heart_disease_classifications_machine_learning.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/frkr/mlearn/blob/master/heart_disease_classifications_machine_learning.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "5878df22aae1c5888a07fe2c49d0bbe1551a3c55",
        "id": "ml2CQLBzzp9n"
      },
      "source": [
        "# INTRODUCTION\n",
        "<br>\n",
        "We have a data which classified if patients have heart disease or not according to features in it. We will try to use this data to create a model which tries predict if a patient has this disease or not. We will use logistic regression (classification) algorithm."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 43,
      "metadata": {
        "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
        "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
        "id": "62kVJxqpzp9t"
      },
      "outputs": [],
      "source": [
        "# This Python 3 environment comes with many helpful analytics libraries installed\n",
        "# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n",
        "# For example, here's several helpful packages to load in \n",
        "\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "# Input data files are available in the \"../input/\" directory.\n",
        "# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_cell_guid": "79c7e3d0-c299-4dcb-8224-4455121ee9b0",
        "_uuid": "d629ff2d2480ee46fbb7e2d37f6b5fab8052498a",
        "id": "0tRFtT-mzp9v"
      },
      "source": [
        "## Read Data"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 44,
      "metadata": {
        "_uuid": "8d0ffd4e0549f6f2eb24c7cc258256f2fb63ec48",
        "id": "IAUook5azp9w"
      },
      "outputs": [],
      "source": [
        "# We are reading our data\n",
        "df = pd.read_csv(\"heart.csv\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 45,
      "metadata": {
        "_uuid": "4dee2636361981b0f92a8a585d49f581283d6222",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "P_UVTFjEzp9w",
        "outputId": "760318c7-c13b-4f26-f5f7-e95845605f2e"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   age  sex  cp  trestbps  chol  fbs  restecg  thalach  exang  oldpeak  slope  \\\n",
              "0   52    1   0       125   212    0        1      168      0      1.0      2   \n",
              "1   53    1   0       140   203    1        0      155      1      3.1      0   \n",
              "2   70    1   0       145   174    0        1      125      1      2.6      0   \n",
              "3   61    1   0       148   203    0        1      161      0      0.0      2   \n",
              "4   62    0   0       138   294    1        1      106      0      1.9      1   \n",
              "\n",
              "   ca  thal  target  \n",
              "0   2     3       0  \n",
              "1   0     3       0  \n",
              "2   0     3       0  \n",
              "3   1     3       0  \n",
              "4   3     2       0  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e6600663-2a94-40d1-bf65-affb4d64ee63\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>age</th>\n",
              "      <th>sex</th>\n",
              "      <th>cp</th>\n",
              "      <th>trestbps</th>\n",
              "      <th>chol</th>\n",
              "      <th>fbs</th>\n",
              "      <th>restecg</th>\n",
              "      <th>thalach</th>\n",
              "      <th>exang</th>\n",
              "      <th>oldpeak</th>\n",
              "      <th>slope</th>\n",
              "      <th>ca</th>\n",
              "      <th>thal</th>\n",
              "      <th>target</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>52</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>125</td>\n",
              "      <td>212</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>168</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2</td>\n",
              "      <td>2</td>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>53</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>140</td>\n",
              "      <td>203</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>155</td>\n",
              "      <td>1</td>\n",
              "      <td>3.1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>70</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>145</td>\n",
              "      <td>174</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>125</td>\n",
              "      <td>1</td>\n",
              "      <td>2.6</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>61</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>148</td>\n",
              "      <td>203</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>161</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>62</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>138</td>\n",
              "      <td>294</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>106</td>\n",
              "      <td>0</td>\n",
              "      <td>1.9</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>2</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e6600663-2a94-40d1-bf65-affb4d64ee63')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-e6600663-2a94-40d1-bf65-affb4d64ee63 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-e6600663-2a94-40d1-bf65-affb4d64ee63');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 45
        }
      ],
      "source": [
        "# First 5 rows of our data\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "e7df2228490edc65cef3d01659b4ef96fe15e191",
        "id": "tOQ5K1cxzp9x"
      },
      "source": [
        "Data contains; <br>\n",
        "\n",
        "* age - age in years <br>\n",
        "* sex - (1 = male; 0 = female) <br>\n",
        "* cp - chest pain type <br>\n",
        "* trestbps - resting blood pressure (in mm Hg on admission to the hospital) <br>\n",
        "* chol - serum cholestoral in mg/dl <br>\n",
        "* fbs - (fasting blood sugar > 120 mg/dl) (1 = true; 0 = false) <br>\n",
        "* restecg - resting electrocardiographic results <br>\n",
        "* thalach - maximum heart rate achieved <br>\n",
        "* exang - exercise induced angina (1 = yes; 0 = no) <br>\n",
        "* oldpeak - ST depression induced by exercise relative to rest <br>\n",
        "* slope - the slope of the peak exercise ST segment <br>\n",
        "* ca - number of major vessels (0-3) colored by flourosopy <br>\n",
        "* thal - 3 = normal; 6 = fixed defect; 7 = reversable defect <br>\n",
        "* target - have disease or not (1=yes, 0=no)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "5c510b6aea2f9083981bf75dc67c5250b3b891c7",
        "id": "B-aaPZuPzp9x"
      },
      "source": [
        "## Data Exploration"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 84,
      "metadata": {
        "_uuid": "00af1961381609399dd80ca7c6a950277c120357",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fA8eAFHrzp9y",
        "outputId": "addb6edd-8787-4305-e679-2d79718aadbe"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    526\n",
              "0    499\n",
              "Name: target, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 84
        }
      ],
      "source": [
        "df.target.value_counts()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 85,
      "metadata": {
        "_uuid": "f0c639a82d794e41978199f7fa4405a01a7b805e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 279
        },
        "id": "lT5ChU3Bzp9z",
        "outputId": "d82d02e6-f299-4582-f3a5-71ca7dcff7b2"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "sns.countplot(x=\"target\", data=df, palette=\"bwr\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 86,
      "metadata": {
        "_uuid": "dd20ffc31d87de07a6f2941b0500cda8c0b1b8e6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cqJdn4c4zp90",
        "outputId": "ff181ba0-61e3-4672-bbc2-788ba136bf4a"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Percentage of Patients Haven't Heart Disease: 48.68%\n",
            "Percentage of Patients Have Heart Disease: 51.32%\n"
          ]
        }
      ],
      "source": [
        "countNoDisease = len(df[df.target == 0])\n",
        "countHaveDisease = len(df[df.target == 1])\n",
        "print(\"Percentage of Patients Haven't Heart Disease: {:.2f}%\".format((countNoDisease / (len(df.target))*100)))\n",
        "print(\"Percentage of Patients Have Heart Disease: {:.2f}%\".format((countHaveDisease / (len(df.target))*100)))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 87,
      "metadata": {
        "_uuid": "aca4074785c40bcf036a59c14c78e3a503904724",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 279
