{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HzaAntZSX_LR"
      },
      "source": [
        "# Linear and Logistic Regression Laboratory\n",
        "\n",
        "## Linear Regression\n",
        "\n",
        "We will use the datatset available at this URL:\n",
        "\n",
        "https://www.kaggle.com/datasets/yasserh/advertising-sales-dataset\n",
        "\n",
        "Let us load the dataset:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 448
        },
        "id": "w2shvBbmkT5k",
        "outputId": "7e7ad2de-bf1a-436b-c41e-2e589b245993"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-189f7dd2-a721-4f33-84da-3175b5a90382\" 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>tv</th>\n",
              "      <th>radio</th>\n",
              "      <th>newspaper</th>\n",
              "      <th>sales</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Index</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>230.1</td>\n",
              "      <td>37.8</td>\n",
              "      <td>69.2</td>\n",
              "      <td>22.1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>44.5</td>\n",
              "      <td>39.3</td>\n",
              "      <td>45.1</td>\n",
              "      <td>10.4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>17.2</td>\n",
              "      <td>45.9</td>\n",
              "      <td>69.3</td>\n",
              "      <td>9.3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>151.5</td>\n",
              "      <td>41.3</td>\n",
              "      <td>58.5</td>\n",
              "      <td>18.5</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>180.8</td>\n",
              "      <td>10.8</td>\n",
              "      <td>58.4</td>\n",
              "      <td>12.9</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>196</th>\n",
              "      <td>38.2</td>\n",
              "      <td>3.7</td>\n",
              "      <td>13.8</td>\n",
              "      <td>7.6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>197</th>\n",
              "      <td>94.2</td>\n",
              "      <td>4.9</td>\n",
              "      <td>8.1</td>\n",
              "      <td>9.7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>198</th>\n",
              "      <td>177.0</td>\n",
              "      <td>9.3</td>\n",
              "      <td>6.4</td>\n",
              "      <td>12.8</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>199</th>\n",
              "      <td>283.6</td>\n",
              "      <td>42.0</td>\n",
              "      <td>66.2</td>\n",
              "      <td>25.5</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>200</th>\n",
              "      <td>232.1</td>\n",
              "      <td>8.6</td>\n",
              "      <td>8.7</td>\n",
              "      <td>13.4</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>200 rows × 4 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-189f7dd2-a721-4f33-84da-3175b5a90382')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-189f7dd2-a721-4f33-84da-3175b5a90382 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-189f7dd2-a721-4f33-84da-3175b5a90382');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-b43c24d2-dc89-49dd-b83c-58836ce54240\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-b43c24d2-dc89-49dd-b83c-58836ce54240')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-b43c24d2-dc89-49dd-b83c-58836ce54240 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "          tv  radio  newspaper  sales\n",
              "Index                                \n",
              "1      230.1   37.8       69.2   22.1\n",
              "2       44.5   39.3       45.1   10.4\n",
              "3       17.2   45.9       69.3    9.3\n",
              "4      151.5   41.3       58.5   18.5\n",
              "5      180.8   10.8       58.4   12.9\n",
              "...      ...    ...        ...    ...\n",
              "196     38.2    3.7       13.8    7.6\n",
              "197     94.2    4.9        8.1    9.7\n",
              "198    177.0    9.3        6.4   12.8\n",
              "199    283.6   42.0       66.2   25.5\n",
              "200    232.1    8.6        8.7   13.4\n",
              "\n",
              "[200 rows x 4 columns]"
            ]
          },
          "execution_count": 3,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "import pandas as pd\n",
        "advertising=pd.read_csv('Advertising Budget and Sales.csv')\n",
        "advertising=advertising.rename(columns={\n",
        "    'Unnamed: 0':'Index',\n",
        "    'TV Ad Budget ($)': 'tv',\n",
        "    'Radio Ad Budget ($)': 'radio',\n",
        "    'Newspaper Ad Budget ($)': 'newspaper',\n",
        "    'Sales ($)': 'sales'\n",
        "    })\n",
        "advertising.set_index('Index')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "dPR_7oIzl8Ey",
        "outputId": "db99fc9e-2816-41de-d83f-810c87786280"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 200 entries, 0 to 199\n",
            "Data columns (total 5 columns):\n",
            " #   Column     Non-Null Count  Dtype  \n",
            "---  ------     --------------  -----  \n",
            " 0   Index      200 non-null    int64  \n",
            " 1   tv         200 non-null    float64\n",
            " 2   radio      200 non-null    float64\n",
            " 3   newspaper  200 non-null    float64\n",
            " 4   sales      200 non-null    float64\n",
            "dtypes: float64(4), int64(1)\n",
            "memory usage: 7.9 KB\n"
          ]
        }
      ],
      "source": [
        "advertising.info()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 785
        },
        "id": "0AMULhMBk9tu",
        "outputId": "3eb2cca1-fbea-4c8c-b719-eb7705517ad2"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<seaborn.axisgrid.PairGrid at 0x7b57ba39b460>"
            ]
          },
          "execution_count": 5,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1000x1000 with 20 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "import seaborn as sns\n",
        "sns.pairplot(advertising.drop('Index',axis=1))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 452
        },
        "id": "QkV4QxL4mh4B",
        "outputId": "278733b8-08bb-4669-c882-9cd5e6ca38c0"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<Axes: >"
            ]
          },
          "execution_count": 6,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "sns.heatmap(advertising.corr(), annot=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "XW4fQ9PLm7lg"
      },
      "outputs": [],
      "source": [
        "from scipy.stats import pearsonr"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4g297oWKnHLI",
        "outputId": "6535da9a-32ec-4e97-a842-64dc79b41203"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "PearsonRResult(statistic=0.05480866446583009, pvalue=0.440806063788431)"
            ]
          },
          "execution_count": 8,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "pearsonr(advertising['tv'],advertising['radio'])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yb_gNrC-xZI-"
      },
      "source": [
        "The correlation between `tv` and `radio` is not statistically significant."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "U_YpfgF6nLoo",
        "outputId": "2a3b227f-c349-49c2-a7e2-2f039d1d1cb5"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "PearsonRResult(statistic=0.35410375076117534, pvalue=2.688835078719109e-07)"
            ]
          },
          "execution_count": 10,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "pearsonr(advertising['newspaper'],advertising['radio'])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 82
        },
        "id": "CJ77rp3qnr11",
        "outputId": "05253412-6d00-42ab-b237-c05de5143e12"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th> <td>   18.4700</td> <td>    2.689</td> <td>    6.870</td> <td> 0.000</td> <td>   13.168</td> <td>   23.772</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>radio</th>     <td>    0.5194</td> <td>    0.097</td> <td>    5.328</td> <td> 0.000</td> <td>    0.327</td> <td>    0.712</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lcccccc}\n",
              "\\toprule\n",
              "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept} &      18.4700  &        2.689     &     6.870  &         0.000        &       13.168    &       23.772     \\\\\n",
              "\\textbf{radio}     &       0.5194  &        0.097     &     5.328  &         0.000        &        0.327    &        0.712     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.table.SimpleTable'>"
            ]
          },
          "execution_count": 11,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "from statsmodels.formula.api import ols\n",
        "ols(\"newspaper ~ radio\", advertising).fit().summary().tables[1]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 82
        },
        "id": "PplFSkcDudgG",
        "outputId": "739b276c-55a1-428b-91b3-f4b92e95b1ca"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th> <td>   15.8883</td> <td>    1.699</td> <td>    9.354</td> <td> 0.000</td> <td>   12.539</td> <td>   19.238</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>newspaper</th> <td>    0.2414</td> <td>    0.045</td> <td>    5.328</td> <td> 0.000</td> <td>    0.152</td> <td>    0.331</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lcccccc}\n",
              "\\toprule\n",
              "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept} &      15.8883  &        1.699     &     9.354  &         0.000        &       12.539    &       19.238     \\\\\n",
              "\\textbf{newspaper} &       0.2414  &        0.045     &     5.328  &         0.000        &        0.152    &        0.331     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.table.SimpleTable'>"
            ]
          },
          "execution_count": 12,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "ols(\"radio ~ newspaper\", advertising).fit().summary().tables[1]"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "liG-GEPBugvz",
        "outputId": "e1521888-87af-4f3d-e905-afec791a7ed9"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<Axes: xlabel='radio', ylabel='newspaper'>"
            ]
          },
          "execution_count": 13,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "sns.regplot(x='radio', y='newspaper', data=advertising)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 440
        },
        "id": "kXq_dP-4wQvZ",
        "outputId": "24f6dd63-6c90-4647-f543-d7d6c30a12fa"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>OLS Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>          <td>sales</td>      <th>  R-squared:         </th> <td>   0.612</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.610</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   312.1</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>             <td>Thu, 30 Nov 2023</td> <th>  Prob (F-statistic):</th> <td>1.47e-42</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                 <td>19:48:09</td>     <th>  Log-Likelihood:    </th> <td> -519.05</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>No. Observations:</th>      <td>   200</td>      <th>  AIC:               </th> <td>   1042.</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Residuals:</th>          <td>   198</td>      <th>  BIC:               </th> <td>   1049.</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th> <td>    7.0326</td> <td>    0.458</td> <td>   15.360</td> <td> 0.000</td> <td>    6.130</td> <td>    7.935</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>tv</th>        <td>    0.0475</td> <td>    0.003</td> <td>   17.668</td> <td> 0.000</td> <td>    0.042</td> <td>    0.053</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "  <th>Omnibus:</th>       <td> 0.531</td> <th>  Durbin-Watson:     </th> <td>   1.935</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Prob(Omnibus):</th> <td> 0.767</td> <th>  Jarque-Bera (JB):  </th> <td>   0.669</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Skew:</th>          <td>-0.089</td> <th>  Prob(JB):          </th> <td>   0.716</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Kurtosis:</th>      <td> 2.779</td> <th>  Cond. No.          </th> <td>    338.</td>\n",
              "</tr>\n",
              "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}    &      sales       & \\textbf{  R-squared:         } &     0.612   \\\\\n",
              "\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.610   \\\\\n",
              "\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     312.1   \\\\\n",
              "\\textbf{Date:}             & Thu, 30 Nov 2023 & \\textbf{  Prob (F-statistic):} &  1.47e-42   \\\\\n",
              "\\textbf{Time:}             &     19:48:09     & \\textbf{  Log-Likelihood:    } &   -519.05   \\\\\n",
              "\\textbf{No. Observations:} &         200      & \\textbf{  AIC:               } &     1042.   \\\\\n",
              "\\textbf{Df Residuals:}     &         198      & \\textbf{  BIC:               } &     1049.   \\\\\n",
              "\\textbf{Df Model:}         &           1      & \\textbf{                     } &             \\\\\n",
              "\\textbf{Covariance Type:}  &    nonrobust     & \\textbf{                     } &             \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept} &       7.0326  &        0.458     &    15.360  &         0.000        &        6.130    &        7.935     \\\\\n",
              "\\textbf{tv}        &       0.0475  &        0.003     &    17.668  &         0.000        &        0.042    &        0.053     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lclc}\n",
              "\\textbf{Omnibus:}       &  0.531 & \\textbf{  Durbin-Watson:     } &    1.935  \\\\\n",
              "\\textbf{Prob(Omnibus):} &  0.767 & \\textbf{  Jarque-Bera (JB):  } &    0.669  \\\\\n",
              "\\textbf{Skew:}          & -0.089 & \\textbf{  Prob(JB):          } &    0.716  \\\\\n",
              "\\textbf{Kurtosis:}      &  2.779 & \\textbf{  Cond. No.          } &     338.  \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{OLS Regression Results}\n",
              "\\end{center}\n",
              "\n",
              "Notes: \\newline\n",
              " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                            OLS Regression Results                            \n",
              "==============================================================================\n",
              "Dep. Variable:                  sales   R-squared:                       0.612\n",
              "Model:                            OLS   Adj. R-squared:                  0.610\n",
              "Method:                 Least Squares   F-statistic:                     312.1\n",
              "Date:                Thu, 30 Nov 2023   Prob (F-statistic):           1.47e-42\n",
              "Time:                        19:48:09   Log-Likelihood:                -519.05\n",
              "No. Observations:                 200   AIC:                             1042.\n",
              "Df Residuals:                     198   BIC:                             1049.\n",
              "Df Model:                           1                                         \n",
              "Covariance Type:            nonrobust                                         \n",
              "==============================================================================\n",
              "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------\n",
              "Intercept      7.0326      0.458     15.360      0.000       6.130       7.935\n",
              "tv             0.0475      0.003     17.668      0.000       0.042       0.053\n",
              "==============================================================================\n",
              "Omnibus:                        0.531   Durbin-Watson:                   1.935\n",
              "Prob(Omnibus):                  0.767   Jarque-Bera (JB):                0.669\n",
              "Skew:                          -0.089   Prob(JB):                        0.716\n",
              "Kurtosis:                       2.779   Cond. No.                         338.\n",
              "==============================================================================\n",
              "\n",
              "Notes:\n",
              "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
              "\"\"\""
            ]
          },
          "execution_count": 14,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "ols(\"sales ~ tv\", advertising).fit().summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "ol3PDPZHw5SI",
        "outputId": "3a850d94-a617-42ba-a639-1c6e5af67803"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<Axes: xlabel='tv', ylabel='sales'>"
            ]
          },
          "execution_count": 15,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "sns.regplot(x='tv', y='sales', data=advertising)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 217
        },
        "id": "XjtGDvmqwUWs",
        "outputId": "57315868-607c-42e5-e6b5-9e5b5a83caaf"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 2000x2200 with 2 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "import statsmodels.api as sm\n",
        "from matplotlib import pyplot as plt\n",
        "model=ols(\"sales ~ tv\", advertising).fit()\n",
        "\n",
        "#otteniamo i valori predetti dal modello:\n",
        "fitted = model.fittedvalues.fillna(0) #rimpiazzo eventuali NaN con zero\n",
        "\n",
        "plt.figure(figsize=(20,22))\n",
        "sns.residplot(x=fitted, y='sales', data=advertising.dropna(),lowess=True,line_kws={'color': 'red', 'lw': 1, 'alpha': 0.8}, ax=plt.subplot(421))\n",
        "sm.qqplot(fitted-advertising.dropna()['sales'], line='45',fit=True, ax=plt.subplot(422))\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 461
        },
        "id": "SRRVZox81gDu",
