{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Загрузка данных"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "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>id</th>\n",
       "      <th>price</th>\n",
       "      <th>bedrooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>sqft_lot</th>\n",
       "      <th>floors</th>\n",
       "      <th>waterfront</th>\n",
       "      <th>view</th>\n",
       "      <th>condition</th>\n",
       "      <th>grade</th>\n",
       "      <th>...</th>\n",
       "      <th>zipcode_98146</th>\n",
       "      <th>zipcode_98148</th>\n",
       "      <th>zipcode_98155</th>\n",
       "      <th>zipcode_98166</th>\n",
       "      <th>zipcode_98168</th>\n",
       "      <th>zipcode_98177</th>\n",
       "      <th>zipcode_98178</th>\n",
       "      <th>zipcode_98188</th>\n",
       "      <th>zipcode_98198</th>\n",
       "      <th>zipcode_98199</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7129300520</td>\n",
       "      <td>221900.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.00</td>\n",
       "      <td>5650</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6414100192</td>\n",
       "      <td>538000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.25</td>\n",
       "      <td>7242</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5631500400</td>\n",
       "      <td>180000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1.00</td>\n",
       "      <td>10000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2487200875</td>\n",
       "      <td>604000.0</td>\n",
       "      <td>4</td>\n",
       "      <td>3.00</td>\n",
       "      <td>5000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1954400510</td>\n",
       "      <td>510000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.00</td>\n",
       "      <td>8080</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21608</th>\n",
       "      <td>263000018</td>\n",
       "      <td>360000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.50</td>\n",
       "      <td>1131</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21609</th>\n",
       "      <td>6600060120</td>\n",
       "      <td>400000.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2.50</td>\n",
       "      <td>5813</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21610</th>\n",
       "      <td>1523300141</td>\n",
       "      <td>402101.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.75</td>\n",
       "      <td>1350</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21611</th>\n",
       "      <td>291310100</td>\n",
       "      <td>400000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.50</td>\n",
       "      <td>2388</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21612</th>\n",
       "      <td>1523300157</td>\n",
       "      <td>325000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0.75</td>\n",
       "      <td>1076</td>\n",
       "      <td>2.0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>21613 rows × 4594 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               id     price  bedrooms  bathrooms  sqft_lot  floors  \\\n",
       "0      7129300520  221900.0         3       1.00      5650     1.0   \n",
       "1      6414100192  538000.0         3       2.25      7242     2.0   \n",
       "2      5631500400  180000.0         2       1.00     10000     1.0   \n",
       "3      2487200875  604000.0         4       3.00      5000     1.0   \n",
       "4      1954400510  510000.0         3       2.00      8080     1.0   \n",
       "...           ...       ...       ...        ...       ...     ...   \n",
       "21608   263000018  360000.0         3       2.50      1131     3.0   \n",
       "21609  6600060120  400000.0         4       2.50      5813     2.0   \n",
       "21610  1523300141  402101.0         2       0.75      1350     2.0   \n",
       "21611   291310100  400000.0         3       2.50      2388     2.0   \n",
       "21612  1523300157  325000.0         2       0.75      1076     2.0   \n",
       "\n",
       "       waterfront  view  condition  grade  ...  zipcode_98146  zipcode_98148  \\\n",
       "0               0     0          3      7  ...            0.0            0.0   \n",
       "1               0     0          3      7  ...            0.0            0.0   \n",
       "2               0     0          3      6  ...            0.0            0.0   \n",
       "3               0     0          5      7  ...            0.0            0.0   \n",
       "4               0     0          3      8  ...            0.0            0.0   \n",
       "...           ...   ...        ...    ...  ...            ...            ...   \n",
       "21608           0     0          3      8  ...            0.0            0.0   \n",
       "21609           0     0          3      8  ...            1.0            0.0   \n",
       "21610           0     0          3      7  ...            0.0            0.0   \n",
       "21611           0     0          3      8  ...            0.0            0.0   \n",
       "21612           0     0          3      7  ...            0.0            0.0   \n",
       "\n",
       "       zipcode_98155  zipcode_98166  zipcode_98168  zipcode_98177  \\\n",
       "0                0.0            0.0            0.0            0.0   \n",
       "1                0.0            0.0            0.0            0.0   \n",
       "2                0.0            0.0            0.0            0.0   \n",
