{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "9hcdRjNhDlfa"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from sklearn.impute import SimpleImputer\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "from sklearn.model_selection import GridSearchCV, train_test_split, cross_val_score\n",
    "from sklearn.neighbors import KNeighborsRegressor\n",
    "from sklearn.metrics import mean_squared_error, r2_score\n",
    "from sklearn import preprocessing\n",
    "from sklearn.linear_model import LinearRegression, Lasso, Ridge\n",
    "from sklearn.feature_selection import VarianceThreshold, SelectFromModel\n",
    "from sklearn.pipeline import Pipeline\n",
    "\n",
    "from sklearn.tree import DecisionTreeRegressor, plot_tree\n",
    "from sklearn.ensemble import BaggingRegressor, RandomForestRegressor\n",
    "from tqdm.auto import trange"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "HoPCr-BoDduR"
   },
   "outputs": [],
   "source": [
    "url_a6tf ='https://drive.google.com/file/d/12V3p_jVKzrkMTLImFLxv_1YRymz5qTWG/view?usp=share_link'\n",
    "url_a6tf='https://drive.google.com/uc?id=' + url_a6tf.split('/')[-2]\n",
    "url_th ='https://drive.google.com/file/d/1XC-fCaBnDiQLm82sWfMuhzPJtIytDfuy/view?usp=share_link'\n",
    "url_th='https://drive.google.com/uc?id=' + url_th.split('/')[-2]\n",
    "url_tet ='https://docs.google.com/spreadsheets/d/1CkelCtYNUOi2VtMP7bY-XfstuGgWSL1f/edit?usp=share_link&ouid=101749734890205141586&rtpof=true&sd=true'\n",
    "url_tet='https://drive.google.com/uc?id=' + url_tet.split('/')[-2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "0Nu5vaqxDiTZ"
   },
   "outputs": [],
   "source": [
    "a6tf = pd.read_csv(url_a6tf)\n",
    "a6tf[['Participant Private ID']] = a6tf[['Participant Private ID']].astype(int)\n",
    "a6tf.drop('Participant Public ID', axis=1, inplace=True)\n",
    "a6tf = a6tf.set_index('Participant Private ID')\n",
    "\n",
    "a6tf['DoBRU-year'].fillna(a6tf['DoBRU-year'].median(), inplace=True)\n",
    "a6tf.columns = ['Gender', 'Age', 'Education']\n",
    "\n",
    "\n",
    "task_huav = pd.read_csv(url_th)\n",
    "task_huav[['Participant Private ID']] = task_huav[['Participant Private ID']].astype(int)\n",
    "task_huav.drop('Participant Public ID', axis=1, inplace=True)\n",
    "task_huav = task_huav.set_index('Participant Private ID')\n",
    "task_huav_con = task_huav[task_huav.columns[:3]]\n",
    "task_huav_con.columns = ['Consent fair offer',\n",
    "       'Consent conditionally fair offer', 'Consent unfair offer']\n",
    "\n",
    "\n",
    "triada_empathy_tolerance = pd.read_excel(url_tet, index_col=1)\n",
    "triada_empathy_tolerance.drop('Unnamed: 0', axis=1, inplace=True)\n",
    "\n",
    "data = pd.concat([a6tf, triada_empathy_tolerance, task_huav_con], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 327
    },
    "id": "s0Qvw9g18Or3",
    "outputId": "36f69508-f09b-4f64-9731-2399c5e34b61"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-7ab50761-a33f-46e2-8300-782d5ec9cf39\" class=\"colab-df-container\">\n",
       "    <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>Gender</th>\n",
       "      <th>Age</th>\n",
       "      <th>Education</th>\n",
       "      <th>Machiavellianism</th>\n",
       "      <th>Psychopathy</th>\n",
       "      <th>Narcissism</th>\n",
       "      <th>Perspective-taking scale</th>\n",
       "      <th>Fantasy scale</th>\n",
       "      <th>Empathic concern scale</th>\n",
       "      <th>Personal distress scale</th>\n",
       "      <th>Tolerance to uncertainty</th>\n",
       "      <th>Intolerance to uncertainty</th>\n",
       "      <th>Interpersonal intolerance to uncertainty</th>\n",
       "      <th>Consent fair offer</th>\n",
       "      <th>Consent conditionally fair offer</th>\n",
       "      <th>Consent unfair offer</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Participant Private ID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>6905533</th>\n",
       "      <td>2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>3</td>\n",
       "      <td>11</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>22</td>\n",
       "      <td>35</td>\n",
       "      <td>27</td>\n",
       "      <td>24</td>\n",
       "      <td>50</td>\n",
       "      <td>49</td>\n",
       "      <td>46</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6908178</th>\n",
       "      <td>2</td>\n",
       "      <td>28.0</td>\n",
       "      <td>5</td>\n",
       "      <td>15</td>\n",
       "      <td>6</td>\n",
       "      <td>17</td>\n",
       "      <td>25</td>\n",
       "      <td>15</td>\n",
       "      <td>29</td>\n",
       "      <td>17</td>\n",
       "      <td>66</td>\n",
       "      <td>64</td>\n",
       "      <td>30</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "      <td>10</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7079747</th>\n",
       "      <td>2</td>\n",
       "      <td>19.0</td>\n",
       "      <td>5</td>\n",
       "      <td>19</td>\n",
       "      <td>18</td>\n",
       "      <td>14</td>\n",
       "      <td>21</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "      <td>7</td>\n",
       "      <td>57</td>\n",
       "      <td>69</td>\n",
       "      <td>29</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7079758</th>\n",
       "      <td>2</td>\n",
       "      <td>21.0</td>\n",
       "      <td>4</td>\n",
       "      <td>9</td>\n",
       "      <td>10</td>\n",
       "      <td>18</td>\n",
       "      <td>26</td>\n",
       "      <td>27</td>\n",
       "      <td>23</td>\n",
       "      <td>26</td>\n",
       "      <td>62</td>\n",
       "      <td>59</td>\n",
       "      <td>44</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7081909</th>\n",
       "      <td>2</td>\n",
       "      <td>20.0</td>\n",
       "      <td>3</td>\n",
       "      <td>10</td>\n",
       "      <td>12</td>\n",
       "      <td>10</td>\n",
       "      <td>24</td>\n",
       "      <td>19</td>\n",
       "      <td>21</td>\n",
       "      <td>21</td>\n",
       "      <td>71</td>\n",
       "      <td>41</td>\n",
       "      <td>36</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-7ab50761-a33f-46e2-8300-782d5ec9cf39')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-7ab50761-a33f-46e2-8300-782d5ec9cf39 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-7ab50761-a33f-46e2-8300-782d5ec9cf39');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "<div id=\"df-a1ca9e13-f9c4-4ce3-b8d4-d100143b074d\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-a1ca9e13-f9c4-4ce3-b8d4-d100143b074d')\"\n",
       "            title=\"Suggest charts.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "     width=\"24px\">\n",
       "    <g>\n",
       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
       "    </g>\n",
       "</svg>\n",
       "  </button>\n",
       "\n",
       "<style>\n",
       "  .colab-df-quickchart {\n",
       "      --bg-color: #E8F0FE;\n",
       "      --fill-color: #1967D2;\n",
       "      --hover-bg-color: #E2EBFA;\n",
       "      --hover-fill-color: #174EA6;\n",
       "      --disabled-fill-color: #AAA;\n",
       "      --disabled-bg-color: #DDD;\n",
       "  }\n",
       "\n",
       "  [theme=dark] .colab-df-quickchart {\n",
       "      --bg-color: #3B4455;\n",
       "      --fill-color: #D2E3FC;\n",
       "      --hover-bg-color: #434B5C;\n",
       "      --hover-fill-color: #FFFFFF;\n",
       "      --disabled-bg-color: #3B4455;\n",
       "      --disabled-fill-color: #666;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart {\n",
       "    background-color: var(--bg-color);\n",
       "    border: none;\n",
       "    border-radius: 50%;\n",
       "    cursor: pointer;\n",
       "    display: none;\n",
       "    fill: var(--fill-color);\n",
       "    height: 32px;\n",
       "    padding: 0;\n",
       "    width: 32px;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart:hover {\n",
       "    background-color: var(--hover-bg-color);\n",
       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "    fill: var(--button-hover-fill-color);\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart-complete:disabled,\n",
       "  .colab-df-quickchart-complete:disabled:hover {\n",
       "    background-color: var(--disabled-bg-color);\n",
       "    fill: var(--disabled-fill-color);\n",
       "    box-shadow: none;\n",
       "  }\n",
       "\n",
       "  .colab-df-spinner {\n",
       "    border: 2px solid var(--fill-color);\n",
       "    border-color: transparent;\n",
       "    border-bottom-color: var(--fill-color);\n",
       "    animation:\n",
       "      spin 1s steps(1) infinite;\n",
       "  }\n",
       "\n",
       "  @keyframes spin {\n",
       "    0% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "      border-left-color: var(--fill-color);\n",
       "    }\n",
       "    20% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    30% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    40% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    60% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    80% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "    90% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "  }\n",
       "</style>\n",
       "\n",
       "  <script>\n",
       "    async function quickchart(key) {\n",
       "      const quickchartButtonEl =\n",
       "        document.querySelector('#' + key + ' button');\n",
       "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
       "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
       "      try {\n",
       "        const charts = await google.colab.kernel.invokeFunction(\n",