        "outputId": "249c9e7a-52d0-4e02-f790-7d22257aa044"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>OLS Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>          <td>sales</td>      <th>  R-squared:         </th> <td>   0.897</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.896</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   859.6</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>             <td>Thu, 30 Nov 2023</td> <th>  Prob (F-statistic):</th> <td>4.83e-98</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                 <td>19:48:42</td>     <th>  Log-Likelihood:    </th> <td> -386.20</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>No. Observations:</th>      <td>   200</td>      <th>  AIC:               </th> <td>   778.4</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Residuals:</th>          <td>   197</td>      <th>  BIC:               </th> <td>   788.3</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Model:</th>              <td>     2</td>      <th>                     </th>     <td> </td>   \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th> <td>    2.9211</td> <td>    0.294</td> <td>    9.919</td> <td> 0.000</td> <td>    2.340</td> <td>    3.502</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>tv</th>        <td>    0.0458</td> <td>    0.001</td> <td>   32.909</td> <td> 0.000</td> <td>    0.043</td> <td>    0.048</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>radio</th>     <td>    0.1880</td> <td>    0.008</td> <td>   23.382</td> <td> 0.000</td> <td>    0.172</td> <td>    0.204</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "  <th>Omnibus:</th>       <td>60.022</td> <th>  Durbin-Watson:     </th> <td>   2.081</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Prob(Omnibus):</th> <td> 0.000</td> <th>  Jarque-Bera (JB):  </th> <td> 148.679</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Skew:</th>          <td>-1.323</td> <th>  Prob(JB):          </th> <td>5.19e-33</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Kurtosis:</th>      <td> 6.292</td> <th>  Cond. No.          </th> <td>    425.</td>\n",
              "</tr>\n",
              "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}    &      sales       & \\textbf{  R-squared:         } &     0.897   \\\\\n",
              "\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.896   \\\\\n",
              "\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     859.6   \\\\\n",
              "\\textbf{Date:}             & Thu, 30 Nov 2023 & \\textbf{  Prob (F-statistic):} &  4.83e-98   \\\\\n",
              "\\textbf{Time:}             &     19:48:42     & \\textbf{  Log-Likelihood:    } &   -386.20   \\\\\n",
              "\\textbf{No. Observations:} &         200      & \\textbf{  AIC:               } &     778.4   \\\\\n",
              "\\textbf{Df Residuals:}     &         197      & \\textbf{  BIC:               } &     788.3   \\\\\n",
              "\\textbf{Df Model:}         &           2      & \\textbf{                     } &             \\\\\n",
              "\\textbf{Covariance Type:}  &    nonrobust     & \\textbf{                     } &             \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept} &       2.9211  &        0.294     &     9.919  &         0.000        &        2.340    &        3.502     \\\\\n",
              "\\textbf{tv}        &       0.0458  &        0.001     &    32.909  &         0.000        &        0.043    &        0.048     \\\\\n",
              "\\textbf{radio}     &       0.1880  &        0.008     &    23.382  &         0.000        &        0.172    &        0.204     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lclc}\n",
              "\\textbf{Omnibus:}       & 60.022 & \\textbf{  Durbin-Watson:     } &    2.081  \\\\\n",
              "\\textbf{Prob(Omnibus):} &  0.000 & \\textbf{  Jarque-Bera (JB):  } &  148.679  \\\\\n",
              "\\textbf{Skew:}          & -1.323 & \\textbf{  Prob(JB):          } & 5.19e-33  \\\\\n",
              "\\textbf{Kurtosis:}      &  6.292 & \\textbf{  Cond. No.          } &     425.  \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{OLS Regression Results}\n",
              "\\end{center}\n",
              "\n",
              "Notes: \\newline\n",
              " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                            OLS Regression Results                            \n",
              "==============================================================================\n",
              "Dep. Variable:                  sales   R-squared:                       0.897\n",
              "Model:                            OLS   Adj. R-squared:                  0.896\n",
              "Method:                 Least Squares   F-statistic:                     859.6\n",
              "Date:                Thu, 30 Nov 2023   Prob (F-statistic):           4.83e-98\n",
              "Time:                        19:48:42   Log-Likelihood:                -386.20\n",
              "No. Observations:                 200   AIC:                             778.4\n",
              "Df Residuals:                     197   BIC:                             788.3\n",
              "Df Model:                           2                                         \n",
              "Covariance Type:            nonrobust                                         \n",
              "==============================================================================\n",
              "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------\n",
              "Intercept      2.9211      0.294      9.919      0.000       2.340       3.502\n",
              "tv             0.0458      0.001     32.909      0.000       0.043       0.048\n",
              "radio          0.1880      0.008     23.382      0.000       0.172       0.204\n",
              "==============================================================================\n",
              "Omnibus:                       60.022   Durbin-Watson:                   2.081\n",
              "Prob(Omnibus):                  0.000   Jarque-Bera (JB):              148.679\n",
              "Skew:                          -1.323   Prob(JB):                     5.19e-33\n",
              "Kurtosis:                       6.292   Cond. No.                         425.\n",
              "==============================================================================\n",
              "\n",
              "Notes:\n",
              "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
              "\"\"\""
            ]
          },
          "execution_count": 18,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "ols(\"sales ~ tv + radio\", advertising).fit().summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 217
        },
        "id": "2n8_pMfw1vJ7",
        "outputId": "aa7b528c-b09c-42af-91d8-4966c4044573"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 2000x2200 with 2 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "import statsmodels.api as sm\n",
        "from matplotlib import pyplot as plt\n",
        "model=ols(\"sales ~ tv + radio\", advertising).fit()\n",
        "\n",
        "#otteniamo i valori predetti dal modello:\n",
        "fitted = model.fittedvalues.fillna(0) #rimpiazzo eventuali NaN con zero\n",
        "\n",
        "plt.figure(figsize=(20,22))\n",
        "sns.residplot(x=fitted, y='sales', data=advertising.dropna(),lowess=True,line_kws={'color': 'red', 'lw': 1, 'alpha': 0.8}, ax=plt.subplot(421))\n",
        "sm.qqplot(fitted-advertising.dropna()['sales'], line='45',fit=True, ax=plt.subplot(422))\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "h1vem_8qxwh-"
      },
      "source": [
        "Let us add an interaction term:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 516
        },
        "id": "tssivqdF-YFB",
        "outputId": "b0a987b5-1295-470d-b95a-0f762d9ce8ac"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>OLS Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>          <td>sales</td>      <th>  R-squared:         </th> <td>   0.968</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.967</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   1963.</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>             <td>Thu, 30 Nov 2023</td> <th>  Prob (F-statistic):</th> <td>6.68e-146</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                 <td>19:49:14</td>     <th>  Log-Likelihood:    </th> <td> -270.14</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>No. Observations:</th>      <td>   200</td>      <th>  AIC:               </th> <td>   548.3</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Residuals:</th>          <td>   196</td>      <th>  BIC:               </th> <td>   561.5</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Model:</th>              <td>     3</td>      <th>                     </th>     <td> </td>    \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>    \n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th> <td>    6.7502</td> <td>    0.248</td> <td>   27.233</td> <td> 0.000</td> <td>    6.261</td> <td>    7.239</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>tv</th>        <td>    0.0191</td> <td>    0.002</td> <td>   12.699</td> <td> 0.000</td> <td>    0.016</td> <td>    0.022</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>radio</th>     <td>    0.0289</td> <td>    0.009</td> <td>    3.241</td> <td> 0.001</td> <td>    0.011</td> <td>    0.046</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>radio:tv</th>  <td>    0.0011</td> <td> 5.24e-05</td> <td>   20.727</td> <td> 0.000</td> <td>    0.001</td> <td>    0.001</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "  <th>Omnibus:</th>       <td>128.132</td> <th>  Durbin-Watson:     </th> <td>   2.224</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Prob(Omnibus):</th> <td> 0.000</td>  <th>  Jarque-Bera (JB):  </th> <td>1183.719</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Skew:</th>          <td>-2.323</td>  <th>  Prob(JB):          </th> <td>9.09e-258</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Kurtosis:</th>      <td>13.975</td>  <th>  Cond. No.          </th> <td>1.80e+04</td> \n",
              "</tr>\n",
              "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.<br/>[2] The condition number is large, 1.8e+04. This might indicate that there are<br/>strong multicollinearity or other numerical problems."
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}    &      sales       & \\textbf{  R-squared:         } &     0.968   \\\\\n",
              "\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.967   \\\\\n",
              "\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     1963.   \\\\\n",
              "\\textbf{Date:}             & Thu, 30 Nov 2023 & \\textbf{  Prob (F-statistic):} & 6.68e-146   \\\\\n",
              "\\textbf{Time:}             &     19:49:14     & \\textbf{  Log-Likelihood:    } &   -270.14   \\\\\n",
              "\\textbf{No. Observations:} &         200      & \\textbf{  AIC:               } &     548.3   \\\\\n",
              "\\textbf{Df Residuals:}     &         196      & \\textbf{  BIC:               } &     561.5   \\\\\n",
              "\\textbf{Df Model:}         &           3      & \\textbf{                     } &             \\\\\n",
              "\\textbf{Covariance Type:}  &    nonrobust     & \\textbf{                     } &             \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept} &       6.7502  &        0.248     &    27.233  &         0.000        &        6.261    &        7.239     \\\\\n",
              "\\textbf{tv}        &       0.0191  &        0.002     &    12.699  &         0.000        &        0.016    &        0.022     \\\\\n",
              "\\textbf{radio}     &       0.0289  &        0.009     &     3.241  &         0.001        &        0.011    &        0.046     \\\\\n",
              "\\textbf{radio:tv}  &       0.0011  &     5.24e-05     &    20.727  &         0.000        &        0.001    &        0.001     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lclc}\n",
              "\\textbf{Omnibus:}       & 128.132 & \\textbf{  Durbin-Watson:     } &     2.224  \\\\\n",
              "\\textbf{Prob(Omnibus):} &   0.000 & \\textbf{  Jarque-Bera (JB):  } &  1183.719  \\\\\n",
              "\\textbf{Skew:}          &  -2.323 & \\textbf{  Prob(JB):          } & 9.09e-258  \\\\\n",
              "\\textbf{Kurtosis:}      &  13.975 & \\textbf{  Cond. No.          } &  1.80e+04  \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{OLS Regression Results}\n",
              "\\end{center}\n",
              "\n",
              "Notes: \\newline\n",
              " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified. \\newline\n",
              " [2] The condition number is large, 1.8e+04. This might indicate that there are \\newline\n",
              " strong multicollinearity or other numerical problems."
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                            OLS Regression Results                            \n",
              "==============================================================================\n",
              "Dep. Variable:                  sales   R-squared:                       0.968\n",
              "Model:                            OLS   Adj. R-squared:                  0.967\n",
              "Method:                 Least Squares   F-statistic:                     1963.\n",
              "Date:                Thu, 30 Nov 2023   Prob (F-statistic):          6.68e-146\n",
              "Time:                        19:49:14   Log-Likelihood:                -270.14\n",
              "No. Observations:                 200   AIC:                             548.3\n",
              "Df Residuals:                     196   BIC:                             561.5\n",
              "Df Model:                           3                                         \n",
              "Covariance Type:            nonrobust                                         \n",
              "==============================================================================\n",
              "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------\n",
              "Intercept      6.7502      0.248     27.233      0.000       6.261       7.239\n",
              "tv             0.0191      0.002     12.699      0.000       0.016       0.022\n",
              "radio          0.0289      0.009      3.241      0.001       0.011       0.046\n",
              "radio:tv       0.0011   5.24e-05     20.727      0.000       0.001       0.001\n",
              "==============================================================================\n",
              "Omnibus:                      128.132   Durbin-Watson:                   2.224\n",
              "Prob(Omnibus):                  0.000   Jarque-Bera (JB):             1183.719\n",
              "Skew:                          -2.323   Prob(JB):                    9.09e-258\n",
              "Kurtosis:                      13.975   Cond. No.                     1.80e+04\n",
              "==============================================================================\n",
              "\n",
              "Notes:\n",
              "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
              "[2] The condition number is large, 1.8e+04. This might indicate that there are\n",
              "strong multicollinearity or other numerical problems.\n",
              "\"\"\""
            ]
          },
          "execution_count": 20,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "ols(\"sales ~ tv   + radio + radio*tv\", advertising).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "f1XS7q_3-1u2"
      },
      "source": [
        "The regressor with interaction terms can be interpreted as follows:\n",
        "\n",
        "$$sales = \\beta_0 + \\beta_1 tv + \\beta_2 radio + \\beta_3 radio \\times tv$$\n",
        "$$sales = \\beta_0 + tv(\\beta_1 + \\beta_3 radio) + \\beta_2 radio$$\n",
        "$$sales = \\beta_0 + \\beta_1 tv + radio(\\beta_2 + tv \\beta_3)$$"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cLAhuc6AtT7d"
      },
      "source": [
        "## Linear Regression vs Mean Values"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 22,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 416
        },
        "id": "uzRl3_MaqWz-",
        "outputId": "090483dd-7be1-42a1-a086-2304148332aa"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-b778ebe7-ec16-4ae3-ba23-2bac6fe95eb2\" 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>y</th>\n",
              "      <th>x</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>10.091945</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>8.620043</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>14.530024</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>16.894454</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>10.864606</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>95</th>\n",
              "      <td>8.241021</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>96</th>\n",
              "      <td>7.561387</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>97</th>\n",
              "      <td>6.688701</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>98</th>\n",
              "      <td>12.406282</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>99</th>\n",
              "      <td>8.094310</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>100 rows × 2 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b778ebe7-ec16-4ae3-ba23-2bac6fe95eb2')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-b778ebe7-ec16-4ae3-ba23-2bac6fe95eb2 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-b778ebe7-ec16-4ae3-ba23-2bac6fe95eb2');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-d3587f8f-b867-4cf9-8c49-a4183c146587\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-d3587f8f-b867-4cf9-8c49-a4183c146587')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-d3587f8f-b867-4cf9-8c49-a4183c146587 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "            y  x\n",
              "0   10.091945  0\n",
              "1    8.620043  1\n",
              "2   14.530024  0\n",
              "3   16.894454  1\n",
              "4   10.864606  1\n",
              "..        ... ..\n",
              "95   8.241021  0\n",
              "96   7.561387  0\n",
              "97   6.688701  0\n",
              "98  12.406282  1\n",
              "99   8.094310  0\n",
              "\n",
              "[100 rows x 2 columns]"
            ]
          },
          "execution_count": 22,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "import numpy as np\n",
        "x = np.random.normal(0,2,100)>0\n",
        "y = np.random.normal(10,2,100) + 2*x\n",
        "d= pd.DataFrame({\n",
        "    'y': y,\n",
        "    'x': x\n",
        "})\n",
        "d['x']=d['x'].astype(int)\n",
        "d"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 296
        },
        "id": "t3XZUP8krHIq",
        "outputId": "951f0004-cc4c-4f80-c180-112d63dc7191"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-50f922d9-b340-4779-98d2-46a0c7e0d1b3\" 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>y</th>\n",
              "      <th>x</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>100.000000</td>\n",
              "      <td>100.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>11.124978</td>\n",
              "      <td>0.490000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>2.509474</td>\n",
