_0_Mod_0_LinearL2 =====\n",
+      "\n",
+      "Linear model: C = 1e-05 score = [-3.2158222]\n",
+      "Linear model: C = 5e-05 score = [-3.2158222]\n",
+      "Linear model: C = 0.0001 score = [-3.2158222]\n",
+      "Lvl_0_Pipe_0_Mod_0_LinearL2 fitting and predicting completed\n",
+      "Time left 86.83387517929077\n",
+      "Start fitting Lvl_0_Pipe_1_Mod_0_LightGBM ...\n",
+      "\n",
+      "===== Start working with fold 0 for Lvl_0_Pipe_1_Mod_0_LightGBM =====\n",
+      "\n",
+      "Training until validation scores don't improve for 200 rounds\n",
+      "[100]\tvalid's l2: 0.175464\tvalid's Opt metric: 2.38008\n",
+      "[200]\tvalid's l2: 0.137539\tvalid's Opt metric: 2.00419\n",
+      "[300]\tvalid's l2: 0.126562\tvalid's Opt metric: 1.85852\n",
+      "[400]\tvalid's l2: 0.122176\tvalid's Opt metric: 1.77832\n",
+      "[500]\tvalid's l2: 0.120404\tvalid's Opt metric: 1.74085\n",
+      "[600]\tvalid's l2: 0.119403\tvalid's Opt metric: 1.71643\n",
+      "[700]\tvalid's l2: 0.118939\tvalid's Opt metric: 1.7027\n",
+      "[800]\tvalid's l2: 0.1189\tvalid's Opt metric: 1.69712\n",
+      "[900]\tvalid's l2: 0.118543\tvalid's Opt metric: 1.68706\n",
+      "[1000]\tvalid's l2: 0.11832\tvalid's Opt metric: 1.68094\n",
+      "[1100]\tvalid's l2: 0.118228\tvalid's Opt metric: 1.67885\n",
+      "[1200]\tvalid's l2: 0.118142\tvalid's Opt metric: 1.67488\n",
+      "[1300]\tvalid's l2: 0.117963\tvalid's Opt metric: 1.66822\n",
+      "[1400]\tvalid's l2: 0.117946\tvalid's Opt metric: 1.66472\n",
+      "[1500]\tvalid's l2: 0.118028\tvalid's Opt metric: 1.66498\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Time limit exceeded after calculating fold 0\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Early stopping, best iteration is:\n",
+      "[1336]\tvalid's l2: 0.117866\tvalid's Opt metric: 1.6654\n",
+      "Lvl_0_Pipe_1_Mod_0_LightGBM fitting and predicting completed\n",
+      "Start fitting Lvl_0_Pipe_1_Mod_2_CatBoost ...\n",
+      "\n",
+      "===== Start working with fold 0 for Lvl_0_Pipe_1_Mod_2_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5690497\ttest: 0.5902307\tbest: 0.5902307 (0)\ttotal: 9.89ms\tremaining: 19.8s\n",
+      "100:\tlearn: 0.3220134\ttest: 0.3603304\tbest: 0.3603304 (100)\ttotal: 241ms\tremaining: 4.53s\n",
+      "200:\tlearn: 0.2853510\ttest: 0.3517094\tbest: 0.3517094 (200)\ttotal: 498ms\tremaining: 4.46s\n",
+      "300:\tlearn: 0.2576051\ttest: 0.3490464\tbest: 0.3490393 (299)\ttotal: 737ms\tremaining: 4.16s\n",
+      "400:\tlearn: 0.2379688\ttest: 0.3474727\tbest: 0.3474727 (400)\ttotal: 1s\tremaining: 4s\n",
+      "500:\tlearn: 0.2222526\ttest: 0.3449390\tbest: 0.3449390 (500)\ttotal: 1.23s\tremaining: 3.67s\n",
+      "600:\tlearn: 0.2078858\ttest: 0.3447732\tbest: 0.3443742 (549)\ttotal: 1.49s\tremaining: 3.46s\n",
+      "700:\tlearn: 0.1960459\ttest: 0.3442549\tbest: 0.3441099 (652)\ttotal: 1.75s\tremaining: 3.24s\n",
+      "800:\tlearn: 0.1857116\ttest: 0.3438032\tbest: 0.3436641 (740)\ttotal: 2s\tremaining: 2.99s\n",
+      "900:\tlearn: 0.1759209\ttest: 0.3433300\tbest: 0.3432126 (844)\ttotal: 2.22s\tremaining: 2.71s\n",
+      "1000:\tlearn: 0.1668783\ttest: 0.3428658\tbest: 0.3428565 (990)\ttotal: 2.47s\tremaining: 2.46s\n",
+      "1100:\tlearn: 0.1586743\ttest: 0.3419130\tbest: 0.3418887 (1090)\ttotal: 2.69s\tremaining: 2.2s\n",
+      "1200:\tlearn: 0.1510258\ttest: 0.3414564\tbest: 0.3414564 (1200)\ttotal: 2.94s\tremaining: 1.96s\n",
+      "1300:\tlearn: 0.1441223\ttest: 0.3414049\tbest: 0.3409616 (1261)\ttotal: 3.18s\tremaining: 1.71s\n",
+      "1400:\tlearn: 0.1377195\ttest: 0.3414637\tbest: 0.3409616 (1261)\ttotal: 3.44s\tremaining: 1.47s\n",
+      "1500:\tlearn: 0.1316497\ttest: 0.3414028\tbest: 0.3409616 (1261)\ttotal: 3.67s\tremaining: 1.22s\n",
+      "Stopped by overfitting detector  (300 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3409616327\n",
+      "bestIteration = 1261\n",
+      "\n",
+      "Shrink model to first 1262 iterations.\n",
+      "\n",
+      "===== Start working with fold 1 for Lvl_0_Pipe_1_Mod_2_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5768234\ttest: 0.5574083\tbest: 0.5574083 (0)\ttotal: 3.21ms\tremaining: 6.42s\n",
+      "100:\tlearn: 0.3247511\ttest: 0.3336189\tbest: 0.3336189 (100)\ttotal: 246ms\tremaining: 4.62s\n",
+      "200:\tlearn: 0.2892813\ttest: 0.3252905\tbest: 0.3252353 (193)\ttotal: 536ms\tremaining: 4.79s\n",
+      "300:\tlearn: 0.2614113\ttest: 0.3229165\tbest: 0.3227958 (299)\ttotal: 767ms\tremaining: 4.33s\n",
+      "400:\tlearn: 0.2413630\ttest: 0.3221904\tbest: 0.3219651 (324)\ttotal: 1.02s\tremaining: 4.08s\n",
+      "500:\tlearn: 0.2248640\ttest: 0.3214037\tbest: 0.3211377 (457)\ttotal: 1.27s\tremaining: 3.81s\n",
+      "600:\tlearn: 0.2108310\ttest: 0.3208134\tbest: 0.3207517 (597)\ttotal: 1.56s\tremaining: 3.62s\n",
+      "700:\tlearn: 0.1988404\ttest: 0.3209918\tbest: 0.3207120 (654)\ttotal: 1.8s\tremaining: 3.33s\n",
+      "800:\tlearn: 0.1880008\ttest: 0.3214166\tbest: 0.3207120 (654)\ttotal: 2.05s\tremaining: 3.06s\n",
+      "900:\tlearn: 0.1778877\ttest: 0.3214287\tbest: 0.3207120 (654)\ttotal: 2.35s\tremaining: 2.86s\n",
+      "Stopped by overfitting detector  (300 iterations wait)\n",
+      "\n",
+      "bestTest = 0.320711959\n",
+      "bestIteration = 654\n",
+      "\n",
+      "Shrink model to first 655 iterations.\n",
+      "\n",
+      "===== Start working with fold 2 for Lvl_0_Pipe_1_Mod_2_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5724626\ttest: 0.5753481\tbest: 0.5753481 (0)\ttotal: 3.17ms\tremaining: 6.33s\n",
+      "100:\tlearn: 0.3239383\ttest: 0.3399819\tbest: 0.3399819 (100)\ttotal: 266ms\tremaining: 5s\n",
+      "200:\tlearn: 0.2867294\ttest: 0.3285307\tbest: 0.3285307 (200)\ttotal: 512ms\tremaining: 4.58s\n",
+      "300:\tlearn: 0.2589989\ttest: 0.3255054\tbest: 0.3254546 (298)\ttotal: 750ms\tremaining: 4.23s\n",
+      "400:\tlearn: 0.2388187\ttest: 0.3247287\tbest: 0.3245618 (398)\ttotal: 976ms\tremaining: 3.89s\n",
+      "500:\tlearn: 0.2222920\ttest: 0.3240440\tbest: 0.3240057 (499)\ttotal: 1.24s\tremaining: 3.7s\n",
+      "600:\tlearn: 0.2086809\ttest: 0.3226891\tbest: 0.3226891 (600)\ttotal: 1.49s\tremaining: 3.46s\n",
+      "700:\tlearn: 0.1960510\ttest: 0.3210332\tbest: 0.3210024 (698)\ttotal: 1.74s\tremaining: 3.22s\n",
+      "800:\tlearn: 0.1854055\ttest: 0.3204972\tbest: 0.3204972 (800)\ttotal: 2s\tremaining: 2.99s\n",
+      "900:\tlearn: 0.1764789\ttest: 0.3205735\tbest: 0.3200469 (851)\ttotal: 2.28s\tremaining: 2.78s\n",
+      "1000:\tlearn: 0.1678033\ttest: 0.3209024\tbest: 0.3200469 (851)\ttotal: 2.52s\tremaining: 2.52s\n",
+      "1100:\tlearn: 0.1599763\ttest: 0.3211878\tbest: 0.3200469 (851)\ttotal: 2.79s\tremaining: 2.28s\n",
+      "Stopped by overfitting detector  (300 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3200468666\n",
+      "bestIteration = 851\n",
+      "\n",
+      "Shrink model to first 852 iterations.\n",
+      "\n",
+      "===== Start working with fold 3 for Lvl_0_Pipe_1_Mod_2_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5652387\ttest: 0.6041895\tbest: 0.6041895 (0)\ttotal: 3.64ms\tremaining: 7.28s\n",