       "            'suggestCharts', [key], {});\n",
       "      } catch (error) {\n",
       "        console.error('Error during call to suggestCharts:', error);\n",
       "      }\n",
       "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
       "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
       "    }\n",
       "    (() => {\n",
       "      let quickchartButtonEl =\n",
       "        document.querySelector('#df-a1ca9e13-f9c4-4ce3-b8d4-d100143b074d button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "                        Gender   Age  Education  Machiavellianism  \\\n",
       "Participant Private ID                                              \n",
       "6905533                      2  20.0          3                11   \n",
       "6908178                      2  28.0          5                15   \n",
       "7079747                      2  19.0          5                19   \n",
       "7079758                      2  21.0          4                 9   \n",
       "7081909                      2  20.0          3                10   \n",
       "\n",
       "                        Psychopathy  Narcissism  Perspective-taking scale  \\\n",
       "Participant Private ID                                                      \n",
       "6905533                           5          15                        22   \n",
       "6908178                           6          17                        25   \n",
       "7079747                          18          14                        21   \n",
       "7079758                          10          18                        26   \n",
       "7081909                          12          10                        24   \n",
       "\n",
       "                        Fantasy scale  Empathic concern scale  \\\n",
       "Participant Private ID                                          \n",
       "6905533                            35                      27   \n",
       "6908178                            15                      29   \n",
       "7079747                             7                       7   \n",
       "7079758                            27                      23   \n",
       "7081909                            19                      21   \n",
       "\n",
       "                        Personal distress scale  Tolerance to uncertainty  \\\n",
       "Participant Private ID                                                      \n",
       "6905533                                      24                        50   \n",
       "6908178                                      17                        66   \n",
       "7079747                                       7                        57   \n",
       "7079758                                      26                        62   \n",
       "7081909                                      21                        71   \n",
       "\n",
       "                        Intolerance to uncertainty  \\\n",
       "Participant Private ID                               \n",
       "6905533                                         49   \n",
       "6908178                                         64   \n",
       "7079747                                         69   \n",
       "7079758                                         59   \n",
       "7081909                                         41   \n",
       "\n",
       "                        Interpersonal intolerance to uncertainty  \\\n",
       "Participant Private ID                                             \n",
       "6905533                                                       46   \n",
       "6908178                                                       30   \n",
       "7079747                                                       29   \n",
       "7079758                                                       44   \n",
       "7081909                                                       36   \n",
       "\n",
       "                        Consent fair offer  Consent conditionally fair offer  \\\n",
       "Participant Private ID                                                         \n",
       "6905533                                  6                                 6   \n",
       "6908178                                  6                                 6   \n",
       "7079747                                  6                                 3   \n",
       "7079758                                  5                                 4   \n",
       "7081909                                  6                                 3   \n",
       "\n",
       "                        Consent unfair offer  \n",
       "Participant Private ID                        \n",
       "6905533                                    0  \n",
       "6908178                                   10  \n",
       "7079747                                    0  \n",
       "7079758                                    4  \n",
       "7081909                                    0  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 388
    },
    "id": "DbpkDapZIlXA",
    "outputId": "9f0de84f-9dd5-47aa-f275-6b5b2f74dc3c"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 600x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(6, 4))\n",
    "plt.hist(data[\"Interpersonal intolerance to uncertainty\"])\n",
    "plt.xlabel(\"Interpersonal intolerance to uncertainty\")\n",
    "plt.ylabel(\"Count\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 506
    },
    "id": "3daXg-37Ku9U",
    "outputId": "88b1a126-0d3c-4a46-be85-236f7710c1fc"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 562.236x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.displot(data, x=\"Interpersonal intolerance to uncertainty\", hue=\"Gender\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 312
    },
    "id": "JSWg2-owaV0Z",
    "outputId": "e0beee0a-c360-4aab-bb9b-ec2f73bbf401"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x300 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10, 3))\n",
    "\n",
    "plt.subplot(1, 3, 1)\n",
    "plt.hist(data[\"Consent fair offer\"])\n",
    "plt.ylabel(\"Count\")\n",
    "plt.xlabel(\"Consent fair offer\")\n",
    "\n",
    "plt.subplot(1, 3, 2)\n",
    "plt.hist(data[\"Consent conditionally fair offer\"])\n",
    "plt.xlabel(\"Consent conditionally fair offer\")\n",
    "\n",
    "plt.subplot(1, 3, 3)\n",
    "plt.hist(data[\"Consent unfair offer\"])\n",
    "plt.xlabel(\"Consent unfair offer\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "SuI5FQ_Re2sg"
   },
   "outputs": [],
   "source": [
    "# sns.heatmap(data.corr(), cmap=\"vlag\", annot=True, fmt=\"0.1f\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 388
    },
    "id": "pMc797oGfWKn",
    "outputId": "8b10b78a-96e2-4616-cfbf-3b2d077d03bc"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 500x400 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(5, 4))\n",
    "plt.scatter(data[\"Personal distress scale\"], data[\"Interpersonal intolerance to uncertainty\"])\n",
    "plt.xlabel(\"Personal distress scale\")\n",
    "plt.ylabel(\"Interpersonal intolerance to uncertainty\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "TofBZ1o6bcu2"
   },
   "outputs": [],
   "source": [
    "X = data.iloc[:, :-3]\n",
    "y = data.iloc[:, -3:]\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "mN7barRo-HyL"
   },
   "source": [
    "Масштабирование"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "W4PINWoboI9A"
   },
   "outputs": [],
   "source": [
    "normalizer = preprocessing.MinMaxScaler()\n",
    "X_train_norm = pd.DataFrame(normalizer.fit_transform(X_train), columns=X_train.columns)\n",
    "X_test_norm = pd.DataFrame(normalizer.transform(X_test), columns=X_test.columns)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "b4zsWwfY8rLw"
   },
   "source": [
    "Линейная регрессия без регуляризации"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "obHTFLg2cnab",
    "outputId": "8ace8299-f043-42e9-e1c0-1f3b9e0f9375"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 8.18966093857268\n",
      "Test MSE: 21.257070536114252\n",
      "Train R2: 0.3157315135538022\n",
      "Test R2: -0.8434039895008049\n"
     ]
    }
   ],
   "source": [
    "lr = LinearRegression().fit(X_train, y_train)\n",
    "pred_train = lr.predict(X_train)\n",
    "pred_test = lr.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 430
    },
    "id": "eiE5lOGQqfPw",
    "outputId": "dd491d84-cbfe-4fe7-ff97-358cede5398f"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.hist(lr.coef_);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "Mk2mucZR9R9k"
   },
   "source": [
    "Регуляризация на масштабированных данных"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "-VUxHUkutTks",
    "outputId": "b05833fc-7816-4fd6-c48d-15585b978049"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 9.217117150729573\n",
      "Test MSE: 15.53059466545225\n",
      "Train R2: 0.09537782055025223\n",
      "Test R2: -0.43227209774871916\n"
     ]
    }
   ],
   "source": [
    "lasso = Lasso(0.1).fit(X_train_norm, y_train)\n",
    "pred_train = lasso.predict(X_train_norm)\n",
    "pred_test = lasso.predict(X_test_norm)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "xz80jFYpuorP",
    "outputId": "eb1b87c2-e6d6-45bf-a6c9-001bda58ee71"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 9.610828591169236\n",
      "Test MSE: 13.348546952378536\n",
      "Train R2: 0.15367984887364175\n",
      "Test R2: -0.35774882913053724\n"
     ]
    }
   ],
   "source": [
    "ridge = Ridge(5.0).fit(X_train_norm, y_train)\n",
    "pred_train = ridge.predict(X_train_norm)\n",
