{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "        age       sex       bmi        bp        s1        s2        s3  \\\n",
      "0  0.038076  0.050680  0.061696  0.021872 -0.044223 -0.034821 -0.043401   \n",
      "1 -0.001882 -0.044642 -0.051474 -0.026328 -0.008449 -0.019163  0.074412   \n",
      "2  0.085299  0.050680  0.044451 -0.005670 -0.045599 -0.034194 -0.032356   \n",
      "3 -0.089063 -0.044642 -0.011595 -0.036656  0.012191  0.024991 -0.036038   \n",
      "4  0.005383 -0.044642 -0.036385  0.021872  0.003935  0.015596  0.008142   \n",
      "\n",
      "         s4        s5        s6  Target  \n",
      "0 -0.002592  0.019907 -0.017646       1  \n",
      "1 -0.039493 -0.068332 -0.092204       0  \n",
      "2 -0.002592  0.002861 -0.025930       1  \n",
      "3  0.034309  0.022688 -0.009362       1  \n",
      "4 -0.002592 -0.031988 -0.046641       0  \n"
     ]
    }
   ],
   "source": [
    "from sklearn.datasets import load_diabetes\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "# Load the diabetes dataset\n",
    "diabetes = load_diabetes()\n",
    "X = diabetes.data\n",
    "y = diabetes.target\n",
    "\n",
    "# Convert the target into a binary classification problem by thresholding at the median\n",
    "threshold = np.median(y)\n",
    "y_binary = (y > threshold).astype(int)\n",
    "\n",
    "# Display the first few rows of the data\n",
    "df = pd.DataFrame(X, columns=diabetes.feature_names)\n",
    "df['Target'] = y_binary\n",
    "print(df.head())\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "X_train shape: (353, 10)\n",
      "X_test shape: (89, 10)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "# Split the data into training and test sets (80% train, 20% test)\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, y_binary, test_size=0.2, random_state=42)\n",
    "\n",
    "# Standardize the features\n",
    "scaler = StandardScaler()\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "# Check the shape of the data\n",
    "print(f\"X_train shape: {X_train_scaled.shape}\")\n",
    "print(f\"X_test shape: {X_test_scaled.shape}\")\n"
   ]
  }
 ],
 "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
}