Model_Evaluation_Metrics.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Model_Evaluation_Metrics.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyOn6hFqVkd5c9hlhQm4CIBf",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/BabritB/step-by-step-ml-beginner/blob/master/Model_Evaluation_Metrics.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0snSVc_KnDOD",
        "colab_type": "text"
      },
      "source": [
        "### Metrics for evaluating the model performance"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BcE2lD4AnG6U",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "from sklearn.model_selection import train_test_split # For splitting the data to test and train\n",
        "from sklearn.model_selection import StratifiedKFold  # For cross validate implementation\n",
        "from sklearn.model_selection import cross_val_score  # For calculating the accuracy score\n",
        "from sklearn.linear_model import LogisticRegression # Regression model\n",
        "from sklearn.metrics import classification_report # After Prediction Evaluation\n",
        "from sklearn.metrics import confusion_matrix # After Prediction Evaluation\n",
        "from sklearn.metrics import accuracy_score # After Prediction Evaluation"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cCCB8k0FuJSE",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "url = \"https://goo.gl/bDdBiA\"\n",
        "names = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age', 'class']"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "DuDHb48quLzF",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "data_frame=pd.read_csv(url,names=names)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lUVYZ3KQuN03",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "features=['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age']\n",
        "target=['class']"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HJiB13H6uPlK",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X=data_frame[features]\n",
        "Y=data_frame[target]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3BuyFeFauSeQ",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "d8cf3027-0998-4e8b-d045-0129cbec52d2"
      },
      "source": [
        "X.head()"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>preg</th>\n",
              "      <th>plas</th>\n",
              "      <th>pres</th>\n",
              "      <th>skin</th>\n",
              "      <th>test</th>\n",
              "      <th>mass</th>\n",
              "      <th>pedi</th>\n",
              "      <th>age</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>6</td>\n",
              "      <td>148</td>\n",
              "      <td>72</td>\n",
              "      <td>35</td>\n",
              "      <td>0</td>\n",
              "      <td>33.6</td>\n",
              "      <td>0.627</td>\n",
              "      <td>50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>85</td>\n",
              "      <td>66</td>\n",
              "      <td>29</td>\n",
              "      <td>0</td>\n",
              "      <td>26.6</td>\n",
              "      <td>0.351</td>\n",
              "      <td>31</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>8</td>\n",
              "      <td>183</td>\n",
              "      <td>64</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>23.3</td>\n",
              "      <td>0.672</td>\n",
              "      <td>32</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>89</td>\n",
              "      <td>66</td>\n",
              "      <td>23</td>\n",
              "      <td>94</td>\n",
              "      <td>28.1</td>\n",
              "      <td>0.167</td>\n",
              "      <td>21</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0</td>\n",
              "      <td>137</td>\n",
              "      <td>40</td>\n",
              "      <td>35</td>\n",
              "      <td>168</td>\n",
              "      <td>43.1</td>\n",
              "      <td>2.288</td>\n",
              "      <td>33</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   preg  plas  pres  skin  test  mass   pedi  age\n",
              "0     6   148    72    35     0  33.6  0.627   50\n",
              "1     1    85    66    29     0  26.6  0.351   31\n",
              "2     8   183    64     0     0  23.3  0.672   32\n",
              "3     1    89    66    23    94  28.1  0.167   21\n",
              "4     0   137    40    35   168  43.1  2.288   33"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9g73GGVOuUvC",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 204
        },
        "outputId": "1e34f6ce-f97b-475c-b72d-aa12b15fd2ee"
      },
      "source": [
        "Y.head()"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>class</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   class\n",
              "0      1\n",
              "1      0\n",
              "2      1\n",
              "3      0\n",
              "4      1"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gVjuXkCbuWID",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X_train,X_test,Y_train,Y_test=train_test_split(X,Y,train_size=0.8,test_size=0.2,random_state=7)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tYwa4fXmubbk",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model=LogisticRegression(solver='liblinear')"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "p67On5v9ufYy",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "kFold=StratifiedKFold(n_splits=10,random_state=1,shuffle=True)  # Usually taking 10 splits is a standard practice"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lLdmD738uhPb",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "outputId": "acf998a7-bcf5-4c4c-b77c-dedb0e521063"
      },
      "source": [
        "cv_results=cross_val_score(model, X_train, Y_train, cv=kFold, scoring='accuracy')"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n",
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TNa0RFO9urXA",
        "colab_type": "text"
      },
      "source": [
        "## Make Predictions:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nMxiE4IUujCW",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 71
        },
        "outputId": "620cc9b4-b8ba-4a70-e699-5be96d59bedc"
      },
      "source": [
        "model.fit(X_train, Y_train)\n",
        "predictions = model.predict(X_test)"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "/usr/local/lib/python3.6/dist-packages/sklearn/utils/validation.py:760: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().\n",
            "  y = column_or_1d(y, warn=True)\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KVI4x7CXu3xj",
        "colab_type": "text"
      },
      "source": [
        "## Prediction Evaluation:"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CrT-ijGKuyf7",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 272
        },
        "outputId": "bddd6db2-fa19-4a0f-d1b7-0a4c5f8505f8"
      },
      "source": [
        "print(f\"  Accuracy --> 1:\\n {accuracy_score(Y_test, predictions)}\")\n",
        "print(f\"  ConfusionMatrix --> 2:\\n {confusion_matrix(Y_test, predictions)}\")\n",
        "print(f\" Classification Report --> 3:\\n {classification_report(Y_test, predictions)}\")"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "  Accuracy --> 1:\n",
            " 0.7922077922077922\n",
            "  ConfusionMatrix --> 2:\n",
            " [[91  6]\n",
            " [26 31]]\n",
            " Classification Report --> 3:\n",
            "               precision    recall  f1-score   support\n",
            "\n",
            "           0       0.78      0.94      0.85        97\n",
            "           1       0.84      0.54      0.66        57\n",
            "\n",
            "    accuracy                           0.79       154\n",
            "   macro avg       0.81      0.74      0.76       154\n",
            "weighted avg       0.80      0.79      0.78       154\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IFRxqfBYu6hj",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        ""
      ],
      "execution_count": 0,
      "outputs": []
    }
  ]
}