    "pred_test = ridge.predict(X_test_norm)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "gT22pmRo_8UY"
   },
   "source": [
    "Можно попробовать удалить признаки, которые имеют низкую дисперсию, и посмотреть, как изменится качество"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "bR3CpHLFvh0T",
    "outputId": "b3709344-ce38-4ee7-98a0-1239d3b7a84a"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Gender              0.160870\n",
       "Education           0.106069\n",
       "Machiavellianism    0.076200\n",
       "Psychopathy         0.071482\n",
       "Fantasy scale       0.069939\n",
       "dtype: float64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "features_variance = X_train_norm.var().sort_values(ascending=False)\n",
    "features_variance.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "dslcb3qt9rX3"
   },
   "outputs": [],
   "source": [
    "vs_transformer = VarianceThreshold(0.05)\n",
    "\n",
    "X_train_var = pd.DataFrame(\n",
    "    data=vs_transformer.fit_transform(X_train_norm),\n",
    "    columns=X_train_norm.columns[vs_transformer.get_support()],\n",
    ")\n",
    "X_test_var = pd.DataFrame(\n",
    "    data=vs_transformer.transform(X_test_norm),\n",
    "    columns=X_test_norm.columns[vs_transformer.get_support()],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "t8bTRF0k9_uZ",
    "outputId": "50ed7f8a-635f-4cb6-cd9b-d7b0c0ac02c2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 8.735283185341022\n",
      "Test MSE: 18.577903316850726\n",
      "Train R2: 0.2541857159529342\n",
      "Test R2: -0.7095808605731854\n"
     ]
    }
   ],
   "source": [
    "lr = LinearRegression().fit(X_train_var, y_train)\n",
    "pred_train = lr.predict(X_train_var)\n",
    "pred_test = lr.predict(X_test_var)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "ZQmTOk7qCRyD"
   },
   "source": [
    "Можно отобрать признаки с помощью L1-регуляризации"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "cHrCojdU-iD3"
   },
   "outputs": [],
   "source": [
    "lasso = Lasso(0.1)\n",
    "l1_select = SelectFromModel(lasso)\n",
    "\n",
    "X_train_l1 = pd.DataFrame(\n",
    "    data=l1_select.fit_transform(X_train_var, y_train),\n",
    "    columns=X_train_var.columns[l1_select.get_support()],\n",
    ")\n",
    "X_test_l1 = pd.DataFrame(\n",
    "    data=l1_select.transform(X_test_var),\n",
    "    columns=X_test_var.columns[l1_select.get_support()],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "S38fekQ6_BWo",
    "outputId": "4d1fa7ed-f9c4-474f-864a-82846673131e"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 8.793567754636923\n",
      "Test MSE: 18.34049933615555\n",
      "Train R2: 0.19187751924745536\n",
      "Test R2: -0.6493567366158864\n"
     ]
    }
   ],
   "source": [
    "lr = LinearRegression().fit(X_train_l1, y_train)\n",
    "pred_train = lr.predict(X_train_l1)\n",
    "pred_test = lr.predict(X_test_l1)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "EjDHc_yk_CIQ"
   },
   "outputs": [],
   "source": [
    "pipe = Pipeline(\n",
    "    steps=[\n",
    "        (\"scaler\", preprocessing.MinMaxScaler()),\n",
    "        (\"variance\", VarianceThreshold(0.05)),\n",
    "        (\"selection\", SelectFromModel(Lasso(0.1))),\n",
    "        (\"regressor\", Ridge(5.0)),\n",
    "    ]\n",
    ")\n",
    "\n",
    "pipe.fit(X_train, y_train);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "40FLilqpBV0F",
    "outputId": "7fcef5cd-74c5-4f15-e1e2-94197e304fa2"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 9.803741027163744\n",
      "Test MSE: 12.840515052707088\n",
      "Train R2: 0.11555920750328763\n",
      "Test R2: -0.329484930006439\n"
     ]
    }
   ],
   "source": [
    "pred_train = pipe.predict(X_train)\n",
    "pred_test = pipe.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "_BSdLhokEWUJ"
   },
   "source": [
    "Подбор гиперпараметров"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 283
    },
    "id": "T9KQrk-6BlPM",
    "outputId": "2c8ce0fc-d6f3-49e9-e738-cc6633addd8f"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[(&#x27;scaler&#x27;, MinMaxScaler()),\n",
       "                                       (&#x27;variance&#x27;,\n",
       "                                        VarianceThreshold(threshold=0.05)),\n",
       "                                       (&#x27;selection&#x27;,\n",
       "                                        SelectFromModel(estimator=Lasso(alpha=0.1))),\n",
       "                                       (&#x27;regressor&#x27;, Ridge(alpha=5.0))]),\n",
       "             param_grid={&#x27;regressor__alpha&#x27;: array([4. , 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5. , 5.1, 5.2,\n",
       "       5.3, 5.4, 5.5, 5.6, 5.7, 5.8, 5.9, 6. ]),\n",
       "                         &#x27;selection__estimator__alpha&#x27;: array([0.01  , 0.0195, 0.029 , 0.0385, 0.048 , 0.0575, 0.067 , 0.0765,\n",
       "       0.086 , 0.0955, 0.105 , 0.1145, 0.124 , 0.1335, 0.143 , 0.1525,\n",
       "       0.162 , 0.1715, 0.181 , 0.1905, 0.2   ]),\n",
       "                         &#x27;variance__threshold&#x27;: [0.004, 0.005, 0.0055, 0.0059,\n",
       "                                                 0.006, 0.065]})</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">GridSearchCV</label><div class=\"sk-toggleable__content\"><pre>GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[(&#x27;scaler&#x27;, MinMaxScaler()),\n",
       "                                       (&#x27;variance&#x27;,\n",
       "                                        VarianceThreshold(threshold=0.05)),\n",
       "                                       (&#x27;selection&#x27;,\n",
       "                                        SelectFromModel(estimator=Lasso(alpha=0.1))),\n",
       "                                       (&#x27;regressor&#x27;, Ridge(alpha=5.0))]),\n",
       "             param_grid={&#x27;regressor__alpha&#x27;: array([4. , 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5. , 5.1, 5.2,\n",
       "       5.3, 5.4, 5.5, 5.6, 5.7, 5.8, 5.9, 6. ]),\n",
       "                         &#x27;selection__estimator__alpha&#x27;: array([0.01  , 0.0195, 0.029 , 0.0385, 0.048 , 0.0575, 0.067 , 0.0765,\n",
       "       0.086 , 0.0955, 0.105 , 0.1145, 0.124 , 0.1335, 0.143 , 0.1525,\n",
       "       0.162 , 0.1715, 0.181 , 0.1905, 0.2   ]),\n",
       "                         &#x27;variance__threshold&#x27;: [0.004, 0.005, 0.0055, 0.0059,\n",
       "                                                 0.006, 0.065]})</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;scaler&#x27;, MinMaxScaler()),\n",
       "                (&#x27;variance&#x27;, VarianceThreshold(threshold=0.05)),\n",
       "                (&#x27;selection&#x27;, SelectFromModel(estimator=Lasso(alpha=0.1))),\n",
       "                (&#x27;regressor&#x27;, Ridge(alpha=5.0))])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">MinMaxScaler</label><div class=\"sk-toggleable__content\"><pre>MinMaxScaler()</pre></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">VarianceThreshold</label><div class=\"sk-toggleable__content\"><pre>VarianceThreshold(threshold=0.05)</pre></div></div></div><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">selection: SelectFromModel</label><div class=\"sk-toggleable__content\"><pre>SelectFromModel(estimator=Lasso(alpha=0.1))</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">estimator: Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso(alpha=0.1)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Lasso</label><div class=\"sk-toggleable__content\"><pre>Lasso(alpha=0.1)</pre></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Ridge</label><div class=\"sk-toggleable__content\"><pre>Ridge(alpha=5.0)</pre></div></div></div></div></div></div></div></div></div></div></div></div>"
      ],
      "text/plain": [
       "GridSearchCV(cv=5,\n",
       "             estimator=Pipeline(steps=[('scaler', MinMaxScaler()),\n",
       "                                       ('variance',\n",
       "                                        VarianceThreshold(threshold=0.05)),\n",
       "                                       ('selection',\n",
       "                                        SelectFromModel(estimator=Lasso(alpha=0.1))),\n",
       "                                       ('regressor', Ridge(alpha=5.0))]),\n",
       "             param_grid={'regressor__alpha': array([4. , 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7, 4.8, 4.9, 5. , 5.1, 5.2,\n",
       "       5.3, 5.4, 5.5, 5.6, 5.7, 5.8, 5.9, 6. ]),\n",
       "                         'selection__estimator__alpha': array([0.01  , 0.0195, 0.029 , 0.0385, 0.048 , 0.0575, 0.067 , 0.0765,\n",
       "       0.086 , 0.0955, 0.105 , 0.1145, 0.124 , 0.1335, 0.143 , 0.1525,\n",
       "       0.162 , 0.1715, 0.181 , 0.1905, 0.2   ]),\n",
       "                         'variance__threshold': [0.004, 0.005, 0.0055, 0.0059,\n",
       "                                                 0.006, 0.065]})"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "param_grid = {\n",
    "    \"variance__threshold\": [0.004, 0.005, 0.0055, 0.0059, 0.006, 0.065],\n",
    "    \"selection__estimator__alpha\": np.linspace(0.01, 0.2, 21),\n",
    "    \"regressor__alpha\": np.linspace(4, 6, 21),\n",
    "}\n",
    "grid_search = GridSearchCV(pipe, param_grid, cv=5)\n",
    "\n",
    "grid_search.fit(X_train, y_train);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "eK7saXk3B3eR",
    "outputId": "91093aad-06f3-468d-ba28-8d280e8be912"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'scaler': MinMaxScaler(),\n",
       " 'variance': VarianceThreshold(threshold=0.065),\n",
