Update app.py

app.py

@@ -518,6 +518,84 @@ def create_visualizations(df, column_mapping):
     
     return visualizations
 
+def analyze_transaction_with_ai(transaction_data, suspicious_transactions, column_mapping):
+    """Use OpenAI to analyze suspicious transactions and provide insights"""
+    if not openai.api_key:
+        return "OpenAI API key not found. Please add it to the Hugging Face Spaces secrets."
+    
+    try:
+        # Prepare information for OpenAI, converting to a JSON-serializable format
+        suspicious_sample = suspicious_transactions.head(5).copy()
+        
+        # Convert any datetime columns to string format to make it JSON serializable
+        for col in suspicious_sample.columns:
+            if pd.api.types.is_datetime64_any_dtype(suspicious_sample[col]):
+                suspicious_sample[col] = suspicious_sample[col].astype(str)
+            # Convert NumPy types to Python native types
+            elif suspicious_sample[col].dtype in (np.int64, np.float64):
+                suspicious_sample[col] = suspicious_sample[col].astype(float)
+            # Handle boolean columns
+            elif suspicious_sample[col].dtype == bool:
+                suspicious_sample[col] = suspicious_sample[col].astype(str)
+        
+        # Convert to dictionary
+        suspicious_dict = suspicious_sample.to_dict(orient='records')
+        
+        # Get summary statistics
+        summary_stats = {
+            "total_transactions": int(len(transaction_data)),
+            "flagged_transactions": int(len(suspicious_transactions)),
+            "flagged_percentage": float(round(len(suspicious_transactions) / len(transaction_data) * 100, 2)),
+        }
+        
+        # Add amount-related statistics if available
+        amount_col = column_mapping.get("amount_column")
+        if amount_col and amount_col in transaction_data.columns:
+            summary_stats.update({
+                "avg_transaction_amount": float(round(transaction_data[amount_col].mean(), 2)),
+                "suspicious_avg_amount": float(round(suspicious_transactions[amount_col].mean(), 2))
+            })
+        
+        # Create prompt for OpenAI
+        prompt = f"""
+        Analyze these potentially fraudulent transactions and identify patterns or anomalies:
+        
+        Transaction Data Summary:
+        {json.dumps(summary_stats)}
+        
+        Column Mapping:
+        {json.dumps(column_mapping)}
+        
+        Sample of Suspicious Transactions:
+        {json.dumps(suspicious_dict)}
+        
+        Provide a concise fraud analysis report with:
+        1. Key patterns and red flags in these transactions
+        2. Possible fraud scenarios explaining the anomalies
+        3. Recommended next steps for investigation
+        """
+        
+        # Create an OpenAI client with the API key
+        client = openai.OpenAI(api_key=openai.api_key)
+        
+        # Call OpenAI API
+        response = client.chat.completions.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are a fraud detection expert helping analyze suspicious financial transactions."},
+                {"role": "user", "content": prompt}
+            ],
+            max_tokens=800
+        )
+        
+        # Return the AI analysis
+        return response.choices[0].message.content
+    
+    except Exception as e:
+        import traceback
+        error_trace = traceback.format_exc()
+        return f"Error in AI analysis: {str(e)}\n\nTrace: {error_trace}"    
+
 def process_transactions(file):
     """Main function to process transaction data and detect fraud"""
     try: