Add portfolio name extraction and matching in app.py: implement a new function to retrieve unique player names from the portfolio, enhance name matching logic, and update session state with matched names for improved data consistency and analysis.

app.py

@@ -16,6 +16,7 @@ from global_func.highlight_rows import highlight_changes, highlight_changes_winn
 from global_func.load_csv import load_csv
 from global_func.find_csv_mismatches import find_csv_mismatches
 from global_func.trim_portfolio import trim_portfolio
+from global_func.get_portfolio_names import get_portfolio_names
 
 freq_format = {'Finish_percentile': '{:.2%}', 'Lineup Edge': '{:.2%}', 'Win%': '{:.2%}'}
 player_wrong_names_mlb = ['Enrique Hernandez']
@@ -139,6 +140,41 @@ with tab1:
         if st.session_state['portfolio'] is not None and projections is not None:
             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'])
+            
+            # Get names from projections
+            projection_names = projections['player_names'].tolist()
+            
+            # Create match dictionary for portfolio names to projection names
+            portfolio_match_dict = {}
+            for portfolio_name in st.session_state['portfolio_names']:
+                match = process.extractOne(
+                    portfolio_name,
+                    projection_names,
+                    score_cutoff=85
+                )
+                if match:
+                    portfolio_match_dict[portfolio_name] = match[0]
+                else:
+                    portfolio_match_dict[portfolio_name] = portfolio_name
+            
+            # Update portfolio with matched names
+            portfolio = st.session_state['portfolio'].copy()
+            player_columns = [col for col in portfolio.columns 
+                            if col not in ['salary', 'median', 'Own']]
+            
+            # 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
+            st.session_state['origin_portfolio'] = st.session_state['portfolio'].copy()
+            
+            # 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()
                 st.session_state['projections_df']['salary'] = (st.session_state['projections_df']['salary'].astype(str).str.replace(',', '').astype(float).astype(int))
@@ -175,9 +211,6 @@ with tab1:
                     match_dict[name] = name_id_map[match[0]]
                 else:
                     match_dict[name] = name
-            
-            print(f"Number of entries in match_dict: {len(match_dict)}")
-            print("Sample of match_dict:", list(match_dict.items())[:3])
 
             # Apply the matches
             projections['upload_match'] = projections['player_names'].map(match_dict)

global_func/get_portfolio_names.py

@@ -0,0 +1,26 @@
+import streamlit as st
+import numpy as np
+import pandas as pd
+import time
+from fuzzywuzzy import process
+
+def get_portfolio_names(portfolio_df):
+    """
+    Get all unique names from the portfolio dataframe's player columns.
+    
+    Args:
+        portfolio_df: DataFrame containing portfolio data
+        
+    Returns:
+        list: List of unique player names
+    """
+    # Get columns that contain player names (excluding non-player columns)
+    player_columns = [col for col in portfolio_df.columns 
+                     if col not in ['salary', 'median', 'Own']]
+    
+    # Get all unique values from these columns
+    unique_names = portfolio_df[player_columns].values.flatten()
+    unique_names = pd.unique(unique_names)  # Remove duplicates
+    unique_names = unique_names[~pd.isna(unique_names)]  # Remove any NaN values
+    
+    return list(unique_names)