Boosting.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Boosting.ipynb",
      "provenance": [],
      "authorship_tag": "ABX9TyMpAc4gIa1BxQ2gzhBdLXbi",
      "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/Boosting.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "YBPbSenYUxQ0",
        "colab_type": "text"
      },
      "source": [
        "# Import All the required packages from sklearn"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PwNQcuuNU0aL",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "from sklearn import model_selection\n",
        "from sklearn.datasets import load_iris\n",
        "from sklearn.ensemble import AdaBoostClassifier  # Boosting Algorithm\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "import numpy as np"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "KB8d4w0XU--C",
        "colab_type": "text"
      },
      "source": [
        "#Load data "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PFk9OJl2U7wX",
        "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": "6up7wHGvVGV5",
        "colab_type": "text"
      },
      "source": [
        "\n",
        "#Split data in training and testing set "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RNGsxs69VC2L",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "X_fit, X_eval, y_fit, y_test= model_selection.train_test_split( X, Y, test_size=0.20, random_state=1)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "T2IhUCtkVKnq",
        "colab_type": "text"
      },
      "source": [
        "#Define a decision tree classifier"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "usB03awyVIrK",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "cart = DecisionTreeClassifier()\n",
        "num_trees = 25"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "i3ekolb-VRr3",
        "colab_type": "text"
      },
      "source": [
        "#Create classification model for bagging"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JxU6Hv0RVN7i",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "model = AdaBoostClassifier(base_estimator=cart, n_estimators=num_trees, learning_rate = 0.1)"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "F9ENpvjbVYaV",
        "colab_type": "text"
      },
      "source": [
        "#Train Classification model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fOQzerhHVZIA",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 289
        },
        "outputId": "a75d90f7-be8c-471c-d992-533198dea2ac"
      },
      "source": [
        "model.fit(X_fit, y_fit)"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "AdaBoostClassifier(algorithm='SAMME.R',\n",
              "                   base_estimator=DecisionTreeClassifier(ccp_alpha=0.0,\n",
              "                                                         class_weight=None,\n",
              "                                                         criterion='gini',\n",
              "                                                         max_depth=None,\n",
              "                                                         max_features=None,\n",
              "                                                         max_leaf_nodes=None,\n",
              "                                                         min_impurity_decrease=0.0,\n",
              "                                                         min_impurity_split=None,\n",
              "                                                         min_samples_leaf=1,\n",
              "                                                         min_samples_split=2,\n",
              "                                                         min_weight_fraction_leaf=0.0,\n",
              "                                                         presort='deprecated',\n",
              "                                                         random_state=None,\n",
              "                                                         splitter='best'),\n",
              "                   learning_rate=0.1, n_estimators=25, random_state=None)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OhKjXBGRVeaD",
        "colab_type": "text"
      },
      "source": [
        "# Test trained model over test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0P3-tonoVbsi",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "pred_label = model.predict(X_eval)\n",
        "nnz = np.float(np.shape(y_test)[0] - np.count_nonzero(pred_label - y_test))\n",
        "acc = 100*nnz/np.shape(y_test)[0]"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "o8hkKajvVot6",
        "colab_type": "text"
      },
      "source": [
        "#Print accuracy of the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nq4d9YG0VhSL",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "dbb47258-dcc1-44ed-efb3-c068d65c5252"
      },
      "source": [
        "print('accuracy is: '+str(acc))"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "accuracy is: 96.66666666666667\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}