       "3                0.0            0.0            0.0            0.0   \n",
       "4                0.0            0.0            0.0            0.0   \n",
       "...              ...            ...            ...            ...   \n",
       "21608            0.0            0.0            0.0            0.0   \n",
       "21609            0.0            0.0            0.0            0.0   \n",
       "21610            0.0            0.0            0.0            0.0   \n",
       "21611            0.0            0.0            0.0            0.0   \n",
       "21612            0.0            0.0            0.0            0.0   \n",
       "\n",
       "       zipcode_98178  zipcode_98188  zipcode_98198  zipcode_98199  \n",
       "0                1.0            0.0            0.0            0.0  \n",
       "1                0.0            0.0            0.0            0.0  \n",
       "2                0.0            0.0            0.0            0.0  \n",
       "3                0.0            0.0            0.0            0.0  \n",
       "4                0.0            0.0            0.0            0.0  \n",
       "...              ...            ...            ...            ...  \n",
       "21608            0.0            0.0            0.0            0.0  \n",
       "21609            0.0            0.0            0.0            0.0  \n",
       "21610            0.0            0.0            0.0            0.0  \n",
       "21611            0.0            0.0            0.0            0.0  \n",
       "21612            0.0            0.0            0.0            0.0  \n",
       "\n",
       "[21613 rows x 4594 columns]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "import numpy as np  # type: ignore\n",
    "\n",
    "from sklearn import set_config\n",
    "\n",
    "set_config(transform_output=\"pandas\")\n",
    "\n",
    "random_state = 9\n",
    "\n",
    "df = pd.read_csv(\"data/kc_house_data.csv\", index_col=False)\n",
    "\n",
    "encoder = OneHotEncoder(sparse_output=False, drop=\"first\")\n",
    "\n",
    "encoded_values = encoder.fit_transform(df[[\"date\",\"price\",\"yr_built\", \"zipcode\"]])\n",
    "\n",
    "encoded_columns = encoder.get_feature_names_out([\"date\",\"price\", \"yr_built\", \"zipcode\"])\n",
    "\n",
    "encoded_values_df = pd.DataFrame(encoded_values, columns=encoded_columns)\n",
    "\n",
    "df = pd.concat([df, encoded_values_df], axis=1)\n",
    "\n",
    "df = df.drop(\n",
    "    [\n",
    "        \"yr_built\",\n",
    "        \"date\",\n",
    "        \"lat\",\n",
    "        \"sqft_living15\",\n",
    "        \"sqft_lot15\",\n",
    "        \"zipcode\",\n",
    "        \"sqft_basement\",\n",
    "        \"sqft_above\",\n",
    "        \"sqft_living\",\n",
    "    ],\n",
    "    axis=1,\n",
    ")\n",
    "\n",
    "df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Формирование выборок"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'X_train'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>id</th>\n",
       "      <th>price</th>\n",
       "      <th>bedrooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>sqft_lot</th>\n",
       "      <th>waterfront</th>\n",
       "      <th>view</th>\n",
       "      <th>condition</th>\n",
       "      <th>grade</th>\n",
       "      <th>yr_renovated</th>\n",
       "      <th>...</th>\n",
       "      <th>zipcode_98146</th>\n",
       "      <th>zipcode_98148</th>\n",
       "      <th>zipcode_98155</th>\n",
       "      <th>zipcode_98166</th>\n",
       "      <th>zipcode_98168</th>\n",
       "      <th>zipcode_98177</th>\n",
       "      <th>zipcode_98178</th>\n",
       "      <th>zipcode_98188</th>\n",
       "      <th>zipcode_98198</th>\n",
       "      <th>zipcode_98199</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20358</th>\n",
       "      <td>9265880170</td>\n",
       "      <td>550000.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2.50</td>\n",
       "      <td>5954</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10171</th>\n",
       "      <td>98030400</td>\n",
       "      <td>790000.0</td>\n",
       "      <td>4</td>\n",
       "      <td>3.50</td>\n",
       "      <td>6098</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21214</th>\n",
       "      <td>3343903611</td>\n",
       "      <td>615000.0</td>\n",
       "      <td>5</td>\n",
       "      <td>3.25</td>\n",
       "      <td>7069</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8181</th>\n",
       "      <td>1139000215</td>\n",
       "      <td>416000.0</td>\n",
       "      <td>2</td>\n",
       "      <td>1.75</td>\n",
       "      <td>7560</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15657</th>\n",
       "      <td>7893805650</td>\n",
       "      <td>475000.0</td>\n",
       "      <td>5</td>\n",
       "      <td>2.00</td>\n",
       "      <td>10200</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14527</th>\n",
       "      <td>3888100133</td>\n",
       "      <td>360000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.00</td>\n",
       "      <td>10988</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13392</th>\n",
       "      <td>7137800085</td>\n",
       "      <td>185000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.75</td>\n",
       "      <td>9085</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15693</th>\n",
       "      <td>2402100675</td>\n",
       "      <td>645000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>3.75</td>\n",
