Update dataframe.py (#8)

- Update dataframe.py (0ddcbc8b197e7eed005e7377ee4098f2e96b2a19)

dataframe.py

@@ -1,27 +1,28 @@
 import pandas as pd
 import streamlit as st
 
-def process_dataframe(ods_file):
+def prepare_dataframe(file):
     try:
         # Read the .ods file into a DataFrame
-        df = pd.read_excel(ods_file, engine='odf')
+        df = pd.read_excel(file, engine='odf')
 
-        # Clean up unnecessary columns and rows
+        # Clean the DataFrame
         df.drop(columns=["Unnamed: 0", "Unnamed: 1"], inplace=True, errors='ignore')
         df.dropna(how='all', inplace=True)
         df.reset_index(drop=True, inplace=True)
 
-        # Identify and set the header row
+        # Identify the header row and reformat the DataFrame
         for idx, row in df.iterrows():
             if row['Unnamed: 2'] == 'Application Number' and row['Unnamed: 3'] == 'Decision':
                 df.columns = ['Application Number', 'Decision']
-                df = df.iloc[idx + 1:]
+                df = df.iloc[idx + 1:]  # Skip the header row
                 break
 
-        # Convert application numbers to strings
+        # Reset the index and convert the Application Number to integers
         df.reset_index(drop=True, inplace=True)
-        df['Application Number'] = df['Application Number'].astype(str)
+        df['Application Number'] = df['Application Number'].astype(str).str.strip()
+
         return df
     except Exception as e:
-        st.error(f"Error processing the data: {e}")
-        return pd.DataFrame()  # Return an empty DataFrame on failure
+        st.error(f"Error preparing the DataFrame: {e}")
+        return None