              "      <td>0.502418</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>5.701657</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>9.310256</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>10.770151</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>12.717417</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>17.218798</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-50f922d9-b340-4779-98d2-46a0c7e0d1b3')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-50f922d9-b340-4779-98d2-46a0c7e0d1b3 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-50f922d9-b340-4779-98d2-46a0c7e0d1b3');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-0612cfd0-12cc-414b-a8dc-8af693aba83c\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0612cfd0-12cc-414b-a8dc-8af693aba83c')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-0612cfd0-12cc-414b-a8dc-8af693aba83c button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "                y           x\n",
              "count  100.000000  100.000000\n",
              "mean    11.124978    0.490000\n",
              "std      2.509474    0.502418\n",
              "min      5.701657    0.000000\n",
              "25%      9.310256    0.000000\n",
              "50%     10.770151    0.000000\n",
              "75%     12.717417    1.000000\n",
              "max     17.218798    1.000000"
            ]
          },
          "execution_count": 23,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "d.describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 24,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VugCivXYqx2D",
        "outputId": "c9c7c9a5-73c7-425a-9b7c-a8544e062bf0"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "10.18727989115969"
            ]
          },
          "execution_count": 24,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "d[d['x']==0]['y'].mean()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 25,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "okkrHsAyrQjj",
        "outputId": "92aed13d-92db-450d-cd61-7decc06107e4"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "12.100950474439491"
            ]
          },
          "execution_count": 25,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "d[d['x']==1]['y'].mean()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 26,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N-9T4aHqs6jM",
        "outputId": "f84b7893-bf71-4e89-d35b-62945a4535ae"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "12.42637989115969"
            ]
          },
          "execution_count": 26,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "d[d['x']==0]['y'].mean() + 2.2391"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 27,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 440
        },
        "id": "UljjzkSTrExg",
        "outputId": "cfbb30d3-6750-4ba6-cce2-301d4de7bec7"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>OLS Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>            <td>y</td>        <th>  R-squared:         </th> <td>   0.147</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                   <td>OLS</td>       <th>  Adj. R-squared:    </th> <td>   0.138</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>             <td>Least Squares</td>  <th>  F-statistic:       </th> <td>   16.86</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>             <td>Thu, 30 Nov 2023</td> <th>  Prob (F-statistic):</th> <td>8.34e-05</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                 <td>19:50:08</td>     <th>  Log-Likelihood:    </th> <td> -225.46</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>No. Observations:</th>      <td>   100</td>      <th>  AIC:               </th> <td>   454.9</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Residuals:</th>          <td>    98</td>      <th>  BIC:               </th> <td>   460.1</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Df Model:</th>              <td>     1</td>      <th>                     </th>     <td> </td>   \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>      <td>nonrobust</td>    <th>                     </th>     <td> </td>   \n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "      <td></td>         <th>coef</th>     <th>std err</th>      <th>t</th>      <th>P>|t|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th> <td>   10.1873</td> <td>    0.326</td> <td>   31.227</td> <td> 0.000</td> <td>    9.540</td> <td>   10.835</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>x</th>         <td>    1.9137</td> <td>    0.466</td> <td>    4.106</td> <td> 0.000</td> <td>    0.989</td> <td>    2.839</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "  <th>Omnibus:</th>       <td> 3.658</td> <th>  Durbin-Watson:     </th> <td>   2.063</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Prob(Omnibus):</th> <td> 0.161</td> <th>  Jarque-Bera (JB):  </th> <td>   3.568</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Skew:</th>          <td> 0.458</td> <th>  Prob(JB):          </th> <td>   0.168</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Kurtosis:</th>      <td> 2.863</td> <th>  Cond. No.          </th> <td>    2.60</td>\n",
              "</tr>\n",
              "</table><br/><br/>Notes:<br/>[1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}    &        y         & \\textbf{  R-squared:         } &     0.147   \\\\\n",
              "\\textbf{Model:}            &       OLS        & \\textbf{  Adj. R-squared:    } &     0.138   \\\\\n",
              "\\textbf{Method:}           &  Least Squares   & \\textbf{  F-statistic:       } &     16.86   \\\\\n",
              "\\textbf{Date:}             & Thu, 30 Nov 2023 & \\textbf{  Prob (F-statistic):} &  8.34e-05   \\\\\n",
              "\\textbf{Time:}             &     19:50:08     & \\textbf{  Log-Likelihood:    } &   -225.46   \\\\\n",
              "\\textbf{No. Observations:} &         100      & \\textbf{  AIC:               } &     454.9   \\\\\n",
              "\\textbf{Df Residuals:}     &          98      & \\textbf{  BIC:               } &     460.1   \\\\\n",
              "\\textbf{Df Model:}         &           1      & \\textbf{                     } &             \\\\\n",
              "\\textbf{Covariance Type:}  &    nonrobust     & \\textbf{                     } &             \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                   & \\textbf{coef} & \\textbf{std err} & \\textbf{t} & \\textbf{P$> |$t$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept} &      10.1873  &        0.326     &    31.227  &         0.000        &        9.540    &       10.835     \\\\\n",
              "\\textbf{x}         &       1.9137  &        0.466     &     4.106  &         0.000        &        0.989    &        2.839     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lclc}\n",
              "\\textbf{Omnibus:}       &  3.658 & \\textbf{  Durbin-Watson:     } &    2.063  \\\\\n",
              "\\textbf{Prob(Omnibus):} &  0.161 & \\textbf{  Jarque-Bera (JB):  } &    3.568  \\\\\n",
              "\\textbf{Skew:}          &  0.458 & \\textbf{  Prob(JB):          } &    0.168  \\\\\n",
              "\\textbf{Kurtosis:}      &  2.863 & \\textbf{  Cond. No.          } &     2.60  \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{OLS Regression Results}\n",
              "\\end{center}\n",
              "\n",
              "Notes: \\newline\n",
              " [1] Standard Errors assume that the covariance matrix of the errors is correctly specified."
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                            OLS Regression Results                            \n",
              "==============================================================================\n",
              "Dep. Variable:                      y   R-squared:                       0.147\n",
              "Model:                            OLS   Adj. R-squared:                  0.138\n",
              "Method:                 Least Squares   F-statistic:                     16.86\n",
              "Date:                Thu, 30 Nov 2023   Prob (F-statistic):           8.34e-05\n",
              "Time:                        19:50:08   Log-Likelihood:                -225.46\n",
              "No. Observations:                 100   AIC:                             454.9\n",
              "Df Residuals:                      98   BIC:                             460.1\n",
              "Df Model:                           1                                         \n",
              "Covariance Type:            nonrobust                                         \n",
              "==============================================================================\n",
              "                 coef    std err          t      P>|t|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------\n",
              "Intercept     10.1873      0.326     31.227      0.000       9.540      10.835\n",
              "x              1.9137      0.466      4.106      0.000       0.989       2.839\n",
              "==============================================================================\n",
              "Omnibus:                        3.658   Durbin-Watson:                   2.063\n",
              "Prob(Omnibus):                  0.161   Jarque-Bera (JB):                3.568\n",
              "Skew:                           0.458   Prob(JB):                        0.168\n",
              "Kurtosis:                       2.863   Cond. No.                         2.60\n",
              "==============================================================================\n",
              "\n",
              "Notes:\n",
              "[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.\n",
              "\"\"\""
            ]
          },
          "execution_count": 27,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "ols('y ~ x', d).fit().summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 28,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "u3cHJeSZrobI",
        "outputId": "3beccf4a-80df-497d-b3fe-02b79d76daa3"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "<Axes: xlabel='x', ylabel='y'>"
            ]
          },
          "execution_count": 28,
          "metadata": {},
          "output_type": "execute_result"
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "sns.scatterplot(x='x', y='y', data=d)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-91yrBlvB5v1"
      },
      "source": [
        "## Logistic regression\n",
        "\n",
        "We will consider this dataset:\n",
        "\n",
        "https://www.kaggle.com/datasets/redwankarimsony/heart-disease-data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 29,
      "metadata": {
        "id": "E3ywdOQfB7u_"
      },
      "outputs": [],
      "source": [
        "data=pd.read_csv('heart_disease_uci.csv')"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 30,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 290
        },
        "id": "s5GIdAjrDG7u",
        "outputId": "a78e0578-ac6a-4a51-f319-bf4a50040482"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-712de7b9-93fc-4cb0-8227-25d08885ea84\" 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>id</th>\n",
              "      <th>age</th>\n",
              "      <th>sex</th>\n",
              "      <th>dataset</th>\n",
              "      <th>cp</th>\n",
              "      <th>trestbps</th>\n",
              "      <th>chol</th>\n",
              "      <th>fbs</th>\n",
              "      <th>restecg</th>\n",
              "      <th>thalch</th>\n",
              "      <th>exang</th>\n",
              "      <th>oldpeak</th>\n",
              "      <th>slope</th>\n",
              "      <th>ca</th>\n",
              "      <th>thal</th>\n",
              "      <th>num</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>63</td>\n",
              "      <td>Male</td>\n",
              "      <td>Cleveland</td>\n",
              "      <td>typical angina</td>\n",
              "      <td>145.0</td>\n",
              "      <td>233.0</td>\n",
              "      <td>True</td>\n",
              "      <td>lv hypertrophy</td>\n",
              "      <td>150.0</td>\n",
              "      <td>False</td>\n",
              "      <td>2.3</td>\n",
              "      <td>downsloping</td>\n",
              "      <td>0.0</td>\n",
              "      <td>fixed defect</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>67</td>\n",
              "      <td>Male</td>\n",
              "      <td>Cleveland</td>\n",
              "      <td>asymptomatic</td>\n",
              "      <td>160.0</td>\n",
              "      <td>286.0</td>\n",
              "      <td>False</td>\n",
              "      <td>lv hypertrophy</td>\n",
              "      <td>108.0</td>\n",
              "      <td>True</td>\n",
              "      <td>1.5</td>\n",
              "      <td>flat</td>\n",
              "      <td>3.0</td>\n",
              "      <td>normal</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>67</td>\n",
              "      <td>Male</td>\n",
              "      <td>Cleveland</td>\n",
              "      <td>asymptomatic</td>\n",
              "      <td>120.0</td>\n",
              "      <td>229.0</td>\n",
              "      <td>False</td>\n",
              "      <td>lv hypertrophy</td>\n",
              "      <td>129.0</td>\n",
              "      <td>True</td>\n",
              "      <td>2.6</td>\n",
              "      <td>flat</td>\n",
              "      <td>2.0</td>\n",
              "      <td>reversable defect</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>37</td>\n",
              "      <td>Male</td>\n",
              "      <td>Cleveland</td>\n",
              "      <td>non-anginal</td>\n",
              "      <td>130.0</td>\n",
              "      <td>250.0</td>\n",
              "      <td>False</td>\n",
              "      <td>normal</td>\n",
              "      <td>187.0</td>\n",
              "      <td>False</td>\n",
              "      <td>3.5</td>\n",
              "      <td>downsloping</td>\n",
              "      <td>0.0</td>\n",
              "      <td>normal</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>41</td>\n",
              "      <td>Female</td>\n",
              "      <td>Cleveland</td>\n",
              "      <td>atypical angina</td>\n",
              "      <td>130.0</td>\n",
              "      <td>204.0</td>\n",
              "      <td>False</td>\n",
              "      <td>lv hypertrophy</td>\n",
              "      <td>172.0</td>\n",
              "      <td>False</td>\n",
              "      <td>1.4</td>\n",
              "      <td>upsloping</td>\n",
              "      <td>0.0</td>\n",
              "      <td>normal</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-712de7b9-93fc-4cb0-8227-25d08885ea84')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-712de7b9-93fc-4cb0-8227-25d08885ea84 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-712de7b9-93fc-4cb0-8227-25d08885ea84');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-93ad365c-acd7-4b59-bc19-c61e09188503\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-93ad365c-acd7-4b59-bc19-c61e09188503')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-93ad365c-acd7-4b59-bc19-c61e09188503 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "   id  age     sex    dataset               cp  trestbps   chol    fbs  \\\n",
              "0   1   63    Male  Cleveland   typical angina     145.0  233.0   True   \n",
              "1   2   67    Male  Cleveland     asymptomatic     160.0  286.0  False   \n",
              "2   3   67    Male  Cleveland     asymptomatic     120.0  229.0  False   \n",
              "3   4   37    Male  Cleveland      non-anginal     130.0  250.0  False   \n",
              "4   5   41  Female  Cleveland  atypical angina     130.0  204.0  False   \n",
              "\n",
              "          restecg  thalch  exang  oldpeak        slope   ca  \\\n",
              "0  lv hypertrophy   150.0  False      2.3  downsloping  0.0   \n",
              "1  lv hypertrophy   108.0   True      1.5         flat  3.0   \n",
              "2  lv hypertrophy   129.0   True      2.6         flat  2.0   \n",
              "3          normal   187.0  False      3.5  downsloping  0.0   \n",
              "4  lv hypertrophy   172.0  False      1.4    upsloping  0.0   \n",
              "\n",
              "                thal  num  \n",
              "0       fixed defect    0  \n",
              "1             normal    2  \n",
              "2  reversable defect    1  \n",
              "3             normal    0  \n",
              "4             normal    0  "
            ]
          },
          "execution_count": 30,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "data.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 31,
      "metadata": {
        "id": "MSR7TUjnB-iZ"
      },
      "outputs": [],
      "source": [
        "data['attack'] = (data['num']>0).astype(int)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 32,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 316
        },
        "id": "YefWMiirCj2p",
        "outputId": "0476b198-8997-47b9-aab6-d5273e1db228"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "\n",
              "  <div id=\"df-1fb289a6-cd3a-4eec-add3-8773ebe819f6\" 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>id</th>\n",
              "      <th>age</th>\n",
              "      <th>trestbps</th>\n",
              "      <th>chol</th>\n",
              "      <th>thalch</th>\n",
              "      <th>oldpeak</th>\n",
              "      <th>ca</th>\n",
              "      <th>num</th>\n",
              "      <th>attack</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>count</th>\n",
              "      <td>920.000000</td>\n",
              "      <td>920.000000</td>\n",
              "      <td>861.000000</td>\n",
              "      <td>890.000000</td>\n",
              "      <td>865.000000</td>\n",
              "      <td>858.000000</td>\n",
              "      <td>309.000000</td>\n",
              "      <td>920.000000</td>\n",
              "      <td>920.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mean</th>\n",
              "      <td>460.500000</td>\n",
              "      <td>53.510870</td>\n",
              "      <td>132.132404</td>\n",
              "      <td>199.130337</td>\n",
              "      <td>137.545665</td>\n",
              "      <td>0.878788</td>\n",
              "      <td>0.676375</td>\n",
              "      <td>0.995652</td>\n",
              "      <td>0.553261</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>std</th>\n",
              "      <td>265.725422</td>\n",
              "      <td>9.424685</td>\n",
              "      <td>19.066070</td>\n",
              "      <td>110.780810</td>\n",
              "      <td>25.926276</td>\n",
