Refactor app.py and find_name_mismatches.py for improved clarity and functionality

- Updated app.py to streamline session state usage for contest and projections data, enhancing readability and maintainability.
- Improved the find_name_mismatches function by directly modifying input dataframes, reducing unnecessary copies and improving performance.
- Enhanced user feedback with success messages upon successful file loading and name matching, improving overall user experience.

app.py

@@ -35,12 +35,12 @@ with tab1:
             del st.session_state['Contest']
 
         if Contest_file:
-            contest_base, ownership_df, fpts_df, st.session_state['entry_list'] = load_contest_file(Contest_file, sport_select)
-            contest_base = contest_base.dropna(how='all')
-            contest_base = contest_base.reset_index(drop=True)
-            if contest_base is not None:
+            st.session_state['Contest'], st.session_state['ownership_dict'], st.session_state['actual_dict'], st.session_state['entry_list'] = load_contest_file(Contest_file, sport_select)
+            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:
                 st.success('Contest file loaded successfully!')
-                st.dataframe(contest_base.head(10))
+                st.dataframe(st.session_state['Contest'].head(10))
 
     with col2:
         st.subheader("Projections File")
@@ -66,17 +66,19 @@ with tab1:
             )
             
         if projections_file:
-            export_projections, projections = load_file(projections_file)
-            if projections is not None:
+            export_projections, st.session_state['projections_df'] = load_file(projections_file)
+            if st.session_state['projections_df'] is not None:
                 st.success('Projections file loaded successfully!')
-                st.dataframe(projections.head(10))
+                st.dataframe(st.session_state['projections_df'].head(10))
 
     if Contest_file and projections_file:
         if 'Contest' not in st.session_state and 'projections_df' not in st.session_state:
-            if contest_base is not None and projections is not None:
-                st.subheader("Name Matching functions")
-                st.session_state['Contest'], st.session_state['projections_df'], ownership_dict, actual_dict = find_name_mismatches(contest_base, projections, ownership_df, fpts_df)
-                st.session_state['projections_df']['salary'] = (st.session_state['projections_df']['salary'].astype(str).str.replace(',', '').astype(float).astype(int))
+            st.subheader("Name Matching functions")
+            st.session_state['Contest'], st.session_state['projections_df'], st.session_state['ownership_dict'], st.session_state['actual_dict'] = find_name_mismatches(st.session_state['Contest'], st.session_state['projections_df'], st.session_state['ownership_dict'], st.session_state['actual_dict'])
+            st.session_state['projections_df']['salary'] = (st.session_state['projections_df']['salary'].astype(str).str.replace(',', '').astype(float).astype(int))
+            st.session_state['ownership_dict'] = dict(zip(st.session_state['ownership_dict']['Player'], st.session_state['ownership_dict']['Own']))
+            st.session_state['actual_dict'] = dict(zip(st.session_state['actual_dict']['Player'], st.session_state['actual_dict']['FPTS']))
+
 
 with tab2:
     if 'Contest' in st.session_state and 'projections_df' in st.session_state:

global_func/find_name_mismatches.py

@@ -5,23 +5,18 @@ import time
 from fuzzywuzzy import process
 
 def find_name_mismatches(contest_df, projections_df, ownership_df, fpts_df):
-    # Create a copy of the projections dataframe to avoid modifying the original
-    projections_raw = projections_df.copy()
-    contest_raw = contest_df.copy()
-    ownership_raw = ownership_df.copy()
-    fpts_raw = fpts_df.copy()
     
-    name_columns = [col for col in contest_raw.columns if not col in ['BaseName', 'EntryCount']]
+    name_columns = [col for col in contest_df.columns if not col in ['BaseName', 'EntryCount']]
     
-    if 'player_names' not in projections_raw.columns:
+    if 'player_names' not in projections_df.columns:
         st.error("No 'player_names' column found in projections file")
-        return contest_raw, projections_raw
+        return contest_df, projections_df
     
     # Get unique player names from portfolio and projections
     portfolio_players = set()
     for col in name_columns:
-        portfolio_players.update(contest_raw[col].unique())
-    projection_players = set(projections_raw['player_names'].unique())
+        portfolio_players.update(contest_df[col].unique())
+    projection_players = set(projections_df['player_names'].unique())
     portfolio_players_list = list(portfolio_players)
     projection_players_list = list(projection_players)
     
@@ -79,9 +74,9 @@ def find_name_mismatches(contest_df, projections_df, ownership_df, fpts_df):
                 # Process automatic matches
                 for projection_name, contest_name in auto_matches.items():
                     for col in name_columns:
-                        contest_raw[col] = contest_raw[col].replace(contest_name, projection_name)
-                    ownership_raw['Player'] = ownership_raw['Player'].replace(contest_name, projection_name)
-                    fpts_raw['Player'] = fpts_raw['Player'].replace(contest_name, projection_name)
+                        contest_df[col] = contest_df[col].replace(contest_name, projection_name)
+                    ownership_df['Player'] = ownership_df['Player'].replace(contest_name, projection_name)
+                    fpts_df['Player'] = fpts_df['Player'].replace(contest_name, projection_name)
                     st.write(contest_name + ' ' + projection_name)
 
                 # Process manual selections
@@ -89,26 +84,21 @@ def find_name_mismatches(contest_df, projections_df, ownership_df, fpts_df):
                     if selection != "None of these":
                         selected_name = selection.split(" (")[0]
                         for col in name_columns:
-                            contest_raw[col] = contest_raw[col].replace(selected_name, projection_name)
-                        ownership_raw['Player'] = ownership_raw['Player'].replace(selected_name, projection_name)
-                        fpts_raw['Player'] = fpts_raw['Player'].replace(selected_name, projection_name)
+                            contest_df[col] = contest_df[col].replace(selected_name, projection_name)
+                        ownership_df['Player'] = ownership_df['Player'].replace(selected_name, projection_name)
+                        fpts_df['Player'] = fpts_df['Player'].replace(selected_name, projection_name)
                         st.write(contest_name + ' ' + projection_name)
                         st.success(f"Replaced '{selected_name}' with '{projection_name}'")
                 
-                ownership_dict = dict(zip(ownership_raw['Player'], ownership_raw['Own']))
-                fpts_dict = dict(zip(fpts_raw['Player'], fpts_raw['FPTS']))
-                
                 st.success("All changes applied successfully!")
-                return contest_raw, projections_raw, ownership_dict, fpts_dict
+                return contest_df, projections_df, ownership_df, fpts_df
     else:
         st.success("All players have been automatically matched!")
         # Apply automatic matches
         for projection_name, contest_name in auto_matches.items():
             for col in name_columns:
-                contest_raw[col] = contest_raw[col].replace(contest_name, projection_name)
-            ownership_raw['Player'] = ownership_raw['Player'].replace(contest_name, projection_name)
-            fpts_raw['Player'] = fpts_raw['Player'].replace(contest_name, projection_name)
+                contest_df[col] = contest_df[col].replace(contest_name, projection_name)
+            ownership_df['Player'] = ownership_df['Player'].replace(contest_name, projection_name)
+            fpts_df['Player'] = fpts_df['Player'].replace(contest_name, projection_name)
             st.write(contest_name + ' ' + projection_name)
-        ownership_dict = dict(zip(ownership_raw['Player'], ownership_raw['Own']))
-        fpts_dict = dict(zip(fpts_raw['Player'], fpts_raw['FPTS']))
-        return contest_raw, projections_raw, ownership_dict, fpts_dict
+        return contest_df, projections_df, ownership_df, fpts_df