Update app.py

app.py

@@ -1,5 +1,6 @@
 import os
-from typing import Optional
+import json
+from typing import Optional, Dict
 
 import gradio as gr
 import pandas as pd
@@ -9,6 +10,29 @@ from components.analysis import DataAnalyzer
 from components.statistical import StatisticalAnalyzer
 from components.visualization import D3Visualizer
 
+def parse_gpt_response(response: str) -> Dict:
+    """Safely parse GPT response into analysis request"""
+    try:
+        # Try to fix common JSON issues
+        cleaned_response = response.replace("```json\n", "").replace("```", "")
+        cleaned_response = cleaned_response.strip()
+        if not cleaned_response.startswith("{"):
+            # Extract JSON if it's embedded in text
+            start = cleaned_response.find("{")
+            end = cleaned_response.rfind("}") + 1
+            if start >= 0 and end > 0:
+                cleaned_response = cleaned_response[start:end]
+        
+        # Parse JSON
+        return json.loads(cleaned_response)
+    except json.JSONDecodeError:
+        # Fallback to default analysis
+        return {
+            "analysis_type": "distribution",
+            "params": {"column": "all"},
+            "explanation": "Performing basic distribution analysis as fallback."
+        }
+
 def analyze_data(
     file: gr.File,
     query: str,
@@ -53,11 +77,19 @@ def analyze_data(
             {
                 "role": "system",
                 "content": """You are a data analysis assistant. 
-                Interpret the user's query and determine which analysis to perform.
-                Return a JSON with:
-                - analysis_type: distribution, forecast, or correlation
-                - params: dictionary of parameters needed
-                - explanation: why this analysis is appropriate"""
+                Interpret the user's query and provide analysis details in JSON format.
+                
+                Return ONLY a JSON object with these fields:
+                {
+                    "analysis_type": "distribution" or "forecast" or "correlation",
+                    "params": {"column": "column_name", ...},
+                    "explanation": "why this analysis is appropriate"
+                }
+                
+                For timeseries data, prefer 'forecast' type.
+                For multiple columns, prefer 'correlation' type.
+                For single column analysis, prefer 'distribution' type.
+                """
             },
             {
                 "role": "user",
@@ -72,7 +104,14 @@ def analyze_data(
         )
         
         # Parse response and perform analysis
-        analysis_request = eval(response.choices[0].message.content)
+        analysis_request = parse_gpt_response(response.choices[0].message.content)
+        
+        # Set default column if not specified
+        if "params" not in analysis_request:
+            analysis_request["params"] = {}
+        if "column" not in analysis_request["params"]:
+            analysis_request["params"]["column"] = df.select_dtypes(include=['number']).columns[0]
+        
         result = analyzer.analyze_data(
             df,
             analysis_request["analysis_type"],
@@ -102,7 +141,9 @@ def analyze_data(
         return html_output
         
     except Exception as e:
-        return f"Error occurred: {str(e)}"
+        import traceback
+        error_details = traceback.format_exc()
+        return f"Error occurred: {str(e)}\n\nDetails:\n{error_details}"
 
 def create_interface():
     """Create Gradio interface"""