Update app.py

app.py

@@ -46,9 +46,9 @@ def safe_display_df(df: pd.DataFrame) -> pd.DataFrame:
 def main():
     st.title("Merge Employee Name from Earnings into PAYE Sheet")
     st.write(
-        "Upload an Earnings Sheet and a PAYE Sheet. "
-        "The app will extract the first two columns (TIN and Employee Name) from the Earnings Sheet, "
-        "clean and standardize the TIN values, and then merge the Employee Name onto the PAYE sheet using the TIN."
+        "Upload an Earnings Sheet and a PAYE Sheet. The app will extract the first two columns "
+        "(TIN and Employee Name) from the Earnings Sheet, skipping the first row which contains currency labels, "
+        "and merge the Employee Name onto the PAYE sheet using the cleaned TIN."
     )
 
     earnings_file = st.file_uploader("Upload Earnings Sheet", type=["csv", "xlsx", "xls"], key="earnings")
@@ -73,17 +73,17 @@ def main():
             return
 
         # Extract first two columns from earnings file.
-        # Assume first column is TIN and second is Employee Name.
-        earnings_subset = earnings_df.iloc[:, :2].copy()
+        # Skip the first row (assumed to contain currency labels) using .iloc[1:]
+        earnings_subset = earnings_df.iloc[1:, :2].copy()
         earnings_subset.columns = ["tin", "employee_name"]
         # Ensure values are stripped of trailing spaces
         earnings_subset["tin"] = earnings_subset["tin"].astype(str).str.strip()
         earnings_subset["employee_name"] = earnings_subset["employee_name"].astype(str).str.strip()
 
-        st.write("Preview of extracted TIN and Employee Name from Earnings Sheet:")
+        st.write("Preview of extracted TIN and Employee Name from Earnings Sheet (first 5 rows after skipping currency row):")
         st.dataframe(safe_display_df(earnings_subset.head()))
 
-        # Verify the PAYE sheet has a 'tin' column
+        # Verify the PAYE sheet has a 'tin' column.
         if "tin" not in paye_df.columns:
             st.error("The PAYE sheet does not have a recognized TIN column (e.g., 'tin' or 'personal id').")
             return