{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Performance for all_with_p_s.csv:\n",
      "TP: 1724, TN: 11907, FP: 919, FN: 272\n",
      "Precision: 0.6523, Recall: 0.8637, Accuracy: 0.9196\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "\n",
    "# Set the group number\n",
    "group_number = 1  # Change this to the desired group number\n",
    "\n",
    "# File paths for the two datasets\n",
    "test_s_path = f'../post_process/0.result/{group_number}/test_s.csv'\n",
    "\n",
    "# Load the CSV files\n",
    "test_s_csv = pd.read_csv(test_s_path, low_memory=False)\n",
    "test_s_csv.fillna('', inplace=True)\n",
    "\n",
    "def evaluate_performance(test_csv):\n",
    "    # Initialize counters for TP, TN, FP, FN\n",
    "    TP = 0\n",
    "    TN = 0\n",
    "    FP = 0\n",
    "    FN = 0\n",
    "\n",
    "    # Iterate over the DataFrame rows\n",
    "    for index, row in test_csv.iterrows():\n",
    "        # True Positive (TP): s_correct is True and MDM is True\n",
    "        if row['s_correct'] and row['MDM']:\n",
    "            TP += 1\n",
    "        # True Negative (TN): s_thing is null and MDM is False\n",
    "        elif row['s_thing'] == '' and not row['MDM']:\n",
    "            TN += 1\n",
    "        # False Positive (FP): \n",
    "        # 1) s_thing is not null and MDM is False \n",
    "        # OR \n",
    "        # 2) s_thing is not null and s_correct is False and MDM is True\n",
    "        elif (row['s_thing'] != '' and not row['MDM']) or (row['s_thing'] != '' and not row['s_correct'] and row['MDM']):\n",
    "            FP += 1\n",
    "        # False Negative (FN): s_thing is null and MDM is True\n",
    "        elif row['s_thing'] == '' and row['MDM']:\n",
    "            FN += 1\n",
    "\n",
    "    # Calculate total\n",
    "    total = TP + TN + FP + FN\n",
    "\n",
    "    # Calculate Precision, Recall, and Accuracy\n",
    "    precision = TP / (TP + FP) if (TP + FP) > 0 else 0\n",
    "    recall = TP / (TP + FN) if (TP + FN) > 0 else 0\n",
    "    accuracy = (TP + TN) / total if total > 0 else 0\n",
    "\n",
    "    return TP, TN, FP, FN, precision, recall, accuracy\n",
    "\n",
    "# Evaluate both datasets\n",
    "tp_s_results = evaluate_performance(test_s_csv)\n",
    "\n",
    "# Print the results for both datasets\n",
    "print(\"Performance for all_with_p_s.csv:\")\n",
    "print(f\"TP: {tp_s_results[0]}, TN: {tp_s_results[1]}, FP: {tp_s_results[2]}, FN: {tp_s_results[3]}\")\n",
    "print(f\"Precision: {tp_s_results[4]:.4f}, Recall: {tp_s_results[5]:.4f}, Accuracy: {tp_s_results[6]:.4f}\")"
   ]
  }
 ],
 "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": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}