        },
        "id": "7U2kNP1rzp90",
        "outputId": "700509ea-918a-450c-ace6-a449547f1225"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "sns.countplot(x='sex', data=df, palette=\"mako_r\")\n",
        "plt.xlabel(\"Sex (0 = female, 1= male)\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 88,
      "metadata": {
        "_uuid": "8780860cb02768a3bf112a41ab67f1f6bebe9146",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XZMv1RGMzp91",
        "outputId": "a5c49588-c229-4fc6-84a0-5887b33e7893"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Percentage of Female Patients: 30.44%\n",
            "Percentage of Male Patients: 69.56%\n"
          ]
        }
      ],
      "source": [
        "countFemale = len(df[df.sex == 0])\n",
        "countMale = len(df[df.sex == 1])\n",
        "print(\"Percentage of Female Patients: {:.2f}%\".format((countFemale / (len(df.sex))*100)))\n",
        "print(\"Percentage of Male Patients: {:.2f}%\".format((countMale / (len(df.sex))*100)))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 89,
      "metadata": {
        "_uuid": "435f8691396c6f2b1a901809286eb64112126582",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 173
        },
        "id": "N3dLBRuPzp92",
        "outputId": "f922557c-a2ca-4693-b378-f1e9dba9fcec"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "              age       sex    trestbps        chol       fbs   restecg  \\\n",
              "target                                                                    \n",
              "0       56.569138  0.827655  134.106212  251.292585  0.164329  0.456914   \n",
              "1       52.408745  0.570342  129.245247  240.979087  0.134981  0.598859   \n",
              "\n",
              "           thalach     exang   oldpeak        ca  ...      cp_1      cp_2  \\\n",
              "target                                            ...                       \n",
              "0       139.130261  0.549098  1.600200  1.158317  ...  0.066132  0.130261   \n",
              "1       158.585551  0.134981  0.569962  0.370722  ...  0.254753  0.416350   \n",
              "\n",
              "            cp_3    thal_0    thal_1    thal_2    thal_3   slope_0   slope_1  \\\n",
              "target                                                                         \n",
              "0       0.052104  0.008016  0.086172  0.264529  0.641283  0.092184  0.649299   \n",
              "1       0.096958  0.005703  0.039924  0.783270  0.171103  0.053232  0.300380   \n",
              "\n",
              "         slope_2  \n",
              "target            \n",
              "0       0.258517  \n",
              "1       0.646388  \n",
              "\n",
              "[2 rows x 21 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3475929c-c3e2-4e6e-894b-7e6f6ab7ed58\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>age</th>\n",
              "      <th>sex</th>\n",
              "      <th>trestbps</th>\n",
              "      <th>chol</th>\n",
              "      <th>fbs</th>\n",
              "      <th>restecg</th>\n",
              "      <th>thalach</th>\n",
              "      <th>exang</th>\n",
              "      <th>oldpeak</th>\n",
              "      <th>ca</th>\n",
              "      <th>...</th>\n",
              "      <th>cp_1</th>\n",
              "      <th>cp_2</th>\n",
              "      <th>cp_3</th>\n",
              "      <th>thal_0</th>\n",
              "      <th>thal_1</th>\n",
              "      <th>thal_2</th>\n",
              "      <th>thal_3</th>\n",
              "      <th>slope_0</th>\n",
              "      <th>slope_1</th>\n",
              "      <th>slope_2</th>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>target</th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "      <th></th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>56.569138</td>\n",
              "      <td>0.827655</td>\n",
              "      <td>134.106212</td>\n",
              "      <td>251.292585</td>\n",
              "      <td>0.164329</td>\n",
              "      <td>0.456914</td>\n",
              "      <td>139.130261</td>\n",
              "      <td>0.549098</td>\n",
              "      <td>1.600200</td>\n",
              "      <td>1.158317</td>\n",
              "      <td>...</td>\n",
              "      <td>0.066132</td>\n",
              "      <td>0.130261</td>\n",
              "      <td>0.052104</td>\n",
              "      <td>0.008016</td>\n",
              "      <td>0.086172</td>\n",
              "      <td>0.264529</td>\n",
              "      <td>0.641283</td>\n",
              "      <td>0.092184</td>\n",
              "      <td>0.649299</td>\n",
              "      <td>0.258517</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>52.408745</td>\n",
              "      <td>0.570342</td>\n",
              "      <td>129.245247</td>\n",
              "      <td>240.979087</td>\n",
              "      <td>0.134981</td>\n",
              "      <td>0.598859</td>\n",
              "      <td>158.585551</td>\n",
              "      <td>0.134981</td>\n",
              "      <td>0.569962</td>\n",
              "      <td>0.370722</td>\n",
              "      <td>...</td>\n",
              "      <td>0.254753</td>\n",
              "      <td>0.416350</td>\n",
              "      <td>0.096958</td>\n",
              "      <td>0.005703</td>\n",
              "      <td>0.039924</td>\n",
              "      <td>0.783270</td>\n",
              "      <td>0.171103</td>\n",
              "      <td>0.053232</td>\n",
              "      <td>0.300380</td>\n",
              "      <td>0.646388</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2 rows × 21 columns</p>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3475929c-c3e2-4e6e-894b-7e6f6ab7ed58')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-3475929c-c3e2-4e6e-894b-7e6f6ab7ed58 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-3475929c-c3e2-4e6e-894b-7e6f6ab7ed58');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 89
        }
      ],
      "source": [
        "df.groupby('target').mean()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 90,
      "metadata": {
        "_uuid": "e0eed947b5490e93a43515ad6d2a6af9713f16ce",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 407
        },
        "id": "uyzy0ISzzp93",
        "outputId": "3ae3b7e9-09db-41bf-f8c0-1737f4d651c9"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1440x432 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAABIwAAAGGCAYAAAAZ9RpuAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+WH4yJAAAgAElEQVR4nOzdeXQUZdr+8StLJw1EcCWAhAkgSkQYAgEMCgxhN2xBWRQXEEUdBJUZxrgHV1RUXnXUQVB0ZlxGCAFBlEUU1BfcQFCDK0gQCBAgbOmk03l+f/izX2pIQidUV6fD93MO56T76ar7rqUrnYvqqghjjBEAAAAAAADw/0WGugEAAAAAAADULARGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAOCo7du3Kzk5WT6fL9StIEDLli1Tjx49lJycrG+//TbU7QAAAAcQGAEAEKbS0tL0ySefWJ7Lzs7W5ZdfHrSa5513nn755ZcKx7Ozs5WUlKTk5GQlJycrLS1Nd9xxhzZv3ux/TZMmTbRu3TpFRUUFrU+7pKWlqV27dv7lSU5OVn5+fqjbctyjjz6qe+65R+vWrdP5559v23wzMzN1/vnna9euXbbNEwAA2IPACAAAHFdpaWnAr23fvr3WrVunzz//XHPmzFFsbKyGDRum77//PogdBs8LL7ygdevW+f/Fx8dbxquybsLV9u3b1apVq2pNW9GZZEeOHNF7772nU045RQsXLjyR9gAAQBAQGAEAUIvl5+dr4sSJuvDCC5WWlqZXX33VP7ZhwwaNHDlSKSkpuvjii3X//ferpKTEP37eeefp3//+t/r27au+fftq9OjRkqQhQ4YoOTlZ77zzTqW1o6Ki1KxZM2VlZalz58569tlnJUnbtm3Teeed5w9asrOz1atXL/8ZSUeHB3PnztWAAQPUqVMnjRs3Tr/++qt/7MEHH1SPHj3UoUMHDRs2TJ9//rll2YYNG6YOHTqoa9eueuSRR/xj69ev16hRo5SSkqLBgwdr7dq1VV6v/71uJGnlypUaMmSIUlJSNGrUKG3atMn/+m+//VYZGRlKTk7Wrbfeqttuu01PPfWUf/n/+6ywo8/kKikp0aOPPqo//elP6tq1q+699155PB5J0tq1a9W9e3e99NJLSk1N1cUXX6x58+b55+PxeDRt2jT17NlTHTt21OWXXy6Px6Px48frn//8p6XmoEGDtGzZMstzJSUl/q8PDhkyRL1795Yk/fTTT7rqqquUkpKi9PR0rVixwj9NZmam7rvvPl1//fVq3759het36dKlql+/vv785z8rJyfHMubxeHT77berU6dOGjBggF588UV1797dP368/bqibQ8AAKrAAACAsNSzZ0/z8ccfW56bN2+eGTVqlDHGGJ/PZzIyMswzzzxjiouLzdatW01aWppZtWqVMcaYjRs3mnXr1hmv12vy8vJM//79zcsvv+yf17nnnmvGjBlj9u3bZ4qKivzPbdmypcKejq5/tLfeesukpqYaY4zJy8sz5557rvF6vebw4cMmOTnZ/PTTT8YYY/Lz8833339vjDFm2bJlpnfv3ubHH380Xq/X/P3vfzcjR470zzMnJ8fs3bvXeL1eM3v2bNO1a1fj8XiMMcaMGDHCzJ8/3xhjzKFDh8y6deuMMcbs3LnTdO7c2XzwwQfG5/OZjz76yHTu3NkUFBQEvI7LWzfffPONufDCC8369etNaWmpyc7ONj179jTFxcWmuLjY/OlPfzIvv/yyKSkpMUuWLDHnn3++efLJJytcZ0ev54ceesjccMMNZt++febgwYPmhhtuMNOnTzfGGLNmzRqTlJRkZsyYYUpKSswHH3xg2rVrZ/bv32+MMSYrK8tceeWVZufOnaa0tNR88cUXpri42CxevNhcdtll/nq5ubmmc+fOpri4uNz1cHQ/JSUlpnfv3ub55583xcXF5pNPPjHt27f3b8Pbb7/ddOjQwXz++efG5/P5t8l/u/rqq82jjz5qdu/ebZKSkszGjRv9Y48//rgZPXq02b9/v9mxY4cZOHCg6datmzHm+Pt1RdseAABUDWcYAQAQxiZMmKCUlBT/v6lTp/rHNm7cqL179+rmm29WTEyMEhISNGLECP+ZQRdccIHat2+v6OhoNW3aVCNHjtRnn31mmf/48eN16qmnyu12n1CfDRs2VGFhYbljkZGR+uGHH+TxeNSwYUP/V5/eeOMNjR8/Xi1btlR0dLRuvPFG5ebm+s8yGjJkiE477TRFR0fr2muvVUlJif9aSdHR0dq6dav27t2revXqqX379pKkBQsWqHv37urRo4ciIyN10UUX6YILLtCHH35YYe9Hr+M///nP5a6bN998UyNHjtQf//hHRUVFKSMjQy6XS+vXr9dXX30lr9era665Ri6XS/3791fbtm0DWm/GGP3nP//RnXfeqVNPPVVxcXG64YYbtHjxYv9roqOjNWHCBLlcLvXo0UN169bV5s2bVVZWpnnz5umuu+5SfHy8oqKi1KFDB8XExKhXr17asmWLtmzZ4l8vAwYMUExMzHF7+uqrr3TkyBGNHz9eMTExSk1NVc+ePS099erVSx07dlRkZKRiY2OPmcf27du1du1aDRo0SGeeeaZSU1MtZxktWbJEN9xwgxo0aKBGjRrp6quv9o8db7+uaNsDAICqiQ51AwAAoPr+/ve/q2vXrv7H2dnZeuuttyRJv/76q3bt2qWUlBT/uM/n8z/evHmzpk2bpq+//lpFRUXy+Xxq06aNZf6NGze2pc/8/Hw1aNDgmOfr1q2rp556Si+99JLuuusudejQQbfffrtatmyp7du36+GHH9ajjz7qf70xRvn5+Tr77LM1e/ZszZ07V7t27VJERIQOHTqkffv2SZIeeughPf300xowYICaNm2qm2++WT179tT27dv17rvvauXKlf55lpaWqkuXLhX2/t/r+HdHr5vt27crJydH//rXv/zPeb1ef2/x8fGKiIjwjzVp0iSg9bZ3714VFRVp2LBhlnVQVlbmf3zqqacqOvr/PtLVqVNHR44c0b59+1RcXKyEhIRj5hsbG6sBAwZo4cKFuvnmm7Vo0SI9/fTTAfW0a9cuNWrUSJGR//f/jk2aNLFcDPx4+82CBQvUsmVLJSUlSfrt63DTpk3T7bffLpfLpV27dlnm0ahRI//Px9uvK9r2AACgagiMAACopRo3bqymTZtq6dKl5Y5nZWXp/PPP1xNPPKG4uDjNmTNH7733nuU1R4ccJ2L58uWWP/CP1q1bN3Xr1k0ej0czZszQPffco9dee02NGzfWjTfeqMGDBx8zzeeff65Zs2Zpzpw5atWqlSIjI9WpUycZYyRJiYmJevLJJ1VWVqalS5dq0qRJWrt2rRo3bqwhQ4bowQcfPOFlOnrd/N7rTTfddMzrPv30U+Xn58sY459m+/bt/iCnTp06/msSSdLu3bv9P5922mlyu91avHjxMRfbPp7TTjtNsbGxysvLU+vWrY8Zz8jI0N/+9jd17NhRderUUXJyckDzbdiwoXbu3KmysjJ/aLRjxw4lJiYG3FtOTo527Nihiy66SNJvod3+/fv14Ycfqnfv3jrrrLO0c+dOnXPOOZKknTt3+qc93n5d0bavW7duwP0BAAAueg0AQK3Vrl071atXTzNnzpTH45HP59P333+vDRs2SJIOHz6sevXqqV69evrpp5/0+uuvH3eeZ555pvLy8gKq7/P5lJeXpwceeECffvqpJkyYcMxr9uzZo+XLl+vIkSOKiYlR3bp1/SHEqFGjNHPmTP3www+SpIMHD2rJkiX+3qOionT66aertLRUzz77rA4dOuSf74IFC7R3715FRkaqfv36kn776tvgwYO1cuVKrV69Wj6fT8XFxVq7dq0lkKiO4cOH64033tBXX30lY4yOHDmiDz74QIcOHfJ/7e/VV1+V1+vV0qVLtXHjRv+0rVu31g8//KDc3FwVFxfrmWee8Y9FRkZq+PDhevjhh1VQUCDpt7O1Vq9efdyeIiMjdemll+qRRx5Rfn6+fD6f1q1b57+weXJysiIjIzVt2rRyQ7mKtGvXTm63W7NmzZLX69XatWv1/vvv65JLLglo+nXr1ikvL09vvfWWcnJylJOTo0WLFmngwIFasGCBJGnAgAH6xz/+ocLCQuXn51vO3Drefl3RtgcAAFXDb08AAGqpqKgovfDCC9q0aZN69eqlCy+8UHfffbc/WLn99tu1aNEidejQQffcc09Af/DffPPNyszMVEpKSoV3SVu/fr2Sk5PVsWNHXX311Tp06JDmzp2r884775jXlpWVac6cOerWrZs6d+6szz77TFlZWZKkPn366LrrrtPkyZPVoUMHDRw4UKtWrZIkXXzxxerWrZv69euntLQ0xcbGWr7CtHr1aqWnpys5OVkPPfSQnnrqKbndbjVu3FjPPfec/vGPfyg1NVU9evTQ7NmzLV/xqo62bdvqgQce0P33369OnTqpb9++ys7OliTFxMTomWee0fz589W5c2e988476tOnj3/a5s2ba8KECRozZoz69u2rjh07WuY9ZcoU/eEPf9CIESPUoUMHjRkzxn+tpuO5/fbbde655+qyyy5T586dNX36dMuyDhkyRN9//72GDBkS8LLGxMTohRde0KpVq3ThhRdq6tSpeuyxx9SyZcuApp8/f7569eql8847T2eddZb/3zXXXKOVK1dq//79mjBhgho1aqRevXppzJgx6tevn//6Ssfbryva9gAAoGoizO/nbgMAAMARmZmZio+P12233RbSPnJycvTmm28GdHZZKL322mt65513LGcaAQCA4OIMIwAAgJNQUVGRXnvtNY0cOTLUrRxj165d+uKLL1RWVqaff/5ZL7/8snr37h3qtgAAOKlw0WsAAICTzOrVqzVx4kSlpqZq4MCBoW7nGF6vV/fdd5+2bdumU045Renp6briiitC3RYAACcVvpIGAAAAAAAAC76SBgAAAAAAAAsCIwAAAAAAAFiExTWM1q9fr9jY2CpNU1xcXOVpToST9agVfvWoFV61nK5HrfCrR63wquV0PWqFVy2n61Er/OpRK7xqOV2PWuFXj1rHTte+ffvyB00Y+Pbbbx2Z5kQ4WY9a4VePWuFVy+l61Aq/etQKr1pO16NWeNVyuh61wq8etcKrltP1qBV+9agV+HR8JQ0AAAAAAAAWBEYAAAAAAACwIDACAAAAAACARVhc9BoAAAAAAKCm8Xq92rZtmzweT7ljubm5jvVRWS23262mTZvK5XIFPE8CIwAAAAAAgGrYtm2bTjnlFCUmJioiIsIyVlRUpDp16jjSR2W1jDEqKCjQtm3b1Lx584DnyVfSAAAAAAAAqsHj8eiMM844JiyqSSIiInTGGWeUexZUZQiMAAAAAAAAqqkmh0W/q06PBEYAAAAAAAA2O3DggP79738Hvc7y5cv1008/2T5fAiMAAAAAAACbHTx4UK+//nrArzfGqKysrMp1li9frp9//rnK0x0PF70GAAAAAACw2dNPP62tW7dqyJAh6tKli7777jsdOHBApaWluuWWW9S7d29t27ZN48aN0x//+Ed98803mjlzpnJycrRw4UKdfvrpaty4sdq0aaNx48Zp69atmjp1qvbt2ye3260HHnhAhYWFev/997V27VrNnj1bzzzzjJo1a2ZL/wRGAAAAAAAANps0aZJ+/vlnLViwQKWlpfJ4PIqLi9PevXs1cuRI9erVS5L0yy+/6NFHH1X79u21YcMGLV26VAsXLpTX69WwYcPUpk0bSdI999yjqVOnKjExUV999ZWmTp2qV199VWlpaeratasGDx5sa/8ERgAAAAAAAEFkjNGTTz6pzz77TJGRkcrPz9eePXskSU2aNFH79u0lSV9++aV69eql2NhYxcbGqmfPnpKkw4cPa926dbrlllv88ywpKQlqzwRGAAAAAAAAQfT2229r7969ys7OlsvlUlpamoqLiyVJdevWPe70xhjVr19fCxYsCHarflz0GgAAALWex+urcKxZYgsHOwEAnCzq1aunw4cPS/rtAthnnHGGXC6X1qxZo19//bXcaTp06KCVK1equLhYhw8f1gcffCBJiouLU9OmTbVkyRJJvwVImzZtOqaOnTjDCAAAALWe2xWlxMzF5Y5tmZbucDcAgJPBqaeeqg4dOmjgwIFq27atfv75Zw0aNEgXXHCBWrQo/z8r2rVrp7S0NA0ePFhnnHGGzj33XJ1yyimSpMcff1xZWVl6/vnnVVpaqksuuUStW7fWJZdcorvvvltvvvmmnn76aS56DQAAAAAAUJM98cQTx33NokWLLI+vvfZaTZw4UUVFRRo9erT/otcJCQmaPXv2MdN37NhR2dnZqlOnjj1N/38ERgAAAAAAADXEvffeqx9//FHFxcXKyMjwB0ZOIzACAAAAAACoIQI5K8kJXPQaAAAAAAAAFgRGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAMLYxx9/rH79+qlPnz6aOXOmLfMkMAIAAAAAALCBx+vz/1ynTh1b51cRn8+nRx55RLNmzdLixYu1aNEi/fjjjydcO/qE5wAAAAAAAAC5XVFKzFxs2/y2TEs/7ms2bNighIQEJSQkSJLS09O1YsUKnXPOOSdUmzOMAAAAAAAAwlR+fr4aNWrkfxwfH6/8/PwTni+BEQAAAAAAACwIjAAAAAAAAMJUfHy8du7c6X+cn5+v+Pj4E54vgREAAAAAAECYatu2rbZu3aq8vDyVlJRo8eLFSktLO+H5ctFrAAAAAACAMBUdHa3MzExdd9118vl8uvTSS9WqVasTn68NvQEAAAAAAJz0PF5fQHc2q8r83K6o476uW7du6tu3r211Jb6SBgAAAAAAYIujw52ioiJb5+c0AiMAAAAAAABYEBgBAAAAAADAgsAIAAAAAAAAFgRGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAQBi77777lJqaqoEDB9o2z6AHRj6fT0OHDtUNN9wgScrLy9Pw4cPVp08f3XrrrSopKQl2CwAAAAAAAMHn9fh/rFOnjq3zq8zgwYM1a9asE693lGhb51aOV199VS1bttShQ4ckSdOnT9eYMWOUnp6ue++9V3PnztUVV1wR7DYAAAAAAACCy+WWshrYN7+swoBe1rFjRxUUFNhXV0E+w2jnzp364IMPdNlll0mSjDFas2aN+vXrJ0nKyMjQihUrgtkCAAAAAAAAqiiogdHDDz+sKVOmKDLytzL79u1T/fr1FR3924lNjRo1Un5+fjBbAAAAAAAAQBVFGGNMMGa8cuVKffjhh8rKytLatWv10ksv6ZFHHtHIkSO1bNkySdKOHTt0/fXXa9GiRZXOa/369YqNja1SfY/HI7fbXe3+q8rJetQKv3rUCq9aTtejVvjVo1Z41XK6HrVqZq2kpCQlZi4ud2zLtHTl5ubaWq8i4b4ea0Itp+tRK7xqOV2PWuFXz+5aXq9XrVq18j+uU6eO7V9JKyoqOu7LjDHavn27Jk2apHnz5pX7mh9++EEul+uY55OSksp9fdCuYfTll1/q/fff16pVq1RcXKxDhw7poYce0oEDB1RaWqro6Gjt3LlT8fHxx51XbGxshQtQkdzc3CpPcyKcrEet8KtHrfCq5XQ9aoVfPWqFVy2n61ErvGr9rjYuW22t5XQ9aoVXLafrUSv86tldKzc3156LW1cikPkXFRXJ7XYrMjKywte7XK5jlr2y/zAJ2lfS/vKXv2jVqlV6//339eSTT+rCCy/UE088oS5duui9996TJM2fP19paWnBagEAAAAAAKDWy8zM1KhRo7R582Z1795db7311gnPM+h3SftvU6ZM0W233aYZM2YoKSlJw4cPd7oFAAAAAAAA+3k9Ad/ZLOD5uY7/Fbpp06bZfqaTI4FRly5d1KVLF0lSQkKC5s6d60RZAAAAAAAA5xwV7hQVFZ14iBNAWBQsQb1LGgAAAAAAAMIPgREAAAAAAAAsCIwAAAAAAACqyRgT6haOqzo9EhgBAAAAAABUg9vtVkFBQY0OjYwxKigokNtdteshOX6XNAAAAAAAgNqgadOm2rZtm3bv3n3MmNfrlcvlcqSP49Vyu91q2rRpleZJYAQAAAAAAFANLpdLzZs3L3csNzdXSUlJjvQRjFp8JQ0AAAAAAAAWBEYAAAAAAACwIDACAAAAAACABYERAAAAAAAALAiMAAAAAAAAYEFgBAAAAAAAAAsCIwAAAAAAAFgQGAEAAAAAAMCCwAgAAAAAAAAWBEYAAAAAAACwIDACAAAAAACABYERAAAAAAAALAiMAAAAAAAAYEFgBAAAAAAAAAsCIwAAAAAAAFgQGAEAAAAAAMCCwAgAAAAAAAAWBEYAAAAICY/XV+7zzRJbONwJAAD4b9GhbgAAAAAnJ7crSomZi495fsu09BB0AwAAjsYZRgAAAAAAALAgMAIAAAAAAIAFgREAAAAAAAAsCIwAAAAAAABgQWAEAAAAAAAACwIjAAAAAAAAWBAYAQAAAAAAwILACAAAAAAAABYERgAAAAAAALAgMAIAAAAAAIAFgREAAAAAAAAsCIwAAAAAAABgQWAEAAAAAAAACwIjAAAAAAAAWBAYAQAAAAAAwILACAAAAAAAABYERgAAAAAAALAgMAIAAAAAAIAFgREAAAAAAAAsCIwAAAAAAABgQWAEAAAAAAAACwIjAAAAAAAAWBAYAQAAAAAAwILACAAAAAAAABYERgAAAAAAALAgMAIAAAAAAIAFgREAAICNWjVPqHjQ63GuEQAAgBMQHeoGAAAAapNod5yU1aD8waxCZ5sBAACoJs4wAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAAABYEBgBAAAANvJ4fRWONUts4WAnAABUX3SoGwAAAABqE7crSomZi8sd2zIt3eFuAACoHs4wAgAAAAAAgAWBEQAAAAAAACyC9pW04uJijR49WiUlJfL5fOrXr58mTZqkvLw8TZ48Wfv371ebNm302GOPKSYmJlhtAAAAAAAAoIqCdoZRTEyMXnnlFS1cuFA5OTlavXq11q9fr+nTp2vMmDFatmyZ6tevr7lz5warBQAAAAAAAFRD0AKjiIgI1atXT5JUWlqq0tJSRUREaM2aNerXr58kKSMjQytWrAhWCwAAAAAAAKiGCGOMCdbMfT6fhg0bpq1bt+qKK67QuHHjNHLkSC1btkyStGPHDl1//fVatGhRpfNZv369YmNjq1Tb4/HI7XZXu/eqcrIetcKvHrXCq5bT9agVfvWoFV61nK6XlJQkZTUofzCrULm5ubbVCvdtlpSUVO7dxLZMS7d1PVVWKxj1nKxVmXDfP2pKPWqFVy2n61Er/OpR61hJSUnlPh+0axhJUlRUlBYsWKADBw5owoQJ+vnnn6s1n9jY2AoXoCK5ublVnuZEOFmPWuFXj1rhVcvpetQKv3rUCq9aoahXGTv7qM3bzOntVRuXrTbvH7V12agVfvWoFX71qHXsdBVx5C5p9evXV5cuXbR+/XodOHBApaWlkqSdO3cqPj7eiRYAAAAAAAAQoKAFRnv37tWBAwck/XZq1CeffKKWLVuqS5cueu+99yRJ8+fPV1paWrBaAAAAAAAAQDUE7Stpu3btUmZmpnw+n4wx6t+/v3r27KlzzjlHt912m2bMmKGkpCQNHz48WC0AAAAAAACgGoIWGLVu3Vo5OTnHPJ+QkKC5c+cGqywAAAAAAABOkCPXMAIAAAAAAED4IDACaplWzRMqHvR6nGsEQNjh+AEAAIDfBe0raQBCI9odJ2U1KH8wq9DZZgCEFY4fAAAA+B1nGAEAAAAAAMCCwAgAAAAAAAAWBEYAAAAAAACwIDACAAAAAACABYERAAAAAAAALAiMAACA41o1T6h40OtxrhEAVeLx+sp9vlliC4c7AQAEW3SoGwAAACefaHeclNWg/MGsQmebARAwtytKiZmLj3l+y7T0EHQDAAgmzjACAAAAAACABYERAAAAAAAALAiMAAAAAAAAYEFgBAAAAAAAAAsCIwAAAAAAAFgQGAEAAABhqqLb3Evc6h4AcGKiQ90AAAAAgOqp6Db3Ere6BwCcGM4wAgAAAAAAgAWBEQAAAAAAACwCCoy+++67YPcBAAAAAACAGiKgaxhNnTpVJSUlysjI0ODBg3XKKacEuy8AAAAAAACESECB0WuvvaYtW7Zo3rx5GjZsmNq1a6dhw4bpoosuCnZ/AAAAAAAAcFjAd0lLTEzUrbfeqgsuuEAPPvigvv32WxljNHnyZPXt2zeYPQKA41o1Tyh/wOuRXG5nmwEAAAAAhwUUGG3atEnZ2dn68MMP1bVrV73wwgtq06aN8vPzNWrUKAIjALVOtDtOympw7EBWofPNAAAAAIDDAgqMHnzwQV122WWaPHmy3O7/+5/1+Ph43XLLLUFrDgAAAAAAAM4LKDD6xz/+IbfbraioKElSWVmZiouLVadOHQ0dOjSoDQIAAAAAAMBZkYG8aOzYsfJ4PP7HRUVFGjt2bNCaAgAAAAAAQOgEFBgVFxerXr16/sf16tVTUVFR0JoCAAAAAABA6AQUGNWpU0fffPON//HXX39tuZYRAAAAAAAAao+ArmF055136pZbblHDhg1ljNGePXv01FNPBbs3AAAAAAAAhEBAgVG7du20ZMkSbd68WZLUvHlzuVyuoDYGAAAAAACA0AgoMJKkjRs36tdff5XP59O3334rSdwhDQAAAAAAoBYKKDCaMmWK8vLy1Lp1a0VFRUmSIiIiCIwAAAAAAABqoYACo6+//lrvvPOOIiIigt0PAAAAAAAAQiygu6S1atVKu3fvDnYvAAAAAAAAqAECOsNo3759Sk9PV7t27SwXu37hhReC1hgAAAAAAABCI6DAaOLEicHuAwAAAAAAADVEQIFR586d9euvv+qXX35R165dVVRUJJ/PF+zeAAAAgODzeiSXu+pjCCqP1ye3K6rcsWaJLRzuBgBOPgEFRv/5z3/05ptvqrCwUMuXL1d+fr7uu+8+vfLKK8HuDwAAAAgulxgK7KQAACAASURBVFvKalD+WFahs73Az+2KUmLm4nLHtkxLd7gbADj5BHTR63//+996/fXXFRcXJ0lKTEzU3r17g9oYAAAAAAAAQiOgwCgmJkYxMTH+x6WlpUFrCAAAAAAAAKEV0FfSOnXqpBdeeEEej0cff/yxXnvtNaWlpQW7NwAAAAAAAIRAQGcY/fWvf9Xpp5+uc889V2+++aZ69OihW2+9Ndi9AQAAAAAAIAQCOsMoMjJSI0aM0IgRI4LdDwAAAAAAAEIsoMAoLS1NERERxzy/YsUK2xsCAAAAACd5vD65XVHljjVLbOFwNwBQMwQUGM2bN8//c0lJiZYsWaLCQm4xCgAAACD8uV1RSsxcXO7YlmnpDncDADVDQNcwOu200/z/4uPjNWbMGH344YfB7g0AAAAAAAAhENAZRt98843/57KyMn399dcqLS0NWlMAAAAAAAAInYACo2nTpv3fBNHROvvsszVjxoygNQUAAAAAAIDQCSgw+uc//xnsPgAAAAAAAFBDBBQYvfzyy5WOjx071pZmAAAAAAAAEHoBBUZff/21Nm7cqLS0NEnSypUr1bZtWyUmJgazNwA1XKvmCRUPej2Sy+1cMwCAE8atxQGEC45XQPAFFBjt3LlT2dnZiouLkyTdfPPNuuGGGzR9+vSgNgegZot2x0lZDcofzCp0thkAwAnj1uIAwgXHKyD4IgN50Z49exQTE+N/HBMToz179gStKQAAAAAAAIROQGcYDR06VJdddpn69OkjSVq+fLkyMjKC2hgAAAAAAABCI6DA6KabblL37t31+eefS5IeeeQRnX/++UFtDAAAAAAAAKER0FfSJKmoqEhxcXG65ppr1KhRI+Xl5QWzLwAAAAAAAIRIQIHRs88+q1mzZmnmzJmSJK/XqylTpgS1MQAAAAAAAIRGQIHRsmXL9Pzzz6tOnTqSpPj4eB0+fDiojQEAANRUHq8v1C3Ubl5P9cYAAIBtArqGkcvlUkREhCIiIiRJR44cCWpTAAAANRm3cw4yl1vKalD+WFahs70AAHCSCigwGjBggO69914dOHBA//nPfzRv3jyNGDEi2L0BAAAAAAAgBI4bGBljdMkll+jnn39WvXr1tHnzZk2aNEkXXXRRpdPt2LFDf/vb31RQUKCIiAiNGDFC11xzjfbv36/bbrtNv/76q84++2zNmDFDDRpU8D9IAAAAAAAAcNxxA6OIiAiNHz9eb7/99nFDoqNFRUUpMzNTbdq00aFDh3TppZfqoosuUnZ2tlJTUzV+/HjNnDlTM2fO5ALaAAAAAAAANUhAF70+//zztWHDhirNuGHDhmrTpo0kKS4uTi1atFB+fr5WrFihoUOHSpKGDh2q5cuXV7FlAAAAAAAABFNA1zD66quvtHDhQp199tn+O6VJ0ttvvx1QkW3btik3N1d//OMfVVBQoIYNG0qSzjrrLBUUFFSjbQAAAAAAAARLpYHR9u3b1aRJE82ePbvaBQ4fPqxJkybpzjvvVFxcnGXs6DuvVaa4uFi5ublVquvxeKo8zYlwsh61wq+ek7WSkpIqHbezDydrOb1/VLZsdvdRW/dF3tPhV6u2Hj8k+9fj8fqvTFX7aJbYQvXqxJY7lpDYIqy3S3XXY3X6cHKb1eb3kpO/H2vzeqxIbf39EoxabLPaU8vpetQKXKWB0YQJEzR//nydffbZmjhxop555pkqzdzr9WrSpEkaNGiQ+vbtK0k644wztGvXLjVs2FC7du3S6aefftz5xMbGVvmXfG5u7gl9MKgqJ+tRK/zqOb1slXGyDztr1eZ1WFv3Rd7T4VfreML1+CGF/3pMzFxc7vNbpqWH9XapLqf7sLtebd1m4b5dakKt2vr7JRTH4Nq4bLW1ltP1qHXsdBWp9BpGxhj/z3l5eVUqaozRXXfdpRYtWmjs2LH+59PS0pSTkyNJysnJUa9evao0XwAAAAAAAARXpWcYHf11sUC+Ona0L774QgsWLNC5556rIUOGSJImT56s8ePH69Zbb9XcuXPVpEkTzZgxoxptAwAAAAAAIFgqDYw2bdqkDh06yBij4uJidejQQdJvZw9FREToyy+/rHDalJQUfffdd+WOvfLKKyfQMgAAAAAAAIKp0sDIyYtcAQAAAAAAoGao9BpGAAAAAAAAOPkQGAFAiLVqnlDxoNfjXCMAACCk+EwAoCap9CtpAIDgi3bHSVkNyh/MKnS2GQAAEDJ8JgBQk3CGEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAAABYEBgBAAAAAADAgsAIAADUehXeqprbVAMAAJQrOtQNAAAABFuFt6rmNtUAAADl4gwjAAAAAAAAWBAYAQAAAAAAwILACAAAAAAAABYERgAAAAAAALAgMAIAAAAAAIAFgREAAACOz+up3hgAAAhL0aFuAAAAAGHA5ZayGpQ/llXobC8AACDoOMMIAAAAAAAAFgRGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAAABYEBgBAAAAAADAgsAIAAAAAAAAFgRGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAACwIjACEhVbNEyoe9HqcawRAlXi8vlC3ANQslf3O4vfZScHJ42JltZoltnCsDwDhKTrUDQBAIKLdcVJWg/IHswqdbQZAwNyuKCVmLj7m+S3T0kPQDVADuNz8PjvJVXRclOw/NjpZC0DtwxlGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAQNC0ap5Q8aDX41wjAKokOtQNAAAAAABqr2h3nJTVoPzBrEJnmwEQMM4wAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAAABYEBgBAAAACC8V3YqdW7QDgG2iQ90AAAAAAFSJy13+bdq5RTsA2IYzjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAAABYEBgBAAAAAADAgsAIAAAAAAAAFgRGAHASadU8oeLBML8VcYXLVluXSwr7ZQMAhFBlv0P4/QJAUnSoGwAAOCfaHVf+bYilsL8VcYXLVluXSwr7ZQMAhJDLze8XAJXiDCMAAAAAAABYEBgBAAAAAADAgsAIAAAAAAAAFgRGAAAAAAAAsCAwAgAAAAAAgAWBEYAaxeP1hbqFsFeb12FtXjYAAMIdv6fDT0XbrFliC0f7aNU8ofwBr8fRPmAVHeoGAOBobleUEjMXH/P8lmnpIegmPFW0DqXwX4+1edkAAAh3fI4LPzVlm0W746SsBscOZBU62gesOMMIAAAAAAAAFgRGAAAAAAAAsAhaYHTHHXcoNTVVAwcO9D+3f/9+jR07Vn379tXYsWNVWMjpZQAAAAAAADVN0AKjYcOGadasWZbnZs6cqdTUVC1dulSpqamaOXNmsMoDAAAAAACgmoIWGHXq1EkNGlgvWrVixQoNHTpUkjR06FAtX748WOUBAAAAAABQTY7eJa2goEANGzaUJJ111lkqKCgIaLri4mLl5uZWqZbH46nyNCfCyXrUssc5iU3Lfb7Uc0g/bM6ztZaTy5aUlFTpuJ19BKPW8eZpZ61miS1Ur06sI7UqY/d6rO46rE6tylT0HpOq/z5zcv+oTDi/p6u731enllRztlllfTi5XNWpV2ktr0dyucsdqs77zOnjh5P7R43ZZk7Wsnn/OF49p38/2tlHTfr8ZGcfJ/N7ujb+DROMWk6+p2tKH+G+zZys5WhgdLSIiAhFREQE9NrY2NgqH3xyc3NP6ABZVU7Wo5aNyrl1Y3RWoe19hGTZKuBkH+FQqzq3aHd6W4bDeqxQebdHVXDeZ5XhPW1Vnf2+urWqq7bWsr2ey11r32c1pZbT9cJ5/wjn42Io5lkdYbsvhqBWbfwbxunPH7V1v6+t26y6tSoLmRy9S9oZZ5yhXbt2SZJ27dql008/3cnyAAAAAAAACICjgVFaWppycnIkSTk5OerVq5eT5QEAAAAAABCAoAVGkydP1qhRo7R582Z1795db731lsaPH6+PP/5Yffv21SeffKLx48cHqzwAAAAAAACqKWjXMHryySfLff6VV14JVkkAAAAAAADYwNGvpAEAAAAAAKDmIzACAAAAAACABYERAABV1Kp5QsWDXk+V5+fx+k6gGwBAUFV2XK/GMR8OqGi7sL2AKgnaNYwAAKitot1xUlaD8gezCqs8P7crSomZi8sd2zItvcrzAwDYyOW29ZgPB1S0zdheQJVwhhEAAAAAAAAsCIwAAAAAAABgQWAEAAAAAAAACwIjAAAAAAAAWBAYAQAAAAAAwILAKAzZfTvnmiLcl6uy22I3S2zhYCeAc2rz7eBr87LVVmwzAAAA+0SHugFUnd23c64pwn25uC02Tka1eb+vzctWW7HNAAAA7MMZRgAAAAAAALAgMAIAAAAAAIAFgREAAAAAAAAsCIwAAAAAAABgQWAEAAAAAAAACwKjGopbAwMAAAAAgFCJDnUDKB+3BgYAAAAAAKHCGUYAAAAAAACwIDACAAAAAACABYERAAAAAAAALAiMAAAAAAAAYEFgBAAAAAAAAAsCI5u0ap5Q/oDX42wjNqtwuaSwXzbASR6vL9QtAAAAoBoq+xx33jmJFU9o899L/G0Gp0WHuoHaItodJ2U1OHYgq9D5ZmxU4XJJYb9sgJPcriglZi4ud2zLtHSHuwEAAECgjvs5zqG/l/jbDE7jDCMAAAAAAABYEBgBAAAAAADAgsAIAAAAAAAAFgRGAAAAAAAAsCAwAgAAAAAAgAWBEQAAAAAAACwIjAAAAAAAAGBBYAQAAAAAAAALAiMAAAAAAABYEBgBAAAAAADAgsAIAAAAAAAAFgRGAAAAAAAAsKi1gVGr5gkVD3o9zjWCY3i8vlpZq7ZiHQIAAADAySc61A0ES7Q7TspqUP5gVqGzzcDC7YpSYubiY57fMi3dsVrBqlcbsQ4BAAAA4ORTa88wAgAAAAAAQPUQGAEAAAAAAMCCwAgAAAAAAAAWBEYAAAAAAACwIDACAAAAAACABYER4ASvp3pjFeBW9wAAoEax+bMOcLKqMZ/za/F7ulXzhIoHbV42u2tVtn80S2xR5fkdT7TtcwRwLJdbympQ/lhWYZVnx63uAQBAjWLzZx3gZFVjPufX4vd0tDvOsWWzu5bT+wdnGAEAAAAAAMCCwAgAAAAAAAAWBEYAAAAAAACwIDACAAAAAACABYERAAAAAAAALAiMAAAAAAAAYEFgBAAAAAAAAAsCIwAAAAAAAFgQGAEAAAAAAMCCwAgAAAAAAAAWBEYAAAAAAACwIDACAAAAAACABYERAAAAAAAALAiMAAAAAAAAYEFgBAAAAAAAAIuQBEarVq1Sv3791KdPH82cOTMULQAAAAAAAKACjgdGPp9P999/v2bNmqXFixdr0aJF+vHHH51uAwAAAAAAABVwPDDasGGD/vCHPyghIUExMTFKT0/XihUrnG4DAAAAAAAAFXA8MMrPz1ejRo38j+Pj45Wfn+90GwAAAAAAAKhAhDHGOFnw3Xff1erVq/XQQw9JknJycrRhwwbde++9FU6zfv16xcbGOtUiAAAAAABArVdcXKz27duXOxbtcC+Kj4/Xzp07/Y/z8/MVHx9f6TQVNQ8AAAAAAAD7Of6VtLZt22rLli3Ky8tTSUmJFi9erLS0NKfbAAAAAAAAQAUcP8MoOjpa9957r6677jr5fD5deumlatWqldNtAAAAAAAAoAKOX8MIAAAAAAAANZvjX0kDAAAAAABAzUZgBAAAAAAAAAsCIwAAAAAAAFgQGAEAAAAAAMCCwAgAAMBGBQUFoW4hKPbt2xfqFoBaj+MHEHxOvs/Cfd+vFYHR4cOH9T//8z9KT09Xx44ddeGFF2rEiBHKzs52pH6/fv2CNu9Nmzb5f/Z6vXruued044036sknn1RRUZGttW6++WYtWLBAhw8ftnW+5cnLy9Mdd9yhp556SocPH9bdd9+tgQMHatKkSdq2bZuttcrKyjR37lyNHz9egwcPVkZGhm677TatXbvW1jqSVFpaqjfeeEPjxo3ToEGDNGjQIF133XV6/fXX5fV6ba9XkXvuucf2efp8Pr3xxhuaMWOGvvjiC8vYc889Z2utoqIivfjii5o1a5aKi4uVnZ2tG2+8UY899pgj+2ew3tNOvp8l6V//+pf27t0rSfrll180evRopaSkaPjw4fruu+9srcXxwx4HDx7U9OnT1b9/f3Xu3FldunTRgAEDNH36dB04cCAoNctz3XXX2Tq/Q4cO6YknntCUKVP09ttvW8aysrJsrbV7927dd999mjp1qvbt26dnnnlGgwYN0i233KJdu3bZWkuS9u/fb/m3b98+DR8+XIWFhdq/f7+ttVatWuX/+eDBg7rzzjs1aNAg/eUvf9GePXtsrTV9+nT/8WPjxo3q1auXRowYoZ49e+rTTz+1tVZGRoaee+45bd261db5VmTjxo266qqr9Ne//lU7duzQ2LFj1bFjR1166aX69ttvba3l5GdUjh/2cPIYwvHjxHH8sEdtPX5Izr7PauO+H2GMMUGt4ICbbrpJffr0UdeuXbVkyRIdOXJE6enpev755xUfH6/JkyfbVis5OVkRERGSpN9XncfjkdvtVkREhL788kvbakm/7Qjz58+XJE2bNk379+/XsGHDtHz5cu3fv1+PPfaYbbW6deum5ORkrVmzRqmpqRo4cKB69OihmJgY22r8bvTo0UpPT9ehQ4e0cOFCDRs2TAMGDNBHH32kt99+W6+++qptte644w41adJEqampeu+99xQXF6eUlBS9+OKL6tWrl6666irbak2ePFmnnHKKMjIy1KhRI0nSzp07NX/+fBUWFmrGjBm21aroAGeM0ZAhQywfDOxw1113yePxqG3btlq4cKE6deqkO+64Q5J1P7XDLbfcosaNG8vj8Wjz5s1q2bKlLrnkEq1YsUJ79uzR448/blstJ9/TTr6fJSk9PV2LFy+WJI0fP17Dhw9Xnz59tHbtWj311FN64403bKvF8cMe48aNU5cuXZSRkaGzzjpL0m9/vMyfP19r1qzRSy+9ZFutb775ptznjTG68cYb9dFHH9lWa+LEifrDH/6g9u3ba+7cuXK5XHriiScUExNj+/Fj3Lhx+tOf/qSioiK9/fbb/vB++fLl+uSTT/T888/bVkuSWrdurSZNmliey8/PV3x8vCIiIrRixQrbah29ru666y6deeaZGjFihJYtW6ZPP/3U1vB+0KBB/j/Or7rqKk2ZMkXt2rXT5s2b9Ze//MXWP1jS0tLUr18/LVmyRGeeeaYGDhyoAQMGKD4+3rYaR7vssss0ceJEHTx4UI8//rjuuOMO9e/fX//7v/+rGTNm6M0337StlpOfUTl+2MPJYwjHjxPH8cMetfX4ITn7PquV+76pBQYNGmR5PGzYMGOMMT6fz/Tr18/WWg888ICZMmWK2b17t/+5nj172lrjaEOGDPH/PHjwYFNSUmKMMaasrMwMHDgwKLUOHjxo5s+fb6677jrTpUsXk5mZaVavXh2UWsYY06NHjwrH7PDf62n48OHGGGOKi4tN//79ba3Vt2/fao1VR+vWrU1aWprp2bOn/9/vj9u0aWNrLWOs69Hr9Zq7777bTJgwwRQXF9u+zQYPHmyM+W0/79q1qykrK/M/tnu/d/I97eT72RjrPvf7cfF3HD8C4+TxwxjnjyFXXXWVufLKK4/517ZtW1tr/f6e/t1zzz1nRo4cafbu3WuGDh1qa63K9o//7sMOs2fPNtdee63ZtGmT/7lgHUOOXlf/vSx2L1v//v2N1+s1xvzffv87u48fRy/XZ599Zu677z7TtWtXc+WVV5o33njD1lrGOHsMcfIzKscPezh5DOH4ceI4ftijth4/jHH2fVYb9/1oe+On0Khbt64+//xzpaSkaMWKFTr11FMlSZGRkf4zBuxy99136+uvv9bkyZPVu3dvXXnllf6zE4Lh4MGDWrp0qYwxKikpkcvlkiRFRETYXvf3+cXFxWno0KEaOnSo9u3bp3fffVczZ87UxRdfbFutyMhIbd68WQcPHlRRUZE2btyotm3b6pdffpHP57OtjiS5XC5t3bpVzZo10zfffONfhzExMbavwwYNGmjJkiXq16+fIiN/+8ZnWVmZ3n33XdWvX9/WWgkJCZozZ84xibkk9ejRw9ZakixfqYuOjtYDDzygZ599VldffbWOHDliez3pt32ye/fu/u0UjP3eyff0wYMHtWzZMpWVlQX9/SxJ/fv3V2ZmpiZMmKA+ffpozpw56tOnj9asWVPufnMiOH7Y4+yzz9aLL76ojIwMnXnmmZKkPXv2KDs7W40bN7a1VsuWLXX//fcrMTHxmDG7jyElJSUqKyvzHxdvuukmxcfH68orr7T9+FFWVub/eciQIRWO2eXaa6/VJZdcoocffliNGzfWxIkTg3YMKSgo0MsvvyxjjA4dOiRjjL+W3ct2xRVXaPz48br++uvVrVs3Pfjgg+rbt6/WrFmj1q1b21rraCkpKUpJSdE999yjjz/+WEuWLNHIkSNtrREbG6uPPvpIBw8eVEREhJYvX67evXvr008/9e+jdnHyMyrHD3s4eQzh+HHijn4fcfyovtp6/JCcfZ/Vxn2/VgRGWVlZuvvuu/XLL7/onHPO0UMPPSRJ2rt3r0aPHm17vQsuuEBz5szRv/71L1155ZUqLi62vcbvOnfurJUrV0qS2rdvrz179ujMM8/U7t27ddppp9laq27dusc8d9ppp+nyyy/X5ZdfbmutKVOm6MYbb1RkZKT+/ve/a+bMmfruu+908P+1d+8hTYUNHMd/c2qaSllpChZozajMCMlBmlSuWlmYdiEiu0Fl0T8VBQVBmZcoUbBAu/wRltlNIdCg6KoRM7ppUWGJaQWlldVck9w87x+yoWbva3jOs3be3+fPU/Dds3N23J6d88xsxsGDB2VvrVmzBt7e3rDZbMjPzwfQfXzMmjVL1lZeXh5yc3Nx4MABDBs2DJIkwWw2Q6/XIy8vT9bW2rVr8ePHj34/+Ctx/29UVBSqqqqQkJDg3LZt2zaMHj1a9jUEoqKiYLFY4Ofnh5ycHOf25uZm+Pn5ydpy9ES8pqdPn45bt24BUP71DADbt29HWVkZduzYgebmZvz69QsXL16EwWBAbm6urC21nz+8vLxgt9udr2Mlzh8AkJ+fjxMnTmD16tX48uULNBoNRo4ciTlz5sh6SyvQ/fr904cEuddBmz17NkwmE2bMmOHclpqailGjRiEzM1PWVmJiovP8sX37duf2pqYmhIeHy9pyCAkJQUFBAW7evIkNGzago6NDkc6KFSuc64SlpKSgra0NI0aMQGtrKyZOnChrKy0tDZGRkSgtLcXbt29ht9vR1NQEg8GALVu2yNrq70ODVqtFQkJCr785ctm/fz9yc3Oh0Whw6tQplJaWYs+ePQgODkZGRobsrZ7vUbOzswEo8x6V5w95iD6H8PwxOP3tEyXPHwcOHMCRI0d4/hgEkecPB1Gvs7S0NOh0Opw/f141x74q1jACgIaGBnz69AlTp07t9YGy7wdcOdTV1QEAoqOj8fDhQ5hMJkyZMkWRGVEAqK2thUajQXR0NN68eYPq6mpEREQo0us5NqVbPcf1+vVrVFVVYfz48Yq0njx5Aq1WK2RcDo4V8bOysmT/cP4nu3fvln0dnH+l52j1/EZMCS0tLVi8eLFiixr3JXqf7dq1S9Y1oP4bkWPbvHkzCgsLZf92D+j+BsfxxhoQO66HDx+irq4OkZGRsl6l9afWs2fPoNPp2Bpk78GDB4iOjlbV2NR6LDp6ahhbbW0tIiIiEBAQAKvVihMnTuDFixcYP3480tPTERAQIGtr3Lhx8Pf3R0dHB44fP46XL19i3LhxirQc41K65ej1HJvjeVRqbI6W1WrF0aNH8eLFC0yePFnR59FxfCi5z3qOSy3HoqPX93hUcmw999nJkycVOxaLi4sxd+5c2a8mcnWrv15HRweam5sRGRmpeEtJolqqmDAqLi7GuXPnEBERgVevXmHv3r0wGAwA5F+M99ixY6iqqoLNZkNcXBzq6uoQGxuL+/fvIz4+XvaZQ5G9vq3a2lro9XohLZHjUrKVnp7+27aamhro9XoAQFFRkVu2RPfYcr8eW/JYtmwZLl++DAC4dOkSSkpKYDAYcO/ePcyZMwebNm1SpHXx4kWUlJRg7ty5bA2yd+7cOSH77NKlSzh79qyQ51FNx2J/PbXss6SkJFy5cgWenp7Yt28ffH19nbdCvHr1CseOHVOs5ePjg/nz57t9S3Tv/2WfqWVc/fXUMraYmBj4+vpi7NixWLRoEYxGo/OLMrn1bCUlJWHBggWKtUT3VPk8yrYakgstWrRIam9vlyRJkt69eyelpKRIp0+fliRJmQVQbTab9PPnT2natGmS2WyWJEmSrFarIovWiuyxNXhLliyRdu7cKZlMJqmmpkYymUxSXFycVFNTI9XU1MjaSk5OFtYS3RPZUvM+U+vY1Npy9BxSU1OlL1++SJIkSRaLRbGFytlynx5b7tcT2eq5EH/fxaCVWNRYjS3RPbbcqyW6J7KVnJws2e12qbq6WtqzZ4+k1+ulDRs2SOXl5c7PTu7YEt1TY0v+a/ddoKury3kbWlhYGM6cOYOqqirk5OTIviCYVquFVqt1zub5+/sDAHx8fBS5FUJkj63BKysrQ1RUFIqKihAQEAC9Xo8hQ4YgNjYWsbGxsrbKy8uFtUT3RLbUvM/UOja1toDuv2ffv39HW1sbJElyflM0dOhQaLVatv6xlugeW+7XE9nS6XQoKysD0P0z0s+ePQMANDY2wtNT3mVL1doS3WPLvVqieyJbGo0GHh4eiI+PR3Z2Nqqrq7Fq1SpUV1c703wVsAAAA+FJREFU79xxx5bonhpbqlj0euTIkXj58qVzwTY/Pz8cP34ce/fuRX19vawtLy8vWK1W+Pr6ory83LndbDYrMmEkssfW4Hl4eGDdunUwGo3Izs7GqFGjZP/VJle0RPfYcr8eW/Job29Hamqqc62ulpYWBAcHw2KxyP4FCFvu12PL/XoiW1lZWcjKykJhYSECAwOxcuVKhISEIDQ01PmDMGz9Wz223Ksluiey1fd85OXlhcTERCQmJsJqtbptS3RPjS1VrGH08eNHaLVaBAUF/fZvjx49QkxMjGytX79+wdvb+7ftX79+RWtrKyZMmCBbS3SPLfnduXMHjx8/xo4dOxRruKIluseW+/XYkpfVasXnz58xZswYttygJbrHlvv1lGy1t7fj/fv3sNlsCAkJcf5EthLU2hLdY8u9WqJ7IlqNjY2K/ZKoK1uie2psqWLCiIiIiIiIiIiI5KOKNYyIiIiIiIiIiEg+nDAiIiIiIiIiIqJeOGFERERE9Bdu3LiBCRMmoKGhwdUPhYiIiEgxnDAiIiIi+gsVFRWIiYlBZWWlqx8KERERkWK46DURERHRAFksFhiNRhQXFyM9PR3Xrl1DV1cXMjIyYDKZEBoaCk9PTyxduhRGoxHPnz/HoUOH8PPnTwQGBiInJwfBwcGuHgYRERHR/8QrjIiIiIgG6ObNm5g5cybCw8MRGBiI58+f4/r16/jw4QOuXr2Kw4cP4+nTpwCAzs5OZGZmoqCgAOXl5Vi6dCny8/NdPAIiIiKigfF09QMgIiIicheVlZVYs2YNAGDhwoWorKyEzWaD0WiEh4cHgoKCoNfrAQCNjY2or6/H+vXrAQBdXV0ICgpy2WMnIiIi+hucMCIiIiIagG/fvsFkMqG+vh4ajQZ2ux0ajQYGg6Hf/y9JEnQ6HS5cuCD4kRIRERENHm9JIyIiIhqAa9euITk5Gbdv38atW7dw9+5dhIWFYfjw4bh+/Tq6urrw+fNnPHjwAAAQHh6Or1+/4smTJwC6b1F7/fq1K4dARERENGC8woiIiIhoACoqKrBx48Ze2+bNm4eGhgaMHj0aCxcuRGhoKCZNmoSAgAB4e3ujoKAAmZmZMJvNsNvtWLt2LXQ6nYtGQERERDRw/JU0IiIiokGyWCzw8/NDW1sbli9fjtLSUq5XRERERG6NVxgRERERDVJ6ejp+/PiBzs5ObN26lZNFRERE5PZ4hREREREREREREfXCRa+JiIiIiIiIiKgXThgREREREREREVEvnDAiIiIiIiIiIqJeOGFERERERERERES9cMKIiIiIiIiIiIh64YQRERERERERERH18h/cYY+R18xBigAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "pd.crosstab(df.age,df.target).plot(kind=\"bar\",figsize=(20,6))\n",
        "plt.title('Heart Disease Frequency for Ages')\n",
        "plt.xlabel('Age')\n",
        "plt.ylabel('Frequency')\n",
        "plt.savefig('heartDiseaseAndAges.png')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 91,
      "metadata": {
        "_uuid": "1cb0e9e4ec00ca7caa2e77a03dd0289e1c549708",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 404
        },
        "id": "rCUSQjgQzp94",
        "outputId": "76dc85a9-6e50-40a9-faef-8b50c37aa91f"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1080x432 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "pd.crosstab(df.sex,df.target).plot(kind=\"bar\",figsize=(15,6),color=['#1CA53B','#AA1111' ])\n",
        "plt.title('Heart Disease Frequency for Sex')\n",
        "plt.xlabel('Sex (0 = Female, 1 = Male)')\n",
        "plt.xticks(rotation=0)\n",
        "plt.legend([\"Haven't Disease\", \"Have Disease\"])\n",
        "plt.ylabel('Frequency')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 92,
      "metadata": {
        "_uuid": "e5fe0744106dc26475e2e0274081789518ad8a51",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 279
        },
        "id": "jPg21Psnzp94",
        "outputId": "d589d285-fd6a-4490-9d32-44f96cb500b1"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.scatter(x=df.age[df.target==1], y=df.thalach[(df.target==1)], c=\"red\")\n",
        "plt.scatter(x=df.age[df.target==0], y=df.thalach[(df.target==0)])\n",
        "plt.legend([\"Disease\", \"Not Disease\"])\n",
        "plt.xlabel(\"Age\")\n",
        "plt.ylabel(\"Maximum Heart Rate\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 93,
      "metadata": {
        "_uuid": "730062aa471d6774f0b761ad2cb6a7043d339615",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 357
        },
        "id": "Sfz9prTPzp95",
        "outputId": "52477edb-e249-4bbe-8ea4-896f5bc1b5ae"
      },
      "outputs": [
        {
          "output_type": "error",
          "ename": "AttributeError",
          "evalue": "ignored",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
            "\u001b[0;32m<ipython-input-93-cf44269cc266>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcrosstab\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mslope\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkind\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"bar\"\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mfigsize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m15\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m6\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0mcolor\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'#DAF7A6'\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m'#FF5733'\u001b[0m \u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtitle\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Heart Disease Frequency for Slope'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mxlabel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'The Slope of The Peak Exercise ST Segment '\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mxticks\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrotation\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mylabel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Frequency'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.8/dist-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36m__getattr__\u001b[0;34m(self, name)\u001b[0m\n\u001b[1;32m   5485\u001b[0m         ):\n\u001b[1;32m   5486\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 5487\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mobject\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__getattribute__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   5488\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   5489\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__setattr__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mAttributeError\u001b[0m: 'DataFrame' object has no attribute 'slope'"
          ]
        }
      ],
      "source": [
        "pd.crosstab(df.slope,df.target).plot(kind=\"bar\",figsize=(15,6),color=['#DAF7A6','#FF5733' ])\n",
        "plt.title('Heart Disease Frequency for Slope')\n",
        "plt.xlabel('The Slope of The Peak Exercise ST Segment ')\n",
        "plt.xticks(rotation = 0)\n",
        "plt.ylabel('Frequency')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_uuid": "3209c3a2fe67592b6ff6851327e98ac7606e14eb",
        "id": "v_xxVE0Tzp95"
      },
      "outputs": [],
      "source": [
        "pd.crosstab(df.fbs,df.target).plot(kind=\"bar\",figsize=(15,6),color=['#FFC300','#581845' ])\n",
        "plt.title('Heart Disease Frequency According To FBS')\n",
        "plt.xlabel('FBS - (Fasting Blood Sugar > 120 mg/dl) (1 = true; 0 = false)')\n",
        "plt.xticks(rotation = 0)\n",
        "plt.legend([\"Haven't Disease\", \"Have Disease\"])\n",
