Update app.py

app.py

@@ -22,16 +22,23 @@ def analyze_transaction_with_ai(transaction_data, suspicious_transactions):
         return "OpenAI API key not found. Please add it to the Hugging Face Spaces secrets."
     
     try:
-        # Prepare information for OpenAI
-        suspicious_sample = suspicious_transactions.head(5).to_dict(orient='records')
+        # Prepare information for OpenAI, converting to a JSON-serializable format
+        suspicious_sample = suspicious_transactions.head(5).copy()
+        
+        # Convert timestamp to string format to make it JSON serializable
+        if 'timestamp' in suspicious_sample.columns:
+            suspicious_sample['timestamp'] = suspicious_sample['timestamp'].astype(str)
+        
+        # Convert to dictionary
+        suspicious_dict = suspicious_sample.to_dict(orient='records')
         
         # Get summary statistics
         summary_stats = {
-            "total_transactions": len(transaction_data),
-            "flagged_transactions": len(suspicious_transactions),
-            "flagged_percentage": round(len(suspicious_transactions) / len(transaction_data) * 100, 2),
-            "avg_transaction_amount": round(transaction_data['amount'].mean(), 2),
-            "suspicious_avg_amount": round(suspicious_transactions['amount'].mean(), 2)
+            "total_transactions": int(len(transaction_data)),
+            "flagged_transactions": int(len(suspicious_transactions)),
+            "flagged_percentage": float(round(len(suspicious_transactions) / len(transaction_data) * 100, 2)),
+            "avg_transaction_amount": float(round(transaction_data['amount'].mean(), 2)),
+            "suspicious_avg_amount": float(round(suspicious_transactions['amount'].mean(), 2))
         }
         
         # Create prompt for OpenAI
@@ -42,7 +49,7 @@ def analyze_transaction_with_ai(transaction_data, suspicious_transactions):
         {json.dumps(summary_stats)}
         
         Sample of Suspicious Transactions:
-        {json.dumps(suspicious_sample)}
+        {json.dumps(suspicious_dict)}
         
         Provide a concise fraud analysis report with:
         1. Key patterns and red flags in these transactions
@@ -136,8 +143,9 @@ def detect_fraud_and_anomalies(df):
     
     # Add time-based features if available
     if 'timestamp' in df.columns:
-        features['hour_of_day'] = df['timestamp'].dt.hour
-        features['day_of_week'] = df['timestamp'].dt.dayofweek
+        # Extract hour and day of week without using .dt.to_pydatetime()
+        features['hour_of_day'] = pd.to_numeric(df['timestamp'].dt.hour)
+        features['day_of_week'] = pd.to_numeric(df['timestamp'].dt.dayofweek)
     
     # Add other relevant features if available
     if 'location' in df.columns:
@@ -163,7 +171,9 @@ def detect_fraud_and_anomalies(df):
     
     # 2. Transactions occurring at unusual hours (if timestamp available)
     if 'timestamp' in df.columns:
-        df['unusual_hour'] = df['timestamp'].dt.hour.isin([0, 1, 2, 3, 4])
+        # Fix for datetime warning
+        hours = np.array(df['timestamp'].dt.hour)
+        df['unusual_hour'] = np.isin(hours, [0, 1, 2, 3, 4])
     else:
         df['unusual_hour'] = False
     
@@ -180,8 +190,12 @@ def detect_fraud_and_anomalies(df):
     if 'timestamp' in df.columns and ('user_id' in df.columns or 'account_id' in df.columns):
         id_col = 'user_id' if 'user_id' in df.columns else 'account_id'
         df = df.sort_values([id_col, 'timestamp'])
-        # Fix for deprecation warning - convert to float explicitly
-        df['time_diff'] = df.groupby(id_col)['timestamp'].diff().dt.total_seconds().fillna(0).astype(float)
+        
+        # Fix for datetime warning by using numpy arrays
+        time_diffs = df.groupby(id_col)['timestamp'].diff()
+        # Convert to seconds and handle NaN values
+        seconds = np.array([td.total_seconds() if pd.notnull(td) else 0 for td in time_diffs])
+        df['time_diff'] = seconds
         df['rapid_succession'] = df['time_diff'] < 300  # Less than 5 minutes
     else:
         df['rapid_succession'] = False
@@ -205,9 +219,14 @@ def create_visualizations(df):
     visualizations = {}
     