+      "100:\tlearn: 0.3086002\ttest: 0.3976876\tbest: 0.3976876 (100)\ttotal: 264ms\tremaining: 4.97s\n",
+      "200:\tlearn: 0.2756635\ttest: 0.3880626\tbest: 0.3880626 (200)\ttotal: 501ms\tremaining: 4.49s\n",
+      "300:\tlearn: 0.2511624\ttest: 0.3852988\tbest: 0.3849651 (283)\ttotal: 754ms\tremaining: 4.25s\n",
+      "400:\tlearn: 0.2321052\ttest: 0.3859294\tbest: 0.3849651 (283)\ttotal: 997ms\tremaining: 3.97s\n",
+      "500:\tlearn: 0.2175329\ttest: 0.3865094\tbest: 0.3849651 (283)\ttotal: 1.26s\tremaining: 3.77s\n",
+      "Stopped by overfitting detector  (300 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3849650533\n",
+      "bestIteration = 283\n",
+      "\n",
+      "Shrink model to first 284 iterations.\n",
+      "\n",
+      "===== Start working with fold 4 for Lvl_0_Pipe_1_Mod_2_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5819025\ttest: 0.5416817\tbest: 0.5416817 (0)\ttotal: 16.8ms\tremaining: 33.5s\n",
+      "100:\tlearn: 0.3282525\ttest: 0.3302178\tbest: 0.3302178 (100)\ttotal: 292ms\tremaining: 5.5s\n",
+      "200:\tlearn: 0.2935099\ttest: 0.3155985\tbest: 0.3154939 (198)\ttotal: 559ms\tremaining: 5s\n",
+      "300:\tlearn: 0.2640830\ttest: 0.3098426\tbest: 0.3098426 (300)\ttotal: 817ms\tremaining: 4.61s\n",
+      "400:\tlearn: 0.2425758\ttest: 0.3053681\tbest: 0.3053681 (400)\ttotal: 1.08s\tremaining: 4.31s\n",
+      "500:\tlearn: 0.2263103\ttest: 0.3027193\tbest: 0.3024671 (488)\ttotal: 1.35s\tremaining: 4.05s\n",
+      "600:\tlearn: 0.2119579\ttest: 0.3012696\tbest: 0.3011144 (582)\ttotal: 1.62s\tremaining: 3.78s\n",
+      "700:\tlearn: 0.1987671\ttest: 0.2997913\tbest: 0.2997913 (700)\ttotal: 1.89s\tremaining: 3.5s\n",
+      "800:\tlearn: 0.1877085\ttest: 0.2993222\tbest: 0.2991978 (796)\ttotal: 2.15s\tremaining: 3.21s\n",
+      "900:\tlearn: 0.1779556\ttest: 0.2988217\tbest: 0.2988217 (900)\ttotal: 2.41s\tremaining: 2.94s\n",
+      "1000:\tlearn: 0.1691039\ttest: 0.2991610\tbest: 0.2988179 (904)\ttotal: 2.67s\tremaining: 2.66s\n",
+      "1100:\tlearn: 0.1609237\ttest: 0.2994798\tbest: 0.2988179 (904)\ttotal: 2.92s\tremaining: 2.38s\n",
+      "1200:\tlearn: 0.1537691\ttest: 0.2996605\tbest: 0.2988179 (904)\ttotal: 3.17s\tremaining: 2.11s\n",
+      "Stopped by overfitting detector  (300 iterations wait)\n",
+      "\n",
+      "bestTest = 0.2988178835\n",
+      "bestIteration = 904\n",
+      "\n",
+      "Shrink model to first 905 iterations.\n",
+      "Lvl_0_Pipe_1_Mod_2_CatBoost fitting and predicting completed\n",
+      "Optuna may run 1 secs\n",
+      "Start fitting Lvl_0_Pipe_1_Mod_3_CatBoost ...\n",
+      "\n",
+      "===== Start working with fold 0 for Lvl_0_Pipe_1_Mod_3_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5696811\ttest: 0.5907190\tbest: 0.5907190 (0)\ttotal: 4.77ms\tremaining: 9.53s\n",
+      "100:\tlearn: 0.3328412\ttest: 0.3613108\tbest: 0.3613108 (100)\ttotal: 196ms\tremaining: 3.68s\n",
+      "200:\tlearn: 0.3027316\ttest: 0.3519878\tbest: 0.3519878 (200)\ttotal: 368ms\tremaining: 3.29s\n",
+      "300:\tlearn: 0.2794207\ttest: 0.3487270\tbest: 0.3487270 (300)\ttotal: 582ms\tremaining: 3.29s\n",
+      "400:\tlearn: 0.2634165\ttest: 0.3479933\tbest: 0.3479933 (400)\ttotal: 775ms\tremaining: 3.09s\n",
+      "500:\tlearn: 0.2504892\ttest: 0.3473465\tbest: 0.3470908 (452)\ttotal: 961ms\tremaining: 2.88s\n",
+      "600:\tlearn: 0.2399381\ttest: 0.3461447\tbest: 0.3458834 (593)\ttotal: 1.17s\tremaining: 2.72s\n",