       "      <td>6000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>5</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19716</th>\n",
       "      <td>3943600070</td>\n",
       "      <td>400000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.50</td>\n",
       "      <td>4788</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7612</th>\n",
       "      <td>6679000720</td>\n",
       "      <td>296000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>2.50</td>\n",
       "      <td>5845</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17290 rows × 4593 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               id     price  bedrooms  bathrooms  sqft_lot  waterfront  view  \\\n",
       "20358  9265880170  550000.0         4       2.50      5954           0     0   \n",
       "10171    98030400  790000.0         4       3.50      6098           0     0   \n",
       "21214  3343903611  615000.0         5       3.25      7069           0     0   \n",
       "8181   1139000215  416000.0         2       1.75      7560           0     0   \n",
       "15657  7893805650  475000.0         5       2.00     10200           0     0   \n",
       "...           ...       ...       ...        ...       ...         ...   ...   \n",
       "14527  3888100133  360000.0         3       1.00     10988           0     0   \n",
       "13392  7137800085  185000.0         3       1.75      9085           0     0   \n",
       "15693  2402100675  645000.0         3       3.75      6000           0     0   \n",
       "19716  3943600070  400000.0         3       2.50      4788           0     0   \n",
       "7612   6679000720  296000.0         3       2.50      5845           0     0   \n",
       "\n",
       "       condition  grade  yr_renovated  ...  zipcode_98146  zipcode_98148  \\\n",
       "20358          3      8             0  ...            0.0            0.0   \n",
       "10171          3     10             0  ...            0.0            0.0   \n",
       "21214          3      9             0  ...            0.0            0.0   \n",
       "8181           4      7             0  ...            0.0            0.0   \n",
       "15657          3      6             0  ...            0.0            0.0   \n",
       "...          ...    ...           ...  ...            ...            ...   \n",
       "14527          3      7             0  ...            0.0            0.0   \n",
       "13392          3      7             0  ...            0.0            0.0   \n",
       "15693          5      7             0  ...            0.0            0.0   \n",
       "19716          3      8             0  ...            0.0            0.0   \n",
       "7612           3      7             0  ...            0.0            0.0   \n",
       "\n",
       "       zipcode_98155  zipcode_98166  zipcode_98168  zipcode_98177  \\\n",
       "20358            0.0            0.0            0.0            0.0   \n",
       "10171            0.0            0.0            0.0            0.0   \n",
       "21214            0.0            0.0            0.0            0.0   \n",
       "8181             0.0            0.0            0.0            0.0   \n",
       "15657            0.0            0.0            0.0            0.0   \n",
       "...              ...            ...            ...            ...   \n",
       "14527            0.0            0.0            0.0            0.0   \n",
       "13392            0.0            0.0            0.0            0.0   \n",
       "15693            0.0            0.0            0.0            0.0   \n",
       "19716            0.0            0.0            0.0            0.0   \n",
       "7612             0.0            0.0            0.0            0.0   \n",
       "\n",
       "       zipcode_98178  zipcode_98188  zipcode_98198  zipcode_98199  \n",
       "20358            0.0            0.0            0.0            0.0  \n",
       "10171            0.0            0.0            0.0            0.0  \n",
       "21214            0.0            0.0            0.0            0.0  \n",
       "8181             0.0            0.0            0.0            0.0  \n",
       "15657            0.0            0.0            1.0            0.0  \n",
       "...              ...            ...            ...            ...  \n",
       "14527            0.0            0.0            0.0            0.0  \n",
       "13392            0.0            0.0            0.0            0.0  \n",
       "15693            0.0            0.0            0.0            0.0  \n",
       "19716            0.0            0.0            0.0            0.0  \n",
       "7612             0.0            0.0            0.0            0.0  \n",
       "\n",
       "[17290 rows x 4593 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'y_train'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>floors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20358</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10171</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21214</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8181</th>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15657</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14527</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13392</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15693</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19716</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7612</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>17290 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       floors\n",
