PythonAML06.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 270
        },
        "id": "kpcr_2mvNr_s",
        "outputId": "1bea15c6-8907-4a7d-b9b8-6b4dd95a6050"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "  user_id\\tweight\\theight\\tsalads_per_week\\tveggies_fruits_per_day\\thealthy_diet\\taerobic_per_week\\tsports_per_week\\tcurrent_smoking\\tsurvey.month\\tprob_cancer\n",
              "0  55\\t140\\t69\\t0\\t\\tBelow average\\t2\\t0\\tNever\\t...                                                                                                           \n",
              "1  36\\t150\\t67\\t2\\t1\\tBelow average\\t3\\t3\\tNever\\...                                                                                                           \n",
              "2  39\\t105\\t66\\t0\\t2\\tAverage\\t1\\t0\\tNever\\t2008....                                                                                                           \n",
              "3  37\\t220\\t77\\t2\\t5\\tVery healthy\\t5\\t5\\tNever\\t...                                                                                                           \n",
              "4  72\\t135\\t62\\t0\\t1\\tUnhealthy\\t0\\t0\\tNever\\t200...                                                                                                           "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e7d71989-f851-4d11-a96f-d45dd03fe51f\">\n",
              "    <div 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>user_id\\tweight\\theight\\tsalads_per_week\\tveggies_fruits_per_day\\thealthy_diet\\taerobic_per_week\\tsports_per_week\\tcurrent_smoking\\tsurvey.month\\tprob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55\\t140\\t69\\t0\\t\\tBelow average\\t2\\t0\\tNever\\t...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36\\t150\\t67\\t2\\t1\\tBelow average\\t3\\t3\\tNever\\...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39\\t105\\t66\\t0\\t2\\tAverage\\t1\\t0\\tNever\\t2008....</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37\\t220\\t77\\t2\\t5\\tVery healthy\\t5\\t5\\tNever\\t...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72\\t135\\t62\\t0\\t1\\tUnhealthy\\t0\\t0\\tNever\\t200...</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e7d71989-f851-4d11-a96f-d45dd03fe51f')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-e7d71989-f851-4d11-a96f-d45dd03fe51f 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-e7d71989-f851-4d11-a96f-d45dd03fe51f');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 1
        }
      ],
      "source": [
        "import pandas as pd\n",
        "df = pd.read_csv('cancer.csv')\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv('cancer.csv', sep='\\t')\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 305
        },
        "id": "SXC-cOKpQbbN",
        "outputId": "6f653a50-b821-4396-e463-a9a2a3604c23"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   user_id  weight  height  salads_per_week  veggies_fruits_per_day  \\\n",
              "0       55   140.0    69.0              0.0                     NaN   \n",
              "1       36   150.0    67.0              2.0                     1.0   \n",
              "2       39   105.0    66.0              0.0                     2.0   \n",
              "3       37   220.0    77.0              2.0                     5.0   \n",
              "4       72   135.0    62.0              0.0                     1.0   \n",
              "\n",
              "    healthy_diet  aerobic_per_week  sports_per_week current_smoking  \\\n",
              "0  Below average               2.0              0.0           Never   \n",
              "1  Below average               3.0              3.0           Never   \n",
              "2        Average               1.0              0.0           Never   \n",
              "3   Very healthy               5.0              5.0           Never   \n",
              "4      Unhealthy               0.0              0.0           Never   \n",
              "\n",
              "   survey.month  prob_cancer  \n",
              "0       2008.09     0.066120  \n",
              "1       2008.09     0.366939  \n",
              "2       2008.09     0.805540  \n",
              "3       2008.09     0.537907  \n",
              "4       2008.09     0.098464  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1ead949d-2cc0-451f-9764-2105be636728\">\n",
              "    <div 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>user_id</th>\n",
              "      <th>weight</th>\n",
              "      <th>height</th>\n",
              "      <th>salads_per_week</th>\n",
              "      <th>veggies_fruits_per_day</th>\n",
              "      <th>healthy_diet</th>\n",
              "      <th>aerobic_per_week</th>\n",
              "      <th>sports_per_week</th>\n",
              "      <th>current_smoking</th>\n",
              "      <th>survey.month</th>\n",
              "      <th>prob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55</td>\n",
              "      <td>140.0</td>\n",
              "      <td>69.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Below average</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.066120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36</td>\n",
              "      <td>150.0</td>\n",
              "      <td>67.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Below average</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.366939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39</td>\n",
              "      <td>105.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Average</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.805540</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37</td>\n",
              "      <td>220.0</td>\n",
              "      <td>77.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Very healthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.537907</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72</td>\n",
              "      <td>135.0</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.098464</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1ead949d-2cc0-451f-9764-2105be636728')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-1ead949d-2cc0-451f-9764-2105be636728 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-1ead949d-2cc0-451f-9764-2105be636728');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.isnull().sum()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_EfLF6kcQ8Zb",
        "outputId": "4503fefe-5ac8-408e-ca50-fb6aa4222ec9"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "user_id                     0\n",
              "weight                     10\n",
              "height                    256\n",
              "salads_per_week            10\n",
              "veggies_fruits_per_day     11\n",
              "healthy_diet               10\n",
              "aerobic_per_week            4\n",
              "sports_per_week             4\n",
              "current_smoking             8\n",
              "survey.month                0\n",
              "prob_cancer                11\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ljpPpN20R-dG",
        "outputId": "f0374034-5bc3-44af-f64f-2bd2ecc5694e"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(385, 11)"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf = df"
      ],
      "metadata": {
        "id": "PyqKiaitSM1j"
      },
      "execution_count": 6,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.dropna()\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kFDx0ZiDSwnz",
        "outputId": "d6e26272-4a83-491b-940e-dfc31e558053"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(113, 11)"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = pdf\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yDXzhXkfTHjQ",
        "outputId": "d714e53f-33c2-4949-b333-50abb955a37d"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(385, 11)"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.dropna(axis=1)\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hQSQO1e9TRfk",
        "outputId": "936c2a96-2fd1-4a37-ec59-5d171ff5bbcc"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(385, 2)"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "kJ6ThOAuUg8J",
        "outputId": "5e6bbe47-eec1-421e-e639-b79ad7ffc974"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   user_id  survey.month\n",