       " 'selection': SelectFromModel(estimator=Lasso(alpha=0.09549999999999999)),\n",
       " 'regressor': Ridge(alpha=6.0)}"
      ]
     },
     "execution_count": 44,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pipe_best = grid_search.best_estimator_\n",
    "pipe_best.named_steps"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "w_LiMHuXB4In",
    "outputId": "315f8883-108a-4806-d499-fb71e75488ef"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 10.73394680649504\n",
      "Test MSE: 11.64374168702121\n",
      "Train R2: 0.06305410929530753\n",
      "Test R2: -0.259554625798409\n"
     ]
    }
   ],
   "source": [
    "pred_train = pipe_best.predict(X_train)\n",
    "pred_test = pipe_best.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "XudF1to3-oRh"
   },
   "source": [
    "Дерево глубины 3. “Fantasy scale”, скорее всего, важный признак."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 406
    },
    "id": "lAkC7PQyCWII",
    "outputId": "f16ec1b1-5b01-4564-bf8f-3831a8489cf0"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dt = DecisionTreeRegressor(max_depth=3, random_state=0)\n",
    "dt.fit(X_train, y_train)\n",
    "\n",
    "plot_tree(dt, feature_names=X_train.columns, filled=True, rounded=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "88Mqx2uNXlw7",
    "outputId": "053e12cb-f3e5-405f-dc1d-ccb349a6ce1e"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 5.298597724947051\n",
      "Test MSE: 16.901072354435566\n",
      "Train R2: 0.3010824020641069\n",
      "Test R2: -0.5331453044688775\n"
     ]
    }
   ],
   "source": [
    "pred_train = dt.predict(X_train)\n",
    "pred_test = dt.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "FwrC62JpBWfB"
   },
   "source": [
    "При увеличении глубины дерева MSE сначала должна уменьшаться, а затем с некоторого значения возрастать (неглубокое дерево недообучено, глубокое - переобучено). Видимо, из-за недостаточного количества данных эту зависимость не удается увидеть."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 472
    },
    "id": "td4BEKHEYGFr",
    "outputId": "37075f14-a9a5-482d-cffc-545aec415237"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "max_depth_array = range(2, 20)\n",
    "mse_array = []\n",
    "\n",
    "for max_depth in max_depth_array:\n",
    "    dt = DecisionTreeRegressor(max_depth=max_depth, random_state=0)\n",
    "    score = -cross_val_score(dt, X, y, cv=3, scoring=\"neg_mean_squared_error\").mean()\n",
    "    mse_array.append(score)\n",
    "\n",
    "plt.plot(max_depth_array, mse_array)\n",
    "plt.title(\"Dependence of MSE on max depth\")\n",
    "plt.xlabel(\"max depth\")\n",
    "plt.ylabel(\"MSE\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "UC57tpCXYrO_",
    "outputId": "4f197a3a-b130-4972-990b-d411d51bdf60"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-e90227d9-9ee6-42c8-a782-08e87d6a4430\" class=\"colab-df-container\">\n",
       "    <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>max_depth</th>\n",
       "      <th>MSE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2</td>\n",
       "      <td>15.886932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>3</td>\n",
       "      <td>20.552046</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>4</td>\n",
       "      <td>25.642643</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>8</td>\n",
       "      <td>25.761934</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6</td>\n",
       "      <td>26.589187</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e90227d9-9ee6-42c8-a782-08e87d6a4430')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-e90227d9-9ee6-42c8-a782-08e87d6a4430 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-e90227d9-9ee6-42c8-a782-08e87d6a4430');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "<div id=\"df-f075e688-ae58-4d21-8a46-8df053fce8ce\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-f075e688-ae58-4d21-8a46-8df053fce8ce')\"\n",
       "            title=\"Suggest charts.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "     width=\"24px\">\n",
       "    <g>\n",
       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
       "    </g>\n",
       "</svg>\n",
       "  </button>\n",
       "\n",
       "<style>\n",
       "  .colab-df-quickchart {\n",
       "      --bg-color: #E8F0FE;\n",
       "      --fill-color: #1967D2;\n",
       "      --hover-bg-color: #E2EBFA;\n",
       "      --hover-fill-color: #174EA6;\n",
       "      --disabled-fill-color: #AAA;\n",
       "      --disabled-bg-color: #DDD;\n",
       "  }\n",
       "\n",
       "  [theme=dark] .colab-df-quickchart {\n",
       "      --bg-color: #3B4455;\n",
       "      --fill-color: #D2E3FC;\n",
       "      --hover-bg-color: #434B5C;\n",
       "      --hover-fill-color: #FFFFFF;\n",
       "      --disabled-bg-color: #3B4455;\n",
       "      --disabled-fill-color: #666;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart {\n",
       "    background-color: var(--bg-color);\n",
       "    border: none;\n",
       "    border-radius: 50%;\n",
       "    cursor: pointer;\n",
       "    display: none;\n",
       "    fill: var(--fill-color);\n",
       "    height: 32px;\n",
       "    padding: 0;\n",
       "    width: 32px;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart:hover {\n",
       "    background-color: var(--hover-bg-color);\n",
       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "    fill: var(--button-hover-fill-color);\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart-complete:disabled,\n",
       "  .colab-df-quickchart-complete:disabled:hover {\n",
       "    background-color: var(--disabled-bg-color);\n",
       "    fill: var(--disabled-fill-color);\n",
       "    box-shadow: none;\n",
       "  }\n",
       "\n",
       "  .colab-df-spinner {\n",
       "    border: 2px solid var(--fill-color);\n",
       "    border-color: transparent;\n",
       "    border-bottom-color: var(--fill-color);\n",
       "    animation:\n",
       "      spin 1s steps(1) infinite;\n",
       "  }\n",
       "\n",
       "  @keyframes spin {\n",
       "    0% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "      border-left-color: var(--fill-color);\n",
       "    }\n",
       "    20% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    30% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    40% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    60% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    80% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "    90% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "  }\n",
       "</style>\n",
       "\n",
       "  <script>\n",
       "    async function quickchart(key) {\n",
       "      const quickchartButtonEl =\n",
       "        document.querySelector('#' + key + ' button');\n",
       "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
       "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
       "      try {\n",
       "        const charts = await google.colab.kernel.invokeFunction(\n",
       "            'suggestCharts', [key], {});\n",
       "      } catch (error) {\n",
       "        console.error('Error during call to suggestCharts:', error);\n",
       "      }\n",
       "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
       "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
       "    }\n",
       "    (() => {\n",
       "      let quickchartButtonEl =\n",
       "        document.querySelector('#df-f075e688-ae58-4d21-8a46-8df053fce8ce button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   max_depth        MSE\n",
       "0          2  15.886932\n",
       "1          3  20.552046\n",
       "2          4  25.642643\n",
       "3          8  25.761934\n",
       "4          6  26.589187"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame({\"max_depth\": max_depth_array, \"MSE\": mse_array}).sort_values(\n",
    "    by=\"MSE\"\n",
    ").reset_index(drop=True).head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "X3coexl0IJXR"
   },
   "source": [
    "При малых значениях “min_samples_leaf” должны наблюдать переобучение, при больших - недообучение."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 472
    },
    "id": "379M58MJaWlr",
    "outputId": "9de05eb8-cb68-43e2-b6c0-e822bcbcab1f"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "min_samples_leaf_array = range(1, 20)\n",
    "mse_array = []\n",
    "\n",
    "for min_samples_leaf in min_samples_leaf_array:\n",
    "    dt = DecisionTreeRegressor(\n",
    "        max_depth=2, min_samples_leaf=min_samples_leaf, random_state=13\n",
    "    )\n",
    "    score = -cross_val_score(dt, X, y, cv=3, scoring=\"neg_mean_squared_error\").mean()\n",
    "    mse_array.append(score)\n",
    "\n",
    "plt.plot(min_samples_leaf_array, mse_array)\n",
    "plt.title(\"Dependence of MSE on min samples leaf\")\n",
    "plt.xlabel(\"min samples leaf\")\n",
    "plt.ylabel(\"MSE\");"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 206
    },
    "id": "_wVl_QnSbASi",
    "outputId": "d717c537-80cc-4ddd-d7bc-a0d8b1aebaa1"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-99edff72-b1ee-45ef-af64-44fd02c82ced\" class=\"colab-df-container\">\n",
       "    <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>min_samples_leaf</th>\n",
       "      <th>MSE</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>15.566753</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>17</td>\n",
       "      <td>15.621588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>16</td>\n",
       "      <td>15.621588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>15</td>\n",
