Refactor name matching logic in app.py: streamline the process of matching portfolio names to projection names by utilizing session state for improved clarity and efficiency, while enhancing the output messages for better user feedback.

app.py

@@ -154,24 +154,25 @@ with tab1:
             st.subheader("Name Matching Analysis")
             # Initialize projections_df in session state if it doesn't exist
             # Get unique names from portfolio
-            st.session_state['portfolio_names'] = get_portfolio_names(st.session_state['portfolio'])
+            portfolio_names = get_portfolio_names(st.session_state['portfolio'])
             
             # Get names from projections
-            projection_names = projections['player_names'].tolist()
+            csv_names = st.session_state['csv_file']['Name'].tolist()
+            projection_names = projections_file['player_names'].tolist()
             
             # Create match dictionary for portfolio names to projection names
             portfolio_match_dict = {}
             unmatched_names = []
-            for portfolio_name in st.session_state['portfolio_names']:
+            for portfolio_name in portfolio_names:
                 match = process.extractOne(
                     portfolio_name,
-                    projection_names,
+                    csv_names,
                     score_cutoff=90
                 )
                 if match:
                     portfolio_match_dict[portfolio_name] = match[0]
                     if match[1] < 100:
-                        st.write(f"{portfolio_name} matched to {match[0]} with a score of {match[1]}%")
+                        st.write(f"{portfolio_name} matched to site csv {match[0]} with a score of {match[1]}%")
                 else:
                     portfolio_match_dict[portfolio_name] = portfolio_name
                     unmatched_names.append(portfolio_name)
@@ -184,65 +185,30 @@ with tab1:
             # For each player column, update names using the match dictionary
             for col in player_columns:
                 portfolio[col] = portfolio[col].map(lambda x: portfolio_match_dict.get(x, x))
-            
-            # Update the portfolio in session state
             st.session_state['portfolio'] = portfolio
             
-            # Store the match dictionary for reference
-            st.session_state['portfolio_to_projection_matches'] = portfolio_match_dict
-            
-            if 'projections_df' not in st.session_state:
-                st.session_state['projections_df'] = projections.copy()
-
-            try:
-                st.session_state['projections_df']['ownership'] = st.session_state['projections_df']['ownership'].str.replace('%', '').astype(float)
-            except:
-                pass
-            
-            try:
-                name_id_map = dict(zip(
-                    st.session_state['csv_file']['Name'], 
-                    st.session_state['csv_file']['Name + ID']
-                ))
-                print("Using Name + ID mapping")
-            except:
-                name_id_map = dict(zip(
-                    st.session_state['csv_file']['Nickname'], 
-                    st.session_state['csv_file']['Id']
-                ))
-                print("Using Nickname + Id mapping")
-            
-            # Get all names at once
-            names = projections['player_names'].tolist()
-            choices = list(name_id_map.keys())
-            
-            # Create a dictionary to store matches
-            match_dict = {}
-            
-            # Process each name individually but more efficiently
-            for name in names:
-                # Use extractOne with score_cutoff for efficiency
+            # Create match dictionary for portfolio names to projection names
+            projections_match_dict = {}
+            unmatched_proj_names = []
+            for projections_name in projection_names:
                 match = process.extractOne(
-                    name,
-                    choices,
-                    score_cutoff=85
+                    projections_name,
+                    csv_names,
+                    score_cutoff=90
                 )
-                
                 if match:
-                    match_dict[name] = name_id_map[match[0]]
+                    projections_match_dict[projections_name] = match[0]
+                    if match[1] < 100:
+                        st.write(f"{projections_name} matched to site csv {match[0]} with a score of {match[1]}%")
                 else:
-                    match_dict[name] = name
+                    projections_match_dict[projections_name] = projections_name
+                    unmatched_proj_names.append(projections_name)
+            
+            # Update projections with matched names
+            projections = st.session_state['projections_df'].copy()
+            projections['player_names'] = projections['player_names'].map(lambda x: projections_match_dict.get(x, x))
+            st.session_state['projections_df'] = projections
 
-            # Apply the matches
-            projections['upload_match'] = projections['player_names'].map(match_dict)
-            st.session_state['export_dict'] = match_dict
-                
-            if unmatched_names:
-                st.warning(f"Found {len(unmatched_names)} names in portfolio without matches in projections:")
-                for name in unmatched_names:
-                    st.write(f"- {name}")
-            else:
-                st.success("All portfolio names were matched to projections!")
             working_frame = st.session_state['portfolio'].copy()
             st.session_state['origin_portfolio'] = st.session_state['portfolio'].copy()
 
@@ -1009,7 +975,7 @@ with tab2:
                     submitted = st.form_submit_button("Trim")
                     if submitted:
                         st.write('initiated')
-                        st.session_state['working_frame'] = predict_dupes(st.session_state['working_frame'], map_dict, site_var, type_var, Contest_Size, strength_var, sport_var)
+                        st.session_state['working_frame'] = predict_dupes(st.session_state['working_frame'], st.session_state['map_dict'], site_var, type_var, Contest_Size, strength_var, sport_var)
                         if 'trimming_dict_maxes' not in st.session_state:
                             st.session_state['trimming_dict_maxes'] = {
                                 'Own': st.session_state['working_frame']['Own'].max(),