Update app.py

app.py

@@ -11,6 +11,7 @@ from sklearn.preprocessing import StandardScaler
 import openai
 from datetime import datetime, timedelta
 import json
+import tempfile
 
 # Set OpenAI API key from Hugging Face Spaces secrets
 openai.api_key = os.environ.get("OPENAI_API_KEY")
@@ -179,7 +180,8 @@ 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'])
-        df['time_diff'] = df.groupby(id_col)['timestamp'].diff().dt.total_seconds().fillna(0)
+        # Fix for deprecation warning - convert to float explicitly
+        df['time_diff'] = df.groupby(id_col)['timestamp'].diff().dt.total_seconds().fillna(0).astype(float)
         df['rapid_succession'] = df['time_diff'] < 300  # Less than 5 minutes
     else:
         df['rapid_succession'] = False
@@ -202,43 +204,54 @@ def create_visualizations(df):
     """Create visualizations for transaction data and anomalies"""
     visualizations = {}
     
-    # 1. Distribution of transaction amounts with anomalies highlighted
-    fig1 = px.histogram(
-        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'}
-    )
-    visualizations['amount_distribution'] = fig1
-    
-    # 2. Time series of transaction amounts
-    if 'timestamp' in df.columns:
-        fig2 = px.scatter(
-            df, x='timestamp', y='amount', color='is_suspicious',
+    try:
+        # 1. Distribution of transaction amounts with anomalies highlighted
+        fig1 = px.histogram(
+            df, x='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'}
+            title='Distribution of Transaction Amounts',
+            labels={'amount': 'Transaction Amount', 'is_suspicious': 'Suspicious'}
         )
-        visualizations['time_series'] = fig2
-    
-    # 3. Fraud score distribution
-    fig3 = px.histogram(
-        df, x='fraud_score',
-        title='Distribution of Fraud Scores',
-        labels={'fraud_score': 'Fraud Score'}
-    )
-    visualizations['fraud_score_dist'] = fig3
-    
-    # 4. Hourly transaction pattern (if timestamp available)
-    if 'timestamp' in df.columns:
-        hourly_counts = df.groupby([df['timestamp'].dt.hour, 'is_suspicious']).size().reset_index(name='count')
-        fig4 = px.line(
-            hourly_counts, x='timestamp', y='count', color='is_suspicious',
-            color_discrete_map={True: 'red', False: 'blue'},
-            title='Hourly Transaction Pattern',
-            labels={'timestamp': 'Hour of Day', 'count': 'Number of Transactions', 'is_suspicious': 'Suspicious'}
+        # Ensure the figure is fully rendered
+        fig1.update_layout(height=500, width=700)
+        visualizations['amount_distribution'] = fig1
+        
+        # 2. Time series of transaction amounts
+        if 'timestamp' in df.columns:
+            fig2 = px.scatter(
+                df, x='timestamp', 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'}
+            )
+            fig2.update_layout(height=500, width=700)
+            visualizations['time_series'] = fig2
+        
+        # 3. Fraud score distribution
+        fig3 = px.histogram(
+            df, x='fraud_score',
+            title='Distribution of Fraud Scores',
+            labels={'fraud_score': 'Fraud Score'}
         )
-        visualizations['hourly_pattern'] = fig4
+        fig3.update_layout(height=500, width=700)
+        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
+            
+            fig4 = px.line(
+                hourly_data, 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'}
+            )
+            fig4.update_layout(height=500, width=700)
+            visualizations['hourly_pattern'] = fig4
+    
+    except Exception as e:
+        print(f"Error in visualization creation: {str(e)}")
     
     return visualizations
 
@@ -279,11 +292,16 @@ def process_transactions(file):
         # Get AI analysis of suspicious transactions
         ai_analysis = analyze_transaction_with_ai(df_with_anomalies, suspicious_transactions)
         
+        # Save suspicious transactions to a temporary file
+        temp_csv = tempfile.NamedTemporaryFile(delete=False, suffix='.csv')
+        suspicious_transactions.to_csv(temp_csv.name, index=False)
+        temp_csv.close()
+        
         # Return results and visualizations
         return (
             stats_summary,
             ai_analysis,
-            suspicious_transactions.to_csv(index=False),
+            temp_csv.name,  # Return the path to the temporary file
             visualizations.get('amount_distribution', None),
             visualizations.get('time_series', None),
             visualizations.get('fraud_score_dist', None)
@@ -329,6 +347,29 @@ def create_gradio_interface():
     
     return app
 
+# For debugging purposes, set this to True to see more detailed error messages
+def enable_debug_mode():
+    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)