       "      <td>15.621588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>14</td>\n",
       "      <td>15.621588</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-99edff72-b1ee-45ef-af64-44fd02c82ced')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-99edff72-b1ee-45ef-af64-44fd02c82ced button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-99edff72-b1ee-45ef-af64-44fd02c82ced');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "<div id=\"df-ce555d01-641e-479b-a8c1-fb1db7c11d1e\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ce555d01-641e-479b-a8c1-fb1db7c11d1e')\"\n",
       "            title=\"Suggest charts.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "     width=\"24px\">\n",
       "    <g>\n",
       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
       "    </g>\n",
       "</svg>\n",
       "  </button>\n",
       "\n",
       "<style>\n",
       "  .colab-df-quickchart {\n",
       "      --bg-color: #E8F0FE;\n",
       "      --fill-color: #1967D2;\n",
       "      --hover-bg-color: #E2EBFA;\n",
       "      --hover-fill-color: #174EA6;\n",
       "      --disabled-fill-color: #AAA;\n",
       "      --disabled-bg-color: #DDD;\n",
       "  }\n",
       "\n",
       "  [theme=dark] .colab-df-quickchart {\n",
       "      --bg-color: #3B4455;\n",
       "      --fill-color: #D2E3FC;\n",
       "      --hover-bg-color: #434B5C;\n",
       "      --hover-fill-color: #FFFFFF;\n",
       "      --disabled-bg-color: #3B4455;\n",
       "      --disabled-fill-color: #666;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart {\n",
       "    background-color: var(--bg-color);\n",
       "    border: none;\n",
       "    border-radius: 50%;\n",
       "    cursor: pointer;\n",
       "    display: none;\n",
       "    fill: var(--fill-color);\n",
       "    height: 32px;\n",
       "    padding: 0;\n",
       "    width: 32px;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart:hover {\n",
       "    background-color: var(--hover-bg-color);\n",
       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "    fill: var(--button-hover-fill-color);\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart-complete:disabled,\n",
       "  .colab-df-quickchart-complete:disabled:hover {\n",
       "    background-color: var(--disabled-bg-color);\n",
       "    fill: var(--disabled-fill-color);\n",
       "    box-shadow: none;\n",
       "  }\n",
       "\n",
       "  .colab-df-spinner {\n",
       "    border: 2px solid var(--fill-color);\n",
       "    border-color: transparent;\n",
       "    border-bottom-color: var(--fill-color);\n",
       "    animation:\n",
       "      spin 1s steps(1) infinite;\n",
       "  }\n",
       "\n",
       "  @keyframes spin {\n",
       "    0% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "      border-left-color: var(--fill-color);\n",
       "    }\n",
       "    20% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    30% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    40% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    60% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    80% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "    90% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "  }\n",
       "</style>\n",
       "\n",
       "  <script>\n",
       "    async function quickchart(key) {\n",
       "      const quickchartButtonEl =\n",
       "        document.querySelector('#' + key + ' button');\n",
       "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
       "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
       "      try {\n",
       "        const charts = await google.colab.kernel.invokeFunction(\n",
       "            'suggestCharts', [key], {});\n",
       "      } catch (error) {\n",
       "        console.error('Error during call to suggestCharts:', error);\n",
       "      }\n",
       "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
       "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
       "    }\n",
       "    (() => {\n",
       "      let quickchartButtonEl =\n",
       "        document.querySelector('#df-ce555d01-641e-479b-a8c1-fb1db7c11d1e button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "   min_samples_leaf        MSE\n",
       "0                 3  15.566753\n",
       "1                17  15.621588\n",
       "2                16  15.621588\n",
       "3                15  15.621588\n",
       "4                14  15.621588"
      ]
     },
     "execution_count": 98,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame({\"min_samples_leaf\": min_samples_leaf_array, \"MSE\": mse_array}).sort_values(\n",
    "    by=\"MSE\"\n",
    ").reset_index(drop=True).head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 406
    },
    "id": "7OMmqfqWcAKq",
    "outputId": "ce56e5f1-ab95-41d5-cd59-7893d1e8c129"
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "dt = DecisionTreeRegressor(max_depth=2, min_samples_leaf=3, random_state=13)\n",
    "dt.fit(X_train, y_train)\n",
    "\n",
    "plot_tree(dt, feature_names=X_train.columns, filled=True, rounded=True)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "1ruFzVDtcLLz",
    "outputId": "ff1406be-4edb-4ed7-ca97-d6061b965ca6"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 7.529089026915115\n",
      "Test MSE: 13.93710648148148\n",
      "Train R2: 0.1838357502829373\n",
      "Test R2: -0.39868380969675493\n"
     ]
    }
   ],
   "source": [
    "pred_train = dt.predict(X_train)\n",
    "pred_test = dt.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "zQeLekYWcarZ",
    "outputId": "9e519daf-05d4-4eaf-c1da-5eceb06243f0"
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.        , 0.        , 0.        , 0.27767424, 0.        ,\n",
       "       0.32824049, 0.        , 0.39408527, 0.        , 0.        ,\n",
       "       0.        , 0.        , 0.        ])"
      ]
     },
     "execution_count": 85,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dt.feature_importances_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 143
    },
    "id": "gfAovnrJcpUo",
    "outputId": "d13f5e00-e904-4488-8a94-cf69d1bab68a"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-9f3a7061-fb24-4451-bcf6-5b8a9278b352\" class=\"colab-df-container\">\n",
       "    <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>importance</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Fantasy scale</td>\n",
       "      <td>0.394085</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Narcissism</td>\n",
       "      <td>0.328240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Machiavellianism</td>\n",
       "      <td>0.277674</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>\n",
       "    <div class=\"colab-df-buttons\">\n",
       "\n",
       "  <div class=\"colab-df-container\">\n",
       "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-9f3a7061-fb24-4451-bcf6-5b8a9278b352')\"\n",
       "            title=\"Convert this dataframe to an interactive table.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
       "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
       "  </svg>\n",
       "    </button>\n",
       "\n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    .colab-df-buttons div {\n",
       "      margin-bottom: 4px;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "    <script>\n",
       "      const buttonEl =\n",
       "        document.querySelector('#df-9f3a7061-fb24-4451-bcf6-5b8a9278b352 button.colab-df-convert');\n",
       "      buttonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "      async function convertToInteractive(key) {\n",
       "        const element = document.querySelector('#df-9f3a7061-fb24-4451-bcf6-5b8a9278b352');\n",
       "        const dataTable =\n",
       "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                    [key], {});\n",
       "        if (!dataTable) return;\n",
       "\n",
       "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "          + ' to learn more about interactive tables.';\n",
       "        element.innerHTML = '';\n",
       "        dataTable['output_type'] = 'display_data';\n",
       "        await google.colab.output.renderOutput(dataTable, element);\n",
       "        const docLink = document.createElement('div');\n",
       "        docLink.innerHTML = docLinkHtml;\n",
       "        element.appendChild(docLink);\n",
       "      }\n",
       "    </script>\n",
       "  </div>\n",
       "\n",
       "\n",
       "<div id=\"df-ec55885c-9edd-4f28-8329-2036c3e49ef3\">\n",
       "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ec55885c-9edd-4f28-8329-2036c3e49ef3')\"\n",
       "            title=\"Suggest charts.\"\n",
       "            style=\"display:none;\">\n",
       "\n",
       "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "     width=\"24px\">\n",
       "    <g>\n",
       "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
       "    </g>\n",
       "</svg>\n",
       "  </button>\n",
       "\n",
       "<style>\n",
       "  .colab-df-quickchart {\n",
       "      --bg-color: #E8F0FE;\n",
       "      --fill-color: #1967D2;\n",
       "      --hover-bg-color: #E2EBFA;\n",
       "      --hover-fill-color: #174EA6;\n",
       "      --disabled-fill-color: #AAA;\n",
       "      --disabled-bg-color: #DDD;\n",
       "  }\n",
       "\n",
       "  [theme=dark] .colab-df-quickchart {\n",
       "      --bg-color: #3B4455;\n",
       "      --fill-color: #D2E3FC;\n",
       "      --hover-bg-color: #434B5C;\n",
       "      --hover-fill-color: #FFFFFF;\n",
       "      --disabled-bg-color: #3B4455;\n",