       "20358     2.0\n",
       "10171     2.0\n",
       "21214     2.0\n",
       "8181      1.5\n",
       "15657     1.0\n",
       "...       ...\n",
       "14527     1.0\n",
       "13392     1.0\n",
       "15693     2.0\n",
       "19716     2.0\n",
       "7612      2.0\n",
       "\n",
       "[17290 rows x 1 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'X_test'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>id</th>\n",
       "      <th>price</th>\n",
       "      <th>bedrooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>sqft_lot</th>\n",
       "      <th>waterfront</th>\n",
       "      <th>view</th>\n",
       "      <th>condition</th>\n",
       "      <th>grade</th>\n",
       "      <th>yr_renovated</th>\n",
       "      <th>...</th>\n",
       "      <th>zipcode_98146</th>\n",
       "      <th>zipcode_98148</th>\n",
       "      <th>zipcode_98155</th>\n",
       "      <th>zipcode_98166</th>\n",
       "      <th>zipcode_98168</th>\n",
       "      <th>zipcode_98177</th>\n",
       "      <th>zipcode_98178</th>\n",
       "      <th>zipcode_98188</th>\n",
       "      <th>zipcode_98198</th>\n",
       "      <th>zipcode_98199</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12435</th>\n",
       "      <td>1217000340</td>\n",
       "      <td>340000.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.00</td>\n",
       "      <td>8100</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19037</th>\n",
       "      <td>984200690</td>\n",
       "      <td>299000.0</td>\n",
       "      <td>5</td>\n",
       "      <td>2.50</td>\n",
       "      <td>9360</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6609</th>\n",
       "      <td>7971300020</td>\n",
       "      <td>800000.0</td>\n",
       "      <td>5</td>\n",
       "      <td>2.00</td>\n",
       "      <td>10960</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11869</th>\n",
       "      <td>1498303905</td>\n",
       "      <td>615000.0</td>\n",
       "      <td>4</td>\n",
       "      <td>1.50</td>\n",
       "      <td>3240</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13414</th>\n",
       "      <td>4402700230</td>\n",
       "      <td>352500.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.50</td>\n",
       "      <td>7680</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12113</th>\n",
       "      <td>3861500340</td>\n",
       "      <td>279900.0</td>\n",
       "      <td>3</td>\n",
       "      <td>1.75</td>\n",
       "      <td>6620</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5776</th>\n",
       "      <td>1870400470</td>\n",
       "      <td>637800.0</td>\n",
       "      <td>4</td>\n",
       "      <td>1.75</td>\n",
       "      <td>4750</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8671</th>\n",
       "      <td>4022900571</td>\n",
       "      <td>385000.0</td>\n",
       "      <td>5</td>\n",
       "      <td>2.00</td>\n",
       "      <td>11750</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21551</th>\n",
       "      <td>1561750040</td>\n",
       "      <td>1375000.0</td>\n",
       "      <td>5</td>\n",
       "      <td>4.50</td>\n",
       "      <td>13405</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6634</th>\n",
       "      <td>1853200190</td>\n",
       "      <td>612000.0</td>\n",
       "      <td>4</td>\n",
       "      <td>2.50</td>\n",
       "      <td>5974</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4323 rows × 4593 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               id      price  bedrooms  bathrooms  sqft_lot  waterfront  view  \\\n",
       "12435  1217000340   340000.0         3       1.00      8100           0     0   \n",
       "19037   984200690   299000.0         5       2.50      9360           0     0   \n",
       "6609   7971300020   800000.0         5       2.00     10960           0     0   \n",
       "11869  1498303905   615000.0         4       1.50      3240           0     0   \n",
       "13414  4402700230   352500.0         3       1.50      7680           0     0   \n",
       "...           ...        ...       ...        ...       ...         ...   ...   \n",
       "12113  3861500340   279900.0         3       1.75      6620           0     0   \n",
       "5776   1870400470   637800.0         4       1.75      4750           0     0   \n",
       "8671   4022900571   385000.0         5       2.00     11750           0     0   \n",
       "21551  1561750040  1375000.0         5       4.50     13405           0     0   \n",
       "6634   1853200190   612000.0         4       2.50      5974           0     0   \n",
       "\n",
       "       condition  grade  yr_renovated  ...  zipcode_98146  zipcode_98148  \\\n",
       "12435          4      7             0  ...            0.0            0.0   \n",
       "19037          4      7             0  ...            0.0            0.0   \n",
       "6609           4      7             0  ...            0.0            0.0   \n",
       "11869          4      8             0  ...            0.0            0.0   \n",
       "13414          3      7             0  ...            0.0            0.0   \n",
       "...          ...    ...           ...  ...            ...            ...   \n",
       "12113          3      7             0  ...            0.0            0.0   \n",
       "5776           4      7             0  ...            0.0            0.0   \n",
       "8671           3      7             0  ...            0.0            0.0   \n",
