Refactor contest data handling in `app.py` and `find_name_mismatches.py` for improved functionality

- Removed the position dictionary from the data returned by `load_file`, simplifying the data structure.
- Updated the `find_name_mismatches` function to use `contest_df` instead of `portfolio_df`, enhancing clarity in variable naming.
- Adjusted the logic in `app.py` to ensure proper handling of projections and contest data, including the addition of name matching analysis.

app.py

@@ -31,7 +31,7 @@ with tab1:
             del st.session_state['Contest']
 
         if Contest_file:
-            st.session_state['Contest'], st.session_state['position_dict'], st.session_state['ownership_dict'], st.session_state['entry_list'] = load_file(Contest_file)
+            st.session_state['Contest'], st.session_state['ownership_dict'], st.session_state['entry_list'] = load_file(Contest_file)
             st.session_state['Contest'] = st.session_state['Contest'].dropna(how='all')
             st.session_state['Contest'] = st.session_state['Contest'].reset_index(drop=True)
             if st.session_state['Contest'] is not None:
@@ -67,39 +67,16 @@ with tab1:
                 st.success('Projections file loaded successfully!')
                 st.dataframe(projections.head(10))
 
-    # if Contest_file and projections_file:
-    #     if st.session_state['Contest'] is not None and projections is not None:
-    #         st.subheader("Name Matching Analysis")
-    #         # Initialize projections_df in session state if it doesn't exist
-    #         if 'projections_df' not in st.session_state:
-    #             st.session_state['projections_df'] = projections.copy()
-    #             st.session_state['projections_df']['salary'] = (st.session_state['projections_df']['salary'].astype(str).str.replace(',', '').astype(float).astype(int))
+    if Contest_file and projections_file:
+        if st.session_state['Contest'] is not None and projections is not None:
+            st.subheader("Name Matching Analysis")
+            # Initialize projections_df in session state if it doesn't exist
+            if 'projections_df' not in st.session_state:
+                st.session_state['projections_df'] = projections.copy()
+                st.session_state['projections_df']['salary'] = (st.session_state['projections_df']['salary'].astype(str).str.replace(',', '').astype(float).astype(int))
             
-    #         # Update projections_df with any new matches
-    #         st.session_state['projections_df'] = find_name_mismatches(st.session_state['Contest'], st.session_state['projections_df'])
-    #         if csv_file is not None and 'export_dict' not in st.session_state:
-    #                 # Create a dictionary of Name to Name+ID from csv_file
-    #                 try:
-    #                     name_id_map = dict(zip(
-    #                         st.session_state['csv_file']['Name'], 
-    #                         st.session_state['csv_file']['Name + ID']
-    #                     ))
-    #                 except:
-    #                     name_id_map = dict(zip(
-    #                         st.session_state['csv_file']['Nickname'], 
-    #                         st.session_state['csv_file']['Id']
-    #                     ))
-                    
-    #                 # Function to find best match
-    #                 def find_best_match(name):
-    #                     best_match = process.extractOne(name, name_id_map.keys())
-    #                     if best_match and best_match[1] >= 85:  # 85% match threshold
-    #                         return name_id_map[best_match[0]]
-    #                     return name  # Return original name if no good match found
-                    
-    #                 # Apply the matching
-    #                 projections['upload_match'] = projections['player_names'].apply(find_best_match)
-    #                 st.session_state['export_dict'] = dict(zip(projections['player_names'], projections['upload_match']))
+            # Update projections_df with any new matches
+            st.session_state['projections_df'] = find_name_mismatches(st.session_state['Contest'], st.session_state['projections_df'])
 
 with tab2:
     if st.button('Clear data', key='reset3'):

global_func/find_name_mismatches.py

@@ -4,12 +4,11 @@ import pandas as pd
 import time
 from fuzzywuzzy import process
 
-def find_name_mismatches(portfolio_df, projections_df):
+def find_name_mismatches(contest_df, projections_df):
     # Create a copy of the projections dataframe to avoid modifying the original
     projections_df = projections_df.copy()
     
-    col_count = len(portfolio_df.columns)
-    portfolio_df.columns = range(col_count)
+    name_columns = [col for col in contest_df.columns if not col in ['BaseName', 'EntryCount']]
     
     if 'player_names' not in projections_df.columns:
         st.error("No 'player_names' column found in projections file")
@@ -17,8 +16,8 @@ def find_name_mismatches(portfolio_df, projections_df):
     
     # Get unique player names from portfolio and projections
     portfolio_players = set()
-    for col in portfolio_df.columns:
-        portfolio_players.update(portfolio_df[col].unique())
+    for col in name_columns:
+        portfolio_players.update(contest_df[col].unique())
     projection_players = set(projections_df['player_names'].unique())
     projection_players_list = list(projection_players)
     

global_func/load_file.py

@@ -45,13 +45,12 @@ def load_file(upload):
                 df[i] = df['Lineup'].str.split(',').str[i].str.strip()
                 # Remove position indicators from the end of each entry
                 df[i] = df[i].str.replace(r'\s+(' + '|'.join(pos_values) + r')$', '', regex=True)
-            position_dict = dict(zip(df['Player'], df['Pos']))
             ownership_dict = dict(zip(df['Player'], df['Own']))
             cleaned_df = df.drop(columns=['EntryId', 'EntryName', 'TimeRemaining', 'Points', 'Lineup', 'Player', 'Pos', 'Own', 'FPTS'])
             entry_list = list(set(df['BaseName']))
             entry_list.sort()
             
-            return cleaned_df, position_dict, ownership_dict, entry_list
+            return cleaned_df, ownership_dict, entry_list
         except Exception as e:
             st.error(f'Error loading file: {str(e)}')
             return None