       "      --disabled-fill-color: #666;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart {\n",
       "    background-color: var(--bg-color);\n",
       "    border: none;\n",
       "    border-radius: 50%;\n",
       "    cursor: pointer;\n",
       "    display: none;\n",
       "    fill: var(--fill-color);\n",
       "    height: 32px;\n",
       "    padding: 0;\n",
       "    width: 32px;\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart:hover {\n",
       "    background-color: var(--hover-bg-color);\n",
       "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "    fill: var(--button-hover-fill-color);\n",
       "  }\n",
       "\n",
       "  .colab-df-quickchart-complete:disabled,\n",
       "  .colab-df-quickchart-complete:disabled:hover {\n",
       "    background-color: var(--disabled-bg-color);\n",
       "    fill: var(--disabled-fill-color);\n",
       "    box-shadow: none;\n",
       "  }\n",
       "\n",
       "  .colab-df-spinner {\n",
       "    border: 2px solid var(--fill-color);\n",
       "    border-color: transparent;\n",
       "    border-bottom-color: var(--fill-color);\n",
       "    animation:\n",
       "      spin 1s steps(1) infinite;\n",
       "  }\n",
       "\n",
       "  @keyframes spin {\n",
       "    0% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "      border-left-color: var(--fill-color);\n",
       "    }\n",
       "    20% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    30% {\n",
       "      border-color: transparent;\n",
       "      border-left-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    40% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-top-color: var(--fill-color);\n",
       "    }\n",
       "    60% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "    }\n",
       "    80% {\n",
       "      border-color: transparent;\n",
       "      border-right-color: var(--fill-color);\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "    90% {\n",
       "      border-color: transparent;\n",
       "      border-bottom-color: var(--fill-color);\n",
       "    }\n",
       "  }\n",
       "</style>\n",
       "\n",
       "  <script>\n",
       "    async function quickchart(key) {\n",
       "      const quickchartButtonEl =\n",
       "        document.querySelector('#' + key + ' button');\n",
       "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
       "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
       "      try {\n",
       "        const charts = await google.colab.kernel.invokeFunction(\n",
       "            'suggestCharts', [key], {});\n",
       "      } catch (error) {\n",
       "        console.error('Error during call to suggestCharts:', error);\n",
       "      }\n",
       "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
       "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
       "    }\n",
       "    (() => {\n",
       "      let quickchartButtonEl =\n",
       "        document.querySelector('#df-ec55885c-9edd-4f28-8329-2036c3e49ef3 button');\n",
       "      quickchartButtonEl.style.display =\n",
       "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "    })();\n",
       "  </script>\n",
       "</div>\n",
       "    </div>\n",
       "  </div>\n"
      ],
      "text/plain": [
       "            feature  importance\n",
       "0     Fantasy scale    0.394085\n",
       "1        Narcissism    0.328240\n",
       "2  Machiavellianism    0.277674"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.DataFrame(\n",
    "    {\"feature\": X.columns, \"importance\": dt.feature_importances_}\n",
    ").sort_values(by=\"importance\", ascending=False).reset_index(drop=True).head(3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "zH0-BSlbhnye"
   },
   "source": [
    "Дерево без ограничений"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "YY3POPsUcxxZ",
    "outputId": "05af7278-75b2-4a14-b53b-79bb78e7b46c"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 0.0\n",
      "Test MSE: 32.416666666666664\n",
      "Train R2: 1.0\n",
      "Test R2: -1.5040509615174555\n"
     ]
    }
   ],
   "source": [
    "dt = DecisionTreeRegressor(random_state=0)\n",
    "dt.fit(X_train, y_train)\n",
    "\n",
    "pred_train = dt.predict(X_train)\n",
    "pred_test = dt.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "o6hS6dx7huJb"
   },
   "source": [
    "Бэггинг"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "lKerIvn3cQa5",
    "outputId": "a695a0aa-c38b-42ac-9435-e945550e1ee0"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 2.76998188405797\n",
      "Test MSE: 17.209114583333335\n",
      "Train R2: 0.781178618603533\n",
      "Test R2: -0.48388189730175307\n"
     ]
    }
   ],
   "source": [
    "bag = BaggingRegressor(dt, n_estimators=20, random_state=0)\n",
    "bag.fit(X_train, y_train)\n",
    "\n",
    "pred_train = bag.predict(X_train)\n",
    "pred_test = bag.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "2fIi80S-h1u0"
   },
   "source": [
    "Случайный лес (добавляем рандомизацию по признакам)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "id": "zt-7b4KxgGxT",
    "outputId": "53c04cb1-ae08-4e7e-858d-ad2f189c7b94"
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Train MSE: 2.423768115942029\n",
      "Test MSE: 14.88828125\n",
      "Train R2: 0.8092182005791608\n",
      "Test R2: -0.4318412950203152\n"
     ]
    }
   ],
   "source": [
    "rf = RandomForestRegressor(n_estimators=20, max_features=\"sqrt\", random_state=0)\n",
    "rf.fit(X_train, y_train)\n",
    "\n",
    "pred_train = rf.predict(X_train)\n",
    "pred_test = rf.predict(X_test)\n",
    "\n",
    "print(f\"Train MSE: {mean_squared_error(y_train, pred_train)}\")\n",
    "print(f\"Test MSE: {mean_squared_error(y_test, pred_test)}\")\n",
    "print(f\"Train R2: {r2_score(y_train, pred_train)}\")\n",
    "print(f\"Test R2: {r2_score(y_test, pred_test)}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 519,
     "referenced_widgets": [
      "ce5b799113074fdcb0ecbe4f5f9a6302",
      "71e2d89208574f1ca0eee5d343b0fb3c",
      "bc6572cf751a455cad1814bb697efbab",
      "70524090c7264c5f902ab8f0f51def6e",
      "d25d6d28a80041c2acb3ad71a00e06c4",
      "c9512e1993ed4500b865938a0693641c",
      "0a12ed00ccc042a38cb63b8a915f6984",
      "fb12850e3903400a9492cd863cf5966c",
      "4ab47e16ef2e4eed989ea73346cbb1b1",
      "2f4e738b4fb24c3f87b97e47c7fe0517",
      "def9bf7c219241cbb98da1c518be661f"
     ]
    },
    "id": "BMpe6tydiZXY",
    "outputId": "63833f20-1b1e-4365-8a23-69d850e9bf55"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "ce5b799113074fdcb0ecbe4f5f9a6302",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/50 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "n_trees = 100\n",
    "train_loss = []\n",
    "test_loss = []\n",
    "\n",
    "for i in trange(1, n_trees, 2):\n",
    "    rf = RandomForestRegressor(n_estimators=i, random_state=0)\n",
    "    rf.fit(X_train, y_train)\n",
    "    train_loss.append(mean_squared_error(y_train, rf.predict(X_train)))\n",
    "    test_loss.append(mean_squared_error(y_test, rf.predict(X_test)))\n",
    "\n",
    "plt.figure(figsize=(8, 5))\n",
    "plt.title(\"Изменение лосса в зависимости от количества деревьев\")\n",
    "plt.grid()\n",
    "plt.plot(np.arange(1, n_trees, 2), train_loss, label=\"MSE_train\")\n",
    "plt.plot(np.arange(1, n_trees, 2), test_loss, label=\"MSE_test\")\n",
    "plt.ylabel(\"MSE\")\n",
    "plt.xlabel(\"# trees\")\n",
    "plt.legend();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "id": "tQmgHyDim3Zc"
   },
   "source": [
    "Число деревьев зафиксировано, меняем глубину"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 519,
     "referenced_widgets": [
      "beec1efcb45145bb809a6698a65d8444",
      "8d316988546c4c4c989b1d3b131465a3",
      "89f5465088d540f29de3a1ff4a2523ac",
      "3545fceca33e406298d635a6df027c32",
      "ddfa543cddaf4443922cb7c04c2925cc",
      "78347f6f9e034205bdedaef12ffff67f",
      "aeb00862aa624886a12db94f11787fd9",
      "ef18baf685994ccf972f2f1a5f536961",
      "f57aa387a36d49af8452bacbeafb32cb",
      "59c08ed9fe254621873ce54dc00cb01d",
      "9e63cbd8f2544141a56694fd12b6937e"
     ]
    },
    "id": "UQD0D2opj4X0",
    "outputId": "c8f26a2a-6971-45df-d663-c4a20f0b205b"
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "beec1efcb45145bb809a6698a65d8444",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/25 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "max_depth = 50\n",
    "train_loss = []\n",
    "test_loss = []\n",
    "\n",
    "for i in trange(1, max_depth, 2):\n",
    "    rf = RandomForestRegressor(n_estimators=7, max_depth=i, random_state=0)\n",
    "    rf.fit(X_train, y_train)\n",
    "    train_loss.append(mean_squared_error(y_train, rf.predict(X_train)))\n",
    "    test_loss.append(mean_squared_error(y_test, rf.predict(X_test)))\n",
    "\n",
    "plt.figure(figsize=(8, 5))\n",
    "plt.title(\"Изменение лосса в зависимости от глубины деревьев\")\n",
    "plt.grid()\n",
    "plt.plot(np.arange(1, max_depth, 2), train_loss, label=\"MSE_train\")\n",
    "plt.plot(np.arange(1, max_depth, 2), test_loss, label=\"MSE_test\")\n",
    "plt.ylabel(\"MSE\")\n",
    "plt.xlabel(\"max_depth\")\n",
    "plt.legend();"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 74
    },
    "id": "YjtM0nF19NbP",
    "outputId": "9af4f894-cbf3-414d-db82-b18b5eff65c3"
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(max_depth=11, n_estimators=7, random_state=0)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(max_depth=11, n_estimators=7, random_state=0)</pre></div></div></div></div></div>"
      ],
      "text/plain": [