+      "700:\tlearn: 0.2293243\ttest: 0.3446773\tbest: 0.3445460 (694)\ttotal: 1.35s\tremaining: 2.5s\n",
+      "800:\tlearn: 0.2201892\ttest: 0.3445020\tbest: 0.3441724 (728)\ttotal: 1.56s\tremaining: 2.34s\n",
+      "900:\tlearn: 0.2122752\ttest: 0.3439144\tbest: 0.3438057 (883)\ttotal: 1.76s\tremaining: 2.15s\n",
+      "1000:\tlearn: 0.2050941\ttest: 0.3442635\tbest: 0.3438057 (883)\ttotal: 1.95s\tremaining: 1.95s\n",
+      "1100:\tlearn: 0.1984862\ttest: 0.3437866\tbest: 0.3437749 (1051)\ttotal: 2.14s\tremaining: 1.75s\n",
+      "1200:\tlearn: 0.1924283\ttest: 0.3433972\tbest: 0.3433483 (1198)\ttotal: 2.36s\tremaining: 1.57s\n",
+      "1300:\tlearn: 0.1863886\ttest: 0.3431625\tbest: 0.3430420 (1288)\ttotal: 2.56s\tremaining: 1.38s\n",
+      "1400:\tlearn: 0.1807727\ttest: 0.3427477\tbest: 0.3427039 (1394)\ttotal: 2.74s\tremaining: 1.17s\n",
+      "1500:\tlearn: 0.1756772\ttest: 0.3423999\tbest: 0.3423999 (1500)\ttotal: 2.95s\tremaining: 979ms\n",
+      "1600:\tlearn: 0.1709954\ttest: 0.3426386\tbest: 0.3421255 (1541)\ttotal: 3.12s\tremaining: 779ms\n",
+      "1700:\tlearn: 0.1662324\ttest: 0.3423893\tbest: 0.3421255 (1541)\ttotal: 3.35s\tremaining: 589ms\n",
+      "1800:\tlearn: 0.1620149\ttest: 0.3419531\tbest: 0.3419456 (1796)\ttotal: 3.52s\tremaining: 390ms\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1900:\tlearn: 0.1579787\ttest: 0.3420298\tbest: 0.3418931 (1815)\ttotal: 3.71s\tremaining: 193ms\n",
+      "1999:\tlearn: 0.1538067\ttest: 0.3423697\tbest: 0.3418931 (1815)\ttotal: 3.89s\tremaining: 0us\n",
+      "\n",
+      "bestTest = 0.3418931473\n",
+      "bestIteration = 1815\n",
+      "\n",
+      "Shrink model to first 1816 iterations.\n",
+      "Lvl_0_Pipe_1_Mod_3_CatBoost fitting and predicting completed\n",
+      "Start fitting Lvl_0_Pipe_1_Mod_3_CatBoost ...\n",
+      "\n",
+      "===== Start working with fold 0 for Lvl_0_Pipe_1_Mod_3_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5749238\ttest: 0.5962756\tbest: 0.5962756 (0)\ttotal: 3.23ms\tremaining: 9.69s\n",
+      "100:\tlearn: 0.3538624\ttest: 0.3750769\tbest: 0.3750769 (100)\ttotal: 205ms\tremaining: 5.9s\n",
+      "200:\tlearn: 0.3247688\ttest: 0.3579003\tbest: 0.3579003 (200)\ttotal: 397ms\tremaining: 5.53s\n",
+      "300:\tlearn: 0.3067646\ttest: 0.3529264\tbest: 0.3529264 (300)\ttotal: 596ms\tremaining: 5.34s\n",
+      "400:\tlearn: 0.2906869\ttest: 0.3494385\tbest: 0.3494385 (400)\ttotal: 773ms\tremaining: 5.01s\n",
+      "500:\tlearn: 0.2787513\ttest: 0.3480935\tbest: 0.3480935 (500)\ttotal: 940ms\tremaining: 4.69s\n",
+      "600:\tlearn: 0.2682686\ttest: 0.3470561\tbest: 0.3470561 (600)\ttotal: 1.14s\tremaining: 4.56s\n",
+      "700:\tlearn: 0.2590796\ttest: 0.3463205\tbest: 0.3463073 (694)\ttotal: 1.33s\tremaining: 4.36s\n",
+      "800:\tlearn: 0.2514009\ttest: 0.3451208\tbest: 0.3451208 (800)\ttotal: 1.51s\tremaining: 4.16s\n",
+      "900:\tlearn: 0.2444905\ttest: 0.3440930\tbest: 0.3440841 (895)\ttotal: 1.71s\tremaining: 3.98s\n",
+      "1000:\tlearn: 0.2378982\ttest: 0.3435150\tbest: 0.3434602 (992)\ttotal: 1.9s\tremaining: 3.79s\n",
+      "1100:\tlearn: 0.2322087\ttest: 0.3431667\tbest: 0.3431153 (1075)\ttotal: 2.1s\tremaining: 3.63s\n",
+      "1200:\tlearn: 0.2265210\ttest: 0.3425909\tbest: 0.3425467 (1188)\ttotal: 2.29s\tremaining: 3.42s\n",
+      "1300:\tlearn: 0.2213036\ttest: 0.3420838\tbest: 0.3420157 (1288)\ttotal: 2.46s\tremaining: 3.21s\n",
+      "1400:\tlearn: 0.2163428\ttest: 0.3418436\tbest: 0.3417805 (1394)\ttotal: 2.67s\tremaining: 3.05s\n",