              "0       55       2008.09\n",
              "1       36       2008.09\n",
              "2       39       2008.09\n",
              "3       37       2008.09\n",
              "4       72       2008.09"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-92f935dd-65a6-4b5e-aa3c-fc2e99037445\">\n",
              "    <div 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>user_id</th>\n",
              "      <th>survey.month</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55</td>\n",
              "      <td>2008.09</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36</td>\n",
              "      <td>2008.09</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39</td>\n",
              "      <td>2008.09</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37</td>\n",
              "      <td>2008.09</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72</td>\n",
              "      <td>2008.09</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-92f935dd-65a6-4b5e-aa3c-fc2e99037445')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-92f935dd-65a6-4b5e-aa3c-fc2e99037445 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-92f935dd-65a6-4b5e-aa3c-fc2e99037445');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = pdf \n",
        "df = df.fillna(df.mean())\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 340
        },
        "id": "ijvcj9t9Uiq-",
        "outputId": "28494050-4dd0-446e-8506-cdcf1e0da4b6"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-12-4f37d2f5c5e8>:2: FutureWarning: The default value of numeric_only in DataFrame.mean is deprecated. In a future version, it will default to False. In addition, specifying 'numeric_only=None' is deprecated. Select only valid columns or specify the value of numeric_only to silence this warning.\n",
            "  df = df.fillna(df.mean())\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   user_id  weight  height  salads_per_week  veggies_fruits_per_day  \\\n",
              "0       55   140.0    69.0              0.0                 2.15508   \n",
              "1       36   150.0    67.0              2.0                 1.00000   \n",
              "2       39   105.0    66.0              0.0                 2.00000   \n",
              "3       37   220.0    77.0              2.0                 5.00000   \n",
              "4       72   135.0    62.0              0.0                 1.00000   \n",
              "\n",
              "    healthy_diet  aerobic_per_week  sports_per_week current_smoking  \\\n",
              "0  Below average               2.0              0.0           Never   \n",
              "1  Below average               3.0              3.0           Never   \n",
              "2        Average               1.0              0.0           Never   \n",
              "3   Very healthy               5.0              5.0           Never   \n",
              "4      Unhealthy               0.0              0.0           Never   \n",
              "\n",
              "   survey.month  prob_cancer  \n",
              "0       2008.09     0.066120  \n",
              "1       2008.09     0.366939  \n",
              "2       2008.09     0.805540  \n",
              "3       2008.09     0.537907  \n",
              "4       2008.09     0.098464  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-d48aaef6-72ba-4d53-9523-49ede2ff66d1\">\n",
              "    <div 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>user_id</th>\n",
              "      <th>weight</th>\n",
              "      <th>height</th>\n",
              "      <th>salads_per_week</th>\n",
              "      <th>veggies_fruits_per_day</th>\n",
              "      <th>healthy_diet</th>\n",
              "      <th>aerobic_per_week</th>\n",
              "      <th>sports_per_week</th>\n",
              "      <th>current_smoking</th>\n",
              "      <th>survey.month</th>\n",
              "      <th>prob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55</td>\n",
              "      <td>140.0</td>\n",
              "      <td>69.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.15508</td>\n",
              "      <td>Below average</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.066120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36</td>\n",
              "      <td>150.0</td>\n",
              "      <td>67.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>Below average</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.366939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39</td>\n",
              "      <td>105.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.00000</td>\n",
              "      <td>Average</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.805540</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37</td>\n",
              "      <td>220.0</td>\n",
              "      <td>77.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.00000</td>\n",
              "      <td>Very healthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.537907</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72</td>\n",
              "      <td>135.0</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.098464</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-d48aaef6-72ba-4d53-9523-49ede2ff66d1')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-d48aaef6-72ba-4d53-9523-49ede2ff66d1 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-d48aaef6-72ba-4d53-9523-49ede2ff66d1');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.isnull().sum()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "riusxJd1VKCL",
        "outputId": "9f80649f-44d2-4228-9b0e-768ecc5e3430"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "user_id                    0\n",
              "weight                     0\n",
              "height                     0\n",
              "salads_per_week            0\n",
              "veggies_fruits_per_day     0\n",
              "healthy_diet              10\n",
              "aerobic_per_week           0\n",
              "sports_per_week            0\n",
              "current_smoking            8\n",
              "survey.month               0\n",
              "prob_cancer                0\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import matplotlib.pyplot as plt\n",
        "plt.boxplot(df['height'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 573
        },
        "id": "0Igz_IsyVRiC",
        "outputId": "efe81d20-31a1-4d27-b045-6caeae364813"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'whiskers': [<matplotlib.lines.Line2D at 0x7f51b5f4d040>,\n",
              "  <matplotlib.lines.Line2D at 0x7f51b5f4d2e0>],\n",
              " 'caps': [<matplotlib.lines.Line2D at 0x7f51b5f4d580>,\n",
              "  <matplotlib.lines.Line2D at 0x7f51b5f4d820>],\n",
              " 'boxes': [<matplotlib.lines.Line2D at 0x7f51b5feee80>],\n",
              " 'medians': [<matplotlib.lines.Line2D at 0x7f51b5f4dac0>],\n",
              " 'fliers': [<matplotlib.lines.Line2D at 0x7f51b5f4dd60>],\n",
              " 'means': []}"
            ]
          },
          "metadata": {},
          "execution_count": 14
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjAAAAGdCAYAAAAMm0nCAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAgiklEQVR4nO3df1BVdeL/8RdgXH9xr5rBhRWVYtcfSfrpxyIVjqwM6KKzpM6saWWO2dRCM/7IGBoz25po7cdWO7p+m9mynbKtHHKKJl1CUbau1lCkWDJauNDCRVfjXiBDhfP9Y4dTt9AAwcv7+nzMnBnvOe977vv0R/fJuefcG2ZZliUAAACDhAd7AgAAAN1FwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwzoBgT6CvtLe3q66uTlFRUQoLCwv2dAAAQBdYlqWmpibFxcUpPPzc51lCNmDq6uoUHx8f7GkAAIAeqK2t1ahRo865PWQDJioqStL//gM4nc4gzwYAAHSF3+9XfHy8/T5+LiEbMB0fGzmdTgIGAADD/NzlH1zECwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjEDAAAMA4BAwAADBOyH6RHYDQ1NbWprKyMtXX1ys2NlapqamKiIgI9rQAXGScgQFgjMLCQiUmJiotLU0LFy5UWlqaEhMTVVhYGOypAbjICBgARigsLNT8+fOVlJQkj8ejpqYmeTweJSUlaf78+UQMcIkJsyzLCvYk+oLf75fL5ZLP5+O3kADDtbW1KTExUUlJSdq2bZvCw7//26u9vV3Z2dmqrKzU4cOH+TgJMFxX3785AwOg3ysrK9PRo0f14IMPBsSLJIWHhys/P1/V1dUqKysL0gwBXGwEDIB+r76+XpI0adKkTrd3rO8YByD0ETAA+r3Y2FhJUmVlZafbO9Z3jAMQ+ggYAP1eamqqxo4dq8cff1zt7e0B29rb21VQUKCEhASlpqYGaYYALjYCBkC/FxERoaefflpFRUXKzs4OuAspOztbRUVFeuqpp7iAF7iE8EV2AIwwd+5cbd26VatWrdKNN95or09ISNDWrVs1d+7cIM4OwMXGbdQAjMI38QKhravv35yBAWCUiIgITZ8+PdjTABBkXAMDAACMQ8AAAADjEDAAAMA4BAwAADAOAQMAAIxDwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjEDAAAMA4BAwAADAOAQMAAIxDwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjdCtgCgoKdMMNNygqKkrR0dHKzs5WVVVVwJjp06crLCwsYLnnnnsCxtTU1CgrK0uDBw9WdHS0Vq9erbNnzwaMKS0t1bXXXiuHw6HExERt3ry5Z0cIAABCTrcCZvfu3crJydHevXtVXFysM2fOKCMjQy0tLQHjli1bpvr6entZv369va2trU1ZWVk6ffq0PvzwQ7388svavHmz1q5da4+prq5WVlaW0tLSVFFRoeXLl+uuu+7Sjh07LvBwAQBAKAizLMvq6ZOPHz+u6Oho7d69W9OmTZP0vzMwU6ZM0bPPPtvpc9577z3Nnj1bdXV1iomJkSRt2rRJeXl5On78uCIjI5WXl6d3331XlZWV9vMWLFigxsZGbd++vUtz8/v9crlc8vl8cjqdPT1EAABwEXX1/fuCroHx+XySpBEjRgSsf/XVVzVy5EhNmjRJ+fn5+vbbb+1tHo9HSUlJdrxIUmZmpvx+vw4ePGiPSU9PD9hnZmamPB7POefS2toqv98fsAAAgNA0oKdPbG9v1/Lly3XTTTdp0qRJ9vqFCxdqzJgxiouL0/79+5WXl6eqqioVFhZKkrxeb0C8SLIfe73e847x+/06deqUBg0a9JP5FBQU6JFHHunp4QAAAIP0OGBycnJUWVmpf/3rXwHr7777bvvfSUlJio2N1YwZM/Tll1/qqquu6vlMf0Z+fr5WrlxpP/b7/YqPj++z1wMAAMHTo4+QcnNzVVRUpF27dmnUqFHnHZucnCxJOnLkiCTJ7XaroaEhYEzHY7fbfd4xTqez07MvkuRwOOR0OgMWAAAQmroVMJZlKTc3V2+99ZZ27typhISEn31ORUWFJCk2NlaSlJKSogMHDujYsWP2mOLiYjmdTk2cONEeU1JSErCf4uJipaSkdGe6AAAgRHUrYHJycvTKK69oy5YtioqKktfrldfr1alTpyRJX375pR599FGVl5fr6NGjevvtt3XHHXdo2rRpuuaaayRJGRkZmjhxom6//XZ99tln2rFjh9asWaOcnBw5HA5J0j333KOvvvpKDzzwgA4dOqSNGzfqjTfe0IoVK3r58AEAgIm6dRt1WFhYp+tfeukl3XnnnaqtrdVtt92myspKtbS0KD4+XrfccovWrFkT8JHOv//9b917770qLS3VkCFDtHjxYj3xxBMaMOD7S3JKS0u1YsUKff755xo1apQeeugh3XnnnV0+MG6jBgDAPF19/76g74HpzwgYAADMc1G+BwYAACAYCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGCcbgVMQUGBbrjhBkVFRSk6OlrZ2dmqqqoKGPPdd98pJydHl19+uYYOHap58+apoaEhYExNTY2ysrI0ePBgRUdHa/Xq1Tp79mzAmNLSUl177bVyOBxKTEzU5s2be3aEAAAg5HQrYHbv3q2cnBzt3btXxcXFOnPmjDIyMtTS0mKPWbFihd555x29+eab2r17t+rq6jR37lx7e1tbm7KysnT69Gl9+OGHevnll7V582atXbvWHlNdXa2srCylpaWpoqJCy5cv11133aUdO3b0wiEDAADThVmWZfX0ycePH1d0dLR2796tadOmyefz6YorrtCWLVs0f/58SdKhQ4c0YcIEeTweTZ06Ve+9955mz56turo6xcTESJI2bdqkvLw8HT9+XJGRkcrLy9O7776ryspK+7UWLFigxsZGbd++vUtz8/v9crlc8vl8cjqdPT1EAP1MW1ubysrKVF9fr9jYWKWmpioiIiLY0wLQS7r6/n1B18D4fD5J0ogRIyRJ5eXlOnPmjNLT0+0x48eP1+jRo+XxeCRJHo9HSUlJdrxIUmZmpvx+vw4ePGiP+eE+OsZ07APApamwsFCJiYlKS0vTwoULlZaWpsTERBUWFgZ7agAush4HTHt7u5YvX66bbrpJkyZNkiR5vV5FRkZq2LBhAWNjYmLk9XrtMT+Ml47tHdvON8bv9+vUqVOdzqe1tVV+vz9gARA6CgsLNX/+fCUlJcnj8aipqcn+g2j+/PlEDHCJ6XHA5OTkqLKyUv/4xz96cz49VlBQIJfLZS/x8fHBnhKAXtLW1qZVq1Zp9uzZ2rZtm6ZOnaqhQ4dq6tSp2rZtm2bPnq37779fbW1twZ4qgIukRwGTm5uroqIi7dq1S6NGjbLXu91unT59Wo2NjQHjGxoa5Ha77TE/viup4/HPjXE6nRo0aFCnc8rPz5fP57OX2tranhwagH6orKxMR48e1YMPPqjw8MD/bYWHhys/P1/V1dUqKysL0gwBXGzdChjLspSbm6u33npLO3fuVEJCQsD26667TpdddplKSkrsdVVVVaqpqVFKSookKSUlRQcOHNCxY8fsMcXFxXI6nZo4caI95of76BjTsY/OOBwOOZ3OgAVAaKivr5ck++PqH+tY3zEOQOjrVsDk5OTolVde0ZYtWxQVFSWv1yuv12tfl+JyubR06VKtXLlSu3btUnl5uZYsWaKUlBRNnTpVkpSRkaGJEyfq9ttv12effaYdO3ZozZo1ysnJkcPhkCTdc889+uqrr/TAAw/o0KFD2rhxo9544w2tWLGilw8fgAliY2MlKeDOxB/qWN8xDsAlwOoGSZ0uL730kj3m1KlT1h/+8Adr+PDh1uDBg61bbrnFqq+vD9jP0aNHrVmzZlmDBg2yRo4caa1atco6c+ZMwJhdu3ZZU6ZMsSIjI60rr7wy4DW6wufzWZIsn8/XrecB6H/Onj1rjR071pozZ47V1tYWsK2trc2aM2eOlZCQYJ09ezZIMwTQW7r6/n1B3wPTn/E9MEBo6bgLafbs2crPz9ekSZNUWVmpgoICFRUVaevWrQFfmgnATF19/x5wEecEAD02d+5cbd26VatWrdKNN95or09ISCBegEsQZ2AAGIVv4gVCG2dgAISkiIgITZ8+PdjTABBkF/RTAgAAAMFAwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADj8FMCAIzCbyEBkDgDA8AghYWFSkxMVFpamhYuXKi0tDQlJiaqsLAw2FMDcJERMACMUFhYqPnz5yspKUkej0dNTU3yeDxKSkrS/PnziRjgEhNmWZYV7En0ha7+HDeA/q+trU2JiYlKSkrStm3bFB7+/d9e7e3tys7OVmVlpQ4fPszHSYDhuvr+zRkYAP1eWVmZjh49qgcffDAgXiQpPDxc+fn5qq6uVllZWZBmCOBiI2AA9Hv19fWSpEmTJnW6vWN9xzgAoY+AAdDvxcbGSpIqKys73d6xvmMcgNBHwADo91JTUzV27Fg9/vjjam9vD9jW3t6ugoICJSQkKDU1NUgzBHCxETAA+r2IiAg9/fTTKioqUnZ2dsBdSNnZ2SoqKtJTTz3FBbzAJYQvsgNghLlz52rr1q1atWqVbrzxRnt9QkKCtm7dqrlz5wZxdgAuNm6jBmAUvokXCG1dff/mDAwAo0RERGj69OnBngaAIOMaGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGKfbAbNnzx7NmTNHcXFxCgsL07Zt2wK233nnnQoLCwtYZs6cGTDm5MmTWrRokZxOp4YNG6alS5equbk5YMz+/fuVmpqqgQMHKj4+XuvXr+/+0QEAgJDU7YBpaWnR5MmTtWHDhnOOmTlzpurr6+3ltddeC9i+aNEiHTx4UMXFxSoqKtKePXt0991329v9fr8yMjI0ZswYlZeX68knn9S6dev0wgsvdHe6AAAgBA3o7hNmzZqlWbNmnXeMw+GQ2+3udNsXX3yh7du36+OPP9b1118vSfrLX/6i3/72t3rqqacUFxenV199VadPn9aLL76oyMhIXX311aqoqNAzzzwTEDoAAODS1CfXwJSWlio6Olrjxo3TvffeqxMnTtjbPB6Phg0bZseLJKWnpys8PFz79u2zx0ybNk2RkZH2mMzMTFVVVembb77p9DVbW1vl9/sDFgAAEJp6PWBmzpypv//97yopKdGf/vQn7d69W7NmzVJbW5skyev1Kjo6OuA5AwYM0IgRI+T1eu0xMTExAWM6HneM+bGCggK5XC57iY+P7+1DAwAA/US3P0L6OQsWLLD/nZSUpGuuuUZXXXWVSktLNWPGjN5+OVt+fr5WrlxpP/b7/UQMAAAhqs9vo77yyis1cuRIHTlyRJLkdrt17NixgDFnz57VyZMn7etm3G63GhoaAsZ0PD7XtTUOh0NOpzNgAQAAoanPA+brr7/WiRMnFBsbK0lKSUlRY2OjysvL7TE7d+5Ue3u7kpOT7TF79uzRmTNn7DHFxcUaN26chg8f3tdTBgAA/Vy3A6a5uVkVFRWqqKiQJFVXV6uiokI1NTVqbm7W6tWrtXfvXh09elQlJSX63e9+p8TERGVmZkqSJkyYoJkzZ2rZsmX66KOP9MEHHyg3N1cLFixQXFycJGnhwoWKjIzU0qVLdfDgQb3++ut67rnnAj4iAgAAl64wy7Ks7jyhtLRUaWlpP1m/ePFi/fWvf1V2drY+/fRTNTY2Ki4uThkZGXr00UcDLso9efKkcnNz9c477yg8PFzz5s3T888/r6FDh9pj9u/fr5ycHH388ccaOXKk7rvvPuXl5XV5nn6/Xy6XSz6fj4+TAAAwRFffv7sdMKYgYAAAME9X37/5LSQAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABin2wGzZ88ezZkzR3FxcQoLC9O2bdsCtluWpbVr1yo2NlaDBg1Senq6Dh8+HDDm5MmTWrRokZxOp4YNG6alS5equbk5YMz+/fuVmpqqgQMHKj4+XuvXr+/+0QEAgJDU7YBpaWnR5MmTtWHDhk63r1+/Xs8//7w2bdqkffv2aciQIcrMzNR3331nj1m0aJEOHjyo4uJiFRUVac+ePbr77rvt7X6/XxkZGRozZozKy8v15JNPat26dXrhhRd6cIgAACDkWBdAkvXWW2/Zj9vb2y232209+eST9rrGxkbL4XBYr732mmVZlvX5559bkqyPP/7YHvPee+9ZYWFh1n/+8x/Lsixr48aN1vDhw63W1lZ7TF5enjVu3Lguz83n81mSLJ/P19PDAwAAF1lX37979RqY6upqeb1epaen2+tcLpeSk5Pl8XgkSR6PR8OGDdP1119vj0lPT1d4eLj27dtnj5k2bZoiIyPtMZmZmaqqqtI333zT6Wu3trbK7/cHLAAAIDT1asB4vV5JUkxMTMD6mJgYe5vX61V0dHTA9gEDBmjEiBEBYzrbxw9f48cKCgrkcrnsJT4+/sIPCAAA9EshcxdSfn6+fD6fvdTW1gZ7SgAAoI/0asC43W5JUkNDQ8D6hoYGe5vb7daxY8cCtp89e1YnT54MGNPZPn74Gj/mcDjkdDoDFgAAEJp6NWASEhLkdrtVUlJir/P7/dq3b59SUlIkSSkpKWpsbFR5ebk9ZufOnWpvb1dycrI9Zs+ePTpz5ow9pri4WOPGjdPw4cN7c8oAAMBA3Q6Y5uZmVVRUqKKiQtL/LtytqKhQTU2NwsLCtHz5cj322GN6++23deDAAd1xxx2Ki4tTdna2JGnChAmaOXOmli1bpo8++kgffPCBcnNztWDBAsXFxUmSFi5cqMjISC1dulQHDx7U66+/rueee04rV67stQMHAAAG6+7tTbt27bIk/WRZvHixZVn/u5X6oYcesmJiYiyHw2HNmDHDqqqqCtjHiRMnrFtvvdUaOnSo5XQ6rSVLllhNTU0BYz777DPr5ptvthwOh/WLX/zCeuKJJ7o1T26jBgDAPF19/w6zLMsKYj/1Gb/fL5fLJZ/Px/UwAAAYoqvv3yFzFxIAALh0EDAAAMA4BAwAADAOAQMAAIxDwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjEDAAAMA4BAwAADAOAQMAAIxDwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjEDAAAMA4BAwAADAOAQMAAIxDwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjEDAAAMA4BAwAADAOAQMAAIxDwAAAAOMQMAAAwDgEDAAAMA4BAwAAjEPAAAAA4xAwAADAOAQMAAAwDgEDAACMQ8AAAADjEDAAAMA4vR4w69atU1hYWMAyfvx4e/t3332nnJwcXX755Ro6dKjmzZunhoaGgH3U1NQoKytLgwcPVnR0tFavXq2zZ8/29lQBAIChBvTFTq+++mq9//7737/IgO9fZsWKFXr33Xf15ptvyuVyKTc3V3PnztUHH3wgSWpra1NWVpbcbrc+/PBD1dfX64477tBll12mxx9/vC+mCwAADNMnATNgwAC53e6frPf5fPrb3/6mLVu26De/+Y0k6aWXXtKECRO0d+9eTZ06Vf/85z/1+eef6/3331dMTIymTJmiRx99VHl5eVq3bp0iIyP7YsoAAMAgfXINzOHDhxUXF6crr7xSixYtUk1NjSSpvLxcZ86cUXp6uj12/PjxGj16tDwejyTJ4/EoKSlJMTEx9pjMzEz5/X4dPHiwL6YLAAAM0+tnYJKTk7V582aNGzdO9fX1euSRR5SamqrKykp5vV5FRkZq2LBhAc+JiYmR1+uVJHm93oB46djese1cWltb1draaj/2+/29dEQAAKC/6fWAmTVrlv3va665RsnJyRozZozeeOMNDRo0qLdfzlZQUKBHHnmkz/YPAAD6jz6/jXrYsGH61a9+pSNHjsjtduv06dNqbGwMGNPQ0GBfM+N2u39yV1LH486uq+mQn58vn89nL7W1tb17IAAAoN/o84Bpbm7Wl19+qdjYWF133XW67LLLVFJSYm+vqqpSTU2NUlJSJEkpKSk6cOCAjh07Zo8pLi6W0+nUxIkTz/k6DodDTqczYAEAAKGp1z9Cuv/++zVnzhyNGTNGdXV1evjhhxUREaFbb71VLpdLS5cu1cqVKzVixAg5nU7dd999SklJ0dSpUyVJGRkZmjhxom6//XatX79eXq9Xa9asUU5OjhwOR29PFwAAGKjXA+brr7/WrbfeqhMnTuiKK67QzTffrL179+qKK66QJP35z39WeHi45s2bp9bWVmVmZmrjxo328yMiIlRUVKR7771XKSkpGjJkiBYvXqw//vGPvT1VAABgqDDLsqxgT6Iv+P1+uVwu+Xw+Pk4CAMAQXX3/5reQAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHAIGAAAYZ0CwJwCgnzv9rWo+LVFLS8sF7aa1tVV1dXW9NKneFRcXJ4fDccH7GTJkiEb/3wwpcnAvzArA+RAwAM6r5tMSjX7vtl7Z15Re2UsfqO29XdXoFY1OntN7OwTQKQIGwHmdCLtc2f+vWY899pgSEhJ6vJ9QPwNTXV2tNWvW6G+/vVyje2leAM6NgAFwXtaAgfrU2y73/2VqwrXXXtC+pvTOlPqlU598ok+9D8oaMDDYUwEuCVzECwAAjEPAAAAA4/AREoDz+vbbbyVJn3zySZBn8r1Tp07p6NGjGjt2rAYNGhTs6UiSvvjii2BPAbikEDAAzuvQoUOSpGXLlgV5JmaIiooK9hSASwIBA+C8srOzJUnjx4/X4ME9/36TL774Qrfd1ju3Y/e2V155RRMmTLjg/URFRemXv/xlL8wIwM8JsyzLCvYk+oLf75fL5ZLP55PT6Qz2dIBL3rfffmufzblQvf0R0oXGGYDe09X3bwIGAAD0G119/+YuJAAAYJx+HTAbNmzQ2LFjNXDgQCUnJ+ujjz4K9pQAAEA/0G8D5vXXX9fKlSv18MMP65NPPtHkyZOVmZmpY8eOBXtqAAAgyPptwDzzzDNatmyZlixZookTJ2rTpk0aPHiwXnzxxWBPDQAABFm/DJjTp0+rvLxc6enp9rrw8HClp6fL4/F0+pzW1lb5/f6ABQAAhKZ+GTD//e9/1dbWppiYmID1MTEx8nq9nT6noKBALpfLXuLj4y/GVAEAQBD0y4Dpifz8fPl8Pnupra0N9pQAAEAf6ZffxDty5EhFRESooaEhYH1DQ4Pcbnenz3E4HHI4HBdjegAAIMj65RmYyMhIXXfddSopKbHXtbe3q6SkRCkpKUGcGQAA6A/65RkYSVq5cqUWL16s66+/Xr/+9a/17LPPqqWlRUuWLAn21AAAQJD124D5/e9/r+PHj2vt2rXyer2aMmWKtm/f/pMLewEAwKWH30ICAAD9Br+FBAAAQla//QjpQnWcWOIL7QAAMEfH+/bPfUAUsgHT1NQkSXyhHQAABmpqapLL5Trn9pC9Bqa9vV11dXWKiopSWFhYsKcDoBf5/X7Fx8ertraWa9yAEGNZlpqamhQXF6fw8HNf6RKyAQMgdHGRPgAu4gUAAMYhYAAAgHEIGADGcTgcevjhh/n9M+ASxjUwAADAOJyBAQAAxiFgAACAcQgYAABgHAIGAAAYh4ABYIw9e/Zozpw5iouLU1hYmLZt2xbsKQEIEgIGgDFaWlo0efJkbdiwIdhTARBkIftjjgBCz6xZszRr1qxgTwNAP8AZGAAAYBwCBgAAGIeAAQAAxiFgAACAcQgYAABgHO5CAmCM5uZmHTlyxH5cXV2tiooKjRgxQqNHjw7izABcbPwaNQBjlJaWKi0t7SfrFy9erM2bN1/8CQEIGgIGAAAYh2tgAACAcQgYAABgHAIGAAAYh4ABAADGIWAAAIBxCBgAAGAcAgYAABiHgAEAAMYhYAAAgHEIGAAAYBwCBgAAGIeAAQAAxvn/0XOrBThNamkAAAAASUVORK5CYII=\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.loc[df['height']>500, 'height'] = df['height'].mean()\n",
