Bagging.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Bagging.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "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/ashishpatel26/Ensemble-Learning-Algorithm-Medium/blob/master/Bagging.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "cKUJ2Od19iHG",
        "colab_type": "text"
      },
      "source": [
        "# Import All the required packages from sklearn"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HhZBMk6j8Ofs",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Import All the required packages from sklearn\n",
        "import numpy as np\n",
        "from sklearn import model_selection\n",
        "from sklearn.ensemble import BaggingClassifier\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.datasets import load_iris"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sUnIoRRn9kJn",
        "colab_type": "text"
      },
      "source": [
        "#Load data "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LVn8bCLi85vq",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "iris = load_iris()\n",
        "X = iris.data\n",
        "Y = iris.target"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "iNSYEzi-9sZk",
        "colab_type": "text"
      },
      "source": [
        "#Split data in training and testing set "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IATJrgBr89Pz",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X_fit, X_eval, y_fit, y_test= model_selection.train_test_split( X, Y, test_size=0.30, random_state=1 )"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J8OfMB4z9vCg",
        "colab_type": "text"
      },
      "source": [
        "#Create random sub sample to train multiple models"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bbybfEus9ERU",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "seed = 7\n",
        "kfold = model_selection.KFold(n_splits=10, random_state=seed)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "t6XlIQQe9yxx",
        "colab_type": "text"
      },
      "source": [
        "#Define a decision tree classifier"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8JuPaqgO9HM1",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "cart = DecisionTreeClassifier()\n",
        "num_trees = 100"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8_XibRu792Z2",
        "colab_type": "text"
      },
      "source": [
        "#Create classification model for bagging"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NLqtRBEO9I3j",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model = BaggingClassifier(base_estimator=cart, n_estimators=num_trees, random_state=seed)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Zf7FrqNN949D",
        "colab_type": "text"
      },
      "source": [
        "#Train different models and print their accuracy"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Wctsy98h9K9z",
        "colab_type": "code",
        "outputId": "1db54ab0-77dc-425a-a852-bec98cd5cf9c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 187
        }
      },
      "source": [
        "results = model_selection.cross_val_score(model, X_fit, y_fit,cv=kfold)\n",
        "for i in range(len(results)):\n",
        "    print(\"Model: \"+str(i)+\" Accuracy is: \"+str(results[i]))"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: 0 Accuracy is: 1.0\n",
            "Model: 1 Accuracy is: 1.0\n",
            "Model: 2 Accuracy is: 1.0\n",
            "Model: 3 Accuracy is: 0.9090909090909091\n",
            "Model: 4 Accuracy is: 1.0\n",
            "Model: 5 Accuracy is: 1.0\n",
            "Model: 6 Accuracy is: 0.9\n",
            "Model: 7 Accuracy is: 1.0\n",
            "Model: 8 Accuracy is: 1.0\n",
            "Model: 9 Accuracy is: 0.7\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6QMgyGK-9OUz",
        "colab_type": "code",
        "outputId": "80fcd9f0-1ef3-4c9c-ab54-7c6d93fe3f09",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "print(\"Mean Accuracy is: \"+str(results.mean()))"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Mean Accuracy is: 0.9509090909090908\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LcRuIQ9n9SFV",
        "colab_type": "code",
        "outputId": "724add97-40dc-46d6-ff87-96177eb70307",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "model.fit(X_fit, y_fit)\n",
        "pred_label = model.predict(X_eval)\n",
        "nnz = np.shape(y_test)[0] - np.count_nonzero(pred_label - y_test)\n",
        "acc = 100*nnz/np.shape(y_test)[0]\n",
        "print('accuracy is: '+str(acc))"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "accuracy is: 95.55555555555556\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}