       "21551          3     11             0  ...            0.0            0.0   \n",
       "6634           3      8             0  ...            0.0            0.0   \n",
       "\n",
       "       zipcode_98155  zipcode_98166  zipcode_98168  zipcode_98177  \\\n",
       "12435            0.0            1.0            0.0            0.0   \n",
       "19037            0.0            0.0            0.0            0.0   \n",
       "6609             0.0            0.0            0.0            0.0   \n",
       "11869            0.0            0.0            0.0            0.0   \n",
       "13414            0.0            0.0            0.0            0.0   \n",
       "...              ...            ...            ...            ...   \n",
       "12113            0.0            0.0            0.0            0.0   \n",
       "5776             0.0            0.0            0.0            0.0   \n",
       "8671             1.0            0.0            0.0            0.0   \n",
       "21551            0.0            0.0            0.0            0.0   \n",
       "6634             0.0            0.0            0.0            0.0   \n",
       "\n",
       "       zipcode_98178  zipcode_98188  zipcode_98198  zipcode_98199  \n",
       "12435            0.0            0.0            0.0            0.0  \n",
       "19037            0.0            0.0            0.0            0.0  \n",
       "6609             0.0            0.0            0.0            0.0  \n",
       "11869            0.0            0.0            0.0            0.0  \n",
       "13414            0.0            0.0            0.0            0.0  \n",
       "...              ...            ...            ...            ...  \n",
       "12113            0.0            0.0            0.0            0.0  \n",
       "5776             0.0            0.0            0.0            0.0  \n",
       "8671             0.0            0.0            0.0            0.0  \n",
       "21551            0.0            0.0            0.0            0.0  \n",
       "6634             0.0            0.0            0.0            0.0  \n",
       "\n",
       "[4323 rows x 4593 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "'y_test'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "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>floors</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>12435</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19037</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6609</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11869</th>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13414</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12113</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5776</th>\n",
       "      <td>1.5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8671</th>\n",
       "      <td>1.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21551</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6634</th>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>4323 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       floors\n",
       "12435     1.0\n",
       "19037     1.0\n",
       "6609      1.0\n",
       "11869     1.5\n",
       "13414     1.0\n",
       "...       ...\n",
       "12113     1.0\n",
       "5776      1.5\n",
       "8671      1.0\n",
       "21551     2.0\n",
       "6634      2.0\n",
       "\n",
       "[4323 rows x 1 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from utils import split_stratified_into_train_val_test\n",
    "\n",
    "X_train, X_val, X_test, y_train, y_val, y_test = split_stratified_into_train_val_test(\n",
    "    df,\n",
    "    stratify_colname=\"floors\",\n",
    "    frac_train=0.80,\n",
    "    frac_val=0,\n",
    "    frac_test=0.20,\n",
    "    random_state=random_state,\n",
    ")\n",
    "\n",
    "X_train = X_train.drop([\"floors\"], axis=1)\n",
    "X_test = X_test.drop([\"floors\"], axis=1)\n",
    "\n",
    "display(\"X_train\", X_train)\n",
    "display(\"y_train\", y_train)\n",
    "\n",
    "display(\"X_test\", X_test)\n",
    "display(\"y_test\", y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Определение перечня алгоритмов решения задачи аппроксимации (регрессии)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.preprocessing import PolynomialFeatures\n",
    "from sklearn import linear_model, tree, neighbors, ensemble, neural_network\n",
    "\n",
    "random_state = 9\n",
    "\n",
    "models = {\n",
    "    \"linear\": {\"model\": linear_model.LinearRegression(n_jobs=-1)},\n",
    "    \"linear_poly\": {\n",
    "        \"model\": make_pipeline(\n",
    "            PolynomialFeatures(degree=2),\n",
    "            linear_model.LinearRegression(fit_intercept=False, n_jobs=-1),\n",
    "        )\n",
    "    },\n",
    "    \"linear_interact\": {\n",
    "        \"model\": make_pipeline(\n",
    "            PolynomialFeatures(interaction_only=True),\n",
    "            linear_model.LinearRegression(fit_intercept=False, n_jobs=-1),\n",
    "        )\n",
    "    },\n",
    "    \"ridge\": {\"model\": linear_model.RidgeCV()},\n",
    "    \"decision_tree\": {\n",
    "        \"model\": tree.DecisionTreeRegressor(max_depth=7, random_state=random_state)\n",
    "    },\n",
    "    \"knn\": {\"model\": neighbors.KNeighborsRegressor(n_neighbors=7, n_jobs=-1)},\n",
    "    \"random_forest\": {\n",
    "        \"model\": ensemble.RandomForestRegressor(\n",
    "            max_depth=7, random_state=random_state, n_jobs=-1\n",