       "RandomForestRegressor(max_depth=11, n_estimators=7, random_state=0)"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rf = RandomForestRegressor(n_estimators=7, max_depth=11, random_state=0)\n",
    "rf.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 468
    },
    "id": "MNWiQpSGsAzL",
    "outputId": "7745d221-e058-4464-f332-e7e1d47c3aae"
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAq8AAAHDCAYAAAAKv/MhAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAxyElEQVR4nO3dfVzUdb7//+eAMiAKYiQDLgpelJkXGCRZlnuOHNHjupGV4raJVHa2tDLMUkvQtPAqo9IjW3uz2u3K9my653RBGUmdbuJFoqdN86o0URsQN0HhJvhlPr8/+jk1gsogOL6nx/12+9yWec/7857X583c4rlvP/Mem2VZlgAAAAADBPi6AAAAAKCpCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwDQSl555RXZbDbt37/f16UAgN8gvAJoMafDWmPHjBkzWuU1169frzlz5ujYsWOtMv4vWU1NjebMmaOioiJflwIAbm18XQAA//Pkk08qPj7eo61v376t8lrr16/X3LlzNXHiRHXs2LFVXqO57rzzTqWnp8tut/u6lGapqanR3LlzJUm//vWvfVsMAPz/CK8AWtzIkSOVlJTk6zIuSHV1tUJDQy9ojMDAQAUGBrZQRRePy+VSXV2dr8sAgEZx2wCAi+6DDz7QjTfeqNDQUHXo0EGjRo3S9u3bPfp8+eWXmjhxorp3767g4GA5HA7dddddOnr0qLvPnDlzNH36dElSfHy8+xaF/fv3a//+/bLZbHrllVcavL7NZtOcOXM8xrHZbNqxY4d+97vfKSIiQkOGDHE//9prrykxMVEhISHq1KmT0tPTVVpaet7rbOye17i4OP3mN79RUVGRkpKSFBISon79+rn/af6dd95Rv379FBwcrMTERG3dutVjzIkTJ6p9+/b69ttvlZqaqtDQUMXExOjJJ5+UZVkefaurqzVt2jTFxsbKbrfryiuv1JIlSxr0s9lsmjJlil5//XVdffXVstvtys/P1+WXXy5Jmjt3rntuT89bU34/P5/bvXv3ulfHw8PDlZmZqZqamgZz9tprr2nQoEFq166dIiIidNNNN+mjjz7y6NOU94/T6VRmZqZ+9atfyW63Kzo6WjfffDP3HwN+gJVXAC2usrJSFRUVHm2RkZGSpL/85S/KyMhQamqqFi5cqJqaGq1YsUJDhgzR1q1bFRcXJ0lau3atvv32W2VmZsrhcGj79u168cUXtX37dm3YsEE2m01jxozR7t279eabb+rZZ591v8bll1+uI0eOeF337bffrl69eunpp592B7ynnnpKs2fP1tixY3XPPffoyJEjeuGFF3TTTTdp69atzbpVYe/evfrd736n//iP/9Dvf/97LVmyRKNHj1Z+fr5mzZql+++/X5KUm5ursWPHateuXQoI+Gmtob6+XiNGjNB1112nRYsWqaCgQDk5Ofp//+//6cknn5QkWZal3/72t1q3bp3uvvtuJSQk6MMPP9T06dN16NAhPfvssx41ffLJJ3r77bc1ZcoURUZGasCAAVqxYoXuu+8+3XLLLRozZowkqX///pKa9vv5ubFjxyo+Pl65ubkqKSnRn/70J3Xu3FkLFy5095k7d67mzJmj66+/Xk8++aSCgoK0ceNGffLJJxo+fLikpr9/br31Vm3fvl0PPPCA4uLiVF5errVr1+rAgQPuPgAMZQFAC3n55ZctSY0elmVZx48ftzp27GhNmjTJ4zyn02mFh4d7tNfU1DQY/80337QkWZ999pm7bfHixZYka9++fR599+3bZ0myXn755QbjSLJycnLcj3NycixJ1vjx4z367d+/3woMDLSeeuopj/Z//OMfVps2bRq0n20+fl5bt27dLEnW+vXr3W0ffvihJckKCQmxvvvuO3f7H//4R0uStW7dOndbRkaGJcl64IEH3G0ul8saNWqUFRQUZB05csSyLMtas2aNJcmaP3++R0233XabZbPZrL1793rMR0BAgLV9+3aPvkeOHGkwV6c19fdzem7vuusuj7633HKLddlll7kf79mzxwoICLBuueUWq76+3qOvy+WyLKvp758ffvjBkmQtXry4QY0AzMdtAwBa3PLly7V27VqPQ/pxte7YsWMaP368Kioq3EdgYKCSk5O1bt069xghISHun0+ePKmKigpdd911kqSSkpJWqfsPf/iDx+N33nlHLpdLY8eO9ajX4XCoV69eHvV6o0+fPho8eLD7cXJysiTpX//1X9W1a9cG7d9++22DMaZMmeL++fQ/+9fV1enjjz+WJL3//vsKDAzUgw8+6HHetGnTZFmWPvjgA4/2oUOHqk+fPk2+Bm9/P2fO7Y033qijR4+qqqpKkrRmzRq5XC5lZ2d7rDKfvj6p6e+fkJAQBQUFqaioSD/88EOTrwmAGbhtAECLGzRoUKMf2NqzZ4+kH0NaY8LCwtw///Of/9TcuXP11ltvqby83KNfZWVlC1b7kzN3SNizZ48sy1KvXr0a7d+2bdtmvc7PA6okhYeHS5JiY2MbbT8zgAUEBKh79+4ebVdccYUkue/p/O677xQTE6MOHTp49Lvqqqvcz//cmdd+Pt7+fs685oiICEk/XltYWJi++eYbBQQEnDNAN/X9Y7fbtXDhQk2bNk1RUVG67rrr9Jvf/EYTJkyQw+Fo+kUCuCQRXgFcNC6XS9KP9y02FiLatPnpP0ljx47V+vXrNX36dCUkJKh9+/ZyuVwaMWKEe5xzOfOey9Pq6+vPes7PVxNP12uz2fTBBx80umtA+/btz1tHY862A8HZ2q0zPmDVGs689vPx9vfTEtfmzftn6tSpGj16tNasWaMPP/xQs2fPVm5urj755BMNHDiwya8J4NJDeAVw0fTo0UOS1LlzZ6WkpJy13w8//KDCwkLNnTtX2dnZ7vbTK28/d7aQenpl78wvLzhzxfF89VqWpfj4ePfK5qXA5XLp22+/9ahp9+7dkuT+MFK3bt308ccf6/jx4x6rrzt37nQ/fz5nm1tvfj9N1aNHD7lcLu3YsUMJCQln7SOd//3z8/7Tpk3TtGnTtGfPHiUkJOiZZ57Ra6+91uw6Afge97wCuGhSU1MVFhamp59+WqdOnWrw/OkdAk6v0p25KpeXl9fgnNN7sZ4ZUsPCwhQZGanPPvvMo/0///M/m1zvmDFjFBgYqLlz5zaoxbKsBttCXUzLli3zqGXZsmVq27athg0bJkn693//d9XX13v0k6Rnn31WNptNI0eOPO9rtGvXTlLDufXm99NUaWlpCggI0JNPPtlg5fb06zT1/VNTU6OTJ096PNejRw916NBBtbW1za4RwKWBlVcAF01YWJhWrFihO++8U9dcc43S09N1+eWX68CBA3rvvfd0ww03aNmyZQoLC9NNN92kRYsW6dSpU+rSpYs++ugj7du3r8GYiYmJkqTHH39c6enpatu2rUaPHq3Q0FDdc889WrBgge655x4lJSXps88+c69QNkWPHj00f/58zZw5U/v371daWpo6dOigffv2afXq1br33nv1yCOPtNj8NFVwcLAKCgqUkZGh5ORkffDBB3rvvfc0a9Ys996so0eP1r/8y7/o8ccf1/79+zVgwAB99NFH+vvf/66pU6e6VzHPJSQkRH369NGqVat0xRVXqFOnTurbt6/69u3b5N9PU/Xs2VOPP/645s2bpxtvvFFjxoyR3W7X5s2bFRMTo9zc3Ca/f3bv3q1hw4Zp7Nix6tOnj9q0aaPVq1errKxM6enpza4RwCXCR7scAPBDp7eG2rx58zn7rVu3zkpNTbXCw8Ot4OBgq0ePHtbEiROtL774wt3n4MGD1i233GJ17NjRCg8Pt26//Xbr8OHDjW7dNG/ePKtLly5WQECAx9ZUNTU11t13322Fh4dbHTp0sMaOHWuVl5efdaus09tMnelvf/ubNWTIECs0NNQKDQ21evfubU2ePNnatWtXk+bjzK2yRo0a1aCvJGvy5Mkebae3+/r5lk8ZGRlWaGio9c0331jDhw+32rVrZ0VFRVk5OTkNtpg6fvy49fDDD1sxMTFW27ZtrV69elmLFy92bz11rtc+bf369VZiYqIVFBTkMW9N/f2cbW4bmxvLsqyVK1daAwcOtOx2uxUREWENHTrUWrt2rUef871/KioqrMmTJ1u9e/e2QkNDrfDwcCs5Odl6++23G71GAGaxWdZF+CQAAKBFTJw4Uf/1X/+lEydO+LoUAPAJ7nkFAACAMQivAAAAMAbhFQAAAMbgnlcAAAAYg5VXAAAAGIPwCgAAAGP4xZcUuFwuHT58WB06dDjr1xkCAADAdyzL0vHjxxUTE6OAgAtYP23O5rDLli2zunXrZtntdmvQoEHWxo0bz9r3b3/7m5WYmGiFh4db7dq1swYMGGD9+c9/9ujjcrms2bNnWw6HwwoODraGDRtm7d69u8n1lJaWWpI4ODg4ODg4ODgu8aO0tLQ58dPN65XXVatWKSsrS/n5+UpOTlZeXp5SU1O1a9cude7cuUH/Tp066fHHH1fv3r0VFBSkd999V5mZmercubNSU1MlSYsWLdLzzz+vV199VfHx8Zo9e7ZSU1O1Y8cOBQcHn7emDh06SJJKS0sVFhbm7SUBAACglVVVVSk2Ntad25rL690GkpOTde2112rZsmWSfvwn+9jYWD3wwAOaMWNGk8a45pprNGrUKM2bN0+WZSkmJkbTpk1zf0d4ZWWloqKi9MorrzTpe6irqqoUHh6uyspKwisAAMAlqKXymlc3HNTV1WnLli1KSUn5aYCAAKWkpKi4uPi851uWpcLCQu3atUs33XSTJGnfvn1yOp0eY4aHhys5OfmsY9bW1qqqqsrjAAAAgP/zKrxWVFSovr5eUVFRHu1RUVFyOp1nPa+yslLt27dXUFCQRo0apRdeeEH/9m//Jknu87wZMzc3V+Hh4e4jNjbWm8sAAACAoS7KVlkdOnTQtm3btHnzZj311FPKyspSUVFRs8ebOXOmKisr3UdpaWnLFQsAAIBLllcf2IqMjFRgYKDKyso82svKyuRwOM56XkBAgHr27ClJSkhI0Ndff63c3Fz9+te/dp9XVlam6OhojzETEhIaHc9ut8tut3tTOgAAAPyAVyuvQUFBSkxMVGFhobvN5XKpsLBQgwcPbvI4LpdLtbW1kqT4+Hg5HA6PMauqqrRx40avxgQAAID/83qrrKysLGVkZCgpKUmDBg1SXl6eqqurlZmZKUmaMGGCunTpotzcXEk/3p+alJSkHj16qLa2Vu+//77+8pe/aMWKFZIkm82mqVOnav78+erVq5d7q6yYmBilpaW13JUCAADAeF6H13HjxunIkSPKzs6W0+lUQkKCCgoK3B+4OnDggMe3JlRXV+v+++/XwYMHFRISot69e+u1117TuHHj3H0effRRVVdX695779WxY8c0ZMgQFRQUNGmPVwAAAPxyeL3P66WIfV4BAAAubT7Z5xUAAADwJcIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGN4/Q1bAAD/EzfjPV+X4LZ/wShflwDgEsbKKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMEazwuvy5csVFxen4OBgJScna9OmTWft+9JLL+nGG29URESEIiIilJKS0qD/xIkTZbPZPI4RI0Y0pzQAAAD4Ma/D66pVq5SVlaWcnByVlJRowIABSk1NVXl5eaP9i4qKNH78eK1bt07FxcWKjY3V8OHDdejQIY9+I0aM0Pfff+8+3nzzzeZdEQAAAPyW1+F16dKlmjRpkjIzM9WnTx/l5+erXbt2WrlyZaP9X3/9dd1///1KSEhQ79699ac//Ukul0uFhYUe/ex2uxwOh/uIiIho3hUBAADAb3kVXuvq6rRlyxalpKT8NEBAgFJSUlRcXNykMWpqanTq1Cl16tTJo72oqEidO3fWlVdeqfvuu09Hjx71pjQAAAD8ArTxpnNFRYXq6+sVFRXl0R4VFaWdO3c2aYzHHntMMTExHgF4xIgRGjNmjOLj4/XNN99o1qxZGjlypIqLixUYGNhgjNraWtXW1rofV1VVeXMZAAAAMJRX4fVCLViwQG+99ZaKiooUHBzsbk9PT3f/3K9fP/Xv3189evRQUVGRhg0b1mCc3NxczZ0796LUDAAAgEuHV7cNREZGKjAwUGVlZR7tZWVlcjgc5zx3yZIlWrBggT766CP179//nH27d++uyMhI7d27t9HnZ86cqcrKSvdRWlrqzWUAAADAUF6F16CgICUmJnp82Or0h68GDx581vMWLVqkefPmqaCgQElJSed9nYMHD+ro0aOKjo5u9Hm73a6wsDCPAwAAAP7P690GsrKy9NJLL+nVV1/V119/rfvuu0/V1dXKzMyUJE2YMEEzZ85091+4cKFmz56tlStXKi4uTk6nU06nUydOnJAknThxQtOnT9eGDRu0f/9+FRYW6uabb1bPnj2VmpraQpcJAAAAf+D1Pa/jxo3TkSNHlJ2dLafTqYSEBBUUFLg/xHXgwAEFBPyUiVesWKG6ujrddtttHuPk5ORozpw5CgwM1JdffqlXX31Vx44dU0xMjIYPH6558+bJbrdf4OUBAADAn9gsy7J8XcSFqqqqUnh4uCorK7mFAACaIW7Ge74uwW3/glG+LgFAK2ipvNasr4cFAAAAfIHwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMZoVXpcvX664uDgFBwcrOTlZmzZtOmvfl156STfeeKMiIiIUERGhlJSUBv0ty1J2draio6MVEhKilJQU7dmzpzmlAQAAwI95HV5XrVqlrKws5eTkqKSkRAMGDFBqaqrKy8sb7V9UVKTx48dr3bp1Ki4uVmxsrIYPH65Dhw65+yxatEjPP/+88vPztXHjRoWGhio1NVUnT55s/pUBAADA79gsy7K8OSE5OVnXXnutli1bJklyuVyKjY3VAw88oBkzZpz3/Pr6ekVERGjZsmWaMGGCLMtSTEyMpk2bpkceeUSSVFlZqaioKL3yyitKT08/75hVVVUKDw9XZWWlwsLCvLkcAICkuBnv+boEt/0LRvm6BACtoKXymlcrr3V1ddqyZYtSUlJ+GiAgQCkpKSouLm7SGDU1NTp16pQ6deokSdq3b5+cTqfHmOHh4UpOTj7rmLW1taqqqvI4AAAA4P+8Cq8VFRWqr69XVFSUR3tUVJScTmeTxnjssccUExPjDqunz/NmzNzcXIWHh7uP2NhYby4DAAAAhrqouw0sWLBAb731llavXq3g4OBmjzNz5kxVVla6j9LS0hasEgAAAJeqNt50joyMVGBgoMrKyjzay8rK5HA4znnukiVLtGDBAn388cfq37+/u/30eWVlZYqOjvYYMyEhodGx7Ha77Ha7N6UDAADAD3i18hoUFKTExEQVFha621wulwoLCzV48OCznrdo0SLNmzdPBQUFSkpK8nguPj5eDofDY8yqqipt3LjxnGMCAADgl8erlVdJysrKUkZGhpKSkjRo0CDl5eWpurpamZmZkqQJEyaoS5cuys3NlSQtXLhQ2dnZeuONNxQXF+e+j7V9+/Zq3769bDabpk6dqvnz56tXr16Kj4/X7NmzFRMTo7S0tJa7UgAAABjP6/A6btw4HTlyRNnZ2XI6nUpISFBBQYH7A1cHDhxQQMBPC7orVqxQXV2dbrvtNo9xcnJyNGfOHEnSo48+qurqat177706duyYhgwZooKCggu6LxYAAAD+x+t9Xi9F7PMKABeGfV4BtDaf7PMKAAAA+BLhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYo1nhdfny5YqLi1NwcLCSk5O1adOms/bdvn27br31VsXFxclmsykvL69Bnzlz5shms3kcvXv3bk5pAAAA8GNeh9dVq1YpKytLOTk5Kikp0YABA5Samqry8vJG+9fU1Kh79+5asGCBHA7HWce9+uqr9f3337uPzz//3NvSAAAA4Oe8Dq9Lly7VpEmTlJmZqT59+ig/P1/t2rXTypUrG+1/7bXXavHixUpPT5fdbj/ruG3atJHD4XAfkZGR3pYGAAAAP+dVeK2rq9OWLVuUkpLy0wABAUpJSVFxcfEFFbJnzx7FxMSoe/fuuuOOO3TgwIELGg8AAAD+x6vwWlFRofr6ekVFRXm0R0VFyel0NruI5ORkvfLKKyooKNCKFSu0b98+3XjjjTp+/Hij/Wtra1VVVeVxAAAAwP+18XUBkjRy5Ej3z/3791dycrK6deumt99+W3fffXeD/rm5uZo7d+7FLBEAAACXAK9WXiMjIxUYGKiysjKP9rKysnN+GMtbHTt21BVXXKG9e/c2+vzMmTNVWVnpPkpLS1vstQEAAHDp8iq8BgUFKTExUYWFhe42l8ulwsJCDR48uMWKOnHihL755htFR0c3+rzdbldYWJjHAQAAAP/n9W0DWVlZysjIUFJSkgYNGqS8vDxVV1crMzNTkjRhwgR16dJFubm5kn78kNeOHTvcPx86dEjbtm1T+/bt1bNnT0nSI488otGjR6tbt246fPiwcnJyFBgYqPHjx7fUdQIAAMAPeB1ex40bpyNHjig7O1tOp1MJCQkqKChwf4jrwIEDCgj4aUH38OHDGjhwoPvxkiVLtGTJEg0dOlRFRUWSpIMHD2r8+PE6evSoLr/8cg0ZMkQbNmzQ5ZdffoGXBwAAAH9isyzL8nURF6qqqkrh4eGqrKzkFgIAaIa4Ge/5ugS3/QtG+boEAK2gpfJas74eFgAAAPAFwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIzRxtcFAAAA/JLwdcwXhpVXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBhtfF0AAN+Im/Ger0tw279glK9LAAAYgpVXAAAAGKNZ4XX58uWKi4tTcHCwkpOTtWnTprP23b59u2699VbFxcXJZrMpLy/vgscEAADAL5PX4XXVqlXKyspSTk6OSkpKNGDAAKWmpqq8vLzR/jU1NerevbsWLFggh8PRImMCAADgl8nr8Lp06VJNmjRJmZmZ6tOnj/Lz89WuXTutXLmy0f7XXnutFi9erPT0dNnt9hYZEwAAAL9MXoXXuro6bdmyRSkpKT8NEBCglJQUFRcXN6uA5oxZW1urqqoqjwMAAAD+z6vwWlFRofr6ekVFRXm0R0VFyel0NquA5oyZm5ur8PBw9xEbG9us1wYAAIBZjNxtYObMmaqsrHQfpaWlvi4JAAAAF4FX+7xGRkYqMDBQZWVlHu1lZWVn/TBWa4xpt9vPev8sAAAA/JdX4TUoKEiJiYkqLCxUWlqaJMnlcqmwsFBTpkxpVgGtMSbgC2z6DwBA6/P6G7aysrKUkZGhpKQkDRo0SHl5eaqurlZmZqYkacKECerSpYtyc3Ml/fiBrB07drh/PnTokLZt26b27durZ8+eTRoTAAAAkJoRXseNG6cjR44oOztbTqdTCQkJKigocH/g6sCBAwoI+OlW2sOHD2vgwIHux0uWLNGSJUs0dOhQFRUVNWlMAAAAQGpGeJWkKVOmnPWf9E8H0tPi4uJkWdYFjQkAAABIhu42AAAAgF8mwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjNHG1wUAAOCtuBnv+boEt/0LRvm6BOAXhZVXAAAAGIOVVwBoBawMAkDrYOUVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYo42vCwAAwN/FzXjP1yW47V8wytclABeElVcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjEF4BAABgjGaF1+XLlysuLk7BwcFKTk7Wpk2bztn/r3/9q3r37q3g4GD169dP77//vsfzEydOlM1m8zhGjBjRnNIAAADgx7wOr6tWrVJWVpZycnJUUlKiAQMGKDU1VeXl5Y32X79+vcaPH6+7775bW7duVVpamtLS0vTVV1959BsxYoS+//579/Hmm28274oAAADgt7wOr0uXLtWkSZOUmZmpPn36KD8/X+3atdPKlSsb7f/cc89pxIgRmj59uq666irNmzdP11xzjZYtW+bRz263y+FwuI+IiIjmXREAAAD8llfhta6uTlu2bFFKSspPAwQEKCUlRcXFxY2eU1xc7NFfklJTUxv0LyoqUufOnXXllVfqvvvu09GjR70pDQAAAL8AbbzpXFFRofr6ekVFRXm0R0VFaefOnY2e43Q6G+3vdDrdj0eMGKExY8YoPj5e33zzjWbNmqWRI0equLhYgYGBDcasra1VbW2t+3FVVZU3lwEAAABDeRVeW0t6err75379+ql///7q0aOHioqKNGzYsAb9c3NzNXfu3ItZIgAAAC4BXt02EBkZqcDAQJWVlXm0l5WVyeFwNHqOw+Hwqr8kde/eXZGRkdq7d2+jz8+cOVOVlZXuo7S01JvLAAAAgKG8Cq9BQUFKTExUYWGhu83lcqmwsFCDBw9u9JzBgwd79JektWvXnrW/JB08eFBHjx5VdHR0o8/b7XaFhYV5HAAAAPB/Xu82kJWVpZdeekmvvvqqvv76a913332qrq5WZmamJGnChAmaOXOmu/9DDz2kgoICPfPMM9q5c6fmzJmjL774QlOmTJEknThxQtOnT9eGDRu0f/9+FRYW6uabb1bPnj2VmpraQpcJAAAAf+D1Pa/jxo3TkSNHlJ2dLafTqYSEBBUUFLg/lHXgwAEFBPyUia+//nq98cYbeuKJJzRr1iz16tVLa9asUd++fSVJgYGB+vLLL/Xqq6/q2LFjiomJ0fDhwzVv3jzZ7fYWukwAAAD4g2Z9YGvKlCnuldMzFRUVNWi7/fbbdfvttzfaPyQkRB9++GFzygAAAMAvzCWx2wAAAEBzxc14z9cluO1fMMrXJfg9r+95BQAAAHyF8AoAAABjcNsAACPwz4IAAImVVwAAABiE8AoAAABjEF4BAABgDMIrAAAAjEF4BQAAgDEIrwAAADAG4RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBhtfF0AAAC4tMTNeM/XJbjtXzDK1yXgEsPKKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBiEVwAAABiD8AoAAABjsM8rLlnsMwgAAM7EyisAAACMwcrrBWBlEAAA4OJi5RUAAADGILwCAADAGIRXAAAAGIPwCgAAAGMQXgEAAGAMwisAAACMQXgFAACAMQivAAAAMAbhFQAAAMbgG7Z+QfhGMAAAYDpWXgEAAGAMwisAAACMQXgFAACAMQivAAAAMEazwuvy5csVFxen4OBgJScna9OmTefs/9e//lW9e/dWcHCw+vXrp/fff9/jecuylJ2drejoaIWEhCglJUV79uxpTmkAAADwY16H11WrVikrK0s5OTkqKSnRgAEDlJqaqvLy8kb7r1+/XuPHj9fdd9+trVu3Ki0tTWlpafrqq6/cfRYtWqTnn39e+fn52rhxo0JDQ5WamqqTJ082/8oAAADgd7wOr0uXLtWkSZOUmZmpPn36KD8/X+3atdPKlSsb7f/cc89pxIgRmj59uq666irNmzdP11xzjZYtWybpx1XXvLw8PfHEE7r55pvVv39//fnPf9bhw4e1Zs2aC7o4AAAA+Bev9nmtq6vTli1bNHPmTHdbQECAUlJSVFxc3Og5xcXFysrK8mhLTU11B9N9+/bJ6XQqJSXF/Xx4eLiSk5NVXFys9PT0BmPW1taqtrbW/biyslKSVFVV5c3lXDBXbc1Ffb1zacq1U2/zUW/rot7WRb2ti3pbF/W2rouZnU6/lmVZFzSOV+G1oqJC9fX1ioqK8miPiorSzp07Gz3H6XQ22t/pdLqfP912tj5nys3N1dy5cxu0x8bGNu1C/FB4nq8r8A71ti7qbV3U27qot3VRb+ui3vM7fvy4wsPDm32+kd+wNXPmTI/VXJfLpX/+859q27atunbtqtLSUoWFhfmwQv9UVVWl2NhY5reVML+ti/ltfcxx62J+Wxfz27pOz++OHTsUExNzQWN5FV4jIyMVGBiosrIyj/aysjI5HI5Gz3E4HOfsf/p/y8rKFB0d7dEnISGh0THtdrvsdrtHW8eOHd3L0WFhYbzxWhHz27qY39bF/LY+5rh1Mb+ti/ltXV26dFFAwIXt1OrV2UFBQUpMTFRhYaG7zeVyqbCwUIMHD270nMGDB3v0l6S1a9e6+8fHx8vhcHj0qaqq0saNG886JgAAAH6ZvL5tICsrSxkZGUpKStKgQYOUl5en6upqZWZmSpImTJigLl26KDc3V5L00EMPaejQoXrmmWc0atQovfXWW/riiy/04osvSpJsNpumTp2q+fPnq1evXoqPj9fs2bMVExOjtLS0lrtSAAAAGM/r8Dpu3DgdOXJE2dnZcjqdSkhIUEFBgfsDVwcOHPBYDr7++uv1xhtv6IknntCsWbPUq1cvrVmzRn379nX3efTRR1VdXa17771Xx44d05AhQ1RQUKDg4GCvarPb7crJyWlwSwFaBvPbupjf1sX8tj7muHUxv62L+W1dLTm/NutC9ysAAAAALpILu2MWAAAAuIgIrwAAADAG4RUAAADGILwCAADAGH4VXpcvX664uDgFBwcrOTlZmzZt8nVJfiE3N1fXXnutOnTooM6dOystLU27du3ydVl+a8GCBe4t5NAyDh06pN///ve67LLLFBISon79+umLL77wdVl+ob6+XrNnz1Z8fLxCQkLUo0cPzZs374K/u/yX6rPPPtPo0aMVExMjm82mNWvWeDxvWZays7MVHR2tkJAQpaSkaM+ePb4p1kDnmt9Tp07pscceU79+/RQaGqqYmBhNmDBBhw8f9l3Bhjnf+/fn/vCHP8hmsykvL8/r1/Gb8Lpq1SplZWUpJydHJSUlGjBggFJTU1VeXu7r0oz36aefavLkydqwYYPWrl2rU6dOafjw4aqurvZ1aX5n8+bN+uMf/6j+/fv7uhS/8cMPP+iGG25Q27Zt9cEHH2jHjh165plnFBER4evS/MLChQu1YsUKLVu2TF9//bUWLlyoRYsW6YUXXvB1aUaqrq7WgAEDtHz58kafX7RokZ5//nnl5+dr48aNCg0NVWpqqk6ePHmRKzXTuea3pqZGJSUlmj17tkpKSvTOO+9o165d+u1vf+uDSs10vvfvaatXr9aGDRua/zWxlp8YNGiQNXnyZPfj+vp6KyYmxsrNzfVhVf6pvLzckmR9+umnvi7Frxw/ftzq1auXtXbtWmvo0KHWQw895OuS/MJjjz1mDRkyxNdl+K1Ro0ZZd911l0fbmDFjrDvuuMNHFfkPSdbq1avdj10ul+VwOKzFixe7244dO2bZ7XbrzTff9EGFZjtzfhuzadMmS5L13XffXZyi/MjZ5vfgwYNWly5drK+++srq1q2b9eyzz3o9tl+svNbV1WnLli1KSUlxtwUEBCglJUXFxcU+rMw/VVZWSpI6derk40r8y+TJkzVq1CiP9zEu3H//938rKSlJt99+uzp37qyBAwfqpZde8nVZfuP6669XYWGhdu/eLUn6v//7P33++ecaOXKkjyvzP/v27ZPT6fT4b0R4eLiSk5P5W9dKKisrZbPZ1LFjR1+X4hdcLpfuvPNOTZ8+XVdffXWzx/H6G7YuRRUVFaqvr3d/y9dpUVFR2rlzp4+q8k8ul0tTp07VDTfc4PEtabgwb731lkpKSrR582Zfl+J3vv32W61YsUJZWVmaNWuWNm/erAcffFBBQUHKyMjwdXnGmzFjhqqqqtS7d28FBgaqvr5eTz31lO644w5fl+Z3nE6nJDX6t+70c2g5J0+e1GOPPabx48crLCzM1+X4hYULF6pNmzZ68MEHL2gcvwivuHgmT56sr776Sp9//rmvS/EbpaWleuihh7R27VqvvxIZ5+dyuZSUlKSnn35akjRw4EB99dVXys/PJ7y2gLfffluvv/663njjDV199dXatm2bpk6dqpiYGOYXxjp16pTGjh0ry7K0YsUKX5fjF7Zs2aLnnntOJSUlstlsFzSWX9w2EBkZqcDAQJWVlXm0l5WVyeFw+Kgq/zNlyhS9++67WrdunX71q1/5uhy/sWXLFpWXl+uaa65RmzZt1KZNG3366ad6/vnn1aZNG9XX1/u6RKNFR0erT58+Hm1XXXWVDhw44KOK/Mv06dM1Y8YMpaenq1+/frrzzjv18MMPKzc319el+Z3Tf8/4W9e6TgfX7777TmvXrmXVtYX87//+r8rLy9W1a1f337rvvvtO06ZNU1xcnFdj+UV4DQoKUmJiogoLC91tLpdLhYWFGjx4sA8r8w+WZWnKlClavXq1PvnkE8XHx/u6JL8ybNgw/eMf/9C2bdvcR1JSku644w5t27ZNgYGBvi7RaDfccEODrd12796tbt26+agi/1JTU6OAAM8/JYGBgXK5XD6qyH/Fx8fL4XB4/K2rqqrSxo0b+VvXQk4H1z179ujjjz/WZZdd5uuS/Madd96pL7/80uNvXUxMjKZPn64PP/zQq7H85raBrKwsZWRkKCkpSYMGDVJeXp6qq6uVmZnp69KMN3nyZL3xxhv6+9//rg4dOrjvrQoPD1dISIiPqzNfhw4dGtw/HBoaqssuu4z7ilvAww8/rOuvv15PP/20xo4dq02bNunFF1/Uiy++6OvS/MLo0aP11FNPqWvXrrr66qu1detWLV26VHfddZevSzPSiRMntHfvXvfjffv2adu2berUqZO6du2qqVOnav78+erVq5fi4+M1e/ZsxcTEKC0tzXdFG+Rc8xsdHa3bbrtNJSUlevfdd1VfX+/+e9epUycFBQX5qmxjnO/9e+b/GWjbtq0cDoeuvPJK717oQrdCuJS88MILVteuXa2goCBr0KBB1oYNG3xdkl+Q1Ojx8ssv+7o0v8VWWS3rf/7nf6y+fftadrvd6t27t/Xiiy/6uiS/UVVVZT300ENW165dreDgYKt79+7W448/btXW1vq6NCOtW7eu0f/eZmRkWJb143ZZs2fPtqKioiy73W4NGzbM2rVrl2+LNsi55nffvn1n/Xu3bt06X5duhPO9f8/U3K2ybJbF16AAAADADH5xzysAAAB+GQivAAAAMAbhFQAAAMYgvAIAAMAYhFcAAAAYg/AKAAAAYxBeAQAAYAzCKwAAAIxBeAUAAIAxCK8AAAAwBuEVAAAAxiC8AgAAwBj/HywCszBUIcf2AAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 800x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(8, 5))\n",
    "plt.title(\"Feature importances\")\n",
    "plt.bar(np.arange(1, 14), rf.feature_importances_);"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "provenance": []
  },
  "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": "3.8.8"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "0a12ed00ccc042a38cb63b8a915f6984": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "2f4e738b4fb24c3f87b97e47c7fe0517": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "3545fceca33e406298d635a6df027c32": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_59c08ed9fe254621873ce54dc00cb01d",
      "placeholder": "​",
      "style": "IPY_MODEL_9e63cbd8f2544141a56694fd12b6937e",
      "value": " 25/25 [00:00&lt;00:00, 49.25it/s]"
     }
    },
    "4ab47e16ef2e4eed989ea73346cbb1b1": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "59c08ed9fe254621873ce54dc00cb01d": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "70524090c7264c5f902ab8f0f51def6e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_2f4e738b4fb24c3f87b97e47c7fe0517",
      "placeholder": "​",
      "style": "IPY_MODEL_def9bf7c219241cbb98da1c518be661f",
      "value": " 50/50 [00:04&lt;00:00,  4.43it/s]"
     }
    },
    "71e2d89208574f1ca0eee5d343b0fb3c": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_c9512e1993ed4500b865938a0693641c",
      "placeholder": "​",
      "style": "IPY_MODEL_0a12ed00ccc042a38cb63b8a915f6984",
      "value": "100%"
     }
    },
    "78347f6f9e034205bdedaef12ffff67f": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "89f5465088d540f29de3a1ff4a2523ac": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ef18baf685994ccf972f2f1a5f536961",
      "max": 25,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_f57aa387a36d49af8452bacbeafb32cb",
      "value": 25
     }
    },
    "8d316988546c4c4c989b1d3b131465a3": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_78347f6f9e034205bdedaef12ffff67f",
      "placeholder": "​",
      "style": "IPY_MODEL_aeb00862aa624886a12db94f11787fd9",
      "value": "100%"
     }
    },
    "9e63cbd8f2544141a56694fd12b6937e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "aeb00862aa624886a12db94f11787fd9": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "bc6572cf751a455cad1814bb697efbab": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_fb12850e3903400a9492cd863cf5966c",
      "max": 50,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_4ab47e16ef2e4eed989ea73346cbb1b1",
      "value": 50
     }
    },
    "beec1efcb45145bb809a6698a65d8444": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_8d316988546c4c4c989b1d3b131465a3",
       "IPY_MODEL_89f5465088d540f29de3a1ff4a2523ac",
       "IPY_MODEL_3545fceca33e406298d635a6df027c32"
      ],
      "layout": "IPY_MODEL_ddfa543cddaf4443922cb7c04c2925cc"
     }
    },
    "c9512e1993ed4500b865938a0693641c": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "ce5b799113074fdcb0ecbe4f5f9a6302": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_71e2d89208574f1ca0eee5d343b0fb3c",
       "IPY_MODEL_bc6572cf751a455cad1814bb697efbab",
       "IPY_MODEL_70524090c7264c5f902ab8f0f51def6e"
      ],
      "layout": "IPY_MODEL_d25d6d28a80041c2acb3ad71a00e06c4"
     }
    },
    "d25d6d28a80041c2acb3ad71a00e06c4": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "ddfa543cddaf4443922cb7c04c2925cc": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "def9bf7c219241cbb98da1c518be661f": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "ef18baf685994ccf972f2f1a5f536961": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "f57aa387a36d49af8452bacbeafb32cb": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "fb12850e3903400a9492cd863cf5966c": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}