        "plt.boxplot(df['height'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 573
        },
        "id": "1ubPMnLGXUgv",
        "outputId": "110b39e8-7624-4ee5-8549-c8d8a4e3eec6"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'whiskers': [<matplotlib.lines.Line2D at 0x7f51b0e72fd0>,\n",
              "  <matplotlib.lines.Line2D at 0x7f51b0e7e2b0>],\n",
              " 'caps': [<matplotlib.lines.Line2D at 0x7f51b0e7e550>,\n",
              "  <matplotlib.lines.Line2D at 0x7f51b0e7e7f0>],\n",
              " 'boxes': [<matplotlib.lines.Line2D at 0x7f51b0e72d30>],\n",
              " 'medians': [<matplotlib.lines.Line2D at 0x7f51b0e7ea90>],\n",
              " 'fliers': [<matplotlib.lines.Line2D at 0x7f51b0e7ed30>],\n",
              " 'means': []}"
            ]
          },
          "metadata": {},
          "execution_count": 16
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.head(8)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 416
        },
        "id": "kMfaOXnkYN6J",
        "outputId": "7d2c7212-bde7-4640-b6d4-3d0ad40abb38"
      },
      "execution_count": 17,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   user_id  weight      height  salads_per_week  veggies_fruits_per_day  \\\n",
              "0       55   140.0   69.000000              0.0                 2.15508   \n",
              "1       36   150.0   67.000000              2.0                 1.00000   \n",
              "2       39   105.0   66.000000              0.0                 2.00000   \n",
              "3       37   220.0   77.000000              2.0                 5.00000   \n",
              "4       72   135.0   62.000000              0.0                 1.00000   \n",
              "5       11   180.0   69.000000              0.0                 1.00000   \n",
              "6       63     0.0  116.945736              7.0                 0.00000   \n",
              "7       21   240.0   75.000000              0.0                 1.00000   \n",
              "\n",
              "     healthy_diet  aerobic_per_week  sports_per_week current_smoking  \\\n",
              "0   Below average               2.0              0.0           Never   \n",
              "1   Below average               3.0              3.0           Never   \n",
              "2         Average               1.0              0.0           Never   \n",
              "3    Very healthy               5.0              5.0           Never   \n",
              "4       Unhealthy               0.0              0.0           Never   \n",
              "5       Unhealthy               5.0              0.0           Never   \n",
              "6  Very unhealthy               0.0              1.0               0   \n",
              "7       Unhealthy               1.0              0.0           Never   \n",
              "\n",
              "   survey.month  prob_cancer  \n",
              "0       2008.09     0.066120  \n",
              "1       2008.09     0.366939  \n",
              "2       2008.09     0.805540  \n",
              "3       2008.09     0.537907  \n",
              "4       2008.09     0.098464  \n",
              "5       2008.09     0.321663  \n",
              "6       2008.09     0.520753  \n",
              "7       2008.09     0.580648  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-5436bc54-72a3-41c0-b44d-20b296567bca\">\n",
              "    <div 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>user_id</th>\n",
              "      <th>weight</th>\n",
              "      <th>height</th>\n",
              "      <th>salads_per_week</th>\n",
              "      <th>veggies_fruits_per_day</th>\n",
              "      <th>healthy_diet</th>\n",
              "      <th>aerobic_per_week</th>\n",
              "      <th>sports_per_week</th>\n",
              "      <th>current_smoking</th>\n",
              "      <th>survey.month</th>\n",
              "      <th>prob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55</td>\n",
              "      <td>140.0</td>\n",
              "      <td>69.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.15508</td>\n",
              "      <td>Below average</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.066120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36</td>\n",
              "      <td>150.0</td>\n",
              "      <td>67.000000</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>Below average</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.366939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39</td>\n",
              "      <td>105.0</td>\n",
              "      <td>66.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.00000</td>\n",
              "      <td>Average</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.805540</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37</td>\n",
              "      <td>220.0</td>\n",
              "      <td>77.000000</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.00000</td>\n",
              "      <td>Very healthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.537907</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72</td>\n",
              "      <td>135.0</td>\n",
              "      <td>62.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.098464</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>11</td>\n",
              "      <td>180.0</td>\n",
              "      <td>69.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.321663</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>63</td>\n",
              "      <td>0.0</td>\n",
              "      <td>116.945736</td>\n",
              "      <td>7.0</td>\n",
              "      <td>0.00000</td>\n",
              "      <td>Very unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.520753</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>21</td>\n",
              "      <td>240.0</td>\n",
              "      <td>75.000000</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.00000</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.580648</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-5436bc54-72a3-41c0-b44d-20b296567bca')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-5436bc54-72a3-41c0-b44d-20b296567bca 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-5436bc54-72a3-41c0-b44d-20b296567bca');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 305
        },
        "id": "nwunzQ_MYjzl",
        "outputId": "93d8b32f-7f27-4eb2-f33e-44bae1f205ac"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   user_id  weight  height  salads_per_week  veggies_fruits_per_day  \\\n",
              "0       55   140.0    69.0              0.0                     NaN   \n",
              "1       36   150.0    67.0              2.0                     1.0   \n",
              "2       39   105.0    66.0              0.0                     2.0   \n",
              "3       37   220.0    77.0              2.0                     5.0   \n",
              "4       72   135.0    62.0              0.0                     1.0   \n",
              "\n",
              "    healthy_diet  aerobic_per_week  sports_per_week current_smoking  \\\n",
              "0  Below average               2.0              0.0           Never   \n",
              "1  Below average               3.0              3.0           Never   \n",
              "2        Average               1.0              0.0           Never   \n",
              "3   Very healthy               5.0              5.0           Never   \n",
              "4      Unhealthy               0.0              0.0           Never   \n",
              "\n",
              "   survey.month  prob_cancer  \n",
              "0       2008.09     0.066120  \n",
              "1       2008.09     0.366939  \n",
              "2       2008.09     0.805540  \n",
              "3       2008.09     0.537907  \n",
              "4       2008.09     0.098464  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-1d2f5d5e-2144-48b4-aa8b-6d0a25b494d4\">\n",