+      "1500:\tlearn: 0.2115906\ttest: 0.3414778\tbest: 0.3414778 (1500)\ttotal: 2.88s\tremaining: 2.87s\n",
+      "1600:\tlearn: 0.2070074\ttest: 0.3410625\tbest: 0.3410625 (1600)\ttotal: 3.09s\tremaining: 2.7s\n",
+      "1700:\tlearn: 0.2026507\ttest: 0.3405289\tbest: 0.3405001 (1679)\ttotal: 3.27s\tremaining: 2.5s\n",
+      "1800:\tlearn: 0.1988309\ttest: 0.3401400\tbest: 0.3401251 (1798)\ttotal: 3.48s\tremaining: 2.31s\n",
+      "1900:\tlearn: 0.1952427\ttest: 0.3398704\tbest: 0.3396758 (1880)\ttotal: 3.68s\tremaining: 2.13s\n",
+      "2000:\tlearn: 0.1915851\ttest: 0.3396242\tbest: 0.3396191 (1999)\ttotal: 3.88s\tremaining: 1.94s\n",
+      "2100:\tlearn: 0.1882232\ttest: 0.3395831\tbest: 0.3395527 (2074)\ttotal: 4.07s\tremaining: 1.74s\n",
+      "2200:\tlearn: 0.1848821\ttest: 0.3393809\tbest: 0.3393421 (2165)\ttotal: 4.31s\tremaining: 1.56s\n",
+      "2300:\tlearn: 0.1817400\ttest: 0.3391877\tbest: 0.3391877 (2300)\ttotal: 4.5s\tremaining: 1.37s\n",
+      "2400:\tlearn: 0.1787974\ttest: 0.3391625\tbest: 0.3391625 (2400)\ttotal: 4.69s\tremaining: 1.17s\n",
+      "2500:\tlearn: 0.1756702\ttest: 0.3388642\tbest: 0.3388608 (2499)\ttotal: 4.88s\tremaining: 973ms\n",
+      "2600:\tlearn: 0.1728922\ttest: 0.3389253\tbest: 0.3388231 (2508)\ttotal: 5.09s\tremaining: 781ms\n",
+      "Stopped by overfitting detector  (100 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3388231235\n",
+      "bestIteration = 2508\n",
+      "\n",
+      "Shrink model to first 2509 iterations.\n",
+      "\n",
+      "===== Start working with fold 1 for Lvl_0_Pipe_1_Mod_3_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5830078\ttest: 0.5633221\tbest: 0.5633221 (0)\ttotal: 8.6ms\tremaining: 25.8s\n",
+      "100:\tlearn: 0.3589969\ttest: 0.3533597\tbest: 0.3533597 (100)\ttotal: 196ms\tremaining: 5.61s\n",
+      "200:\tlearn: 0.3307810\ttest: 0.3362463\tbest: 0.3362463 (200)\ttotal: 377ms\tremaining: 5.25s\n",
+      "300:\tlearn: 0.3120042\ttest: 0.3301034\tbest: 0.3301034 (300)\ttotal: 551ms\tremaining: 4.94s\n",
+      "400:\tlearn: 0.2950774\ttest: 0.3273159\tbest: 0.3273074 (398)\ttotal: 732ms\tremaining: 4.74s\n",
+      "500:\tlearn: 0.2822802\ttest: 0.3260960\tbest: 0.3260960 (500)\ttotal: 908ms\tremaining: 4.53s\n",
+      "600:\tlearn: 0.2718319\ttest: 0.3244773\tbest: 0.3244541 (597)\ttotal: 1.11s\tremaining: 4.42s\n",
+      "700:\tlearn: 0.2631367\ttest: 0.3236967\tbest: 0.3236967 (700)\ttotal: 1.29s\tremaining: 4.23s\n",
+      "800:\tlearn: 0.2555498\ttest: 0.3241221\tbest: 0.3236444 (718)\ttotal: 1.48s\tremaining: 4.05s\n",
+      "Stopped by overfitting detector  (100 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3236443836\n",
+      "bestIteration = 718\n",
+      "\n",
+      "Shrink model to first 719 iterations.\n",
+      "\n",
+      "===== Start working with fold 2 for Lvl_0_Pipe_1_Mod_3_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5784948\ttest: 0.5817224\tbest: 0.5817224 (0)\ttotal: 15.4ms\tremaining: 46.3s\n",
+      "100:\tlearn: 0.3581544\ttest: 0.3571058\tbest: 0.3571058 (100)\ttotal: 211ms\tremaining: 6.05s\n",
+      "200:\tlearn: 0.3282811\ttest: 0.3383338\tbest: 0.3383338 (200)\ttotal: 395ms\tremaining: 5.5s\n",
+      "300:\tlearn: 0.3097713\ttest: 0.3322135\tbest: 0.3320776 (297)\ttotal: 573ms\tremaining: 5.14s\n",
+      "400:\tlearn: 0.2938576\ttest: 0.3299511\tbest: 0.3299511 (400)\ttotal: 769ms\tremaining: 4.98s\n",
+      "500:\tlearn: 0.2805774\ttest: 0.3287883\tbest: 0.3287883 (500)\ttotal: 946ms\tremaining: 4.72s\n",
+      "600:\tlearn: 0.2703739\ttest: 0.3269768\tbest: 0.3269716 (599)\ttotal: 1.13s\tremaining: 4.5s\n",
