{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np \n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.feature_selection import SelectKBest\n",
    "from sklearn.feature_selection import chi2\n",
    "from sklearn.preprocessing import StandardScaler \n",
    "from sklearn.linear_model import LogisticRegression\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load Breast Cancer dataset\n",
    "url = \"https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/wdbc.data\"\n",
    "\n",
    "# Define column names\n",
    "columns = [\"ID\", \"Diagnosis\", \"Radius_mean\", \"Texture_mean\", \"Perimeter_mean\", \"Area_mean\",\n",
    "           \"Smoothness_mean\", \"Compactness_mean\", \"Concavity_mean\", \"Concave_points_mean\",\n",
    "           \"Symmetry_mean\", \"Fractal_dimension_mean\", \"Radius_se\", \"Texture_se\", \n",
    "           \"Perimeter_se\", \"Area_se\", \"Smoothness_se\", \"Compactness_se\", \"Concavity_se\", \n",
    "           \"Concave_points_se\", \"Symmetry_se\", \"Fractal_dimension_se\", \"Radius_worst\",\n",
    "           \"Texture_worst\", \"Perimeter_worst\", \"Area_worst\", \"Smoothness_worst\", \n",
    "           \"Compactness_worst\", \"Concavity_worst\", \"Concave_points_worst\", \n",
    "           \"Symmetry_worst\", \"Fractal_dimension_worst\"]\n",
    "\n",
    "# Load data\n",
    "df=pd.read_csv(url,names=columns)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Drop the 'ID' column and convert diagnosis to numeric (Malignant = 1, Benign = 0)\n",
    "df.drop(columns=[\"ID\"], inplace=True)\n",
    "df[\"Diagnosis\"] = df[\"Diagnosis\"].map({\"M\": 1, \"B\": 0})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Separate features and target\n",
    "X = df.drop(columns=[\"Diagnosis\"])\n",
    "y = df[\"Diagnosis\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Select the best 5 features using the chi-square test\n",
    "selector = SelectKBest(chi2, k=5)  # Adjust k to select the number of features you want\n",
    "X_new = selector.fit_transform(X, y)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}