              "    <div 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>user_id</th>\n",
              "      <th>weight</th>\n",
              "      <th>height</th>\n",
              "      <th>salads_per_week</th>\n",
              "      <th>veggies_fruits_per_day</th>\n",
              "      <th>healthy_diet</th>\n",
              "      <th>aerobic_per_week</th>\n",
              "      <th>sports_per_week</th>\n",
              "      <th>current_smoking</th>\n",
              "      <th>survey.month</th>\n",
              "      <th>prob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55</td>\n",
              "      <td>140.0</td>\n",
              "      <td>69.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Below average</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.066120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36</td>\n",
              "      <td>150.0</td>\n",
              "      <td>67.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Below average</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.366939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39</td>\n",
              "      <td>105.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Average</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.805540</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37</td>\n",
              "      <td>220.0</td>\n",
              "      <td>77.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Very healthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.537907</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72</td>\n",
              "      <td>135.0</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.098464</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1d2f5d5e-2144-48b4-aa8b-6d0a25b494d4')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-1d2f5d5e-2144-48b4-aa8b-6d0a25b494d4 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-1d2f5d5e-2144-48b4-aa8b-6d0a25b494d4');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf['height'].fillna(df['height'].mean(), inplace=True)\n",
        "print(pdf.shape)\n",
        "pdf.head()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 323
        },
        "id": "kKnvBnUJZAQf",
        "outputId": "88215ac4-d2f0-4b1c-d258-f0c192c6b88c"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(385, 11)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   user_id  weight  height  salads_per_week  veggies_fruits_per_day  \\\n",
              "0       55   140.0    69.0              0.0                     NaN   \n",
              "1       36   150.0    67.0              2.0                     1.0   \n",
              "2       39   105.0    66.0              0.0                     2.0   \n",
              "3       37   220.0    77.0              2.0                     5.0   \n",
              "4       72   135.0    62.0              0.0                     1.0   \n",
              "\n",
              "    healthy_diet  aerobic_per_week  sports_per_week current_smoking  \\\n",
              "0  Below average               2.0              0.0           Never   \n",
              "1  Below average               3.0              3.0           Never   \n",
              "2        Average               1.0              0.0           Never   \n",
              "3   Very healthy               5.0              5.0           Never   \n",
              "4      Unhealthy               0.0              0.0           Never   \n",
              "\n",
              "   survey.month  prob_cancer  \n",
              "0       2008.09     0.066120  \n",
              "1       2008.09     0.366939  \n",
              "2       2008.09     0.805540  \n",
              "3       2008.09     0.537907  \n",
              "4       2008.09     0.098464  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-db6b80e9-9734-4776-a7c9-c2a4aba9e56d\">\n",
              "    <div 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>user_id</th>\n",
              "      <th>weight</th>\n",
              "      <th>height</th>\n",
              "      <th>salads_per_week</th>\n",
              "      <th>veggies_fruits_per_day</th>\n",
              "      <th>healthy_diet</th>\n",
              "      <th>aerobic_per_week</th>\n",
              "      <th>sports_per_week</th>\n",
              "      <th>current_smoking</th>\n",
              "      <th>survey.month</th>\n",
              "      <th>prob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>55</td>\n",
              "      <td>140.0</td>\n",
              "      <td>69.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>NaN</td>\n",
              "      <td>Below average</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.066120</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>36</td>\n",
              "      <td>150.0</td>\n",
              "      <td>67.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Below average</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.366939</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>39</td>\n",
              "      <td>105.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Average</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.805540</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>37</td>\n",
              "      <td>220.0</td>\n",
              "      <td>77.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Very healthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.537907</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>72</td>\n",
              "      <td>135.0</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>2008.09</td>\n",
              "      <td>0.098464</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-db6b80e9-9734-4776-a7c9-c2a4aba9e56d')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-db6b80e9-9734-4776-a7c9-c2a4aba9e56d 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-db6b80e9-9734-4776-a7c9-c2a4aba9e56d');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf.dropna(subset=['current_smoking'], inplace=True)\n",
        "pdf.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2pIbspJtZncL",
        "outputId": "0078a38c-5832-491d-f7af-85ce16bd342a"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(377, 11)"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf.isnull().sum()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5ZWydDSEbjzk",
        "outputId": "068cb9dd-5747-484a-98ef-468e4bf90a43"
      },
      "execution_count": 25,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "user_id                    0\n",
              "weight                     8\n",
              "height                     0\n",
              "salads_per_week            7\n",
              "veggies_fruits_per_day     8\n",
              "healthy_diet               7\n",
              "aerobic_per_week           1\n",
              "sports_per_week            1\n",
              "current_smoking            0\n",
              "survey.month               0\n",
              "prob_cancer               10\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf.drop(['user_id', 'survey.month'], axis=1, inplace=True)\n",
        "pdf.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-8YkRK9gbyz2",
        "outputId": "8063ca38-f2f6-41d9-b26f-b20c00923b3b"
      },
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(377, 9)"
            ]
          },
          "metadata": {},
          "execution_count": 27
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf = pdf.dropna()\n",
        "pdf.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JbYkfzfHcoRB",
        "outputId": "ada77ade-bf2f-42e7-f984-67a89ec656ed"
      },
      "execution_count": 28,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(336, 9)"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf['prob_cancer']= pd.cut(pdf['prob_cancer'], bins=[0.0, 0.65, 1.0], labels=[0.0, 1.0])\n",
        "pdf.head(10)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 568
        },
        "id": "pvuyThgudDx3",
        "outputId": "ccbc228e-fcf8-4251-f8b6-96cc598f5ae9"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-29-59e4dd56cd95>:1: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  pdf['prob_cancer']= pd.cut(pdf['prob_cancer'], bins=[0.0, 0.65, 1.0], labels=[0.0, 1.0])\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "    weight  height  salads_per_week  veggies_fruits_per_day    healthy_diet  \\\n",