              "      <td>1.091226</td>\n",
              "      <td>0.935653</td>\n",
              "      <td>1.142693</td>\n",
              "      <td>0.497426</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>min</th>\n",
              "      <td>1.000000</td>\n",
              "      <td>28.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>60.000000</td>\n",
              "      <td>-2.600000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25%</th>\n",
              "      <td>230.750000</td>\n",
              "      <td>47.000000</td>\n",
              "      <td>120.000000</td>\n",
              "      <td>175.000000</td>\n",
              "      <td>120.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50%</th>\n",
              "      <td>460.500000</td>\n",
              "      <td>54.000000</td>\n",
              "      <td>130.000000</td>\n",
              "      <td>223.000000</td>\n",
              "      <td>140.000000</td>\n",
              "      <td>0.500000</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>75%</th>\n",
              "      <td>690.250000</td>\n",
              "      <td>60.000000</td>\n",
              "      <td>140.000000</td>\n",
              "      <td>268.000000</td>\n",
              "      <td>157.000000</td>\n",
              "      <td>1.500000</td>\n",
              "      <td>1.000000</td>\n",
              "      <td>2.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>max</th>\n",
              "      <td>920.000000</td>\n",
              "      <td>77.000000</td>\n",
              "      <td>200.000000</td>\n",
              "      <td>603.000000</td>\n",
              "      <td>202.000000</td>\n",
              "      <td>6.200000</td>\n",
              "      <td>3.000000</td>\n",
              "      <td>4.000000</td>\n",
              "      <td>1.000000</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-1fb289a6-cd3a-4eec-add3-8773ebe819f6')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-1fb289a6-cd3a-4eec-add3-8773ebe819f6 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-1fb289a6-cd3a-4eec-add3-8773ebe819f6');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-f1f5513b-455d-4d30-b34d-76e1f3a4515c\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-f1f5513b-455d-4d30-b34d-76e1f3a4515c')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-f1f5513b-455d-4d30-b34d-76e1f3a4515c button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "text/plain": [
              "               id         age    trestbps        chol      thalch     oldpeak  \\\n",
              "count  920.000000  920.000000  861.000000  890.000000  865.000000  858.000000   \n",
              "mean   460.500000   53.510870  132.132404  199.130337  137.545665    0.878788   \n",
              "std    265.725422    9.424685   19.066070  110.780810   25.926276    1.091226   \n",
              "min      1.000000   28.000000    0.000000    0.000000   60.000000   -2.600000   \n",
              "25%    230.750000   47.000000  120.000000  175.000000  120.000000    0.000000   \n",
              "50%    460.500000   54.000000  130.000000  223.000000  140.000000    0.500000   \n",
              "75%    690.250000   60.000000  140.000000  268.000000  157.000000    1.500000   \n",
              "max    920.000000   77.000000  200.000000  603.000000  202.000000    6.200000   \n",
              "\n",
              "               ca         num      attack  \n",
              "count  309.000000  920.000000  920.000000  \n",
              "mean     0.676375    0.995652    0.553261  \n",
              "std      0.935653    1.142693    0.497426  \n",
              "min      0.000000    0.000000    0.000000  \n",
              "25%      0.000000    0.000000    0.000000  \n",
              "50%      0.000000    1.000000    1.000000  \n",
              "75%      1.000000    2.000000    1.000000  \n",
              "max      3.000000    4.000000    1.000000  "
            ]
          },
          "execution_count": 32,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "data.describe()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 38,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 296
        },
        "id": "qttx-RwUClNf",
        "outputId": "6c7e2a2b-51e0-447a-8a9d-583dea77dc76"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.639394\n",
            "         Iterations 5\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   920</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   918</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>     1</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.06992</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>19:51:22</td>     <th>  Log-Likelihood:    </th> <td> -588.24</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -632.47</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>5.220e-21</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "       <td></td>          <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>   <td>   -1.0578</td> <td>    0.164</td> <td>   -6.444</td> <td> 0.000</td> <td>   -1.380</td> <td>   -0.736</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex[T.Male]</th> <td>    1.5996</td> <td>    0.181</td> <td>    8.823</td> <td> 0.000</td> <td>    1.244</td> <td>    1.955</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}   &      attack      & \\textbf{  No. Observations:  } &      920    \\\\\n",
              "\\textbf{Model:}           &      Logit       & \\textbf{  Df Residuals:      } &      918    \\\\\n",
              "\\textbf{Method:}          &       MLE        & \\textbf{  Df Model:          } &        1    \\\\\n",
              "\\textbf{Date:}            & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &  0.06992    \\\\\n",
              "\\textbf{Time:}            &     19:51:22     & \\textbf{  Log-Likelihood:    } &   -588.24   \\\\\n",
              "\\textbf{converged:}       &       True       & \\textbf{  LL-Null:           } &   -632.47   \\\\\n",
              "\\textbf{Covariance Type:} &    nonrobust     & \\textbf{  LLR p-value:       } & 5.220e-21   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                     & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{Intercept}   &      -1.0578  &        0.164     &    -6.444  &         0.000        &       -1.380    &       -0.736     \\\\\n",
              "\\textbf{sex[T.Male]} &       1.5996  &        0.181     &     8.823  &         0.000        &        1.244    &        1.955     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  920\n",
              "Model:                          Logit   Df Residuals:                      918\n",
              "Method:                           MLE   Df Model:                            1\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                 0.06992\n",
              "Time:                        19:51:22   Log-Likelihood:                -588.24\n",
              "converged:                       True   LL-Null:                       -632.47\n",
              "Covariance Type:            nonrobust   LLR p-value:                 5.220e-21\n",
              "===============================================================================\n",
              "                  coef    std err          z      P>|z|      [0.025      0.975]\n",
              "-------------------------------------------------------------------------------\n",
              "Intercept      -1.0578      0.164     -6.444      0.000      -1.380      -0.736\n",
              "sex[T.Male]     1.5996      0.181      8.823      0.000       1.244       1.955\n",
              "===============================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 38,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "from statsmodels.formula.api import logit\n",
        "logit(\"attack ~ sex\", data).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DXY6t3YQyUev"
      },
      "source": [
        "The coefficient of `sex[T.Male]` is telling us that males have a risk of heart attack $e^{1.5996} \\approx 4.95$ times higher than females."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lUP9_IvBy-C5"
      },
      "source": [
        "To compute a multiple logistic regressor, let us first extend the dataset with dummy variables:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 49,
      "metadata": {
        "id": "ruZ0i5wczCxE"
      },
      "outputs": [],
      "source": [
        "data2 = pd.get_dummies(data.dropna(), columns=[\"sex\", \"dataset\", \"cp\", \"fbs\", \"restecg\", \"exang\", \"slope\", \"thal\"], drop_first=True)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "tUUde6aczdj4"
      },
      "source": [
        "We will use the non-forumla API:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 64,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 650
        },
        "id": "XZB2npcuzCRn",
        "outputId": "b3a2797e-f63b-441d-848d-dd0726aee86c"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.321016\n",
            "         Iterations 8\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   280</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    18</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5352</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:04:07</td>     <th>  Log-Likelihood:    </th> <td> -95.984</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>5.920e-37</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "              <td></td>                <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>age</th>                      <td>   -0.0137</td> <td>    0.025</td> <td>   -0.554</td> <td> 0.579</td> <td>   -0.062</td> <td>    0.035</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>                 <td>    0.0244</td> <td>    0.011</td> <td>    2.170</td> <td> 0.030</td> <td>    0.002</td> <td>    0.046</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>chol</th>                     <td>    0.0042</td> <td>    0.004</td> <td>    1.064</td> <td> 0.287</td> <td>   -0.004</td> <td>    0.012</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                   <td>   -0.0180</td> <td>    0.011</td> <td>   -1.625</td> <td> 0.104</td> <td>   -0.040</td> <td>    0.004</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                  <td>    0.3610</td> <td>    0.231</td> <td>    1.566</td> <td> 0.117</td> <td>   -0.091</td> <td>    0.813</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                       <td>    1.3099</td> <td>    0.280</td> <td>    4.682</td> <td> 0.000</td> <td>    0.762</td> <td>    1.858</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>                 <td>    1.5500</td> <td>    0.531</td> <td>    2.920</td> <td> 0.003</td> <td>    0.510</td> <td>    2.590</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>       <td>   -0.8454</td> <td>    0.561</td> <td>   -1.508</td> <td> 0.132</td> <td>   -1.944</td> <td>    0.253</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>           <td>   -1.8501</td> <td>    0.501</td> <td>   -3.690</td> <td> 0.000</td> <td>   -2.833</td> <td>   -0.867</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>        <td>   -2.1010</td> <td>    0.667</td> <td>   -3.151</td> <td> 0.002</td> <td>   -3.408</td> <td>   -0.794</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>fbs_True</th>                 <td>   -0.5952</td> <td>    0.609</td> <td>   -0.977</td> <td> 0.329</td> <td>   -1.789</td> <td>    0.599</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>           <td>   -0.4695</td> <td>    0.384</td> <td>   -1.222</td> <td> 0.222</td> <td>   -1.222</td> <td>    0.283</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_st-t abnormality</th> <td>    0.3128</td> <td>    2.439</td> <td>    0.128</td> <td> 0.898</td> <td>   -4.467</td> <td>    5.092</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>               <td>    0.7190</td> <td>    0.440</td> <td>    1.634</td> <td> 0.102</td> <td>   -0.143</td> <td>    1.581</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>               <td>    0.6474</td> <td>    0.851</td> <td>    0.761</td> <td> 0.447</td> <td>   -1.020</td> <td>    2.315</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_upsloping</th>          <td>   -0.5167</td> <td>    0.922</td> <td>   -0.560</td> <td> 0.575</td> <td>   -2.325</td> <td>    1.291</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_normal</th>              <td>    0.0313</td> <td>    0.790</td> <td>    0.040</td> <td> 0.968</td> <td>   -1.517</td> <td>    1.579</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th>   <td>    1.4329</td> <td>    0.775</td> <td>    1.850</td> <td> 0.064</td> <td>   -0.085</td> <td>    2.951</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>                <td>   -2.8907</td> <td>    2.847</td> <td>   -1.015</td> <td> 0.310</td> <td>   -8.472</td> <td>    2.690</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}            &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                    &      Logit       & \\textbf{  Df Residuals:      } &      280    \\\\\n",
              "\\textbf{Method:}                   &       MLE        & \\textbf{  Df Model:          } &       18    \\\\\n",
              "\\textbf{Date:}                     & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5352    \\\\\n",
              "\\textbf{Time:}                     &     20:04:07     & \\textbf{  Log-Likelihood:    } &   -95.984   \\\\\n",
              "\\textbf{converged:}                &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}          &    nonrobust     & \\textbf{  LLR p-value:       } & 5.920e-37   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                   & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{age}                       &      -0.0137  &        0.025     &    -0.554  &         0.579        &       -0.062    &        0.035     \\\\\n",
              "\\textbf{trestbps}                  &       0.0244  &        0.011     &     2.170  &         0.030        &        0.002    &        0.046     \\\\\n",
              "\\textbf{chol}                      &       0.0042  &        0.004     &     1.064  &         0.287        &       -0.004    &        0.012     \\\\\n",
              "\\textbf{thalch}                    &      -0.0180  &        0.011     &    -1.625  &         0.104        &       -0.040    &        0.004     \\\\\n",
              "\\textbf{oldpeak}                   &       0.3610  &        0.231     &     1.566  &         0.117        &       -0.091    &        0.813     \\\\\n",
              "\\textbf{ca}                        &       1.3099  &        0.280     &     4.682  &         0.000        &        0.762    &        1.858     \\\\\n",
              "\\textbf{sex\\_Male}                 &       1.5500  &        0.531     &     2.920  &         0.003        &        0.510    &        2.590     \\\\\n",
              "\\textbf{cp\\_atypical angina}       &      -0.8454  &        0.561     &    -1.508  &         0.132        &       -1.944    &        0.253     \\\\\n",
              "\\textbf{cp\\_non-anginal}           &      -1.8501  &        0.501     &    -3.690  &         0.000        &       -2.833    &       -0.867     \\\\\n",
              "\\textbf{cp\\_typical angina}        &      -2.1010  &        0.667     &    -3.151  &         0.002        &       -3.408    &       -0.794     \\\\\n",
              "\\textbf{fbs\\_True}                 &      -0.5952  &        0.609     &    -0.977  &         0.329        &       -1.789    &        0.599     \\\\\n",
              "\\textbf{restecg\\_normal}           &      -0.4695  &        0.384     &    -1.222  &         0.222        &       -1.222    &        0.283     \\\\\n",
              "\\textbf{restecg\\_st-t abnormality} &       0.3128  &        2.439     &     0.128  &         0.898        &       -4.467    &        5.092     \\\\\n",
              "\\textbf{exang\\_True}               &       0.7190  &        0.440     &     1.634  &         0.102        &       -0.143    &        1.581     \\\\\n",
              "\\textbf{slope\\_flat}               &       0.6474  &        0.851     &     0.761  &         0.447        &       -1.020    &        2.315     \\\\\n",
              "\\textbf{slope\\_upsloping}          &      -0.5167  &        0.922     &    -0.560  &         0.575        &       -2.325    &        1.291     \\\\\n",
              "\\textbf{thal\\_normal}              &       0.0313  &        0.790     &     0.040  &         0.968        &       -1.517    &        1.579     \\\\\n",
              "\\textbf{thal\\_reversable defect}   &       1.4329  &        0.775     &     1.850  &         0.064        &       -0.085    &        2.951     \\\\\n",
              "\\textbf{Intercept}                 &      -2.8907  &        2.847     &    -1.015  &         0.310        &       -8.472    &        2.690     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      280\n",
              "Method:                           MLE   Df Model:                           18\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5352\n",
              "Time:                        20:04:07   Log-Likelihood:                -95.984\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 5.920e-37\n",
              "============================================================================================\n",
              "                               coef    std err          z      P>|z|      [0.025      0.975]\n",
              "--------------------------------------------------------------------------------------------\n",
              "age                         -0.0137      0.025     -0.554      0.579      -0.062       0.035\n",
              "trestbps                     0.0244      0.011      2.170      0.030       0.002       0.046\n",
              "chol                         0.0042      0.004      1.064      0.287      -0.004       0.012\n",
              "thalch                      -0.0180      0.011     -1.625      0.104      -0.040       0.004\n",
              "oldpeak                      0.3610      0.231      1.566      0.117      -0.091       0.813\n",
              "ca                           1.3099      0.280      4.682      0.000       0.762       1.858\n",
              "sex_Male                     1.5500      0.531      2.920      0.003       0.510       2.590\n",
              "cp_atypical angina          -0.8454      0.561     -1.508      0.132      -1.944       0.253\n",
              "cp_non-anginal              -1.8501      0.501     -3.690      0.000      -2.833      -0.867\n",
              "cp_typical angina           -2.1010      0.667     -3.151      0.002      -3.408      -0.794\n",
              "fbs_True                    -0.5952      0.609     -0.977      0.329      -1.789       0.599\n",
