kermitting soon

util/app.py

@@ -60,7 +60,7 @@ champion_encoder.fit(CHAMPIONS)
 def get_user_training_df(player_opgg_url):
     try:
         print("========= Inside get_user_training_df(player_opgg_url) ============= \n") 
-        print("player_opgg_url: ", player_opgg_url, "\n type(player_opgg_url): ", type(player_opgg_url), "\n")
+        #print("player_opgg_url: ", player_opgg_url, "\n type(player_opgg_url): ", type(player_opgg_url), "\n")
 
         # Add input validation
         if not player_opgg_url or not isinstance(player_opgg_url, str):
@@ -133,7 +133,7 @@ def predict_champion(player_opgg_url, *champions):
             return training_df
 
         training_df = convert_df(training_df)
-        print("type(training_df): ", type(training_df), "\n")
+        #print("type(training_df): ", type(training_df), "\n")
         print("check_datatypes(training_df) BEFORE feature eng. :", check_datatypes(training_df), "\n")
 
         training_df = apply_feature_engineering(training_df)

util/helper.py

@@ -951,15 +951,15 @@ def calculate_champion_loyalty(df):
 
             season_games = [int(x) if isinstance(x, str) and x.isdigit() else 0 for x in season_games]
 
-            print(f"recent_games was: {recent_games}, types: {[type(x) for x in recent_games]}")
-            print(f"season_games was: {season_games}, types: {[type(x) for x in season_games]}")
+            #print(f"recent_games was: {recent_games}, types: {[type(x) for x in recent_games]}")
+            #print(f"season_games was: {season_games}, types: {[type(x) for x in season_games]}")
             
-            print("\nSumming recent games... \n")
+            #print("\nSumming recent games... \n")
             total_recent_games = sum(recent_games)
-            print("total_recent_games: ", total_recent_games, "\n")
+            #print("total_recent_games: ", total_recent_games, "\n")
             total_season_games = sum(season_games)
-            print("total_season_games: ", total_season_games, "\n")
-            print("End of summing recent games... \n Total recent_games = ", total_recent_games, "\n total_season_games: ", total_season_games, "\n \n \n")
+            #print("total_season_games: ", total_season_games, "\n")
+            #print("End of summing recent games... \n Total recent_games = ", total_recent_games, "\n total_season_games: ", total_season_games, "\n \n \n")
             
             if total_recent_games == 0:
                 return {
@@ -993,11 +993,14 @@ def calculate_champion_loyalty(df):
             confidence_score += 0.2 if pd.notna(row['most_champ_2']) else 0  # Increased weight for second
             confidence_score += sum(0.1 for i in range(1, 4) if pd.notna(row[f'season_champ_{i}']))
             confidence_score += sum(0.05 for i in range(4, 8) if pd.notna(row[f'season_champ_{i}']))
-            
+            print("...END calculate confidence score\n")
+
             recent_games = sum((row[f'W_{i}'] + row[f'L_{i}']) if pd.notna(row[f'most_champ_{i}']) else 0 
                              for i in range(1, 3))  # Only top 2
             confidence_score += min(0.1, recent_games / 100)
             
+            print(f"loyalty_score, confidence score: [{loyalty_score}], [{confidence_score}]  \n")
+            print("===================== exiting: get_loyalty_scores()===================")
             return {
                 'loyalty_score': round(min(loyalty_score, 1.0), 3),
                 'confidence_score': round(min(confidence_score, 1.0), 3),