+      "700:\tlearn: 0.2616548\ttest: 0.3258652\tbest: 0.3257247 (696)\ttotal: 1.31s\tremaining: 4.29s\n",
+      "800:\tlearn: 0.2540794\ttest: 0.3248115\tbest: 0.3246713 (780)\ttotal: 1.49s\tremaining: 4.09s\n",
+      "900:\tlearn: 0.2470055\ttest: 0.3240086\tbest: 0.3239652 (896)\ttotal: 1.68s\tremaining: 3.9s\n",
+      "1000:\tlearn: 0.2407159\ttest: 0.3232904\tbest: 0.3232768 (993)\ttotal: 1.87s\tremaining: 3.74s\n",
+      "1100:\tlearn: 0.2349685\ttest: 0.3226389\tbest: 0.3224739 (1072)\ttotal: 2.08s\tremaining: 3.58s\n",
+      "1200:\tlearn: 0.2291905\ttest: 0.3219706\tbest: 0.3219349 (1195)\ttotal: 2.28s\tremaining: 3.42s\n",
+      "1300:\tlearn: 0.2242843\ttest: 0.3216330\tbest: 0.3216282 (1299)\ttotal: 2.48s\tremaining: 3.24s\n",
+      "1400:\tlearn: 0.2193816\ttest: 0.3213742\tbest: 0.3211652 (1345)\ttotal: 2.71s\tremaining: 3.09s\n",
+      "1500:\tlearn: 0.2150231\ttest: 0.3210364\tbest: 0.3209320 (1480)\ttotal: 2.9s\tremaining: 2.9s\n",
+      "1600:\tlearn: 0.2108812\ttest: 0.3206202\tbest: 0.3206202 (1600)\ttotal: 3.08s\tremaining: 2.69s\n",
+      "1700:\tlearn: 0.2066767\ttest: 0.3199278\tbest: 0.3199118 (1699)\ttotal: 3.27s\tremaining: 2.5s\n",
+      "1800:\tlearn: 0.2027083\ttest: 0.3198993\tbest: 0.3198815 (1726)\ttotal: 3.48s\tremaining: 2.31s\n",
+      "Stopped by overfitting detector  (100 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3198814937\n",
+      "bestIteration = 1726\n",
+      "\n",
+      "Shrink model to first 1727 iterations.\n",
+      "\n",
+      "===== Start working with fold 3 for Lvl_0_Pipe_1_Mod_3_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5710290\ttest: 0.6096694\tbest: 0.6096694 (0)\ttotal: 2.86ms\tremaining: 8.58s\n",
+      "100:\tlearn: 0.3444958\ttest: 0.4152803\tbest: 0.4152803 (100)\ttotal: 224ms\tremaining: 6.42s\n",
+      "200:\tlearn: 0.3159040\ttest: 0.3996337\tbest: 0.3996337 (200)\ttotal: 420ms\tremaining: 5.85s\n",
+      "300:\tlearn: 0.2999551\ttest: 0.3924528\tbest: 0.3924528 (300)\ttotal: 601ms\tremaining: 5.38s\n",
+      "400:\tlearn: 0.2851919\ttest: 0.3881614\tbest: 0.3881614 (400)\ttotal: 768ms\tremaining: 4.98s\n",
+      "500:\tlearn: 0.2728422\ttest: 0.3868374\tbest: 0.3867807 (490)\ttotal: 936ms\tremaining: 4.67s\n",
+      "600:\tlearn: 0.2631856\ttest: 0.3861455\tbest: 0.3861455 (600)\ttotal: 1.1s\tremaining: 4.4s\n",
+      "700:\tlearn: 0.2550000\ttest: 0.3857666\tbest: 0.3856754 (668)\ttotal: 1.29s\tremaining: 4.25s\n",
+      "800:\tlearn: 0.2474017\ttest: 0.3856947\tbest: 0.3856013 (792)\ttotal: 1.49s\tremaining: 4.09s\n",
+      "900:\tlearn: 0.2405549\ttest: 0.3855558\tbest: 0.3855096 (888)\ttotal: 1.68s\tremaining: 3.9s\n",
+      "Stopped by overfitting detector  (100 iterations wait)\n",
+      "\n",
+      "bestTest = 0.3855095628\n",
+      "bestIteration = 888\n",
+      "\n",
+      "Shrink model to first 889 iterations.\n",
+      "\n",
+      "===== Start working with fold 4 for Lvl_0_Pipe_1_Mod_3_CatBoost =====\n",
+      "\n",
+      "0:\tlearn: 0.5877937\ttest: 0.5433457\tbest: 0.5433457 (0)\ttotal: 2.46ms\tremaining: 7.39s\n",
+      "100:\tlearn: 0.3635841\ttest: 0.3502432\tbest: 0.3502432 (100)\ttotal: 205ms\tremaining: 5.9s\n",
+      "200:\tlearn: 0.3350821\ttest: 0.3277620\tbest: 0.3277620 (200)\ttotal: 394ms\tremaining: 5.48s\n",
+      "300:\tlearn: 0.3163325\ttest: 0.3186592\tbest: 0.3186268 (298)\ttotal: 581ms\tremaining: 5.21s\n",
+      "400:\tlearn: 0.2991828\ttest: 0.3114547\tbest: 0.3114547 (400)\ttotal: 765ms\tremaining: 4.96s\n",