              "restecg_normal              -0.4695      0.384     -1.222      0.222      -1.222       0.283\n",
              "restecg_st-t abnormality     0.3128      2.439      0.128      0.898      -4.467       5.092\n",
              "exang_True                   0.7190      0.440      1.634      0.102      -0.143       1.581\n",
              "slope_flat                   0.6474      0.851      0.761      0.447      -1.020       2.315\n",
              "slope_upsloping             -0.5167      0.922     -0.560      0.575      -2.325       1.291\n",
              "thal_normal                  0.0313      0.790      0.040      0.968      -1.517       1.579\n",
              "thal_reversable defect       1.4329      0.775      1.850      0.064      -0.085       2.951\n",
              "Intercept                   -2.8907      2.847     -1.015      0.310      -8.472       2.690\n",
              "============================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 64,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "from statsmodels.api import Logit\n",
        "data2['Intercept']=1 # we need to add the intercept manually when using this API\n",
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "M-UMuWhxz16B"
      },
      "source": [
        "Let us proceed removing the variables with largest p-values wih backward elimination. We'll drop `thal_normal`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 68,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 629
        },
        "id": "VN3E7lgWHVie",
        "outputId": "17bcc072-8ad7-44e5-c9d1-e0c2acb91246"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.321018\n",
            "         Iterations 8\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   281</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    17</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5352</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:05:21</td>     <th>  Log-Likelihood:    </th> <td> -95.984</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>1.611e-37</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "              <td></td>                <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>age</th>                      <td>   -0.0137</td> <td>    0.025</td> <td>   -0.555</td> <td> 0.579</td> <td>   -0.062</td> <td>    0.035</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>                 <td>    0.0244</td> <td>    0.011</td> <td>    2.171</td> <td> 0.030</td> <td>    0.002</td> <td>    0.046</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>chol</th>                     <td>    0.0042</td> <td>    0.004</td> <td>    1.067</td> <td> 0.286</td> <td>   -0.004</td> <td>    0.012</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                   <td>   -0.0180</td> <td>    0.011</td> <td>   -1.636</td> <td> 0.102</td> <td>   -0.040</td> <td>    0.004</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                  <td>    0.3604</td> <td>    0.230</td> <td>    1.567</td> <td> 0.117</td> <td>   -0.090</td> <td>    0.811</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                       <td>    1.3098</td> <td>    0.280</td> <td>    4.682</td> <td> 0.000</td> <td>    0.761</td> <td>    1.858</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>                 <td>    1.5445</td> <td>    0.512</td> <td>    3.016</td> <td> 0.003</td> <td>    0.541</td> <td>    2.548</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>       <td>   -0.8443</td> <td>    0.560</td> <td>   -1.508</td> <td> 0.132</td> <td>   -1.942</td> <td>    0.253</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>           <td>   -1.8479</td> <td>    0.498</td> <td>   -3.709</td> <td> 0.000</td> <td>   -2.824</td> <td>   -0.871</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>        <td>   -2.0968</td> <td>    0.658</td> <td>   -3.186</td> <td> 0.001</td> <td>   -3.387</td> <td>   -0.807</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>fbs_True</th>                 <td>   -0.5979</td> <td>    0.605</td> <td>   -0.988</td> <td> 0.323</td> <td>   -1.784</td> <td>    0.589</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>           <td>   -0.4707</td> <td>    0.383</td> <td>   -1.229</td> <td> 0.219</td> <td>   -1.221</td> <td>    0.280</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_st-t abnormality</th> <td>    0.3147</td> <td>    2.439</td> <td>    0.129</td> <td> 0.897</td> <td>   -4.465</td> <td>    5.094</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>               <td>    0.7186</td> <td>    0.440</td> <td>    1.634</td> <td> 0.102</td> <td>   -0.143</td> <td>    1.581</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>               <td>    0.6484</td> <td>    0.850</td> <td>    0.763</td> <td> 0.446</td> <td>   -1.018</td> <td>    2.314</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_upsloping</th>          <td>   -0.5133</td> <td>    0.919</td> <td>   -0.559</td> <td> 0.576</td> <td>   -2.314</td> <td>    1.287</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th>   <td>    1.4068</td> <td>    0.405</td> <td>    3.471</td> <td> 0.001</td> <td>    0.612</td> <td>    2.201</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>                <td>   -2.8676</td> <td>    2.786</td> <td>   -1.029</td> <td> 0.303</td> <td>   -8.329</td> <td>    2.593</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}            &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                    &      Logit       & \\textbf{  Df Residuals:      } &      281    \\\\\n",
              "\\textbf{Method:}                   &       MLE        & \\textbf{  Df Model:          } &       17    \\\\\n",
              "\\textbf{Date:}                     & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5352    \\\\\n",
              "\\textbf{Time:}                     &     20:05:21     & \\textbf{  Log-Likelihood:    } &   -95.984   \\\\\n",
              "\\textbf{converged:}                &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}          &    nonrobust     & \\textbf{  LLR p-value:       } & 1.611e-37   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                   & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{age}                       &      -0.0137  &        0.025     &    -0.555  &         0.579        &       -0.062    &        0.035     \\\\\n",
              "\\textbf{trestbps}                  &       0.0244  &        0.011     &     2.171  &         0.030        &        0.002    &        0.046     \\\\\n",
              "\\textbf{chol}                      &       0.0042  &        0.004     &     1.067  &         0.286        &       -0.004    &        0.012     \\\\\n",
              "\\textbf{thalch}                    &      -0.0180  &        0.011     &    -1.636  &         0.102        &       -0.040    &        0.004     \\\\\n",
              "\\textbf{oldpeak}                   &       0.3604  &        0.230     &     1.567  &         0.117        &       -0.090    &        0.811     \\\\\n",
              "\\textbf{ca}                        &       1.3098  &        0.280     &     4.682  &         0.000        &        0.761    &        1.858     \\\\\n",
              "\\textbf{sex\\_Male}                 &       1.5445  &        0.512     &     3.016  &         0.003        &        0.541    &        2.548     \\\\\n",
              "\\textbf{cp\\_atypical angina}       &      -0.8443  &        0.560     &    -1.508  &         0.132        &       -1.942    &        0.253     \\\\\n",
              "\\textbf{cp\\_non-anginal}           &      -1.8479  &        0.498     &    -3.709  &         0.000        &       -2.824    &       -0.871     \\\\\n",
              "\\textbf{cp\\_typical angina}        &      -2.0968  &        0.658     &    -3.186  &         0.001        &       -3.387    &       -0.807     \\\\\n",
              "\\textbf{fbs\\_True}                 &      -0.5979  &        0.605     &    -0.988  &         0.323        &       -1.784    &        0.589     \\\\\n",
              "\\textbf{restecg\\_normal}           &      -0.4707  &        0.383     &    -1.229  &         0.219        &       -1.221    &        0.280     \\\\\n",
              "\\textbf{restecg\\_st-t abnormality} &       0.3147  &        2.439     &     0.129  &         0.897        &       -4.465    &        5.094     \\\\\n",
              "\\textbf{exang\\_True}               &       0.7186  &        0.440     &     1.634  &         0.102        &       -0.143    &        1.581     \\\\\n",
              "\\textbf{slope\\_flat}               &       0.6484  &        0.850     &     0.763  &         0.446        &       -1.018    &        2.314     \\\\\n",
              "\\textbf{slope\\_upsloping}          &      -0.5133  &        0.919     &    -0.559  &         0.576        &       -2.314    &        1.287     \\\\\n",
              "\\textbf{thal\\_reversable defect}   &       1.4068  &        0.405     &     3.471  &         0.001        &        0.612    &        2.201     \\\\\n",
              "\\textbf{Intercept}                 &      -2.8676  &        2.786     &    -1.029  &         0.303        &       -8.329    &        2.593     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      281\n",
              "Method:                           MLE   Df Model:                           17\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5352\n",
              "Time:                        20:05:21   Log-Likelihood:                -95.984\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 1.611e-37\n",
              "============================================================================================\n",
              "                               coef    std err          z      P>|z|      [0.025      0.975]\n",
              "--------------------------------------------------------------------------------------------\n",
              "age                         -0.0137      0.025     -0.555      0.579      -0.062       0.035\n",
              "trestbps                     0.0244      0.011      2.171      0.030       0.002       0.046\n",
              "chol                         0.0042      0.004      1.067      0.286      -0.004       0.012\n",
              "thalch                      -0.0180      0.011     -1.636      0.102      -0.040       0.004\n",
              "oldpeak                      0.3604      0.230      1.567      0.117      -0.090       0.811\n",
              "ca                           1.3098      0.280      4.682      0.000       0.761       1.858\n",
              "sex_Male                     1.5445      0.512      3.016      0.003       0.541       2.548\n",
              "cp_atypical angina          -0.8443      0.560     -1.508      0.132      -1.942       0.253\n",
              "cp_non-anginal              -1.8479      0.498     -3.709      0.000      -2.824      -0.871\n",
              "cp_typical angina           -2.0968      0.658     -3.186      0.001      -3.387      -0.807\n",
              "fbs_True                    -0.5979      0.605     -0.988      0.323      -1.784       0.589\n",
              "restecg_normal              -0.4707      0.383     -1.229      0.219      -1.221       0.280\n",
              "restecg_st-t abnormality     0.3147      2.439      0.129      0.897      -4.465       5.094\n",
              "exang_True                   0.7186      0.440      1.634      0.102      -0.143       1.581\n",
              "slope_flat                   0.6484      0.850      0.763      0.446      -1.018       2.314\n",
              "slope_upsloping             -0.5133      0.919     -0.559      0.576      -2.314       1.287\n",
              "thal_reversable defect       1.4068      0.405      3.471      0.001       0.612       2.201\n",
              "Intercept                   -2.8676      2.786     -1.029      0.303      -8.329       2.593\n",
              "============================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 68,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','thal_normal'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MiPH0ciD0HdO"
      },
      "source": [
        "Let us remove `restecg_st-t abnormality`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 69,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 608
        },
        "id": "6rMm5xtg0EUK",
        "outputId": "08032de1-315f-41ec-9105-c51b1ace4547"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.321046\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   282</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    16</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5352</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:05:33</td>     <th>  Log-Likelihood:    </th> <td> -95.993</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>4.281e-38</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>age</th>                    <td>   -0.0137</td> <td>    0.025</td> <td>   -0.553</td> <td> 0.581</td> <td>   -0.062</td> <td>    0.035</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0245</td> <td>    0.011</td> <td>    2.187</td> <td> 0.029</td> <td>    0.003</td> <td>    0.046</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>chol</th>                   <td>    0.0042</td> <td>    0.004</td> <td>    1.061</td> <td> 0.289</td> <td>   -0.004</td> <td>    0.012</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0181</td> <td>    0.011</td> <td>   -1.650</td> <td> 0.099</td> <td>   -0.040</td> <td>    0.003</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.3633</td> <td>    0.229</td> <td>    1.588</td> <td> 0.112</td> <td>   -0.085</td> <td>    0.812</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.3091</td> <td>    0.280</td> <td>    4.680</td> <td> 0.000</td> <td>    0.761</td> <td>    1.857</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.5371</td> <td>    0.508</td> <td>    3.023</td> <td> 0.003</td> <td>    0.541</td> <td>    2.534</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -0.8440</td> <td>    0.560</td> <td>   -1.507</td> <td> 0.132</td> <td>   -1.942</td> <td>    0.254</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -1.8463</td> <td>    0.498</td> <td>   -3.705</td> <td> 0.000</td> <td>   -2.823</td> <td>   -0.870</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.0996</td> <td>    0.658</td> <td>   -3.192</td> <td> 0.001</td> <td>   -3.389</td> <td>   -0.810</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>fbs_True</th>               <td>   -0.6002</td> <td>    0.605</td> <td>   -0.991</td> <td> 0.321</td> <td>   -1.787</td> <td>    0.586</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>         <td>   -0.4752</td> <td>    0.381</td> <td>   -1.246</td> <td> 0.213</td> <td>   -1.223</td> <td>    0.272</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>             <td>    0.7188</td> <td>    0.440</td> <td>    1.634</td> <td> 0.102</td> <td>   -0.143</td> <td>    1.581</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    0.6525</td> <td>    0.850</td> <td>    0.768</td> <td> 0.443</td> <td>   -1.014</td> <td>    2.319</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_upsloping</th>        <td>   -0.5079</td> <td>    0.918</td> <td>   -0.553</td> <td> 0.580</td> <td>   -2.308</td> <td>    1.292</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.4075</td> <td>    0.405</td> <td>    3.474</td> <td> 0.001</td> <td>    0.614</td> <td>    2.202</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -2.8552</td> <td>    2.784</td> <td>   -1.025</td> <td> 0.305</td> <td>   -8.312</td> <td>    2.602</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      282    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       16    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5352    \\\\\n",
              "\\textbf{Time:}                   &     20:05:33     & \\textbf{  Log-Likelihood:    } &   -95.993   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 4.281e-38   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{age}                     &      -0.0137  &        0.025     &    -0.553  &         0.581        &       -0.062    &        0.035     \\\\\n",
              "\\textbf{trestbps}                &       0.0245  &        0.011     &     2.187  &         0.029        &        0.003    &        0.046     \\\\\n",
              "\\textbf{chol}                    &       0.0042  &        0.004     &     1.061  &         0.289        &       -0.004    &        0.012     \\\\\n",
              "\\textbf{thalch}                  &      -0.0181  &        0.011     &    -1.650  &         0.099        &       -0.040    &        0.003     \\\\\n",
              "\\textbf{oldpeak}                 &       0.3633  &        0.229     &     1.588  &         0.112        &       -0.085    &        0.812     \\\\\n",
              "\\textbf{ca}                      &       1.3091  &        0.280     &     4.680  &         0.000        &        0.761    &        1.857     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.5371  &        0.508     &     3.023  &         0.003        &        0.541    &        2.534     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -0.8440  &        0.560     &    -1.507  &         0.132        &       -1.942    &        0.254     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -1.8463  &        0.498     &    -3.705  &         0.000        &       -2.823    &       -0.870     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.0996  &        0.658     &    -3.192  &         0.001        &       -3.389    &       -0.810     \\\\\n",
              "\\textbf{fbs\\_True}               &      -0.6002  &        0.605     &    -0.991  &         0.321        &       -1.787    &        0.586     \\\\\n",
              "\\textbf{restecg\\_normal}         &      -0.4752  &        0.381     &    -1.246  &         0.213        &       -1.223    &        0.272     \\\\\n",
              "\\textbf{exang\\_True}             &       0.7188  &        0.440     &     1.634  &         0.102        &       -0.143    &        1.581     \\\\\n",
              "\\textbf{slope\\_flat}             &       0.6525  &        0.850     &     0.768  &         0.443        &       -1.014    &        2.319     \\\\\n",
              "\\textbf{slope\\_upsloping}        &      -0.5079  &        0.918     &    -0.553  &         0.580        &       -2.308    &        1.292     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.4075  &        0.405     &     3.474  &         0.001        &        0.614    &        2.202     \\\\\n",
              "\\textbf{Intercept}               &      -2.8552  &        2.784     &    -1.025  &         0.305        &       -8.312    &        2.602     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      282\n",
              "Method:                           MLE   Df Model:                           16\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5352\n",