        "plt.ylabel('Frequency of Disease or Not')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_uuid": "10be6f01d184480eca7437799c214b4847fd3543",
        "id": "RVJIWJvRzp96"
      },
      "outputs": [],
      "source": [
        "pd.crosstab(df.cp,df.target).plot(kind=\"bar\",figsize=(15,6),color=['#11A5AA','#AA1190' ])\n",
        "plt.title('Heart Disease Frequency According To Chest Pain Type')\n",
        "plt.xlabel('Chest Pain Type')\n",
        "plt.xticks(rotation = 0)\n",
        "plt.ylabel('Frequency of Disease or Not')\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "e2a8abf83186e8ddff507765dcea4e575e677624",
        "id": "w14K_PIwzp96"
      },
      "source": [
        "### Creating Dummy Variables"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "5d3461c57453ac62a71185997d716b755d00fa33",
        "id": "fm54VuVSzp96"
      },
      "source": [
        "![](http://)Since 'cp', 'thal' and 'slope' are categorical variables we'll turn them into dummy variables."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_uuid": "c2fb6259a757a62926b86aa0eea6f663a8ec094f",
        "id": "wGK8R-cizp96"
      },
      "outputs": [],
      "source": [
        "a = pd.get_dummies(df['cp'], prefix = \"cp\")\n",
        "b = pd.get_dummies(df['thal'], prefix = \"thal\")\n",
        "c = pd.get_dummies(df['slope'], prefix = \"slope\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_uuid": "50380d91358131ae6b852c9666e4da5c2e4dee66",
        "id": "ITT0Prc5zp97"
      },
      "outputs": [],
      "source": [
        "frames = [df, a, b, c]\n",
        "df = pd.concat(frames, axis = 1)\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "_uuid": "01011d45333bde3d9f95e3db93ae4517c72a741f",
        "id": "s7Uc3qfezp97"
      },
      "outputs": [],
      "source": [
        "df = df.drop(columns = ['cp', 'thal', 'slope'])\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "ea92dc67483868424e1bb15527d28be93dfeb208",
        "id": "u81s-98Ozp98"
      },
      "source": [
        "## Creating Model for Logistic Regression\n",
        "<br>\n",
        "We can use sklearn library or we can write functions ourselves. Let's them both. Firstly we will write our functions after that we'll use sklearn library to calculate score."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 61,
      "metadata": {
        "_uuid": "2e4577118ef837e24c955ea81562d8fb51a22b1c",
        "id": "R4C7nU1czp98"
      },
      "outputs": [],
      "source": [
        "y = df.target.values\n",
        "x_data = df.drop(['target'], axis = 1)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "ee237d0ae2c7686cf7fda643f32bb55add7b4787",
        "id": "k8_OZwVzzp98"
      },
      "source": [
        "### Normalize Data\n",
        "<br>\n",
        "<br>\n",
        "<img src=\"https://beyondbacktesting.files.wordpress.com/2017/07/normalization.png?w=863\" width=\"400px\"/>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 62,
      "metadata": {
        "_uuid": "c60916b235e1962a53f95593b8d020c0acc079ed",
        "id": "KAs28Sr6zp98"
      },
      "outputs": [],
      "source": [
        "# Normalize\n",
        "x = (x_data - np.min(x_data)) / (np.max(x_data) - np.min(x_data)).values"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "ef33f3d73211dca77ef04035492c6772685822bb",
        "id": "WwC-lwY2zp98"
      },
      "source": [
        "We will split our data. 80% of our data will be train data and 20% of it will be test data."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 63,
      "metadata": {
        "_uuid": "3090d1ba1e8776706d23a1175db6d1451908a954",
        "id": "MXwlUnijzp98"
      },
      "outputs": [],
      "source": [
        "x_train, x_test, y_train, y_test = train_test_split(x,y,test_size = 0.2,random_state=0)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 64,
      "metadata": {
        "_uuid": "880e2db253fd1125bfa065ba0ae8840b68687e42",
        "id": "p_q_XE5Mzp99"
      },
      "outputs": [],
      "source": [
        "#transpose matrices\n",
        "x_train = x_train.T\n",
        "y_train = y_train.T\n",
        "x_test = x_test.T\n",
        "y_test = y_test.T"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "4933da952d5df4899eac737063ec7dc1aff23b2e",
        "id": "c7dLaczvzp99"
      },
      "source": [
        "Let's say weight = 0.01 and bias = 0.0"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 65,
      "metadata": {
        "_uuid": "e98deb17b979b67f57be48517cdcf631cd5363bc",
        "id": "Bg_dI1L3zp99"
      },
      "outputs": [],
      "source": [
        "#initialize\n",
        "def initialize(dimension):\n",
        "    \n",
        "    weight = np.full((dimension,1),0.01)\n",
        "    bias = 0.0\n",
        "    return weight,bias"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "d707c6af5f7d32c9d699494cfbeddc04a687d4f3",
        "id": "5FW87wmuzp99"
      },
      "source": [
        "### Sigmoid Function\n",
        "<br>\n",
        "<img src=\"https://qph.fs.quoracdn.net/main-qimg-05edc1873d0103e36064862a45566dba\" width=\"500px\"/>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 66,
      "metadata": {
        "_uuid": "116fc66d415563ca82b5400b7852cce9dad004ba",
        "id": "oRYUGpI1zp99"
      },
      "outputs": [],
      "source": [
        "def sigmoid(z):\n",
        "    \n",
        "    y_head = 1/(1+ np.exp(-z))\n",
        "    return y_head"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "3363dced8043a7db0ec0dc0464e14ff669c5b1d6",
        "id": "q_e70U6pzp9-"
      },
      "source": [
        "### Forward and Backward Propagation\n",
        "<br>\n",
        "<img src=\"https://image.slidesharecdn.com/gradientdescentbackpropandautomaticdifferentiation-160829164205/95/gradient-descent-back-propagation-and-auto-differentiation-advanced-spark-and-tensorflow-meetup-08042016-62-638.jpg?cb=1472489358\" width=\"500px\"/>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "656c61dffe4729c195d84d117b2b8aa63c1cf9aa",
        "id": "TQBVxIjGzp9-"
      },
      "source": [
        "### Cost Function\n",
        "<br>\n",
        "<img src=\"https://i.stack.imgur.com/XbU4S.png\" width=\"500px\"/>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "948cf49e3a372a223ffcb809933e6aa0c1ad9515",
        "id": "CJRbnxQEzp9-"
      },
      "source": [
        "### Gradient Descent\n",
        "<br>\n",
        "<img src=\"https://i.stack.imgur.com/pYVzl.png\" width=\"500px\"/>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "34307d9833893a492402f94a467267175a24c8d8",
        "id": "U54GoaLgzp9-"
      },
      "source": [
        "By the way in formulas; <br>\n",
        "* h0(x^i)= y_head\n",
        "* y^i = y_train\n",
        "* x^i = x_train"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 67,
      "metadata": {
        "_uuid": "5998fbc58a696070458297830e30d4e4b036396d",
        "id": "czlVmd90zp9-"
      },
      "outputs": [],
      "source": [
        "def forwardBackward(weight,bias,x_train,y_train):\n",
        "    # Forward\n",
        "    \n",
        "    y_head = sigmoid(np.dot(weight.T,x_train) + bias)\n",
        "    loss = -(y_train*np.log(y_head) + (1-y_train)*np.log(1-y_head))\n",
        "    cost = np.sum(loss) / x_train.shape[1]\n",
        "    \n",
        "    # Backward\n",
        "    derivative_weight = np.dot(x_train,((y_head-y_train).T))/x_train.shape[1]\n",
        "    derivative_bias = np.sum(y_head-y_train)/x_train.shape[1]\n",
        "    gradients = {\"Derivative Weight\" : derivative_weight, \"Derivative Bias\" : derivative_bias}\n",
        "    \n",
        "    return cost,gradients"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 68,
      "metadata": {
        "_uuid": "0241c5bec516229c2832728e27782c273ca35b57",
        "id": "mDLnf_Bczp9_"
      },
      "outputs": [],
      "source": [
        "def update(weight,bias,x_train,y_train,learningRate,iteration) :\n",
        "    costList = []\n",
        "    index = []\n",
        "    \n",
        "    #for each iteration, update weight and bias values\n",
        "    for i in range(iteration):\n",
        "        cost,gradients = forwardBackward(weight,bias,x_train,y_train)\n",
        "        weight = weight - learningRate * gradients[\"Derivative Weight\"]\n",
        "        bias = bias - learningRate * gradients[\"Derivative Bias\"]\n",
        "        \n",
        "        costList.append(cost)\n",
        "        index.append(i)\n",
        "\n",
        "    parameters = {\"weight\": weight,\"bias\": bias}\n",
        "    \n",
        "    print(\"iteration:\",iteration)\n",
        "    print(\"cost:\",cost)\n",
        "\n",
        "    plt.plot(index,costList)\n",
        "    plt.xlabel(\"Number of Iteration\")\n",
        "    plt.ylabel(\"Cost\")\n",
        "    plt.show()\n",
        "\n",
        "    return parameters, gradients"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 69,
      "metadata": {
        "_uuid": "a97c3ff651d88b280eb87ec076040f0becaf1f3e",
        "id": "iKkPOHOVzp9_"
      },
      "outputs": [],
      "source": [
        "def predict(weight,bias,x_test):\n",
        "    z = np.dot(weight.T,x_test) + bias\n",
        "    y_head = sigmoid(z)\n",
        "\n",
        "    y_prediction = np.zeros((1,x_test.shape[1]))\n",
        "    \n",
        "    for i in range(y_head.shape[1]):\n",
        "        if y_head[0,i] <= 0.5:\n",
        "            y_prediction[0,i] = 0\n",
        "        else:\n",
        "            y_prediction[0,i] = 1\n",
        "    return y_prediction"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 70,
      "metadata": {
        "_uuid": "1b3ae665060ba757d8e0f5f29458fadf4be144ff",
        "id": "PU1XkQ9Dzp9_"
      },
      "outputs": [],
      "source": [
        "def logistic_regression(x_train,y_train,x_test,y_test,learningRate,iteration):\n",
        "    dimension = x_train.shape[0]\n",
        "    weight,bias = initialize(dimension)\n",
        "    \n",
        "    parameters, gradients = update(weight,bias,x_train,y_train,learningRate,iteration)\n",
        "\n",
        "    y_prediction = predict(parameters[\"weight\"],parameters[\"bias\"],x_test)\n",
        "    \n",
        "    print(\"Manuel Test Accuracy: {:.2f}%\".format((100 - np.mean(np.abs(y_prediction - y_test))*100)))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 71,
      "metadata": {
        "_uuid": "d866efadafcc3b49a90016c00da6c4d981cd8837",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "oRIVBXuYzp9_",
        "outputId": "0d638226-a746-4c9a-a351-56788ca7be62"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "iteration: 100\n",
            "cost: 0.37214880873836975\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Manuel Test Accuracy: 86.34%\n"
          ]
        }
      ],
      "source": [
        "logistic_regression(x_train,y_train,x_test,y_test,1,100)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "75562006d1e3767f2a62c07301cce8766a3cf917",
        "id": "9wrZfwx4zp9_"
      },
      "source": [
        "## <font color=\"blue\">Manuel Test Accuracy is <font color=\"red\">**86.89%**</font></font><br>\n",
        "Let's find out sklearn's score."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "7ffb9f8fde45b53fb9bb6fbe25dc7339b1b15649",
        "id": "5x7a_59Yzp-A"
      },
      "source": [
        "### Sklearn Logistic Regression"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 72,
      "metadata": {
        "_uuid": "5592396ddebe9346767a2a34dd20abf300e5c730",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H5hP5EH-zp-A",
        "outputId": "4b6d1a75-5e41-4e8b-f298-5eff4b8e31dd"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Accuracy 85.85%\n"
          ]
        }
      ],
      "source": [
        "accuracies = {}\n",
        "\n",
        "lr = LogisticRegression()\n",
        "lr.fit(x_train.T,y_train.T)\n",
        "acc = lr.score(x_test.T,y_test.T)*100\n",
        "\n",
        "accuracies['Logistic Regression'] = acc\n",
        "print(\"Test Accuracy {:.2f}%\".format(acc))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "e483010f6bf26cc8801061b5122e632fcac5337e",
        "id": "ua7r7ynvzp-A"
      },
      "source": [
        "1. ## <font color = \"purple\">Our model works with <font color=\"red\">**86.89%**</font> accuracy.</font>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "b0a524cdd6eb069d02aab429a1cf2024ab54cf18",
        "id": "zv4WsNXRzp-A"
      },
      "source": [
        "## K-Nearest Neighbour (KNN) Classification\n",
        "<br>\n",
        "Let's see what will be score if we use KNN algorithm."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "2a9f77931e249f18b5247349932fbf650d9052fe",
        "id": "VHp7ITyZzp-B"
      },
      "source": [
        "**KNN Algorithm**\n",
        "<br>\n",
        "<img src=\"http://res.cloudinary.com/dyd911kmh/image/upload/f_auto,q_auto:best/v1531424125/KNN_final_a1mrv9.png\"/>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 73,
      "metadata": {
        "_uuid": "b5d2956d9f265b47645ec2a6cd2eb7d50af5783a",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "mnOJRFCvzp-B",
        "outputId": "87cc9c4e-b347-4723-9f3d-8fababc9e862"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "2 NN Score: 100.00%\n"
          ]
        }
      ],
      "source": [
        "# KNN Model\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "knn = KNeighborsClassifier(n_neighbors = 2)  # n_neighbors means k\n",
        "knn.fit(x_train.T, y_train.T)\n",
        "prediction = knn.predict(x_test.T)\n",
        "\n",
        "print(\"{} NN Score: {:.2f}%\".format(2, knn.score(x_test.T, y_test.T)*100))"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 74,
      "metadata": {
        "_uuid": "8db6f0c13aa1462624cf0da04a03c9ee4db8a991",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 296
        },
        "id": "pCEHr38Czp-B",
        "outputId": "763a3ad6-d967-4d9c-c1af-23735293a37c"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Maximum KNN Score is 100.00%\n"
          ]
        }
      ],
      "source": [
        "# try ro find best k value\n",
        "scoreList = []\n",
        "for i in range(1,20):\n",
        "    knn2 = KNeighborsClassifier(n_neighbors = i)  # n_neighbors means k\n",
        "    knn2.fit(x_train.T, y_train.T)\n",
        "    scoreList.append(knn2.score(x_test.T, y_test.T))\n",
        "    \n",
        "plt.plot(range(1,20), scoreList)\n",
        "plt.xticks(np.arange(1,20,1))\n",
        "plt.xlabel(\"K value\")\n",
        "plt.ylabel(\"Score\")\n",
        "plt.show()\n",
        "\n",
        "acc = max(scoreList)*100\n",
        "accuracies['KNN'] = acc\n",
        "print(\"Maximum KNN Score is {:.2f}%\".format(acc))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "02ec17348cc5c31a9f15ed8c132b8e3cf6e915c4",
        "id": "3W4tfZ43zp-B"
      },
      "source": [
        "As you can see above if we define k as 3-7-8 we will reach maximum score. <br>\n",
        "## <font color=\"green\">KNN Model's Accuracy is <font color=\"red\">88.52%</font></font>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "ca03737d17129db8ac352aa7e2eb5ea71826f63b",
        "id": "-FbweXOvzp-B"
      },
      "source": [
        "## Support Vector Machine (SVM) Algorithm \n",
        "Now we will use SVM algorithm. "
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "a0eec2569ee5065a6f6fd7a25ed7f38c371b0afa",
        "id": "oukh0Z6Rzp-B"
      },
      "source": [
        "**Support Vector Machine Algorithm**\n",
        "<br>\n",
        "<img src=\"https://cdn-images-1.medium.com/max/1600/1*TudH6YvvH7-h5ZyF2dJV2w.jpeg\" width=\"500px\"/><br>\n",
        "<img src=\"https://aitrends.com/wp-content/uploads/2018/01/1-19SVM-2.jpg\" width=\"500px\"/>\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 75,
      "metadata": {
        "_uuid": "f51e85b552168f5ce56a43dd8ccb6452ee661317",
        "id": "393zX7Okzp-C"
      },
      "outputs": [],
      "source": [
        "from sklearn.svm import SVC"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 76,
      "metadata": {
        "_uuid": "28b9d504870997c3213b4c26e75cd4e3d92d6275",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jJkukX_Dzp-C",
        "outputId": "30b8b118-b15c-485a-a30b-839190bdb074"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Test Accuracy of SVM Algorithm: 91.71%\n"
          ]
        }
      ],
      "source": [
        "svm = SVC(random_state = 1)\n",
        "svm.fit(x_train.T, y_train.T)\n",
        "\n",
        "acc = svm.score(x_test.T,y_test.T)*100\n",
        "accuracies['SVM'] = acc\n",
        "print(\"Test Accuracy of SVM Algorithm: {:.2f}%\".format(acc))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "d4107ae5690372c7c5ebdea21a46ea7e04adeefa",
        "id": "pfMMA4uczp-C"
      },
      "source": [
        "## <font color=\"orange\">Test Accuracy of SVM Algorithm is <font color=\"red\"> 86.89%</font></font>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "058a659cd261c900ff5ce0c6894420cbc0d00232",
        "id": "W6yCTTtxzp-C"
      },
      "source": [
        "## Naive Bayes Algorithm"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "cb36324c6650e7371de9e77e53d6a531dd94a93a",
        "id": "-zBe4h1czp-C"
      },
      "source": [
        "**Naive Bayes Algorithm**\n",
        "<br>\n",
