{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cdf017bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.preprocessing import StandardScaler"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1411b520",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load patient data\n",
    "df = pd.read_csv('patient_data.csv')\n",
    "X = df.drop('diagnosis', axis=1)\n",
    "y = df['diagnosis']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "abe11b89",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Preprocess — BUG: scaler fit on ALL data before split\n",
    "scaler = StandardScaler()\n",
    "X_scaled = scaler.fit_transform(X)\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X_scaled, y, test_size=0.2\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "748b6189",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Train model — BUG: no random seed\n",
    "model = LogisticRegression()\n",
    "model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c2ec2976",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Evaluate — no subgroup reporting\n",
    "accuracy = model.score(X_test, y_test)\n",
    "print(f'Accuracy: {accuracy}')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}