              "Time:                        20:05:33   Log-Likelihood:                -95.993\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 4.281e-38\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "age                       -0.0137      0.025     -0.553      0.581      -0.062       0.035\n",
              "trestbps                   0.0245      0.011      2.187      0.029       0.003       0.046\n",
              "chol                       0.0042      0.004      1.061      0.289      -0.004       0.012\n",
              "thalch                    -0.0181      0.011     -1.650      0.099      -0.040       0.003\n",
              "oldpeak                    0.3633      0.229      1.588      0.112      -0.085       0.812\n",
              "ca                         1.3091      0.280      4.680      0.000       0.761       1.857\n",
              "sex_Male                   1.5371      0.508      3.023      0.003       0.541       2.534\n",
              "cp_atypical angina        -0.8440      0.560     -1.507      0.132      -1.942       0.254\n",
              "cp_non-anginal            -1.8463      0.498     -3.705      0.000      -2.823      -0.870\n",
              "cp_typical angina         -2.0996      0.658     -3.192      0.001      -3.389      -0.810\n",
              "fbs_True                  -0.6002      0.605     -0.991      0.321      -1.787       0.586\n",
              "restecg_normal            -0.4752      0.381     -1.246      0.213      -1.223       0.272\n",
              "exang_True                 0.7188      0.440      1.634      0.102      -0.143       1.581\n",
              "slope_flat                 0.6525      0.850      0.768      0.443      -1.014       2.319\n",
              "slope_upsloping           -0.5079      0.918     -0.553      0.580      -2.308       1.292\n",
              "thal_reversable defect     1.4075      0.405      3.474      0.001       0.614       2.202\n",
              "Intercept                 -2.8552      2.784     -1.025      0.305      -8.312       2.602\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 69,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "CKzZeaFW0LgJ"
      },
      "source": [
        "We now remove `age`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 70,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 588
        },
        "id": "VUDACSvXIFcB",
        "outputId": "85ed590e-292b-46d7-f0f8-839e877eb2e7"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.321559\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   283</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    15</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5344</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:05:46</td>     <th>  Log-Likelihood:    </th> <td> -96.146</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>1.261e-38</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0228</td> <td>    0.011</td> <td>    2.126</td> <td> 0.034</td> <td>    0.002</td> <td>    0.044</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>chol</th>                   <td>    0.0039</td> <td>    0.004</td> <td>    1.002</td> <td> 0.316</td> <td>   -0.004</td> <td>    0.011</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0159</td> <td>    0.010</td> <td>   -1.561</td> <td> 0.119</td> <td>   -0.036</td> <td>    0.004</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.3710</td> <td>    0.228</td> <td>    1.626</td> <td> 0.104</td> <td>   -0.076</td> <td>    0.818</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.2705</td> <td>    0.269</td> <td>    4.718</td> <td> 0.000</td> <td>    0.743</td> <td>    1.798</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.5667</td> <td>    0.504</td> <td>    3.106</td> <td> 0.002</td> <td>    0.578</td> <td>    2.555</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -0.8593</td> <td>    0.560</td> <td>   -1.536</td> <td> 0.125</td> <td>   -1.956</td> <td>    0.237</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -1.8614</td> <td>    0.498</td> <td>   -3.738</td> <td> 0.000</td> <td>   -2.837</td> <td>   -0.885</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.1148</td> <td>    0.656</td> <td>   -3.224</td> <td> 0.001</td> <td>   -3.400</td> <td>   -0.829</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>fbs_True</th>               <td>   -0.6053</td> <td>    0.602</td> <td>   -1.006</td> <td> 0.315</td> <td>   -1.785</td> <td>    0.574</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>         <td>   -0.4670</td> <td>    0.381</td> <td>   -1.227</td> <td> 0.220</td> <td>   -1.213</td> <td>    0.279</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>             <td>    0.7299</td> <td>    0.438</td> <td>    1.666</td> <td> 0.096</td> <td>   -0.129</td> <td>    1.589</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    0.6455</td> <td>    0.851</td> <td>    0.758</td> <td> 0.448</td> <td>   -1.023</td> <td>    2.314</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_upsloping</th>        <td>   -0.5038</td> <td>    0.920</td> <td>   -0.548</td> <td> 0.584</td> <td>   -2.307</td> <td>    1.299</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.3990</td> <td>    0.404</td> <td>    3.466</td> <td> 0.001</td> <td>    0.608</td> <td>    2.190</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -3.6527</td> <td>    2.381</td> <td>   -1.534</td> <td> 0.125</td> <td>   -8.319</td> <td>    1.013</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      283    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       15    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5344    \\\\\n",
              "\\textbf{Time:}                   &     20:05:46     & \\textbf{  Log-Likelihood:    } &   -96.146   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 1.261e-38   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0228  &        0.011     &     2.126  &         0.034        &        0.002    &        0.044     \\\\\n",
              "\\textbf{chol}                    &       0.0039  &        0.004     &     1.002  &         0.316        &       -0.004    &        0.011     \\\\\n",
              "\\textbf{thalch}                  &      -0.0159  &        0.010     &    -1.561  &         0.119        &       -0.036    &        0.004     \\\\\n",
              "\\textbf{oldpeak}                 &       0.3710  &        0.228     &     1.626  &         0.104        &       -0.076    &        0.818     \\\\\n",
              "\\textbf{ca}                      &       1.2705  &        0.269     &     4.718  &         0.000        &        0.743    &        1.798     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.5667  &        0.504     &     3.106  &         0.002        &        0.578    &        2.555     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -0.8593  &        0.560     &    -1.536  &         0.125        &       -1.956    &        0.237     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -1.8614  &        0.498     &    -3.738  &         0.000        &       -2.837    &       -0.885     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.1148  &        0.656     &    -3.224  &         0.001        &       -3.400    &       -0.829     \\\\\n",
              "\\textbf{fbs\\_True}               &      -0.6053  &        0.602     &    -1.006  &         0.315        &       -1.785    &        0.574     \\\\\n",
              "\\textbf{restecg\\_normal}         &      -0.4670  &        0.381     &    -1.227  &         0.220        &       -1.213    &        0.279     \\\\\n",
              "\\textbf{exang\\_True}             &       0.7299  &        0.438     &     1.666  &         0.096        &       -0.129    &        1.589     \\\\\n",
              "\\textbf{slope\\_flat}             &       0.6455  &        0.851     &     0.758  &         0.448        &       -1.023    &        2.314     \\\\\n",
              "\\textbf{slope\\_upsloping}        &      -0.5038  &        0.920     &    -0.548  &         0.584        &       -2.307    &        1.299     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.3990  &        0.404     &     3.466  &         0.001        &        0.608    &        2.190     \\\\\n",
              "\\textbf{Intercept}               &      -3.6527  &        2.381     &    -1.534  &         0.125        &       -8.319    &        1.013     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      283\n",
              "Method:                           MLE   Df Model:                           15\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5344\n",
              "Time:                        20:05:46   Log-Likelihood:                -96.146\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 1.261e-38\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0228      0.011      2.126      0.034       0.002       0.044\n",
              "chol                       0.0039      0.004      1.002      0.316      -0.004       0.011\n",
              "thalch                    -0.0159      0.010     -1.561      0.119      -0.036       0.004\n",
              "oldpeak                    0.3710      0.228      1.626      0.104      -0.076       0.818\n",
              "ca                         1.2705      0.269      4.718      0.000       0.743       1.798\n",
              "sex_Male                   1.5667      0.504      3.106      0.002       0.578       2.555\n",
              "cp_atypical angina        -0.8593      0.560     -1.536      0.125      -1.956       0.237\n",
              "cp_non-anginal            -1.8614      0.498     -3.738      0.000      -2.837      -0.885\n",
              "cp_typical angina         -2.1148      0.656     -3.224      0.001      -3.400      -0.829\n",
              "fbs_True                  -0.6053      0.602     -1.006      0.315      -1.785       0.574\n",
              "restecg_normal            -0.4670      0.381     -1.227      0.220      -1.213       0.279\n",
              "exang_True                 0.7299      0.438      1.666      0.096      -0.129       1.589\n",
              "slope_flat                 0.6455      0.851      0.758      0.448      -1.023       2.314\n",
              "slope_upsloping           -0.5038      0.920     -0.548      0.584      -2.307       1.299\n",
              "thal_reversable defect     1.3990      0.404      3.466      0.001       0.608       2.190\n",
              "Intercept                 -3.6527      2.381     -1.534      0.125      -8.319       1.013\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 70,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "M-rr8d4L0RMJ"
      },
      "source": [
        "It's now the turn of `slope_upsloping`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 71,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 567
        },
        "id": "8lGjAkVwC-6e",
        "outputId": "a77b0dcc-2b48-4c62-c9ed-593b6f207b9e"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.322049\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   284</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    14</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5337</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:05:54</td>     <th>  Log-Likelihood:    </th> <td> -96.293</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>3.566e-39</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0227</td> <td>    0.011</td> <td>    2.116</td> <td> 0.034</td> <td>    0.002</td> <td>    0.044</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>chol</th>                   <td>    0.0037</td> <td>    0.004</td> <td>    0.970</td> <td> 0.332</td> <td>   -0.004</td> <td>    0.011</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0164</td> <td>    0.010</td> <td>   -1.619</td> <td> 0.105</td> <td>   -0.036</td> <td>    0.003</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.4256</td> <td>    0.205</td> <td>    2.078</td> <td> 0.038</td> <td>    0.024</td> <td>    0.827</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.2458</td> <td>    0.264</td> <td>    4.715</td> <td> 0.000</td> <td>    0.728</td> <td>    1.764</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.5501</td> <td>    0.502</td> <td>    3.087</td> <td> 0.002</td> <td>    0.566</td> <td>    2.534</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -0.8492</td> <td>    0.558</td> <td>   -1.521</td> <td> 0.128</td> <td>   -1.943</td> <td>    0.245</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -1.8661</td> <td>    0.498</td> <td>   -3.744</td> <td> 0.000</td> <td>   -2.843</td> <td>   -0.889</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.1161</td> <td>    0.654</td> <td>   -3.235</td> <td> 0.001</td> <td>   -3.398</td> <td>   -0.834</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>fbs_True</th>               <td>   -0.5632</td> <td>    0.594</td> <td>   -0.947</td> <td> 0.343</td> <td>   -1.728</td> <td>    0.602</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>         <td>   -0.4814</td> <td>    0.379</td> <td>   -1.269</td> <td> 0.205</td> <td>   -1.225</td> <td>    0.262</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>             <td>    0.7304</td> <td>    0.438</td> <td>    1.669</td> <td> 0.095</td> <td>   -0.127</td> <td>    1.588</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    1.0485</td> <td>    0.429</td> <td>    2.442</td> <td> 0.015</td> <td>    0.207</td> <td>    1.890</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.4014</td> <td>    0.404</td> <td>    3.472</td> <td> 0.001</td> <td>    0.610</td> <td>    2.193</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -3.9750</td> <td>    2.302</td> <td>   -1.727</td> <td> 0.084</td> <td>   -8.487</td> <td>    0.537</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      284    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       14    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5337    \\\\\n",
              "\\textbf{Time:}                   &     20:05:54     & \\textbf{  Log-Likelihood:    } &   -96.293   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 3.566e-39   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0227  &        0.011     &     2.116  &         0.034        &        0.002    &        0.044     \\\\\n",
              "\\textbf{chol}                    &       0.0037  &        0.004     &     0.970  &         0.332        &       -0.004    &        0.011     \\\\\n",
              "\\textbf{thalch}                  &      -0.0164  &        0.010     &    -1.619  &         0.105        &       -0.036    &        0.003     \\\\\n",
              "\\textbf{oldpeak}                 &       0.4256  &        0.205     &     2.078  &         0.038        &        0.024    &        0.827     \\\\\n",
              "\\textbf{ca}                      &       1.2458  &        0.264     &     4.715  &         0.000        &        0.728    &        1.764     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.5501  &        0.502     &     3.087  &         0.002        &        0.566    &        2.534     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -0.8492  &        0.558     &    -1.521  &         0.128        &       -1.943    &        0.245     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -1.8661  &        0.498     &    -3.744  &         0.000        &       -2.843    &       -0.889     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.1161  &        0.654     &    -3.235  &         0.001        &       -3.398    &       -0.834     \\\\\n",
              "\\textbf{fbs\\_True}               &      -0.5632  &        0.594     &    -0.947  &         0.343        &       -1.728    &        0.602     \\\\\n",
              "\\textbf{restecg\\_normal}         &      -0.4814  &        0.379     &    -1.269  &         0.205        &       -1.225    &        0.262     \\\\\n",
              "\\textbf{exang\\_True}             &       0.7304  &        0.438     &     1.669  &         0.095        &       -0.127    &        1.588     \\\\\n",
              "\\textbf{slope\\_flat}             &       1.0485  &        0.429     &     2.442  &         0.015        &        0.207    &        1.890     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.4014  &        0.404     &     3.472  &         0.001        &        0.610    &        2.193     \\\\\n",
              "\\textbf{Intercept}               &      -3.9750  &        2.302     &    -1.727  &         0.084        &       -8.487    &        0.537     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      284\n",
              "Method:                           MLE   Df Model:                           14\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5337\n",
              "Time:                        20:05:54   Log-Likelihood:                -96.293\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 3.566e-39\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0227      0.011      2.116      0.034       0.002       0.044\n",
              "chol                       0.0037      0.004      0.970      0.332      -0.004       0.011\n",
              "thalch                    -0.0164      0.010     -1.619      0.105      -0.036       0.003\n",
              "oldpeak                    0.4256      0.205      2.078      0.038       0.024       0.827\n",
              "ca                         1.2458      0.264      4.715      0.000       0.728       1.764\n",
              "sex_Male                   1.5501      0.502      3.087      0.002       0.566       2.534\n",
              "cp_atypical angina        -0.8492      0.558     -1.521      0.128      -1.943       0.245\n",
              "cp_non-anginal            -1.8661      0.498     -3.744      0.000      -2.843      -0.889\n",
              "cp_typical angina         -2.1161      0.654     -3.235      0.001      -3.398      -0.834\n",
              "fbs_True                  -0.5632      0.594     -0.947      0.343      -1.728       0.602\n",
              "restecg_normal            -0.4814      0.379     -1.269      0.205      -1.225       0.262\n",
              "exang_True                 0.7304      0.438      1.669      0.095      -0.127       1.588\n",
              "slope_flat                 1.0485      0.429      2.442      0.015       0.207       1.890\n",
              "thal_reversable defect     1.4014      0.404      3.472      0.001       0.610       2.193\n",
              "Intercept                 -3.9750      2.302     -1.727      0.084      -8.487       0.537\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 71,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age','slope_upsloping'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "67r0B60L09NA"
      },
      "source": [
        "Let's remove `fbs_True`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 72,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 546