              "1    150.0    67.0              2.0                     1.0   Below average   \n",
              "2    105.0    66.0              0.0                     2.0         Average   \n",
              "3    220.0    77.0              2.0                     5.0    Very healthy   \n",
              "4    135.0    62.0              0.0                     1.0       Unhealthy   \n",
              "5    180.0    69.0              0.0                     1.0       Unhealthy   \n",
              "6      0.0  2801.0              7.0                     0.0  Very unhealthy   \n",
              "7    240.0    75.0              0.0                     1.0       Unhealthy   \n",
              "8    170.0    72.0              3.0                     3.0         Average   \n",
              "9    145.0    68.0              1.0                     3.0         Healthy   \n",
              "10   170.0    65.0              0.0                     1.0         Average   \n",
              "\n",
              "    aerobic_per_week  sports_per_week current_smoking prob_cancer  \n",
              "1                3.0              3.0           Never         0.0  \n",
              "2                1.0              0.0           Never         1.0  \n",
              "3                5.0              5.0           Never         0.0  \n",
              "4                0.0              0.0           Never         0.0  \n",
              "5                5.0              0.0           Never         0.0  \n",
              "6                0.0              1.0               0         0.0  \n",
              "7                1.0              0.0           Never         0.0  \n",
              "8                5.0              5.0           Never         0.0  \n",
              "9                3.0              0.0           Never         0.0  \n",
              "10               0.0              0.0           Never         0.0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-2c99bb43-a3d6-4dc9-92a2-e7f2c63de512\">\n",
              "    <div 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>weight</th>\n",
              "      <th>height</th>\n",
              "      <th>salads_per_week</th>\n",
              "      <th>veggies_fruits_per_day</th>\n",
              "      <th>healthy_diet</th>\n",
              "      <th>aerobic_per_week</th>\n",
              "      <th>sports_per_week</th>\n",
              "      <th>current_smoking</th>\n",
              "      <th>prob_cancer</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>150.0</td>\n",
              "      <td>67.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Below average</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>105.0</td>\n",
              "      <td>66.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Average</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>220.0</td>\n",
              "      <td>77.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Very healthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>135.0</td>\n",
              "      <td>62.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>180.0</td>\n",
              "      <td>69.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>5.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0.0</td>\n",
              "      <td>2801.0</td>\n",
              "      <td>7.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Very unhealthy</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>240.0</td>\n",
              "      <td>75.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Unhealthy</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>170.0</td>\n",
              "      <td>72.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Average</td>\n",
              "      <td>5.0</td>\n",
              "      <td>5.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>145.0</td>\n",
              "      <td>68.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>Healthy</td>\n",
              "      <td>3.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>170.0</td>\n",
              "      <td>65.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>Average</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Never</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-2c99bb43-a3d6-4dc9-92a2-e7f2c63de512')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-2c99bb43-a3d6-4dc9-92a2-e7f2c63de512 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-2c99bb43-a3d6-4dc9-92a2-e7f2c63de512');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "pdf.drop(['healthy_diet', 'current_smoking'], axis=1, inplace=True)\n",
        "pdf.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lTsFkWSnegzS",
        "outputId": "5ed08fa8-820e-44f1-8f0e-c336daf74907"
      },
      "execution_count": 33,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "<ipython-input-33-4261dae654d8>:1: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  pdf.drop(['healthy_diet', 'current_smoking'], axis=1, inplace=True)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(336, 7)"
            ]
          },
          "metadata": {},
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X = pdf.drop('prob_cancer', axis=1)\n",
        "y = pdf['prob_cancer']\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)"
      ],
      "metadata": {
        "id": "I2pj_PLTfBg8"
      },
      "execution_count": 34,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9G0WUqihiTx2",
        "outputId": "de1ae52d-af4b-4eed-d4f4-946b2b1b8b76"
      },
      "execution_count": 35,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(336, 6)"
            ]
          },
          "metadata": {},
          "execution_count": 35
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J7DslyvZiVsP",
        "outputId": "24015fc9-a97e-49af-e69b-c4d74bf2c52b"
      },
      "execution_count": 36,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(336,)"
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "scl = StandardScaler()\n",
        "X_train = scl.fit_transform(X_train)\n",
        "X_test = scl.transform(X_test)"
      ],
      "metadata": {
        "id": "209Ee7sUiaxD"
      },
      "execution_count": 38,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_test"
      ],
      "metadata": {
        "id": "kwlUuHnNjT4X"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "param = {\n",
        "    'max_depth': [2,3,4,5]\n",
        "}"
      ],
      "metadata": {
        "id": "ABvyMd8bjcvc"
      },
      "execution_count": 40,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.tree import DecisionTreeClassifier\n",
        "model =DecisionTreeClassifier()\n"
      ],
      "metadata": {
        "id": "eBoBUTGBkEx9"
      },
      "execution_count": 41,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import GridSearchCV\n",
        "gs = GridSearchCV(model, param)\n",
        "gs.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 117
        },
        "id": "hGVsMh86kTBI",
        "outputId": "38d965ef-f596-48a0-b9ac-0fc00b73176e"
      },
      "execution_count": 43,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(estimator=DecisionTreeClassifier(),\n",
              "             param_grid={'max_depth': [2, 3, 4, 5]})"
            ],
            "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(estimator=DecisionTreeClassifier(),\n",
              "             param_grid={&#x27;max_depth&#x27;: [2, 3, 4, 5]})</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(estimator=DecisionTreeClassifier(),\n",
              "             param_grid={&#x27;max_depth&#x27;: [2, 3, 4, 5]})</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: DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</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-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier()</pre></div></div></div></div></div></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "gs.best_params_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bOBVrDaPktHK",
        "outputId": "9f5e9245-d317-41bd-9f57-d85af1a0caa2"
      },
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'max_depth': 3}"
            ]
          },
          "metadata": {},
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score"
      ],
      "metadata": {
        "id": "bI9hqR1jk6tn"
      },
      "execution_count": 46,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model =DecisionTreeClassifier(max_depth = 3)\n",
