{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "from sklearn.linear_model import LinearRegression\n",
        "from sklearn.preprocessing import PolynomialFeatures\n",
        "from sklearn.model_selection import train_test_split\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "np.random.seed(42)\n",
        "X = np.linspace(0, 1, 50).reshape(-1, 1)\n",
        "y = np.sin(2 * np.pi * X).ravel() + np.random.normal(0, 0.2, 50)\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)\n",
        "\n",
        "def bias_variance_error_bootstrap(model, X_train, y_train, X_test, y_test, runs=30):\n",
        "    preds = []\n",
        "    n = X_train.shape[0]\n",
        "    for _ in range(runs):\n",
        "        idx = np.random.choice(n, n, replace=True)\n",
        "        X_sample = X_train[idx]\n",
        "        y_sample = y_train[idx]\n",
        "        preds.append(model.fit(X_sample, y_sample).predict(X_test))\n",
        "\n",
        "    preds = np.array(preds)\n",
        "    y_pred_mean = preds.mean(axis=0)\n",
        "\n",
        "    bias_sq = ((y_test - y_pred_mean)**2).mean()\n",
        "    variance = preds.var(axis=0).mean()\n",
        "    total_error = bias_sq + variance\n",
        "\n",
        "    return bias_sq, variance, total_error\n",
        "\n",
        "lin_model = LinearRegression()\n",
        "b_lin, v_lin, e_lin = bias_variance_error_bootstrap(lin_model, X_train, y_train, X_test, y_test)\n",
        "print(f\"Linear Regression -> Bias^2: {b_lin:.3f}, Variance: {v_lin:.3f}, Total Error: {e_lin:.3f}\")\n",
        "\n",
        "poly = PolynomialFeatures(degree=10)\n",
        "X_train_poly = poly.fit_transform(X_train)\n",
        "X_test_poly = poly.transform(X_test)\n",
        "\n",
        "poly_model = LinearRegression()\n",
        "b_poly, v_poly, e_poly = bias_variance_error_bootstrap(poly_model, X_train_poly, y_train, X_test_poly, y_test)\n",
        "print(f\"Polynomial Regression -> Bias^2: {b_poly:.3f}, Variance: {v_poly:.3f}, Total Error: {e_poly:.3f}\")\n",
        "\n",
        "plt.scatter(X, y, label=\"Data\", color='blue')\n",
        "plt.plot(X_test, lin_model.fit(X_train, y_train).predict(X_test), color='red', label=\"Linear Regression\")\n",
        "plt.scatter(X_test, poly_model.fit(X_train_poly, y_train).predict(X_test_poly), color='green', label=\"Polynomial Regression\", s=20)\n",
        "plt.title(\"Bias vs Variance: Linear vs Polynomial Regression\")\n",
        "plt.legend()\n",
        "plt.show()\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "id": "GgMsI_5-Kfw3",
        "outputId": "bbc4ea81-d35a-48e3-b41e-7b9f32511262"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Linear Regression -> Bias^2: 0.218, Variance: 0.014, Total Error: 0.232\n",
            "Polynomial Regression -> Bias^2: 0.043, Variance: 0.416, Total Error: 0.459\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}