+      "500:\tlearn: 0.2853312\ttest: 0.3067744\tbest: 0.3067744 (500)\ttotal: 961ms\tremaining: 4.79s\n",
+      "600:\tlearn: 0.2746053\ttest: 0.3043128\tbest: 0.3043128 (600)\ttotal: 1.19s\tremaining: 4.75s\n",
+      "700:\tlearn: 0.2651369\ttest: 0.3024191\tbest: 0.3024121 (699)\ttotal: 1.4s\tremaining: 4.6s\n",
+      "800:\tlearn: 0.2573767\ttest: 0.3007672\tbest: 0.3007672 (800)\ttotal: 1.61s\tremaining: 4.43s\n",
+      "900:\tlearn: 0.2503800\ttest: 0.2996296\tbest: 0.2996044 (890)\ttotal: 1.85s\tremaining: 4.3s\n",
+      "1000:\tlearn: 0.2433897\ttest: 0.2990408\tbest: 0.2990408 (1000)\ttotal: 2.05s\tremaining: 4.1s\n",
+      "1100:\tlearn: 0.2373764\ttest: 0.2977549\tbest: 0.2977112 (1099)\ttotal: 2.24s\tremaining: 3.87s\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1200:\tlearn: 0.2311849\ttest: 0.2972003\tbest: 0.2971525 (1196)\ttotal: 2.42s\tremaining: 3.63s\n",
+      "1300:\tlearn: 0.2256356\ttest: 0.2963918\tbest: 0.2963918 (1300)\ttotal: 2.62s\tremaining: 3.42s\n",
+      "1400:\tlearn: 0.2204745\ttest: 0.2958023\tbest: 0.2958023 (1400)\ttotal: 2.81s\tremaining: 3.2s\n",
+      "1500:\tlearn: 0.2158370\ttest: 0.2953656\tbest: 0.2953011 (1496)\ttotal: 2.98s\tremaining: 2.97s\n",
+      "1600:\tlearn: 0.2115284\ttest: 0.2947484\tbest: 0.2947203 (1567)\ttotal: 3.14s\tremaining: 2.75s\n",
+      "1700:\tlearn: 0.2073122\ttest: 0.2944945\tbest: 0.2944290 (1697)\ttotal: 3.37s\tremaining: 2.57s\n",
+      "Stopped by overfitting detector  (100 iterations wait)\n",
+      "\n",
+      "bestTest = 0.2944289789\n",
+      "bestIteration = 1697\n",
+      "\n",
+      "Shrink model to first 1698 iterations.\n",
+      "Lvl_0_Pipe_1_Mod_3_CatBoost fitting and predicting completed\n",
+      "Time left 37.47469425201416\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Time limit exceeded in one of the tasks. AutoML will blend level 1 models.\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Blending: Optimization starts with equal weights and score -1.7954214419609544\n",
+      "Blending, iter 0: score = -1.4724501895733335, weights = [0.         0.86662203 0.05572809 0.07764989]\n",
+      "Blending, iter 1: score = -1.4661120519816215, weights = [0.         0.7553367  0.10243508 0.14222825]\n",
+      "Blending, iter 2: score = -1.4661120519816215, weights = [0.         0.7553367  0.10243508 0.14222825]\n",
+      "No score update. Terminated\n",
+      "\n",
+      "Automl preset training completed in 66.05 seconds.\n"
+     ]
+    }
+   ],
+   "source": [
+    "automl = TabularUtilizedAutoML(task = task,\n",
+    "                               timeout = TIMEOUT,\n",
+    "                               cpu_limit = N_THREADS,\n",
+    "                               reader_params = {'n_jobs': N_THREADS,\n",
+    "                                                'cv': N_FOLDS,\n",
+    "                                                'random_state': RANDOM_STATE})\n",
+    "\n",
+    "oof_pred = automl.fit_predict(train_data, roles = roles)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#deviation_metric(np.array(train_df['per_square_meter_price']), oof_pred.data[:, 0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output['per_square_meter_price'] = output['per_square_meter_price'] * 0.9\n",
+    "\n",
+    "output.loc[output['per_square_meter_price'] >= 200000, 'per_square_meter_price'] \\\n",
+    "    = output.loc[output['per_square_meter_price'] >= 200000, 'per_square_meter_price'] * 0.9"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 50,
+   "metadata": {
+    "id": "e0d6dfe7"