        "model.fit(X_train, y_train)\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 75
        },
        "id": "P-UxlUn5lGt-",
        "outputId": "34b5a93b-ce95-4ea4-ab9f-4c122a36929c"
      },
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DecisionTreeClassifier(max_depth=3)"
            ],
            "text/html": [
              "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 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-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 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-2 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-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 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-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 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-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 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-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier(max_depth=3)</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-4\" type=\"checkbox\" checked><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">DecisionTreeClassifier</label><div class=\"sk-toggleable__content\"><pre>DecisionTreeClassifier(max_depth=3)</pre></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "y_p = model.predict(X_test)\n",
        "accuracy_score(y_test, y_p)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cUQLCa5XlWbW",
        "outputId": "5c0ec7f5-d6db-4ecf-81e9-7a0d1ec7b5e9"
      },
      "execution_count": 49,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.6039603960396039"
            ]
          },
          "metadata": {},
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.tree import export_graphviz\n",
        "import graphviz\n",
        "dot_data = export_graphviz(model, feature_names=X.columns, class_names=['NEG', 'POS'])\n",
        "graphviz.Source(dot_data)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 618
        },
        "id": "DCuCnmLvlpso",
        "outputId": "09198463-faa9-451a-e078-8cccb74ce691"
      },
      "execution_count": 51,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "image/svg+xml": "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n<!-- Generated by graphviz version 2.43.0 (0)\n -->\n<!-- Title: Tree Pages: 1 -->\n<svg width=\"955pt\" height=\"433pt\"\n viewBox=\"0.00 0.00 954.50 433.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 429)\">\n<title>Tree</title>\n<polygon fill=\"white\" stroke=\"transparent\" points=\"-4,4 -4,-429 950.5,-429 950.5,4 -4,4\"/>\n<!-- 0 -->\n<g id=\"node1\" class=\"node\">\n<title>0</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"550,-425 433,-425 433,-342 550,-342 550,-425\"/>\n<text text-anchor=\"middle\" x=\"491.5\" y=\"-409.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">height &lt;= &#45;0.212</text>\n<text text-anchor=\"middle\" x=\"491.5\" y=\"-394.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.411</text>\n<text text-anchor=\"middle\" x=\"491.5\" y=\"-379.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 235</text>\n<text text-anchor=\"middle\" x=\"491.5\" y=\"-364.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [167, 68]</text>\n<text text-anchor=\"middle\" x=\"491.5\" y=\"-349.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 1 -->\n<g id=\"node2\" class=\"node\">\n<title>1</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"462,-306 283,-306 283,-223 462,-223 462,-306\"/>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-290.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">salads_per_week &lt;= 0.029</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-275.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.469</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-260.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 16</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-245.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [6, 10]</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-230.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = POS</text>\n</g>\n<!-- 0&#45;&gt;1 -->\n<g id=\"edge1\" class=\"edge\">\n<title>0&#45;&gt;1</title>\n<path fill=\"none\" stroke=\"black\" d=\"M450.21,-341.91C440.8,-332.65 430.71,-322.73 421.02,-313.21\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"423.3,-310.54 413.71,-306.02 418.39,-315.53 423.3,-310.54\"/>\n<text text-anchor=\"middle\" x=\"413.93\" y=\"-327.32\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">True</text>\n</g>\n<!-- 8 -->\n<g id=\"node9\" class=\"node\">\n<title>8</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"676.5,-306 494.5,-306 494.5,-223 676.5,-223 676.5,-306\"/>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-290.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">sports_per_week &lt;= &#45;0.308</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-275.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.389</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-260.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 219</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-245.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [161, 58]</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-230.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 0&#45;&gt;8 -->\n<g id=\"edge8\" class=\"edge\">\n<title>0&#45;&gt;8</title>\n<path fill=\"none\" stroke=\"black\" d=\"M524.11,-341.91C531.33,-332.92 539.05,-323.32 546.49,-314.05\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"549.41,-316.01 552.94,-306.02 543.95,-311.62 549.41,-316.01\"/>\n<text text-anchor=\"middle\" x=\"555.65\" y=\"-327.17\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">False</text>\n</g>\n<!-- 2 -->\n<g id=\"node3\" class=\"node\">\n<title>2</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"251.5,-187 69.5,-187 69.5,-104 251.5,-104 251.5,-187\"/>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-171.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">aerobic_per_week &lt;= &#45;0.79</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-156.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.5</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-141.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 10</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-126.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [5, 5]</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-111.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 1&#45;&gt;2 -->\n<g id=\"edge2\" class=\"edge\">\n<title>1&#45;&gt;2</title>\n<path fill=\"none\" stroke=\"black\" d=\"M298.95,-222.91C280.86,-212.92 261.38,-202.17 242.9,-191.98\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"244.37,-188.79 233.92,-187.02 240.99,-194.92 244.37,-188.79\"/>\n</g>\n<!-- 5 -->\n<g id=\"node6\" class=\"node\">\n<title>5</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"462,-187 283,-187 283,-104 462,-104 462,-187\"/>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-171.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">salads_per_week &lt;= 1.666</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-156.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.278</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-141.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 6</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-126.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [1, 5]</text>\n<text text-anchor=\"middle\" x=\"372.5\" y=\"-111.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = POS</text>\n</g>\n<!-- 1&#45;&gt;5 -->\n<g id=\"edge5\" class=\"edge\">\n<title>1&#45;&gt;5</title>\n<path fill=\"none\" stroke=\"black\" d=\"M372.5,-222.91C372.5,-214.65 372.5,-205.86 372.5,-197.3\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"376,-197.02 372.5,-187.02 369,-197.02 376,-197.02\"/>\n</g>\n<!-- 3 -->\n<g id=\"node4\" class=\"node\">\n<title>3</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"95,-68 0,-68 0,0 95,0 95,-68\"/>\n<text text-anchor=\"middle\" x=\"47.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.375</text>\n<text text-anchor=\"middle\" x=\"47.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 4</text>\n<text text-anchor=\"middle\" x=\"47.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [1, 3]</text>\n<text text-anchor=\"middle\" x=\"47.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = POS</text>\n</g>\n<!