Update app.py

app.py

@@ -26,8 +26,8 @@ def standardize_dataframe(df: pd.DataFrame) -> pd.DataFrame:
     Standardize DataFrame column names and data types.
     - Renames synonyms to common names (e.g., tin, salary).
     - Creates an employee_name column if missing but first_name and last_name exist.
-    - Converts the salary column to numeric.
     - Combines duplicate key columns (e.g., multiple 'salary' or 'tin' columns) into one.
+    - Ensures key columns 'tin' and 'employee_name' are strings.
     """
     rename_map = {}
 
@@ -51,7 +51,6 @@ def standardize_dataframe(df: pd.DataFrame) -> pd.DataFrame:
     # Combine duplicate columns for 'salary'
     if 'salary' in df.columns and list(df.columns).count('salary') > 1:
         salary_cols = [col for col in df.columns if col == 'salary']
-        # Use backfill across the duplicate columns and take the first non-null value
         df['salary'] = df[salary_cols].bfill(axis=1).iloc[:, 0]
         df = df.loc[:, ~df.columns.duplicated()]
 
@@ -69,6 +68,12 @@ def standardize_dataframe(df: pd.DataFrame) -> pd.DataFrame:
     if 'salary' in df.columns:
         df['salary'] = pd.to_numeric(df['salary'], errors='coerce')
 
+    # Ensure key columns are strings for consistency
+    if 'tin' in df.columns:
+        df['tin'] = df['tin'].astype(str)
+    if 'employee_name' in df.columns:
+        df['employee_name'] = df['employee_name'].astype(str)
+
     return df