Gradient_Boosted_Decision_Tree.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Gradient Boosted Decision Tree.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyM592gyYgGJnzhli5Gr5iwW",
      "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/jackqk/sklearn-note/blob/master/Gradient_Boosted_Decision_Tree.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "XWz6tyMKMEaM",
        "colab_type": "text"
      },
      "source": [
        "# **Gradient Boosted Decision Tree**"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ACxKuODPMNuK",
        "colab_type": "text"
      },
      "source": [
        "# **Hello**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aOdEJQPiMQlc",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        },
        "outputId": "5c47e2ee-a399-4d6c-f996-26adcb1d1e5f"
      },
      "source": [
        "from sklearn.ensemble import GradientBoostingClassifier\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.datasets import make_blobs\n",
        "\n",
        "X_D2, y_D2 = make_blobs(n_samples = 100, n_features = 2, centers = 8, cluster_std = 1.3, random_state = 4)\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X_D2, y_D2, random_state = 0)\n",
        "clf = GradientBoostingClassifier().fit(X_train, y_train)\n",
        "print('Accuracy of training dataset:{:.2f}'.format(clf.score(X_train, y_train)))\n",
        "print('Accuracy of test dataset:{:.2f}'.format(clf.score(X_test, y_test)))"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy of training dataset:1.00\n",
            "Accuracy of test dataset:0.80\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "aLFwzmvLMX2g",
        "colab_type": "text"
      },
      "source": [
        "# **Fruit Dataset Demo**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jiKYt7aiOkqa",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        },
        "outputId": "45cab4b0-798a-4718-8c62-eedb8cdaa9ce"
      },
      "source": [
        "import pandas as pd\n",
        "from sklearn.ensemble import GradientBoostingClassifier\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "fruits = pd.read_csv('https://raw.githubusercontent.com/jackqk/sklearn-note/master/data/fruit_data_with_colors.txt', sep='\\t')\n",
        "X = fruits[['mass', 'width', 'height', 'color_score']]\n",
        "y = fruits['fruit_label']\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)\n",
        "\n",
        "clf = GradientBoostingClassifier(n_estimators=10, random_state=0).fit(X_train, y_train)\n",
        "print('Accuracy on training set: {:.2f}'.format(clf.score(X_train, y_train)))\n",
        "print('Accuracy on test set: {:.2f}'.format(clf.score(X_test, y_test)))"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Accuracy on training set: 1.00\n",
            "Accuracy on test set: 0.87\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LKItdrDLOvQF",
        "colab_type": "text"
      },
      "source": [
        "# **Cancer Dataset Demo**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "36CkHs9pOxnu",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 67
        },
        "outputId": "2ea86407-3511-4cbd-8de4-255d03aeb96e"
      },
      "source": [
        "import pandas as pd\n",
        "from sklearn.datasets import load_breast_cancer\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "cancer = load_breast_cancer()\n",
        "(X_cancer, y_cancer) = load_breast_cancer(return_X_y = True) \n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X_cancer, y_cancer, random_state = 0)\n",
        "\n",
        "clf = RandomForestClassifier(max_features = 8, random_state = 0)\n",
        "clf.fit(X_train, y_train)\n",
        "\n",
        "print('Breast cancer dataset')\n",
        "print('Accuracy on training set: {:.2f}'.format(clf.score(X_train, y_train)))\n",
        "print('Accuracy on test set: {:.2f}'.format(clf.score(X_test, y_test)))"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Breast cancer dataset\n",
            "Accuracy on training set: 1.00\n",
            "Accuracy on test set: 0.97\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}