Update app.py

app.py

@@ -1,4 +1,5 @@
 import pandas as pd
+import numpy as np
 import os
 import warnings
 import gradio as gr
@@ -42,9 +43,10 @@ class ExcelPandasAgent:
             for sheet_name in sheet_names:
                 try:
                     df = pd.read_excel(file_path, sheet_name=sheet_name)
+                    # The cleaning function is called here for each sheet
                     df = self._clean_dataframe(df)
                     self.excel_data[sheet_name] = df
-                    self.logs.append(f"  - Indexed sheet '{sheet_name}' ({df.shape[0]} rows × {df.shape[1]} columns)")
+                    self.logs.append(f"  - Indexed and cleaned sheet '{sheet_name}' ({df.shape[0]} rows × {df.shape[1]} columns)")
                 except Exception as e:
                     self.logs.append(f"⚠️ Error loading sheet '{sheet_name}': {str(e)}")
                     continue
@@ -55,19 +57,22 @@ class ExcelPandasAgent:
             raise Exception(f"Error loading Excel file: {str(e)}")
 
     def _clean_dataframe(self, df: pd.DataFrame) -> pd.DataFrame:
-        """Cleans a DataFrame by removing empty rows/columns."""
+        """
+        Cleans a DataFrame by removing empty rows/columns and robustly converting types.
+        """
         df = df.dropna(how='all').dropna(axis=1, how='all').reset_index(drop=True)
-        # Attempt to convert object columns to numeric or datetime where possible
         for col in df.columns:
+            # Apply to object columns that might contain mixed numeric/text data
             if df[col].dtype == 'object':
-                try:
-                    df[col] = pd.to_numeric(df[col], errors='ignore')
-                except:
-                    pass
-                try:
-                    df[col] = pd.to_datetime(df[col], errors='ignore')
-                except:
-                    pass
+                # This is the key change. It attempts to convert the column
+                # to numbers. Any value that fails (like 'Apr') becomes NaN (Not a Number).
+                df[col] = pd.to_numeric(df[col], errors='coerce')
+
+        # Now, find all numeric columns (including those just converted)
+        # and fill any resulting NaN values with 0. This prepares them for calculations.
+        for col in df.select_dtypes(include=np.number).columns:
+            df[col] = df[col].fillna(0)
+
         return df
 
     def query_sheet(self, query: str, sheet_name: str) -> str:
@@ -85,8 +90,8 @@ class ExcelPandasAgent:
                 self.llm,
                 df,
                 verbose=True,
-                max_iterations=50,                  # <-- Correct placement
-                max_execution_time=300,             # <-- Correct placement
+                max_iterations=50,
+                max_execution_time=300,
                 agent_executor_kwargs={"handle_parsing_errors": True},
                 allow_dangerous_code=True
             )