Update main.py

main.py

@@ -546,6 +546,50 @@ def read_any_excel(content: bytes) -> pd.DataFrame:
         logger.error(f"Excel reading failed: {str(e)}")
         raise HTTPException(422, f"Could not process Excel file: {str(e)}")
 
+
+def clean_and_convert_data(df: pd.DataFrame) -> pd.DataFrame:
+    """
+    Clean and convert data types in a DataFrame with proper error handling
+    """
+    df_clean = df.copy()
+    
+    for col in df_clean.columns:
+        # Try numeric conversion with proper error handling
+        try:
+            numeric_vals = pd.to_numeric(df_clean[col])
+            df_clean[col] = numeric_vals
+            continue  # Skip to next column if successful
+        except (ValueError, TypeError):
+            pass
+        
+        # Try datetime conversion with format inference
+        try:
+            # First try ISO format
+            datetime_vals = pd.to_datetime(df_clean[col], format='ISO8601')
+            df_clean[col] = datetime_vals
+            continue
+        except (ValueError, TypeError):
+            try:
+                # Fallback to mixed format
+                datetime_vals = pd.to_datetime(df_clean[col], format='mixed')
+                df_clean[col] = datetime_vals
+                continue
+            except (ValueError, TypeError):
+                pass
+        
+        # Clean string columns
+        if df_clean[col].dtype == object:
+            df_clean[col] = (
+                df_clean[col]
+                .astype(str)
+                .str.strip()
+                .replace(['nan', 'None', 'NaT', ''], pd.NA)
+            )
+    
+    return df_clean
+
+
+    
 def is_date_like(s: str) -> bool:
     """Helper to detect date-like strings"""
     date_patterns = [
@@ -771,65 +815,6 @@ async def question_answering(
         logger.error(f"QA processing failed: {str(e)}")
         raise HTTPException(500, detail=f"Analysis failed: {str(e)}")
 
-@app.post("/visualize/code")
-@limiter.limit("5/minute")
-async def visualize_with_code(
-    request: Request,
-    file: UploadFile = File(...),
-    chart_type: str = Form(...),
-    x_column: Optional[str] = Form(None),
-    y_column: Optional[str] = Form(None),
-    hue_column: Optional[str] = Form(None),
-    title: Optional[str] = Form(None),
-    x_label: Optional[str] = Form(None),
-    y_label: Optional[str] = Form(None),
-    style: str = Form("seaborn-v0_8"),  # Updated default
-    filters: Optional[str] = Form(None)
-):
-    try:
-        file_ext, content = await process_uploaded_file(file)
-
-        if file_ext not in {"xlsx", "xls"}:
-            raise HTTPException(400, "Visualization is only supported for Excel files")
-
-        df = pd.read_excel(io.BytesIO(content))
-
-        if df.empty:
-            raise HTTPException(400, "The uploaded Excel file is empty")
-
-        # Convert filters from string to dictionary safely
-        filters_dict = None
-        if filters:
-            try:
-                filters_dict = ast.literal_eval(filters)
-                if not isinstance(filters_dict, dict):
-                    raise ValueError()
-            except Exception:
-                raise HTTPException(400, "Invalid format for filters. Must be a valid dictionary string.")
-
-        viz_request = VisualizationRequest(
-            chart_type=chart_type,
-            x_column=x_column,
-            y_column=y_column,
-            hue_column=hue_column,
-            title=title,
-            x_label=x_label,
-            y_label=y_label,
-            style=style,
-            filters=filters_dict
-        )
-
-        code = generate_visualization_code(df, viz_request)
-        return {"code": code}
-
-    except HTTPException:
-        raise
-    except Exception as e:
-        logger.error(f"Visualization code generation failed: {str(e)}")
-        raise HTTPException(500, f"Visualization code generation failed: {str(e)}")
-
-from fastapi.responses import FileResponse  # Add this import at the top
-
 
      
 # [Previous imports remain exactly the same...]