Summary Added

app.py

@@ -69,18 +69,40 @@ def get_data_df(schema):
     print('Getting Dataframe from the Database')
     return conn.sql(f"SELECT * FROM {schema} LIMIT 1000").df()
 
+def df_summary(df):
+    summary = []
+
+    for column in df.columns:
+        if pd.api.types.is_numeric_dtype(df[column]):
+            summary.append({
+                "column": column,
+                "max": df[column].max(),
+                "min": df[column].min(),
+                "count": df[column].count(),
+                "nunique": df[column].nunique(),
+                "dtype": str(df[column].dtype),
+                "top": None
+            })
+            
+        elif pd.api.types.is_categorical_dtype(df[column]) or pd.api.types.is_object_dtype(df[column]):
+            top_value = df[column].mode().iloc[0] if not df[column].mode().empty else None
+            
+            summary.append({
+                "column": column,
+                "max": None,  
+                "min": None, 
+                "count": df[column].count(),
+                "nunique": df[column].nunique(),
+                "dtype": str(df[column].dtype),
+                "top": top_value
+            })
+    summary_df = pd.DataFrame(summary)
+    return summary_df.reset_index(drop=True)
 
 def format_prompt(df):
-    summary_df = pd.DataFrame({
-        "max": df.max(),
-        "min": df.min(),
-        "top": df.mode().iloc[0],
-        "nunique": df.nunique(),
-        "count": df.count(),
-        "dtype": df.dtypes.astype(str)
-        }).reset_index().rename(columns={"index": "column"})
+    summary = df_summary(df)
     return prompt_autogenerate.format_prompt(data=df.head().to_json(orient='records'),
-                                           summary=summary_df.to_json(orient='records'))
+                                           summary=summary.to_json(orient='records'))
 def format_user_prompt(df):
     return prompt_user_input.format_prompt(data=df.head().to_json(orient='records'))