Gradient Boost.ipynb

gradient-boost.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "authorship_tag": "ABX9TyOqs816zoTuG51c7rpQyzQv",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/flyfir248/21e0529a8a9c02a1beece13cae553296/gradient-boost.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NJoN1LDzRE5E",
        "outputId": "5129631d-14d9-4e24-a0d7-654ec864b10f"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy: 0.9590643274853801\n"
          ]
        }
      ],
      "source": [
        "from sklearn.datasets import load_breast_cancer\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.ensemble import GradientBoostingClassifier\n",
        "from sklearn.metrics import accuracy_score\n",
        "\n",
        "# Load the breast cancer dataset\n",
        "data = load_breast_cancer()\n",
        "X = data.data\n",
        "y = data.target\n",
        "\n",
        "# Split the dataset into training and testing sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n",
        "\n",
        "# Create an instance of the GradientBoostingClassifier class\n",
        "clf = GradientBoostingClassifier(random_state=42)\n",
        "\n",
        "# Fit the classifier to the training data\n",
        "clf.fit(X_train, y_train)\n",
        "\n",
        "# Make predictions on the testing data\n",
        "y_pred = clf.predict(X_test)\n",
        "\n",
        "# Evaluate the accuracy of the classifier\n",
        "acc = accuracy_score(y_test, y_pred)\n",
        "print(\"Accuracy:\", acc)"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.datasets import make_classification\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.ensemble import GradientBoostingClassifier\n",
        "from sklearn.metrics import accuracy_score\n",
        "\n",
        "# Generate a synthetic dataset for binary classification\n",
        "X, y = make_classification(n_samples=100, n_features=2, n_redundant=0, n_informative=2,\n",
        "                            n_clusters_per_class=1, class_sep=1.5, random_state=42)\n",
        "\n",
        "# Split the dataset into training and testing sets\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n",
        "\n",
        "# Create an instance of the GradientBoostingClassifier class\n",
        "clf = GradientBoostingClassifier(random_state=42)\n",
        "\n",
        "# Fit the classifier to the training data\n",
        "clf.fit(X_train, y_train)\n",
        "\n",
        "# Make predictions on the testing data\n",
        "y_pred = clf.predict(X_test)\n",
        "\n",
        "# Evaluate the accuracy of the classifier\n",
        "acc = accuracy_score(y_test, y_pred)\n",
        "print(\"Accuracy:\", acc)\n",
        "\n",
        "# Plot the decision boundary and the testing data\n",
        "xx, yy = np.meshgrid(np.linspace(-4, 4, 100), np.linspace(-4, 4, 100))\n",
        "Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])\n",
        "Z = Z.reshape(xx.shape)\n",
        "plt.contourf(xx, yy, Z, cmap=plt.cm.RdBu, alpha=0.6)\n",
        "plt.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=plt.cm.RdBu, edgecolors='k')\n",
        "plt.xlabel(\"Feature 1\")\n",
        "plt.ylabel(\"Feature 2\")\n",
        "plt.title(\"Gradient Boosting\")\n",
        "plt.colorbar()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 489
        },
        "id": "F8WXZ65iSF4D",
        "outputId": "47a85c01-b8e5-49f2-c479-a26b2b2e1bab"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Accuracy: 1.0\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}