classification_APS.ipynb

classification_aps.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "classification_APS.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyM0qoC0a1/ExAP4qMEjxFil",
      "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/gist/redoxate/c5cb93e0d5cf8f67d98eeeb20d949f98/classification_aps.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vfxAtXT_gbeu"
      },
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "from sklearn.impute import SimpleImputer\n",
        "from sklearn.metrics import confusion_matrix\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.neighbors import KNeighborsClassifier\n"
      ],
      "execution_count": 98,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "llFVfVvor71S"
      },
      "source": [
        "data =  pd.DataFrame(pd.read_csv('aps_failure_training_set.csv', encoding='utf-8'))"
      ],
      "execution_count": 99,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "v2WOZuo-sO1T"
      },
      "source": [
        "data = data.replace(['na'],np.nan)\n",
        "data = data.replace(['neg'],0)\n",
        "data = data.replace(['pos'],1)"
      ],
      "execution_count": 100,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Ny-keFEE3BEo"
      },
      "source": [
        "imputer = SimpleImputer(missing_values=np.nan, strategy='mean')\n",
        "#imputer.fit(data)\n",
        "#data = imputer.transform(data)\n",
        "data = imputer.fit_transform(data)\n",
        "y = data[:,0]\n",
        "X = data[:,1:]\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.20, random_state=42)\n",
        "\n"
      ],
      "execution_count": 101,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "bVyLgG3A9Pal",
        "outputId": "8c44cb16-8414-4bbc-db1c-2173cd3d423e"
      },
      "source": [
        "for n_voisins in [3,4,5,6,7]:\n",
        "  KN = KNeighborsClassifier(n_neighbors=n_voisins)\n",
        "  KN.fit(X_train,y_train)\n",
        "  y_kn_predict= KN.predict(X_test)\n",
        "\n",
        "  tn, fp, fn, tp = confusion_matrix(y_test, y_kn_predict).ravel()\n",
        "  print('KN avec n_voisins : ', n_voisins , (tn, fp, fn, tp))"
      ],
      "execution_count": 103,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "KN avec n_voisins :  3 (11745, 43, 115, 97)\n",
            "KN avec n_voisins :  4 (11764, 24, 141, 71)\n",
            "KN avec n_voisins :  5 (11747, 41, 115, 97)\n",
            "KN avec n_voisins :  6 (11763, 25, 143, 69)\n",
            "KN avec n_voisins :  7 (11750, 38, 118, 94)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "t8UYjaMxCSlx",
        "outputId": "5d58a69f-1e7f-4ac5-febe-052b54c29613"
      },
      "source": [
        "\n",
        "\n",
        "clf = DecisionTreeClassifier()\n",
        "clf = clf.fit(X_train,y_train)\n",
        "y_clf_predict = clf.predict(X_test)\n",
        "\n",
        "tn, fp, fn, tp = confusion_matrix(y_test, y_clf_predict).ravel()\n",
        "print('DecisionTree: ', (tn, fp, fn, tp))\n"
      ],
      "execution_count": 91,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "DecisionTree :  (11713, 75, 69, 143)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "GHG3s7b9IYfb",
        "outputId": "bf51fa5f-bef2-46c1-ef52-926cdafc513f"
      },
      "source": [
        "\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "\n",
        "logisticRegr = LogisticRegression()\n",
        "param_grid = [    \n",
        "    {'solver' : ['lbfgs','newton-cg','liblinear','sag','saga'],\n",
        "     'penalty' : ['l1', 'l2', 'elasticnet', 'none'],\n",
        "    'max_iter' : [100, 1000,2500, 5000]\n",
        "    }\n",
        "]\n",
        "logisticRegr\n"
      ],
      "execution_count": 108,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
              "                   intercept_scaling=1, l1_ratio=None, max_iter=100,\n",
              "                   multi_class='auto', n_jobs=None, penalty='l2',\n",
              "                   random_state=None, solver='lbfgs', tol=0.0001, verbose=0,\n",
              "                   warm_start=False)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 108
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "38wqorNOkOKQ",
        "outputId": "179f681c-bf73-4be6-9e23-65c3e059157a"
      },
      "source": [
        "clf = GridSearchCV(logisticRegr, param_grid = param_grid, cv = 3, verbose=True, n_jobs=-1)\n",
        "best_clf = clf.fit(X_train,y_train)\n",
        "best_clf.best_estimator_"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fitting 3 folds for each of 80 candidates, totalling 240 fits\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "[Parallel(n_jobs=-1)]: Using backend LokyBackend with 2 concurrent workers.\n",
            "[Parallel(n_jobs=-1)]: Done  46 tasks      | elapsed: 29.4min\n"
          ],
          "name": "stderr"
        }
      ]
    }
  ]
}