-- 2&#45;&gt;3 -->\n<g id=\"edge3\" class=\"edge\">\n<title>2&#45;&gt;3</title>\n<path fill=\"none\" stroke=\"black\" d=\"M118.42,-103.73C108.82,-94.42 98.63,-84.54 89.05,-75.26\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"91.48,-72.75 81.86,-68.3 86.61,-77.77 91.48,-72.75\"/>\n</g>\n<!-- 4 -->\n<g id=\"node5\" class=\"node\">\n<title>4</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"208,-68 113,-68 113,0 208,0 208,-68\"/>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.444</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 6</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [4, 2]</text>\n<text text-anchor=\"middle\" x=\"160.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 2&#45;&gt;4 -->\n<g id=\"edge4\" class=\"edge\">\n<title>2&#45;&gt;4</title>\n<path fill=\"none\" stroke=\"black\" d=\"M160.5,-103.73C160.5,-95.52 160.5,-86.86 160.5,-78.56\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"164,-78.3 160.5,-68.3 157,-78.3 164,-78.3\"/>\n</g>\n<!-- 6 -->\n<g id=\"node7\" class=\"node\">\n<title>6</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"321,-68 226,-68 226,0 321,0 321,-68\"/>\n<text text-anchor=\"middle\" x=\"273.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.0</text>\n<text text-anchor=\"middle\" x=\"273.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 4</text>\n<text text-anchor=\"middle\" x=\"273.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [0, 4]</text>\n<text text-anchor=\"middle\" x=\"273.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = POS</text>\n</g>\n<!-- 5&#45;&gt;6 -->\n<g id=\"edge6\" class=\"edge\">\n<title>5&#45;&gt;6</title>\n<path fill=\"none\" stroke=\"black\" d=\"M335.64,-103.73C327.39,-94.61 318.64,-84.93 310.39,-75.81\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"312.91,-73.37 303.61,-68.3 307.72,-78.06 312.91,-73.37\"/>\n</g>\n<!-- 7 -->\n<g id=\"node8\" class=\"node\">\n<title>7</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"434,-68 339,-68 339,0 434,0 434,-68\"/>\n<text text-anchor=\"middle\" x=\"386.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.5</text>\n<text text-anchor=\"middle\" x=\"386.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 2</text>\n<text text-anchor=\"middle\" x=\"386.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [1, 1]</text>\n<text text-anchor=\"middle\" x=\"386.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 5&#45;&gt;7 -->\n<g id=\"edge7\" class=\"edge\">\n<title>5&#45;&gt;7</title>\n<path fill=\"none\" stroke=\"black\" d=\"M377.71,-103.73C378.77,-95.43 379.89,-86.67 380.97,-78.28\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"384.45,-78.66 382.24,-68.3 377.5,-77.77 384.45,-78.66\"/>\n</g>\n<!-- 9 -->\n<g id=\"node10\" class=\"node\">\n<title>9</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"644,-187 527,-187 527,-104 644,-104 644,-187\"/>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-171.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">height &lt;= &#45;0.179</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-156.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.308</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-141.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 126</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-126.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [102, 24]</text>\n<text text-anchor=\"middle\" x=\"585.5\" y=\"-111.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 8&#45;&gt;9 -->\n<g id=\"edge9\" class=\"edge\">\n<title>8&#45;&gt;9</title>\n<path fill=\"none\" stroke=\"black\" d=\"M585.5,-222.91C585.5,-214.65 585.5,-205.86 585.5,-197.3\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"589,-197.02 585.5,-187.02 582,-197.02 589,-197.02\"/>\n</g>\n<!-- 12 -->\n<g id=\"node13\" class=\"node\">\n<title>12</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"852,-187 675,-187 675,-104 852,-104 852,-187\"/>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-171.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">sports_per_week &lt;= 0.341</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-156.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.464</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-141.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 93</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-126.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [59, 34]</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-111.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 8&#45;&gt;12 -->\n<g id=\"edge12\" class=\"edge\">\n<title>8&#45;&gt;12</title>\n<path fill=\"none\" stroke=\"black\" d=\"M647.26,-222.91C662.17,-213.11 678.21,-202.56 693.47,-192.53\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"695.42,-195.44 701.85,-187.02 691.57,-189.59 695.42,-195.44\"/>\n</g>\n<!-- 10 -->\n<g id=\"node11\" class=\"node\">\n<title>10</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"562.5,-68 452.5,-68 452.5,0 562.5,0 562.5,-68\"/>\n<text text-anchor=\"middle\" x=\"507.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.452</text>\n<text text-anchor=\"middle\" x=\"507.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 29</text>\n<text text-anchor=\"middle\" x=\"507.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [19, 10]</text>\n<text text-anchor=\"middle\" x=\"507.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 9&#45;&gt;10 -->\n<g id=\"edge10\" class=\"edge\">\n<title>9&#45;&gt;10</title>\n<path fill=\"none\" stroke=\"black\" d=\"M556.46,-103.73C550.15,-94.88 543.48,-85.51 537.15,-76.63\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"539.87,-74.41 531.22,-68.3 534.17,-78.48 539.87,-74.41\"/>\n</g>\n<!-- 11 -->\n<g id=\"node12\" class=\"node\">\n<title>11</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"690.5,-68 580.5,-68 580.5,0 690.5,0 690.5,-68\"/>\n<text text-anchor=\"middle\" x=\"635.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.247</text>\n<text text-anchor=\"middle\" x=\"635.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 97</text>\n<text text-anchor=\"middle\" x=\"635.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [83, 14]</text>\n<text text-anchor=\"middle\" x=\"635.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 9&#45;&gt;11 -->\n<g id=\"edge11\" class=\"edge\">\n<title>9&#45;&gt;11</title>\n<path fill=\"none\" stroke=\"black\" d=\"M604.12,-103.73C608.03,-95.15 612.17,-86.09 616.11,-77.46\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"619.32,-78.85 620.29,-68.3 612.96,-75.94 619.32,-78.85\"/>\n</g>\n<!-- 13 -->\n<g id=\"node14\" class=\"node\">\n<title>13</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"818.5,-68 708.5,-68 708.5,0 818.5,0 818.5,-68\"/>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.5</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 38</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [19, 19]</text>\n<text text-anchor=\"middle\" x=\"763.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 12&#45;&gt;13 -->\n<g id=\"edge13\" class=\"edge\">\n<title>12&#45;&gt;13</title>\n<path fill=\"none\" stroke=\"black\" d=\"M763.5,-103.73C763.5,-95.52 763.5,-86.86 763.5,-78.56\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"767,-78.3 763.5,-68.3 760,-78.3 767,-78.3\"/>\n</g>\n<!-- 14 -->\n<g id=\"node15\" class=\"node\">\n<title>14</title>\n<polygon fill=\"none\" stroke=\"black\" points=\"946.5,-68 836.5,-68 836.5,0 946.5,0 946.5,-68\"/>\n<text text-anchor=\"middle\" x=\"891.5\" y=\"-52.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">gini = 0.397</text>\n<text text-anchor=\"middle\" x=\"891.5\" y=\"-37.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">samples = 55</text>\n<text text-anchor=\"middle\" x=\"891.5\" y=\"-22.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">value = [40, 15]</text>\n<text text-anchor=\"middle\" x=\"891.5\" y=\"-7.8\" font-family=\"Helvetica,sans-Serif\" font-size=\"14.00\">class = NEG</text>\n</g>\n<!-- 12&#45;&gt;14 -->\n<g id=\"edge14\" class=\"edge\">\n<title>12&#45;&gt;14</title>\n<path fill=\"none\" stroke=\"black\" d=\"M811.16,-103.73C822.14,-94.33 833.81,-84.35 844.76,-74.99\"/>\n<polygon fill=\"black\" stroke=\"black\" points=\"847.25,-77.46 852.57,-68.3 842.7,-72.14 847.25,-77.46\"/>\n</g>\n</g>\n</svg>\n",
            "text/plain": [
              "<graphviz.sources.Source at 0x7f51a8902820>"
            ]
          },
          "metadata": {},
          "execution_count": 51
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "hdDeLIngmk2Z"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}