    "        )\n",
    "    },\n",
    "    \"mlp\": {\n",
    "        \"model\": neural_network.MLPRegressor(\n",
    "            activation=\"tanh\",\n",
    "            hidden_layer_sizes=(3,),\n",
    "            max_iter=500,\n",
    "            early_stopping=True,\n",
    "            random_state=random_state,\n",
    "        )\n",
    "    },\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Определение функции для стандартизации значений в столбце \"Температура\" для MLP"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pandas import DataFrame\n",
    "from sklearn import preprocessing\n",
    "\n",
    "\n",
    "stndart_scaler = preprocessing.StandardScaler()\n",
    "\n",
    "\n",
    "def std_q(df: DataFrame) -> DataFrame:\n",
    "    df[\"price\"] = np.array(\n",
    "        stndart_scaler.fit_transform(df[\"price\"].to_numpy().reshape(-1, 1))\n",
    "    ).reshape(df[\"price\"].shape)\n",
    "    df[\"bedrooms\"] = np.array(\n",
    "        stndart_scaler.fit_transform(df[\"bedrooms\"].to_numpy().reshape(-1, 1))\n",
    "    ).reshape(df[\"bedrooms\"].shape)\n",
    "    return df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Обучение и оценка моделей с помощью различных алгоритмов"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: linear\n",
      "Model: linear_poly\n",
      "Model: linear_interact\n",
      "Model: ridge\n",
      "Model: decision_tree\n",
      "Model: knn\n",
      "Model: random_forest\n",
      "Model: mlp\n"
     ]
    }
   ],
   "source": [
    "from sklearn.decomposition import PCA\n",
    "import math\n",
    "from pandas import DataFrame\n",
    "from sklearn import metrics\n",
    "\n",
    "# Adding PCA to reduce dimensionality\n",
    "pca = PCA(n_components=100)  # Adjust based on memory constraints\n",
    "\n",
    "# Transform X_train and X_test\n",
    "X_train_reduced = pca.fit_transform(X_train)\n",
    "X_test_reduced = pca.transform(X_test)\n",
    "\n",
    "for model_name in models.keys():\n",
    "    print(f\"Model: {model_name}\")\n",
    "\n",
    "    X_train_model = X_train_reduced\n",
    "    X_test_model = X_test_reduced\n",
    "\n",
    "    if model_name == \"mlp\":\n",
    "        X_train_model = std_q(X_train)\n",
    "        X_test_model = std_q(X_test)\n",
    "\n",
    "    fitted_model = models[model_name][\"model\"].fit(\n",
    "        X_train_model, y_train.values.ravel()\n",
    "    )\n",
    "    y_train_pred = fitted_model.predict(X_train_model)\n",
    "    y_test_pred = fitted_model.predict(X_test_model)\n",
    "    models[model_name][\"fitted\"] = fitted_model\n",
    "    models[model_name][\"train_preds\"] = y_train_pred\n",
    "    models[model_name][\"preds\"] = y_test_pred\n",
    "    models[model_name][\"RMSE_train\"] = math.sqrt(\n",
    "        metrics.mean_squared_error(y_train, y_train_pred)\n",
    "    )\n",
    "    models[model_name][\"RMSE_test\"] = math.sqrt(\n",
    "        metrics.mean_squared_error(y_test, y_test_pred)\n",
    "    )\n",
    "    models[model_name][\"RMAE_test\"] = math.sqrt(\n",
    "        metrics.mean_absolute_error(y_test, y_test_pred)\n",
    "    )\n",
    "    models[model_name][\"R2_test\"] = metrics.r2_score(y_test, y_test_pred)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Вывод результатов оценки"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style type=\"text/css\">\n",
       "#T_67096_row0_col0, #T_67096_row0_col1, #T_67096_row1_col0, #T_67096_row1_col1, #T_67096_row2_col0, #T_67096_row2_col1, #T_67096_row3_col0, #T_67096_row3_col1, #T_67096_row4_col0, #T_67096_row4_col1, #T_67096_row5_col0, #T_67096_row5_col1, #T_67096_row6_col0, #T_67096_row6_col1 {\n",
       "  background-color: #26818e;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_67096_row0_col2, #T_67096_row1_col2, #T_67096_row2_col2, #T_67096_row3_col2, #T_67096_row4_col2, #T_67096_row5_col2, #T_67096_row6_col2, #T_67096_row7_col3 {\n",
       "  background-color: #4e02a2;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_67096_row0_col3, #T_67096_row1_col3, #T_67096_row2_col3, #T_67096_row3_col3, #T_67096_row4_col3, #T_67096_row5_col3, #T_67096_row6_col3, #T_67096_row7_col2 {\n",
       "  background-color: #da5a6a;\n",
       "  color: #f1f1f1;\n",
       "}\n",
       "#T_67096_row7_col0, #T_67096_row7_col1 {\n",
       "  background-color: #a8db34;\n",
       "  color: #000000;\n",
       "}\n",
       "</style>\n",
       "<table id=\"T_67096\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th class=\"blank level0\" >&nbsp;</th>\n",
       "      <th id=\"T_67096_level0_col0\" class=\"col_heading level0 col0\" >RMSE_train</th>\n",
       "      <th id=\"T_67096_level0_col1\" class=\"col_heading level0 col1\" >RMSE_test</th>\n",
       "      <th id=\"T_67096_level0_col2\" class=\"col_heading level0 col2\" >RMAE_test</th>\n",
       "      <th id=\"T_67096_level0_col3\" class=\"col_heading level0 col3\" >R2_test</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row0\" class=\"row_heading level0 row0\" >random_forest</th>\n",
       "      <td id=\"T_67096_row0_col0\" class=\"data row0 col0\" >0.345951</td>\n",
       "      <td id=\"T_67096_row0_col1\" class=\"data row0 col1\" >0.377087</td>\n",
       "      <td id=\"T_67096_row0_col2\" class=\"data row0 col2\" >0.535564</td>\n",
       "      <td id=\"T_67096_row0_col3\" class=\"data row0 col3\" >0.513150</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row1\" class=\"row_heading level0 row1\" >linear</th>\n",
       "      <td id=\"T_67096_row1_col0\" class=\"data row1 col0\" >0.395435</td>\n",
       "      <td id=\"T_67096_row1_col1\" class=\"data row1 col1\" >0.394567</td>\n",
       "      <td id=\"T_67096_row1_col2\" class=\"data row1 col2\" >0.556776</td>\n",
       "      <td id=\"T_67096_row1_col3\" class=\"data row1 col3\" >0.466967</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row2\" class=\"row_heading level0 row2\" >decision_tree</th>\n",
       "      <td id=\"T_67096_row2_col0\" class=\"data row2 col0\" >0.370941</td>\n",
       "      <td id=\"T_67096_row2_col1\" class=\"data row2 col1\" >0.419609</td>\n",
       "      <td id=\"T_67096_row2_col2\" class=\"data row2 col2\" >0.546781</td>\n",
       "      <td id=\"T_67096_row2_col3\" class=\"data row2 col3\" >0.397161</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row3\" class=\"row_heading level0 row3\" >knn</th>\n",
       "      <td id=\"T_67096_row3_col0\" class=\"data row3 col0\" >0.407775</td>\n",
       "      <td id=\"T_67096_row3_col1\" class=\"data row3 col1\" >0.480928</td>\n",
       "      <td id=\"T_67096_row3_col2\" class=\"data row3 col2\" >0.599105</td>\n",
       "      <td id=\"T_67096_row3_col3\" class=\"data row3 col3\" >0.208099</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row4\" class=\"row_heading level0 row4\" >mlp</th>\n",
       "      <td id=\"T_67096_row4_col0\" class=\"data row4 col0\" >0.542558</td>\n",
       "      <td id=\"T_67096_row4_col1\" class=\"data row4 col1\" >0.545098</td>\n",
       "      <td id=\"T_67096_row4_col2\" class=\"data row4 col2\" >0.700044</td>\n",
       "      <td id=\"T_67096_row4_col3\" class=\"data row4 col3\" >-0.017329</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row5\" class=\"row_heading level0 row5\" >linear_interact</th>\n",
       "      <td id=\"T_67096_row5_col0\" class=\"data row5 col0\" >0.689103</td>\n",
       "      <td id=\"T_67096_row5_col1\" class=\"data row5 col1\" >0.688884</td>\n",
       "      <td id=\"T_67096_row5_col2\" class=\"data row5 col2\" >0.681739</td>\n",
       "      <td id=\"T_67096_row5_col3\" class=\"data row5 col3\" >-0.624815</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row6\" class=\"row_heading level0 row6\" >linear_poly</th>\n",
       "      <td id=\"T_67096_row6_col0\" class=\"data row6 col0\" >4.966961</td>\n",
       "      <td id=\"T_67096_row6_col1\" class=\"data row6 col1\" >5.119087</td>\n",
       "      <td id=\"T_67096_row6_col2\" class=\"data row6 col2\" >1.798987</td>\n",
       "      <td id=\"T_67096_row6_col3\" class=\"data row6 col3\" >-88.721546</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th id=\"T_67096_level0_row7\" class=\"row_heading level0 row7\" >ridge</th>\n",
       "      <td id=\"T_67096_row7_col0\" class=\"data row7 col0\" >76554.119536</td>\n",
       "      <td id=\"T_67096_row7_col1\" class=\"data row7 col1\" >77087.654118</td>\n",
       "      <td id=\"T_67096_row7_col2\" class=\"data row7 col2\" >261.058309</td>\n",
       "      <td id=\"T_67096_row7_col3\" class=\"data row7 col3\" >-20346113161.492393</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n"
      ],
      "text/plain": [
       "<pandas.io.formats.style.Styler at 0x19c965a4170>"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "reg_metrics = pd.DataFrame.from_dict(models, \"index\")[\n",
    "    [\"RMSE_train\", \"RMSE_test\", \"RMAE_test\", \"R2_test\"]\n",
    "]\n",
    "reg_metrics.sort_values(by=\"RMSE_test\").style.background_gradient(\n",
    "    cmap=\"viridis\", low=1, high=0.3, subset=[\"RMSE_train\", \"RMSE_test\"]\n",
    ").background_gradient(cmap=\"plasma\", low=0.3, high=1, subset=[\"RMAE_test\", \"R2_test\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Вывод реального и \"спрогнозированного\" результата для обучающей и тестовой выборок"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Получение лучшей модели"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'random_forest'"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "best_model = str(reg_metrics.sort_values(by=\"RMSE_test\").iloc[0].name)\n",
    "\n",
    "display(best_model)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Вывод для обучающей выборки"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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>id</th>\n",
       "      <th>price</th>\n",
       "      <th>bedrooms</th>\n",
       "      <th>bathrooms</th>\n",
       "      <th>sqft_lot</th>\n",
       "      <th>waterfront</th>\n",
       "      <th>view</th>\n",
       "      <th>condition</th>\n",
       "      <th>grade</th>\n",
       "      <th>yr_renovated</th>\n",
       "      <th>...</th>\n",
       "      <th>zipcode_98155</th>\n",
       "      <th>zipcode_98166</th>\n",
       "      <th>zipcode_98168</th>\n",
       "      <th>zipcode_98177</th>\n",
       "      <th>zipcode_98178</th>\n",
       "      <th>zipcode_98188</th>\n",
       "      <th>zipcode_98198</th>\n",
       "      <th>zipcode_98199</th>\n",
       "      <th>floors</th>\n",
       "      <th>DensityPred</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>20358</th>\n",
       "      <td>9265880170</td>\n",
       "      <td>0.026934</td>\n",
       "      <td>0.674642</td>\n",
       "      <td>2.50</td>\n",
       "      <td>5954</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.763424</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10171</th>\n",
       "      <td>98030400</td>\n",
       "      <td>0.684474</td>\n",
       "      <td>0.674642</td>\n",
       "      <td>3.50</td>\n",
       "      <td>6098</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.951525</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21214</th>\n",
       "      <td>3343903611</td>\n",
       "      <td>0.205017</td>\n",
       "      <td>1.742826</td>\n",
       "      <td>3.25</td>\n",
       "      <td>7069</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.802658</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8181</th>\n",
       "      <td>1139000215</td>\n",
       "      <td>-0.340193</td>\n",
       "      <td>-1.461725</td>\n",
       "      <td>1.75</td>\n",
       "      <td>7560</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.5</td>\n",
       "      <td>1.183226</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15657</th>\n",
       "      <td>7893805650</td>\n",
       "      <td>-0.178548</td>\n",
       "      <td>1.742826</td>\n",
       "      <td>2.00</td>\n",
       "      <td>10200</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1.201648</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 4595 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               id     price  bedrooms  bathrooms  sqft_lot  waterfront  view  \\\n",
       "20358  9265880170  0.026934  0.674642       2.50      5954           0     0   \n",
       "10171    98030400  0.684474  0.674642       3.50      6098           0     0   \n",
       "21214  3343903611  0.205017  1.742826       3.25      7069           0     0   \n",
       "8181   1139000215 -0.340193 -1.461725       1.75      7560           0     0   \n",
       "15657  7893805650 -0.178548  1.742826       2.00     10200           0     0   \n",
       "\n",
       "       condition  grade  yr_renovated  ...  zipcode_98155  zipcode_98166  \\\n",
       "20358          3      8             0  ...            0.0            0.0   \n",
       "10171          3     10             0  ...            0.0            0.0   \n",
       "21214          3      9             0  ...            0.0            0.0   \n",
       "8181           4      7             0  ...            0.0            0.0   \n",
       "15657          3      6             0  ...            0.0            0.0   \n",
       "\n",
       "       zipcode_98168  zipcode_98177  zipcode_98178  zipcode_98188  \\\n",
       "20358            0.0            0.0            0.0            0.0   \n",
       "10171            0.0            0.0            0.0            0.0   \n",
       "21214            0.0            0.0            0.0            0.0   \n",
       "8181             0.0            0.0            0.0            0.0   \n",
       "15657            0.0            0.0            0.0            0.0   \n",
       "\n",
       "       zipcode_98198  zipcode_98199  floors  DensityPred  \n",
       "20358            0.0            0.0     2.0     1.763424  \n",
       "10171            0.0            0.0     2.0     1.951525  \n",
       "21214            0.0            0.0     2.0     1.802658  \n",
       "8181             0.0            0.0     1.5     1.183226  \n",
       "15657            1.0            0.0     1.0     1.201648  \n",
       "\n",
       "[5 rows x 4595 columns]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat(\n",
    "    [\n",
    "        X_train,\n",
    "        y_train,\n",
    "        pd.Series(\n",
    "            models[best_model][\"train_preds\"],\n",
    "            index=y_train.index,\n",
    "            name=\"FloorPred\",\n",
    "        ),\n",
    "    ],\n",
    "    axis=1,\n",
    ").head(5)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Вывод для тестовой выборки"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "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>T</th>\n",
       "      <th>Al2O3</th>\n",
       "      <th>TiO2</th>\n",
       "      <th>Density</th>\n",
       "      <th>DensityPred</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>30</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.05696</td>\n",
       "      <td>1.057040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>55</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.04158</td>\n",
       "      <td>1.041341</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>25</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.08438</td>\n",
       "      <td>1.084063</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>30</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.08112</td>\n",
       "      <td>1.080764</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>35</td>\n",
       "      <td>0.05</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1.07781</td>\n",
       "      <td>1.077444</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    T  Al2O3  TiO2  Density  DensityPred\n",
       "0  30   0.00   0.0  1.05696     1.057040\n",
       "1  55   0.00   0.0  1.04158     1.041341\n",
       "2  25   0.05   0.0  1.08438     1.084063\n",
       "3  30   0.05   0.0  1.08112     1.080764\n",
       "4  35   0.05   0.0  1.07781     1.077444"
      ]
     },
     "execution_count": 154,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.concat(\n",
    "    [\n",
    "        X_test,\n",
    "        y_test,\n",
    "        pd.Series(\n",
    "            models[best_model][\"preds\"],\n",
    "            index=y_test.index,\n",
    "            name=\"FloorsPred\",\n",
    "        ),\n",
    "    ],\n",
    "    axis=1,\n",
    ").head(5)"
   ]
  }
 ],
 "metadata": {
  "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": "3.12.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}