Remove redundant NaN logging from 'Data Load' section of 'app.py' and add initial data load debug statements in 'load_ss_file.py' to enhance data validation and transparency during file loading.

app.py

@@ -310,15 +310,6 @@ if selected_tab == 'Data Load':
                     st.session_state['export_portfolio'] = st.session_state['export_portfolio'].dropna(how='all')
                     st.session_state['export_portfolio'] = st.session_state['export_portfolio'].reset_index(drop=True)
                     print(st.session_state['portfolio'].isna().sum())
-                    st.write(f"Total rows before dropping NaN: {len(st.session_state['portfolio'])}")
-                    st.write("NaN count per column:")
-                    st.write(st.session_state['portfolio'].isna().sum())
-
-                    rows_with_na = st.session_state['portfolio'][st.session_state['portfolio'].isna().any(axis=1)]
-                    st.write(f"Number of rows with at least one NaN: {len(rows_with_na)}")
-                    if len(rows_with_na) > 0:
-                        st.write("Sample of rows with NaN values:")
-                        st.dataframe(rows_with_na.head(10))
                     st.session_state['portfolio'] = st.session_state['portfolio'].dropna(how='all')
                     st.session_state['portfolio'] = st.session_state['portfolio'].reset_index(drop=True)
                 elif upload_toggle == 'Draftkings/Fanduel (Names + IDs)':

global_func/load_ss_file.py

@@ -96,6 +96,16 @@ def load_ss_file(lineups, csv_file, site_var, type_var, sport_var):
         
         if clean_name.endswith('.csv'):
             lineups_df = pd.read_csv(lineups)
+            # Debug: Check what we loaded initially
+            print(f"Initial load - Total rows: {len(lineups_df)}")
+            print(f"Initial load - Total columns: {len(lineups_df.columns)}")
+            print("First few rows of raw data:")
+            print(lineups_df.head())
+            print("Data types:")
+            print(lineups_df.dtypes)
+            print("Any NaN values in original data:")
+            print(lineups_df.isna().sum())
+            
             lineups_df = lineups_df.replace(0, np.nan)
         elif clean_name.endswith(('.xls', '.xlsx')):
             lineups_df = pd.read_excel(lineups)