        },
        "id": "BRE_QZid0-Xl",
        "outputId": "73a020b3-4425-4590-dc7a-79c382a3aef9"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.323582\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   285</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    13</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5315</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:06:06</td>     <th>  Log-Likelihood:    </th> <td> -96.751</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>1.307e-39</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0210</td> <td>    0.011</td> <td>    1.998</td> <td> 0.046</td> <td>    0.000</td> <td>    0.042</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>chol</th>                   <td>    0.0036</td> <td>    0.004</td> <td>    0.936</td> <td> 0.349</td> <td>   -0.004</td> <td>    0.011</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0164</td> <td>    0.010</td> <td>   -1.628</td> <td> 0.103</td> <td>   -0.036</td> <td>    0.003</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.4380</td> <td>    0.205</td> <td>    2.135</td> <td> 0.033</td> <td>    0.036</td> <td>    0.840</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.1942</td> <td>    0.256</td> <td>    4.664</td> <td> 0.000</td> <td>    0.692</td> <td>    1.696</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.4928</td> <td>    0.498</td> <td>    3.000</td> <td> 0.003</td> <td>    0.518</td> <td>    2.468</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -0.8841</td> <td>    0.554</td> <td>   -1.596</td> <td> 0.110</td> <td>   -1.970</td> <td>    0.201</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -1.9746</td> <td>    0.489</td> <td>   -4.039</td> <td> 0.000</td> <td>   -2.933</td> <td>   -1.016</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.1802</td> <td>    0.653</td> <td>   -3.340</td> <td> 0.001</td> <td>   -3.460</td> <td>   -0.901</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>         <td>   -0.4735</td> <td>    0.379</td> <td>   -1.250</td> <td> 0.211</td> <td>   -1.216</td> <td>    0.269</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>             <td>    0.6861</td> <td>    0.435</td> <td>    1.578</td> <td> 0.115</td> <td>   -0.166</td> <td>    1.539</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    1.0228</td> <td>    0.428</td> <td>    2.391</td> <td> 0.017</td> <td>    0.184</td> <td>    1.861</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.4331</td> <td>    0.402</td> <td>    3.564</td> <td> 0.000</td> <td>    0.645</td> <td>    2.221</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -3.6750</td> <td>    2.257</td> <td>   -1.628</td> <td> 0.104</td> <td>   -8.099</td> <td>    0.749</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      285    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       13    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5315    \\\\\n",
              "\\textbf{Time:}                   &     20:06:06     & \\textbf{  Log-Likelihood:    } &   -96.751   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 1.307e-39   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0210  &        0.011     &     1.998  &         0.046        &        0.000    &        0.042     \\\\\n",
              "\\textbf{chol}                    &       0.0036  &        0.004     &     0.936  &         0.349        &       -0.004    &        0.011     \\\\\n",
              "\\textbf{thalch}                  &      -0.0164  &        0.010     &    -1.628  &         0.103        &       -0.036    &        0.003     \\\\\n",
              "\\textbf{oldpeak}                 &       0.4380  &        0.205     &     2.135  &         0.033        &        0.036    &        0.840     \\\\\n",
              "\\textbf{ca}                      &       1.1942  &        0.256     &     4.664  &         0.000        &        0.692    &        1.696     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.4928  &        0.498     &     3.000  &         0.003        &        0.518    &        2.468     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -0.8841  &        0.554     &    -1.596  &         0.110        &       -1.970    &        0.201     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -1.9746  &        0.489     &    -4.039  &         0.000        &       -2.933    &       -1.016     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.1802  &        0.653     &    -3.340  &         0.001        &       -3.460    &       -0.901     \\\\\n",
              "\\textbf{restecg\\_normal}         &      -0.4735  &        0.379     &    -1.250  &         0.211        &       -1.216    &        0.269     \\\\\n",
              "\\textbf{exang\\_True}             &       0.6861  &        0.435     &     1.578  &         0.115        &       -0.166    &        1.539     \\\\\n",
              "\\textbf{slope\\_flat}             &       1.0228  &        0.428     &     2.391  &         0.017        &        0.184    &        1.861     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.4331  &        0.402     &     3.564  &         0.000        &        0.645    &        2.221     \\\\\n",
              "\\textbf{Intercept}               &      -3.6750  &        2.257     &    -1.628  &         0.104        &       -8.099    &        0.749     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      285\n",
              "Method:                           MLE   Df Model:                           13\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5315\n",
              "Time:                        20:06:06   Log-Likelihood:                -96.751\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 1.307e-39\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0210      0.011      1.998      0.046       0.000       0.042\n",
              "chol                       0.0036      0.004      0.936      0.349      -0.004       0.011\n",
              "thalch                    -0.0164      0.010     -1.628      0.103      -0.036       0.003\n",
              "oldpeak                    0.4380      0.205      2.135      0.033       0.036       0.840\n",
              "ca                         1.1942      0.256      4.664      0.000       0.692       1.696\n",
              "sex_Male                   1.4928      0.498      3.000      0.003       0.518       2.468\n",
              "cp_atypical angina        -0.8841      0.554     -1.596      0.110      -1.970       0.201\n",
              "cp_non-anginal            -1.9746      0.489     -4.039      0.000      -2.933      -1.016\n",
              "cp_typical angina         -2.1802      0.653     -3.340      0.001      -3.460      -0.901\n",
              "restecg_normal            -0.4735      0.379     -1.250      0.211      -1.216       0.269\n",
              "exang_True                 0.6861      0.435      1.578      0.115      -0.166       1.539\n",
              "slope_flat                 1.0228      0.428      2.391      0.017       0.184       1.861\n",
              "thal_reversable defect     1.4331      0.402      3.564      0.000       0.645       2.221\n",
              "Intercept                 -3.6750      2.257     -1.628      0.104      -8.099       0.749\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 72,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age','slope_upsloping','fbs_True'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WEVCN0Uq1Bqv"
      },
      "source": [
        "Let's remove `chol`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 73,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 525
        },
        "id": "4K8_SBSj1GnH",
        "outputId": "e2bf0c0f-511f-42fa-b33e-a74b11795974"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.325012\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   286</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    12</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5294</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:06:19</td>     <th>  Log-Likelihood:    </th> <td> -97.179</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>4.481e-40</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0215</td> <td>    0.010</td> <td>    2.045</td> <td> 0.041</td> <td>    0.001</td> <td>    0.042</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0152</td> <td>    0.010</td> <td>   -1.538</td> <td> 0.124</td> <td>   -0.035</td> <td>    0.004</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.4460</td> <td>    0.205</td> <td>    2.174</td> <td> 0.030</td> <td>    0.044</td> <td>    0.848</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.1928</td> <td>    0.255</td> <td>    4.686</td> <td> 0.000</td> <td>    0.694</td> <td>    1.692</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.3485</td> <td>    0.467</td> <td>    2.889</td> <td> 0.004</td> <td>    0.434</td> <td>    2.263</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -0.8627</td> <td>    0.551</td> <td>   -1.565</td> <td> 0.118</td> <td>   -1.943</td> <td>    0.218</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -1.9666</td> <td>    0.488</td> <td>   -4.026</td> <td> 0.000</td> <td>   -2.924</td> <td>   -1.009</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.1905</td> <td>    0.651</td> <td>   -3.365</td> <td> 0.001</td> <td>   -3.466</td> <td>   -0.915</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>restecg_normal</th>         <td>   -0.5380</td> <td>    0.371</td> <td>   -1.448</td> <td> 0.147</td> <td>   -1.266</td> <td>    0.190</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>             <td>    0.6821</td> <td>    0.432</td> <td>    1.579</td> <td> 0.114</td> <td>   -0.164</td> <td>    1.529</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    1.0435</td> <td>    0.427</td> <td>    2.446</td> <td> 0.014</td> <td>    0.207</td> <td>    1.880</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.4706</td> <td>    0.402</td> <td>    3.659</td> <td> 0.000</td> <td>    0.683</td> <td>    2.258</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -2.9396</td> <td>    2.092</td> <td>   -1.405</td> <td> 0.160</td> <td>   -7.039</td> <td>    1.160</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      286    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       12    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5294    \\\\\n",
              "\\textbf{Time:}                   &     20:06:19     & \\textbf{  Log-Likelihood:    } &   -97.179   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 4.481e-40   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0215  &        0.010     &     2.045  &         0.041        &        0.001    &        0.042     \\\\\n",
              "\\textbf{thalch}                  &      -0.0152  &        0.010     &    -1.538  &         0.124        &       -0.035    &        0.004     \\\\\n",
              "\\textbf{oldpeak}                 &       0.4460  &        0.205     &     2.174  &         0.030        &        0.044    &        0.848     \\\\\n",
              "\\textbf{ca}                      &       1.1928  &        0.255     &     4.686  &         0.000        &        0.694    &        1.692     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.3485  &        0.467     &     2.889  &         0.004        &        0.434    &        2.263     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -0.8627  &        0.551     &    -1.565  &         0.118        &       -1.943    &        0.218     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -1.9666  &        0.488     &    -4.026  &         0.000        &       -2.924    &       -1.009     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.1905  &        0.651     &    -3.365  &         0.001        &       -3.466    &       -0.915     \\\\\n",
              "\\textbf{restecg\\_normal}         &      -0.5380  &        0.371     &    -1.448  &         0.147        &       -1.266    &        0.190     \\\\\n",
              "\\textbf{exang\\_True}             &       0.6821  &        0.432     &     1.579  &         0.114        &       -0.164    &        1.529     \\\\\n",
              "\\textbf{slope\\_flat}             &       1.0435  &        0.427     &     2.446  &         0.014        &        0.207    &        1.880     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.4706  &        0.402     &     3.659  &         0.000        &        0.683    &        2.258     \\\\\n",
              "\\textbf{Intercept}               &      -2.9396  &        2.092     &    -1.405  &         0.160        &       -7.039    &        1.160     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      286\n",
              "Method:                           MLE   Df Model:                           12\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5294\n",
              "Time:                        20:06:19   Log-Likelihood:                -97.179\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 4.481e-40\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0215      0.010      2.045      0.041       0.001       0.042\n",
              "thalch                    -0.0152      0.010     -1.538      0.124      -0.035       0.004\n",
              "oldpeak                    0.4460      0.205      2.174      0.030       0.044       0.848\n",
              "ca                         1.1928      0.255      4.686      0.000       0.694       1.692\n",
              "sex_Male                   1.3485      0.467      2.889      0.004       0.434       2.263\n",
              "cp_atypical angina        -0.8627      0.551     -1.565      0.118      -1.943       0.218\n",
              "cp_non-anginal            -1.9666      0.488     -4.026      0.000      -2.924      -1.009\n",
              "cp_typical angina         -2.1905      0.651     -3.365      0.001      -3.466      -0.915\n",
              "restecg_normal            -0.5380      0.371     -1.448      0.147      -1.266       0.190\n",
              "exang_True                 0.6821      0.432      1.579      0.114      -0.164       1.529\n",
              "slope_flat                 1.0435      0.427      2.446      0.014       0.207       1.880\n",
              "thal_reversable defect     1.4706      0.402      3.659      0.000       0.683       2.258\n",
              "Intercept                 -2.9396      2.092     -1.405      0.160      -7.039       1.160\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 73,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age','slope_upsloping','fbs_True','chol'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "q1zWDDy21vrP"
      },
      "source": [
        "Let's remove `restecg_normal`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 74,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 504
        },
        "id": "2xb9tKVq1GI3",
        "outputId": "2da85bbb-318e-4784-b6a3-e8ad80b0013b"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.328559\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   287</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    11</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5243</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:06:47</td>     <th>  Log-Likelihood:    </th> <td> -98.239</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>2.704e-40</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0225</td> <td>    0.010</td> <td>    2.196</td> <td> 0.028</td> <td>    0.002</td> <td>    0.043</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0152</td> <td>    0.010</td> <td>   -1.530</td> <td> 0.126</td> <td>   -0.035</td> <td>    0.004</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.4357</td> <td>    0.200</td> <td>    2.183</td> <td> 0.029</td> <td>    0.045</td> <td>    0.827</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.2152</td> <td>    0.253</td> <td>    4.806</td> <td> 0.000</td> <td>    0.720</td> <td>    1.711</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.3796</td> <td>    0.466</td> <td>    2.961</td> <td> 0.003</td> <td>    0.466</td> <td>    2.293</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -0.8622</td> <td>    0.550</td> <td>   -1.567</td> <td> 0.117</td> <td>   -1.940</td> <td>    0.216</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -1.9589</td> <td>    0.485</td> <td>   -4.038</td> <td> 0.000</td> <td>   -2.910</td> <td>   -1.008</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.1394</td> <td>    0.646</td> <td>   -3.313</td> <td> 0.001</td> <td>   -3.405</td> <td>   -0.874</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>exang_True</th>             <td>    0.6737</td> <td>    0.432</td> <td>    1.560</td> <td> 0.119</td> <td>   -0.173</td> <td>    1.520</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    1.1014</td> <td>    0.422</td> <td>    2.608</td> <td> 0.009</td> <td>    0.274</td> <td>    1.929</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.4078</td> <td>    0.395</td> <td>    3.567</td> <td> 0.000</td> <td>    0.634</td> <td>    2.181</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -3.3894</td> <td>    2.056</td> <td>   -1.648</td> <td> 0.099</td> <td>   -7.420</td> <td>    0.641</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      287    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       11    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5243    \\\\\n",
              "\\textbf{Time:}                   &     20:06:47     & \\textbf{  Log-Likelihood:    } &   -98.239   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 2.704e-40   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0225  &        0.010     &     2.196  &         0.028        &        0.002    &        0.043     \\\\\n",
              "\\textbf{thalch}                  &      -0.0152  &        0.010     &    -1.530  &         0.126        &       -0.035    &        0.004     \\\\\n",
              "\\textbf{oldpeak}                 &       0.4357  &        0.200     &     2.183  &         0.029        &        0.045    &        0.827     \\\\\n",
              "\\textbf{ca}                      &       1.2152  &        0.253     &     4.806  &         0.000        &        0.720    &        1.711     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.3796  &        0.466     &     2.961  &         0.003        &        0.466    &        2.293     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -0.8622  &        0.550     &    -1.567  &         0.117        &       -1.940    &        0.216     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -1.9589  &        0.485     &    -4.038  &         0.000        &       -2.910    &       -1.008     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.1394  &        0.646     &    -3.313  &         0.001        &       -3.405    &       -0.874     \\\\\n",
              "\\textbf{exang\\_True}             &       0.6737  &        0.432     &     1.560  &         0.119        &       -0.173    &        1.520     \\\\\n",