     try:
+        # Convert timestamp to string for plotly to avoid datetime warning
+        plot_df = df.copy()
+        if 'timestamp' in plot_df.columns:
+            plot_df['timestamp_str'] = plot_df['timestamp'].dt.strftime('%Y-%m-%d %H:%M:%S')
+        
         # 1. Distribution of transaction amounts with anomalies highlighted
         fig1 = px.histogram(
-            df, x='amount', color='is_suspicious',
+            plot_df, x='amount', color='is_suspicious',
             color_discrete_map={True: 'red', False: 'blue'},
             title='Distribution of Transaction Amounts',
             labels={'amount': 'Transaction Amount', 'is_suspicious': 'Suspicious'}
@@ -217,19 +236,19 @@ def create_visualizations(df):
         visualizations['amount_distribution'] = fig1
         
         # 2. Time series of transaction amounts
-        if 'timestamp' in df.columns:
+        if 'timestamp' in plot_df.columns:
             fig2 = px.scatter(
-                df, x='timestamp', y='amount', color='is_suspicious',
+                plot_df, x='timestamp_str', y='amount', color='is_suspicious',
                 color_discrete_map={True: 'red', False: 'blue'},
                 title='Transaction Amounts Over Time',
-                labels={'amount': 'Transaction Amount', 'timestamp': 'Time', 'is_suspicious': 'Suspicious'}
+                labels={'amount': 'Transaction Amount', 'timestamp_str': 'Time', 'is_suspicious': 'Suspicious'}
             )
             fig2.update_layout(height=500, width=700)
             visualizations['time_series'] = fig2
         
         # 3. Fraud score distribution
         fig3 = px.histogram(
-            df, x='fraud_score',
+            plot_df, x='fraud_score',
             title='Distribution of Fraud Scores',
             labels={'fraud_score': 'Fraud Score'}
         )
@@ -237,12 +256,14 @@ def create_visualizations(df):
         visualizations['fraud_score_dist'] = fig3
         
         # 4. Hourly transaction pattern (if timestamp available)
-        if 'timestamp' in df.columns:
-            hourly_data = df.groupby([df['timestamp'].dt.hour, 'is_suspicious']).size().reset_index()
-            hourly_data.columns = ['hour', 'is_suspicious', 'count']  # Rename columns
+        if 'timestamp' in plot_df.columns:
+            # Fixed approach to get hourly data
+            hourly_counts = plot_df.groupby([plot_df['timestamp'].dt.hour, 'is_suspicious']).size()
+            hourly_df = hourly_counts.reset_index()
+            hourly_df.columns = ['hour', 'is_suspicious', 'count']
             
             fig4 = px.line(
-                hourly_data, x='hour', y='count', color='is_suspicious',
+                hourly_df, x='hour', y='count', color='is_suspicious',
                 color_discrete_map={True: 'red', False: 'blue'},
                 title='Hourly Transaction Pattern',
                 labels={'hour': 'Hour of Day', 'count': 'Number of Transactions', 'is_suspicious': 'Suspicious'}
@@ -308,7 +329,9 @@ def process_transactions(file):
         )
     
     except Exception as e:
-        return f"Error: {str(e)}", None, None, None, None, None
+        import traceback
+        error_trace = traceback.format_exc()
+        return f"Error: {str(e)}\n\nTrace: {error_trace}", None, None, None, None, None
 
 def create_gradio_interface():
     """Create Gradio interface for the application"""
@@ -347,29 +370,10 @@ def create_gradio_interface():
     
     return app
 
-# For debugging purposes, set this to True to see more detailed error messages
-def enable_debug_mode():
+if __name__ == "__main__":
+    # Enable debug mode to get detailed error messages
     import logging
     logging.basicConfig(level=logging.DEBUG)
     
-    # Override process_transactions to catch and log all exceptions
-    global process_transactions
-    original_process_transactions = process_transactions
-    
-    def debug_process_transactions(*args, **kwargs):
-        try:
-            return original_process_transactions(*args, **kwargs)
-        except Exception as e:
-            import traceback
-            error_trace = traceback.format_exc()
-            logging.error(f"Exception in process_transactions: {error_trace}")
-            return f"Error: {str(e)}\n\nFull traceback:\n{error_trace}", None, None, None, None, None
-    
-    process_transactions = debug_process_transactions
-
-if __name__ == "__main__":
-    # Uncomment to enable debug mode
-    # enable_debug_mode()
-    
     app = create_gradio_interface()
     app.launch(share=True)