98 lines
3.1 KiB
Plaintext
98 lines
3.1 KiB
Plaintext
|
{
|
||
|
|
"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
|
||
|
|
}
|