        "<img src=\"https://s3.ap-south-1.amazonaws.com/techleer/204.png\" width=\"500px\"/>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 77,
      "metadata": {
        "_uuid": "0544f45710912dab11c597b9a743bdc712f1e826",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "N-M0CXr8zp-C",
        "outputId": "65749ea5-df64-428a-9a85-859c8f6feff3"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy of Naive Bayes: 88.29%\n"
          ]
        }
      ],
      "source": [
        "from sklearn.naive_bayes import GaussianNB\n",
        "nb = GaussianNB()\n",
        "nb.fit(x_train.T, y_train.T)\n",
        "\n",
        "acc = nb.score(x_test.T,y_test.T)*100\n",
        "accuracies['Naive Bayes'] = acc\n",
        "print(\"Accuracy of Naive Bayes: {:.2f}%\".format(acc))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "678daa3a73af2129b879f759a22eb6ea7e70370e",
        "id": "kVbkoGcEzp-D"
      },
      "source": [
        "## <font color=\"magenta\">Accuracy of Naive Bayes: <font color=\"red\">86.89%</font></font>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "998124b79b0c01da04cf9992112eafb60bdb857a",
        "id": "L7C333bVzp-D"
      },
      "source": [
        "## Decision Tree Algorithm"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "cd08ae4ab93fa7de207a80412f4a8cdfb8cfd932",
        "id": "yU_Uq3WKzp-D"
      },
      "source": [
        "**Decision Tree Algorithm**\n",
        "<br>\n",
        "![image.png](attachment:image.png)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 78,
      "metadata": {
        "_uuid": "a3f57a094e75c7072857cb8adb40afa3fead5a26",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_XHoZDAwzp-D",
        "outputId": "c3c950aa-00fd-4e4c-9290-2e52bfc3d37c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Decision Tree Test Accuracy 100.00%\n"
          ]
        }
      ],
      "source": [
        "from sklearn.tree import DecisionTreeClassifier\n",
        "dtc = DecisionTreeClassifier()\n",
        "dtc.fit(x_train.T, y_train.T)\n",
        "\n",
        "acc = dtc.score(x_test.T, y_test.T)*100\n",
        "accuracies['Decision Tree'] = acc\n",
        "print(\"Decision Tree Test Accuracy {:.2f}%\".format(acc))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "b6914af2063b8991db2db75edb1e5eebee108b1c",
        "id": "ZVQ9qLVlzp-D"
      },
      "source": [
        "## <font color=\"#CFC60E\">Test Accuracy of Decision Tree Algorithm: <font color=\"red\">78.69%</font></font>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "8b409e74067d3b7acfb1841fb35be018fbb92183",
        "id": "i0ejKHdkzp-E"
      },
      "source": [
        "## Random Forest Classification"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 79,
      "metadata": {
        "_uuid": "c81ae8e5658bea3a910901e6bc35a319bba701a9",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1yt0_PAvzp-E",
        "outputId": "b9b8c07e-a73f-4c6a-86eb-410ba180f994"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Random Forest Algorithm Accuracy Score : 100.00%\n"
          ]
        }
      ],
      "source": [
        "# Random Forest Classification\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "rf = RandomForestClassifier(n_estimators = 1000, random_state = 1)\n",
        "rf.fit(x_train.T, y_train.T)\n",
        "\n",
        "acc = rf.score(x_test.T,y_test.T)*100\n",
        "accuracies['Random Forest'] = acc\n",
        "print(\"Random Forest Algorithm Accuracy Score : {:.2f}%\".format(acc))"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "a0ce99be479572718f67cf4cc178299fdd9ff6a1",
        "id": "DWm9NwUlzp-E"
      },
      "source": [
        "## <font color=\"#0FBBAE\">Test Accuracy of Random Forest: <font color=\"red\">88.52%</font></font>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "3ba9f36a63105b2557e4314be41dc9620fab27f6",
        "id": "lzk8p4k8zp-E"
      },
      "source": [
        "## Comparing Models"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 80,
      "metadata": {
        "_uuid": "9e594d64f9a20255ca8687179d858e3dce855136",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "lx_qJmB5zp-E",
        "outputId": "00f2405a-3cd8-4f35-89d4-a4d1440f090b"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1152x360 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "colors = [\"purple\", \"green\", \"orange\", \"magenta\",\"#CFC60E\",\"#0FBBAE\"]\n",
        "\n",
        "sns.set_style(\"whitegrid\")\n",
        "plt.figure(figsize=(16,5))\n",
        "plt.yticks(np.arange(0,100,10))\n",
        "plt.ylabel(\"Accuracy %\")\n",
        "plt.xlabel(\"Algorithms\")\n",
        "sns.barplot(x=list(accuracies.keys()), y=list(accuracies.values()), palette=colors)\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "3300e662f1fffbcc9c9aea95d6c11e559e84e412",
        "id": "URRsAEsDzp-F"
      },
      "source": [
        "Our models work fine but best of them are KNN and Random Forest with 88.52% of accuracy. Let's look their confusion matrixes."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "0f8e3cd00eb3f1c573468e4a8708d7a6ca8df67b",
        "id": "bA-yMxqNzp-F"
      },
      "source": [
        "## Confusion Matrix"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 81,
      "metadata": {
        "_uuid": "3a280577a5739b773e3ce0ca50d3cda671ba9a32",
        "id": "Gb-F6rEWzp-F"
      },
      "outputs": [],
      "source": [
        "# Predicted values\n",
        "y_head_lr = lr.predict(x_test.T)\n",
        "knn3 = KNeighborsClassifier(n_neighbors = 3)\n",
        "knn3.fit(x_train.T, y_train.T)\n",
        "y_head_knn = knn3.predict(x_test.T)\n",
        "y_head_svm = svm.predict(x_test.T)\n",
        "y_head_nb = nb.predict(x_test.T)\n",
        "y_head_dtc = dtc.predict(x_test.T)\n",
        "y_head_rf = rf.predict(x_test.T)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 82,
      "metadata": {
        "_uuid": "89e2140778e93d3eecfc41d5b995cb9131633313",
        "id": "4yVKj4I0zp-F"
      },
      "outputs": [],
      "source": [
        "from sklearn.metrics import confusion_matrix\n",
        "\n",
        "cm_lr = confusion_matrix(y_test,y_head_lr)\n",
        "cm_knn = confusion_matrix(y_test,y_head_knn)\n",
        "cm_svm = confusion_matrix(y_test,y_head_svm)\n",
        "cm_nb = confusion_matrix(y_test,y_head_nb)\n",
        "cm_dtc = confusion_matrix(y_test,y_head_dtc)\n",
        "cm_rf = confusion_matrix(y_test,y_head_rf)\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 83,
      "metadata": {
        "_uuid": "b91a2a68b5cc12ea58f255731cf76d49fd2ed5ec",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "7-85sF6Vzp-F",
        "outputId": "40fb535c-9f39-4923-b62f-34ba3955e0af"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1728x864 with 6 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.figure(figsize=(24,12))\n",
        "\n",
        "plt.suptitle(\"Confusion Matrixes\",fontsize=24)\n",
        "plt.subplots_adjust(wspace = 0.4, hspace= 0.4)\n",
        "\n",
        "plt.subplot(2,3,1)\n",
        "plt.title(\"Logistic Regression Confusion Matrix\")\n",
        "sns.heatmap(cm_lr,annot=True,cmap=\"Blues\",fmt=\"d\",cbar=False, annot_kws={\"size\": 24})\n",
        "\n",
        "plt.subplot(2,3,2)\n",
        "plt.title(\"K Nearest Neighbors Confusion Matrix\")\n",
        "sns.heatmap(cm_knn,annot=True,cmap=\"Blues\",fmt=\"d\",cbar=False, annot_kws={\"size\": 24})\n",
        "\n",
        "plt.subplot(2,3,3)\n",
        "plt.title(\"Support Vector Machine Confusion Matrix\")\n",
        "sns.heatmap(cm_svm,annot=True,cmap=\"Blues\",fmt=\"d\",cbar=False, annot_kws={\"size\": 24})\n",
        "\n",
        "plt.subplot(2,3,4)\n",
        "plt.title(\"Naive Bayes Confusion Matrix\")\n",
        "sns.heatmap(cm_nb,annot=True,cmap=\"Blues\",fmt=\"d\",cbar=False, annot_kws={\"size\": 24})\n",
        "\n",
        "plt.subplot(2,3,5)\n",
        "plt.title(\"Decision Tree Classifier Confusion Matrix\")\n",
        "sns.heatmap(cm_dtc,annot=True,cmap=\"Blues\",fmt=\"d\",cbar=False, annot_kws={\"size\": 24})\n",
        "\n",
        "plt.subplot(2,3,6)\n",
        "plt.title(\"Random Forest Confusion Matrix\")\n",
        "sns.heatmap(cm_rf,annot=True,cmap=\"Blues\",fmt=\"d\",cbar=False, annot_kws={\"size\": 24})\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "_uuid": "e6ac9b36fd4b17bd96a5879f8c269f90171d5982",
        "id": "YUikXL-lzp-F"
      },
      "source": [
        "**I am new with data science. Please comment me your feedbacks to help me improve myself. Thanks for your time.**"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.6.6"
    },
    "colab": {
      "provenance": [],
      "toc_visible": true,
      "include_colab_link": true
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}