+   },
+   "outputs": [],
+   "source": [
+    "output = pd.DataFrame({'id': test_data['id'],\n",
+    "                       'per_square_meter_price': automl.predict(test_data).data[:, 0]})\n",
+    "output['per_square_meter_price'] = output['per_square_meter_price'] * 0.9\n",
+    "\n",
+    "output.loc[output['per_square_meter_price'] >= 200000, 'per_square_meter_price'] \\\n",
+    "    = output.loc[output['per_square_meter_price'] >= 200000, 'per_square_meter_price'] * 0.9\n",
+    "\n",
+    "output.to_csv('raifHack_ki7.csv', index=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 51,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(2974, 2)"
+      ]
+     },
+     "execution_count": 51,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "collapsed_sections": [],
+   "name": "housePrice_AutoML.ipynb",
+   "provenance": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/Yapiki_publ/Read me.txt b/Yapiki_publ/Read me.txt
new file mode 100644
index 0000000..4f3107e
--- /dev/null
+++ b/Yapiki_publ/Read me.txt	
@@ -0,0 +1,39 @@
+Решение основано на алгоритме LightAutoML с дополнительным обогащением данных из открытых источников (Росстат).  
+
+
+- Проведен EDA инструментами pandas_profile и сравнениями корреляции метрик разными методами в зависимости от фичей  - 
+Pandas profiling - https://drive.google.com/file/d/1xQl3LvpX9J0G6gJoaBjzRcBFKZi6QZXz/view?usp=sharing
+- Введены дополнительные метрики: премиальность этажей и типирование города  
+- Использованы дополнительные стат данные (среднемесячная заработная плата и численность населения по регионам, Источник: Росстат);
+- Учтен дисконт, закладываемый при ручном расчете (использовали вариант из публичного решения, ссылка на github: https://github.com/BatyaZhizni/Raifhack-DS)
+
+
+Для обогащения данных использованы дополнительные датасеты:
+
+
+1. zarplaty.xlsx - Среднемесячная номинальная начисленная заработная плата работников в целом по экономике по субъектам Российской Федерации за 2000-2020 гг. Источник: Росстат, https://rosstat.gov.ru/labor_market_employment_salaries Ссылка - https://docs.google.com/spreadsheets/d/1S1ORmz2W4QTG-d8odUOqT6Czu21NF2Vw/edit?usp=sharing&ouid=108685579276627434305&rtpof=true&sd=true
+2. zarplaty.xlsx - Численность населения по населенным пунктам России. Источник: Росстат, https://rosstat.gov.ru/folder/12781.  Ссылка: https://drive.google.com/file/d/19hJI_zlTZboxSh_JwPrWt8vYx9lkNlM0/view?usp=sharing
+
+
+Для обучения использовали модель LightAutoML*
+
+
+1. LightAutoML project from Sberbank AI Lab AutoML group is the framework for automatic classification and regression model creation.
+
+
+Authors: Alexander Ryzhkov, Anton Vakhrushev, Dmitry Simakov, Vasilii Bunakov, Rinchin Damdinov, Pavel Shvets, Alexander Kirilin
+
+
+2. Библиотеки
+!pip install https://github.com/pandas-profiling/pandas-profiling/archive/master.zip
+import pandas as pd
+import numpy as np
+import typing
+import torch
+import matplotlib.pyplot as plt
+
+
+!pip install -U lightautoml
+from sklearn.model_selection import train_test_split
+from lightautoml.automl.presets.tabular_presets import TabularUtilizedAutoML
+from lightautoml.tasks import Task
\ No newline at end of file
diff --git a/Yapiki_publ/city_population.rar b/Yapiki_publ/city_population.rar
new file mode 100644
index 0000000..4cad566
Binary files /dev/null and b/Yapiki_publ/city_population.rar differ
diff --git a/Yapiki_publ/zarplaty.xlsx b/Yapiki_publ/zarplaty.xlsx
new file mode 100644
index 0000000..296673c
Binary files /dev/null and b/Yapiki_publ/zarplaty.xlsx differ