Update app.py

app.py

@@ -1,12 +1,12 @@
 import pandas as pd
 import numpy as np
+import json
 import gradio as gr
 import matplotlib.pyplot as plt
 import seaborn as sns
 from datetime import datetime
 from sklearn.metrics import confusion_matrix, precision_score, recall_score
 
-# Sample data preparation
 data = {
     'transaction_amount': [2500, 799, 9338, 11749, 8999, 1500, 3000, 4000, 300, 5000, 24990],
     'transaction_date': ['01-11-2024 16:08', '01-11-2024 16:15', '02-11-2024 14:43', '03-11-2024 11:14', 
@@ -25,13 +25,50 @@ data = {
 }
 
 df = pd.DataFrame(data)
-
 df['transaction_date'] = pd.to_datetime(df['transaction_date'], format='%d-%m-%Y %H:%M')
 
 np.random.seed(42)
 df['is_fraud_predicted'] = np.random.choice([0, 1], size=len(df), p=[0.3, 0.7])
 df['is_fraud_reported'] = np.random.choice([0, 1], size=len(df), p=[0.4, 0.6])
 
+df_fraud = pd.DataFrame(data)
+df_fraud['fraud_reason'] = 'Suspicious Activity'
+df_fraud['fraud_score'] = np.random.uniform(0.6, 0.95, size=len(df_fraud))
+
+fraud_dict = {
+    row['transaction_id_anonymous']: {
+        'is_fraud': True,
+        'fraud_reason': row['fraud_reason'],
+        'fraud_score': float(row['fraud_score'])
+    }
+    for _, row in df_fraud.iterrows()
+}
+
+def generate_non_fraud_transactions(n, start_id=1000):
+    non_fraud_dict = {}
+    
+    for i in range(n):
+        tx_id = f'ANON_{start_id + i}'
+        if tx_id in fraud_dict:
+            continue
+            
+        non_fraud_dict[tx_id] = {
+            'is_fraud': False,
+            'fraud_reason': 'Not Fraud',
+            'fraud_score': float(np.random.uniform(0.01, 0.4))
+        }
+    
+    return non_fraud_dict
+
+total_records = 172927
+fraud_records = len(fraud_dict)
+non_fraud_needed = total_records - fraud_records
+
+sample_non_fraud = generate_non_fraud_transactions(5, start_id=200000)
+
+with open('transactions_train.csv', 'w') as f:
+    json.dump(fraud_dict, f, indent=2)
+
 def filter_data(start_date, end_date, payer_id, payee_id, transaction_id):
     filtered_df = df.copy()