              "\\textbf{slope\\_flat}             &       1.1014  &        0.422     &     2.608  &         0.009        &        0.274    &        1.929     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.4078  &        0.395     &     3.567  &         0.000        &        0.634    &        2.181     \\\\\n",
              "\\textbf{Intercept}               &      -3.3894  &        2.056     &    -1.648  &         0.099        &       -7.420    &        0.641     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      287\n",
              "Method:                           MLE   Df Model:                           11\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5243\n",
              "Time:                        20:06:47   Log-Likelihood:                -98.239\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 2.704e-40\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0225      0.010      2.196      0.028       0.002       0.043\n",
              "thalch                    -0.0152      0.010     -1.530      0.126      -0.035       0.004\n",
              "oldpeak                    0.4357      0.200      2.183      0.029       0.045       0.827\n",
              "ca                         1.2152      0.253      4.806      0.000       0.720       1.711\n",
              "sex_Male                   1.3796      0.466      2.961      0.003       0.466       2.293\n",
              "cp_atypical angina        -0.8622      0.550     -1.567      0.117      -1.940       0.216\n",
              "cp_non-anginal            -1.9589      0.485     -4.038      0.000      -2.910      -1.008\n",
              "cp_typical angina         -2.1394      0.646     -3.313      0.001      -3.405      -0.874\n",
              "exang_True                 0.6737      0.432      1.560      0.119      -0.173       1.520\n",
              "slope_flat                 1.1014      0.422      2.608      0.009       0.274       1.929\n",
              "thal_reversable defect     1.4078      0.395      3.567      0.000       0.634       2.181\n",
              "Intercept                 -3.3894      2.056     -1.648      0.099      -7.420       0.641\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 74,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age','slope_upsloping','fbs_True','chol','restecg_normal'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3NA20ZQ211VJ"
      },
      "source": [
        "Let us now remove `exang_True`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 75,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 484
        },
        "id": "kspLFfheJcNl",
        "outputId": "aff46f4b-a44d-44a0-e0d9-01400cfb19fe"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.332571\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   288</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>    10</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5185</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:07:11</td>     <th>  Log-Likelihood:    </th> <td> -99.439</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>1.791e-40</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0233</td> <td>    0.010</td> <td>    2.278</td> <td> 0.023</td> <td>    0.003</td> <td>    0.043</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thalch</th>                 <td>   -0.0180</td> <td>    0.010</td> <td>   -1.845</td> <td> 0.065</td> <td>   -0.037</td> <td>    0.001</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.4647</td> <td>    0.197</td> <td>    2.354</td> <td> 0.019</td> <td>    0.078</td> <td>    0.852</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.2033</td> <td>    0.252</td> <td>    4.781</td> <td> 0.000</td> <td>    0.710</td> <td>    1.697</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.3780</td> <td>    0.458</td> <td>    3.006</td> <td> 0.003</td> <td>    0.480</td> <td>    2.276</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -1.0592</td> <td>    0.537</td> <td>   -1.973</td> <td> 0.048</td> <td>   -2.111</td> <td>   -0.007</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -2.1451</td> <td>    0.472</td> <td>   -4.549</td> <td> 0.000</td> <td>   -3.069</td> <td>   -1.221</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.3297</td> <td>    0.642</td> <td>   -3.626</td> <td> 0.000</td> <td>   -3.589</td> <td>   -1.071</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    1.1436</td> <td>    0.420</td> <td>    2.724</td> <td> 0.006</td> <td>    0.321</td> <td>    1.966</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.4692</td> <td>    0.391</td> <td>    3.758</td> <td> 0.000</td> <td>    0.703</td> <td>    2.235</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -2.8221</td> <td>    2.011</td> <td>   -1.404</td> <td> 0.160</td> <td>   -6.763</td> <td>    1.119</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      288    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &       10    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5185    \\\\\n",
              "\\textbf{Time:}                   &     20:07:11     & \\textbf{  Log-Likelihood:    } &   -99.439   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 1.791e-40   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0233  &        0.010     &     2.278  &         0.023        &        0.003    &        0.043     \\\\\n",
              "\\textbf{thalch}                  &      -0.0180  &        0.010     &    -1.845  &         0.065        &       -0.037    &        0.001     \\\\\n",
              "\\textbf{oldpeak}                 &       0.4647  &        0.197     &     2.354  &         0.019        &        0.078    &        0.852     \\\\\n",
              "\\textbf{ca}                      &       1.2033  &        0.252     &     4.781  &         0.000        &        0.710    &        1.697     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.3780  &        0.458     &     3.006  &         0.003        &        0.480    &        2.276     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -1.0592  &        0.537     &    -1.973  &         0.048        &       -2.111    &       -0.007     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -2.1451  &        0.472     &    -4.549  &         0.000        &       -3.069    &       -1.221     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.3297  &        0.642     &    -3.626  &         0.000        &       -3.589    &       -1.071     \\\\\n",
              "\\textbf{slope\\_flat}             &       1.1436  &        0.420     &     2.724  &         0.006        &        0.321    &        1.966     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.4692  &        0.391     &     3.758  &         0.000        &        0.703    &        2.235     \\\\\n",
              "\\textbf{Intercept}               &      -2.8221  &        2.011     &    -1.404  &         0.160        &       -6.763    &        1.119     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      288\n",
              "Method:                           MLE   Df Model:                           10\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5185\n",
              "Time:                        20:07:11   Log-Likelihood:                -99.439\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 1.791e-40\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0233      0.010      2.278      0.023       0.003       0.043\n",
              "thalch                    -0.0180      0.010     -1.845      0.065      -0.037       0.001\n",
              "oldpeak                    0.4647      0.197      2.354      0.019       0.078       0.852\n",
              "ca                         1.2033      0.252      4.781      0.000       0.710       1.697\n",
              "sex_Male                   1.3780      0.458      3.006      0.003       0.480       2.276\n",
              "cp_atypical angina        -1.0592      0.537     -1.973      0.048      -2.111      -0.007\n",
              "cp_non-anginal            -2.1451      0.472     -4.549      0.000      -3.069      -1.221\n",
              "cp_typical angina         -2.3297      0.642     -3.626      0.000      -3.589      -1.071\n",
              "slope_flat                 1.1436      0.420      2.724      0.006       0.321       1.966\n",
              "thal_reversable defect     1.4692      0.391      3.758      0.000       0.703       2.235\n",
              "Intercept                 -2.8221      2.011     -1.404      0.160      -6.763       1.119\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 75,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age','slope_upsloping','fbs_True','chol','restecg_normal','exang_True'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "lC_doPHJ17Kt"
      },
      "source": [
        "Let us now remove `thalch`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 76,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 463
        },
        "id": "LzepPi8-2Acb",
        "outputId": "cfe09daa-383f-4a99-b1ac-0e187f721f54"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Optimization terminated successfully.\n",
            "         Current function value: 0.338536\n",
            "         Iterations 7\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<table class=\"simpletable\">\n",
              "<caption>Logit Regression Results</caption>\n",
              "<tr>\n",
              "  <th>Dep. Variable:</th>        <td>attack</td>      <th>  No. Observations:  </th>  <td>   299</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Model:</th>                 <td>Logit</td>      <th>  Df Residuals:      </th>  <td>   289</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Method:</th>                 <td>MLE</td>       <th>  Df Model:          </th>  <td>     9</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Date:</th>            <td>Thu, 30 Nov 2023</td> <th>  Pseudo R-squ.:     </th>  <td>0.5099</td>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Time:</th>                <td>20:07:42</td>     <th>  Log-Likelihood:    </th> <td> -101.22</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>converged:</th>             <td>True</td>       <th>  LL-Null:           </th> <td> -206.51</td> \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Covariance Type:</th>     <td>nonrobust</td>    <th>  LLR p-value:       </th> <td>1.996e-40</td>\n",
              "</tr>\n",
              "</table>\n",
              "<table class=\"simpletable\">\n",
              "<tr>\n",
              "             <td></td>               <th>coef</th>     <th>std err</th>      <th>z</th>      <th>P>|z|</th>  <th>[0.025</th>    <th>0.975]</th>  \n",
              "</tr>\n",
              "<tr>\n",
              "  <th>trestbps</th>               <td>    0.0220</td> <td>    0.010</td> <td>    2.145</td> <td> 0.032</td> <td>    0.002</td> <td>    0.042</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>oldpeak</th>                <td>    0.5145</td> <td>    0.194</td> <td>    2.659</td> <td> 0.008</td> <td>    0.135</td> <td>    0.894</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>ca</th>                     <td>    1.2539</td> <td>    0.252</td> <td>    4.985</td> <td> 0.000</td> <td>    0.761</td> <td>    1.747</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>sex_Male</th>               <td>    1.3382</td> <td>    0.455</td> <td>    2.942</td> <td> 0.003</td> <td>    0.447</td> <td>    2.230</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_atypical angina</th>     <td>   -1.2521</td> <td>    0.521</td> <td>   -2.403</td> <td> 0.016</td> <td>   -2.274</td> <td>   -0.231</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_non-anginal</th>         <td>   -2.3023</td> <td>    0.464</td> <td>   -4.966</td> <td> 0.000</td> <td>   -3.211</td> <td>   -1.394</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>cp_typical angina</th>      <td>   -2.5791</td> <td>    0.644</td> <td>   -4.004</td> <td> 0.000</td> <td>   -3.842</td> <td>   -1.317</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>slope_flat</th>             <td>    1.3792</td> <td>    0.397</td> <td>    3.470</td> <td> 0.001</td> <td>    0.600</td> <td>    2.158</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>thal_reversable defect</th> <td>    1.5143</td> <td>    0.388</td> <td>    3.907</td> <td> 0.000</td> <td>    0.755</td> <td>    2.274</td>\n",
              "</tr>\n",
              "<tr>\n",
              "  <th>Intercept</th>              <td>   -5.4495</td> <td>    1.485</td> <td>   -3.669</td> <td> 0.000</td> <td>   -8.361</td> <td>   -2.538</td>\n",
              "</tr>\n",
              "</table>"
            ],
            "text/latex": [
              "\\begin{center}\n",
              "\\begin{tabular}{lclc}\n",
              "\\toprule\n",
              "\\textbf{Dep. Variable:}          &      attack      & \\textbf{  No. Observations:  } &      299    \\\\\n",
              "\\textbf{Model:}                  &      Logit       & \\textbf{  Df Residuals:      } &      289    \\\\\n",
              "\\textbf{Method:}                 &       MLE        & \\textbf{  Df Model:          } &        9    \\\\\n",
              "\\textbf{Date:}                   & Thu, 30 Nov 2023 & \\textbf{  Pseudo R-squ.:     } &   0.5099    \\\\\n",
              "\\textbf{Time:}                   &     20:07:42     & \\textbf{  Log-Likelihood:    } &   -101.22   \\\\\n",
              "\\textbf{converged:}              &       True       & \\textbf{  LL-Null:           } &   -206.51   \\\\\n",
              "\\textbf{Covariance Type:}        &    nonrobust     & \\textbf{  LLR p-value:       } & 1.996e-40   \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "\\begin{tabular}{lcccccc}\n",
              "                                 & \\textbf{coef} & \\textbf{std err} & \\textbf{z} & \\textbf{P$> |$z$|$} & \\textbf{[0.025} & \\textbf{0.975]}  \\\\\n",
              "\\midrule\n",
              "\\textbf{trestbps}                &       0.0220  &        0.010     &     2.145  &         0.032        &        0.002    &        0.042     \\\\\n",
              "\\textbf{oldpeak}                 &       0.5145  &        0.194     &     2.659  &         0.008        &        0.135    &        0.894     \\\\\n",
              "\\textbf{ca}                      &       1.2539  &        0.252     &     4.985  &         0.000        &        0.761    &        1.747     \\\\\n",
              "\\textbf{sex\\_Male}               &       1.3382  &        0.455     &     2.942  &         0.003        &        0.447    &        2.230     \\\\\n",
              "\\textbf{cp\\_atypical angina}     &      -1.2521  &        0.521     &    -2.403  &         0.016        &       -2.274    &       -0.231     \\\\\n",
              "\\textbf{cp\\_non-anginal}         &      -2.3023  &        0.464     &    -4.966  &         0.000        &       -3.211    &       -1.394     \\\\\n",
              "\\textbf{cp\\_typical angina}      &      -2.5791  &        0.644     &    -4.004  &         0.000        &       -3.842    &       -1.317     \\\\\n",
              "\\textbf{slope\\_flat}             &       1.3792  &        0.397     &     3.470  &         0.001        &        0.600    &        2.158     \\\\\n",
              "\\textbf{thal\\_reversable defect} &       1.5143  &        0.388     &     3.907  &         0.000        &        0.755    &        2.274     \\\\\n",
              "\\textbf{Intercept}               &      -5.4495  &        1.485     &    -3.669  &         0.000        &       -8.361    &       -2.538     \\\\\n",
              "\\bottomrule\n",
              "\\end{tabular}\n",
              "%\\caption{Logit Regression Results}\n",
              "\\end{center}"
            ],
            "text/plain": [
              "<class 'statsmodels.iolib.summary.Summary'>\n",
              "\"\"\"\n",
              "                           Logit Regression Results                           \n",
              "==============================================================================\n",
              "Dep. Variable:                 attack   No. Observations:                  299\n",
              "Model:                          Logit   Df Residuals:                      289\n",
              "Method:                           MLE   Df Model:                            9\n",
              "Date:                Thu, 30 Nov 2023   Pseudo R-squ.:                  0.5099\n",
              "Time:                        20:07:42   Log-Likelihood:                -101.22\n",
              "converged:                       True   LL-Null:                       -206.51\n",
              "Covariance Type:            nonrobust   LLR p-value:                 1.996e-40\n",
              "==========================================================================================\n",
              "                             coef    std err          z      P>|z|      [0.025      0.975]\n",
              "------------------------------------------------------------------------------------------\n",
              "trestbps                   0.0220      0.010      2.145      0.032       0.002       0.042\n",
              "oldpeak                    0.5145      0.194      2.659      0.008       0.135       0.894\n",
              "ca                         1.2539      0.252      4.985      0.000       0.761       1.747\n",
              "sex_Male                   1.3382      0.455      2.942      0.003       0.447       2.230\n",
              "cp_atypical angina        -1.2521      0.521     -2.403      0.016      -2.274      -0.231\n",
              "cp_non-anginal            -2.3023      0.464     -4.966      0.000      -3.211      -1.394\n",
              "cp_typical angina         -2.5791      0.644     -4.004      0.000      -3.842      -1.317\n",
              "slope_flat                 1.3792      0.397      3.470      0.001       0.600       2.158\n",
              "thal_reversable defect     1.5143      0.388      3.907      0.000       0.755       2.274\n",
              "Intercept                 -5.4495      1.485     -3.669      0.000      -8.361      -2.538\n",
              "==========================================================================================\n",
              "\"\"\""
            ]
          },
          "execution_count": 76,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "Logit(data2['attack'], data2.drop(['dataset','attack','num','id','restecg_st-t abnormality','thal_normal','age','slope_upsloping','fbs_True','chol','restecg_normal','exang_True','thalch'],axis=1)).fit().summary()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zJn_LSco2Em1"
      },
      "source": [
        "Al p-values are now below the significance level $\\alpha=0.05$. We can now proceed interpreting the result."
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}