hockey-blast-common-lib 0.1.61__py3-none-any.whl → 0.1.63__py3-none-any.whl

hockey_blast_common_lib/aggregate_goalie_stats.py

@@ -9,13 +9,19 @@ import sqlalchemy
 from hockey_blast_common_lib.models import Game, Organization, Division, Human, GoalieSaves
 from hockey_blast_common_lib.stats_models import OrgStatsGoalie, DivisionStatsGoalie, OrgStatsWeeklyGoalie, OrgStatsDailyGoalie, DivisionStatsWeeklyGoalie, DivisionStatsDailyGoalie, LevelStatsGoalie
 from hockey_blast_common_lib.db_connection import create_session
-from sqlalchemy.sql import func
+from sqlalchemy.sql import func, case
 from hockey_blast_common_lib.options import MIN_GAMES_FOR_ORG_STATS, MIN_GAMES_FOR_DIVISION_STATS, MIN_GAMES_FOR_LEVEL_STATS
 from hockey_blast_common_lib.utils import get_non_human_ids, get_all_division_ids_for_org, get_start_datetime
 from hockey_blast_common_lib.utils import assign_ranks
 from hockey_blast_common_lib.stats_utils import ALL_ORGS_ID
 from hockey_blast_common_lib.progress_utils import create_progress_tracker
 
+# Import status constants for game filtering
+FINAL_STATUS = "Final"
+FINAL_SO_STATUS = "Final(SO)"
+FORFEIT_STATUS = "FORFEIT"
+NOEVENTS_STATUS = "NOEVENTS"
+
 def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_human_id=None, aggregation_window=None):
     human_ids_to_filter = get_non_human_ids(session)
 
@@ -72,13 +78,19 @@ def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_huma
 
 
     # Aggregate games played, goals allowed, and shots faced for each goalie using GoalieSaves table
+    # Filter games by status upfront for performance (avoid CASE statements)
+    # Only count games with these statuses: FINAL, FINAL_SO, FORFEIT, NOEVENTS
     query = session.query(
         GoalieSaves.goalie_id.label('human_id'),
         func.count(GoalieSaves.game_id).label('games_played'),
+        func.count(GoalieSaves.game_id).label('games_participated'),  # Same as games_played after filtering
+        func.count(GoalieSaves.game_id).label('games_with_stats'),  # Same as games_played after filtering
         func.sum(GoalieSaves.goals_allowed).label('goals_allowed'),
         func.sum(GoalieSaves.shots_against).label('shots_faced'),
         func.array_agg(GoalieSaves.game_id).label('game_ids')
-    ).join(Game, GoalieSaves.game_id == Game.id).join(Division, Game.division_id == Division.id).filter(filter_condition)
+    ).join(Game, GoalieSaves.game_id == Game.id).filter(
+        Game.status.in_([FINAL_STATUS, FINAL_SO_STATUS, FORFEIT_STATUS, NOEVENTS_STATUS])
+    ).join(Division, Game.division_id == Division.id).filter(filter_condition)
 
     # Filter for specific human_id if provided
     if debug_human_id:
@@ -94,7 +106,9 @@ def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_huma
         key = (aggregation_id, stat.human_id)
         if key not in stats_dict:
             stats_dict[key] = {
-                'games_played': 0,
+                'games_played': 0,  # DEPRECATED - for backward compatibility
+                'games_participated': 0,  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+                'games_with_stats': 0,  # Games with full stats: FINAL, FINAL_SO only
                 'goals_allowed': 0,
                 'shots_faced': 0,
                 'goals_allowed_per_game': 0.0,
@@ -104,6 +118,8 @@ def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_huma
                 'last_game_id': None
             }
         stats_dict[key]['games_played'] += stat.games_played
+        stats_dict[key]['games_participated'] += stat.games_participated
+        stats_dict[key]['games_with_stats'] += stat.games_with_stats
         stats_dict[key]['goals_allowed'] += stat.goals_allowed if stat.goals_allowed is not None else 0
         stats_dict[key]['shots_faced'] += stat.shots_faced if stat.shots_faced is not None else 0
         stats_dict[key]['game_ids'].extend(stat.game_ids)
@@ -111,10 +127,10 @@ def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_huma
     # Filter out entries with games_played less than min_games
     stats_dict = {key: value for key, value in stats_dict.items() if value['games_played'] >= min_games}
 
-    # Calculate per game stats
+    # Calculate per game stats (using games_with_stats as denominator for accuracy)
     for key, stat in stats_dict.items():
-        if stat['games_played'] > 0:
-            stat['goals_allowed_per_game'] = stat['goals_allowed'] / stat['games_played']
+        if stat['games_with_stats'] > 0:
+            stat['goals_allowed_per_game'] = stat['goals_allowed'] / stat['games_with_stats']
             stat['save_percentage'] = (stat['shots_faced'] - stat['goals_allowed']) / stat['shots_faced'] if stat['shots_faced'] > 0 else 0.0
 
     # Ensure all keys have valid human_id values
@@ -134,6 +150,8 @@ def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_huma
 
     # Assign ranks within each level
     assign_ranks(stats_dict, 'games_played')
+    assign_ranks(stats_dict, 'games_participated')  # Rank by total participation
+    assign_ranks(stats_dict, 'games_with_stats')  # Rank by games with full stats
     assign_ranks(stats_dict, 'goals_allowed', reverse_rank=True)
     assign_ranks(stats_dict, 'shots_faced')
     assign_ranks(stats_dict, 'goals_allowed_per_game', reverse_rank=True)
@@ -159,7 +177,11 @@ def aggregate_goalie_stats(session, aggregation_type, aggregation_id, debug_huma
         goalie_stat = StatsModel(
             aggregation_id=aggregation_id,
             human_id=human_id,
-            games_played=stat['games_played'],
+            games_played=stat['games_played'],  # DEPRECATED - for backward compatibility
+            games_participated=stat['games_participated'],  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+            games_participated_rank=stat['games_participated_rank'],
+            games_with_stats=stat['games_with_stats'],  # Games with full stats: FINAL, FINAL_SO only
+            games_with_stats_rank=stat['games_with_stats_rank'],
             goals_allowed=stat['goals_allowed'],
             shots_faced=stat['shots_faced'],
             goals_allowed_per_game=goals_allowed_per_game,

hockey_blast_common_lib/aggregate_human_stats.py

@@ -61,7 +61,7 @@ def aggregate_human_stats(session, aggregation_type, aggregation_id, human_id_fi
 
     # Apply aggregation window filter
     if aggregation_window:
-        last_game_datetime_str = session.query(func.max(func.concat(Game.date, ' ', Game.time))).filter(filter_condition, Game.status.like('Final%')).scalar()
+        last_game_datetime_str = session.query(func.max(func.concat(Game.date, ' ', Game.time))).filter(filter_condition, (Game.status.like('Final%')) | (Game.status == 'NOEVENTS')).scalar()
         start_datetime = get_start_datetime(last_game_datetime_str, aggregation_window)
         if start_datetime:
             game_window_filter = func.cast(func.concat(Game.date, ' ', Game.time), sqlalchemy.types.TIMESTAMP).between(start_datetime, last_game_datetime_str)
@@ -75,8 +75,8 @@ def aggregate_human_stats(session, aggregation_type, aggregation_id, human_id_fi
     if human_id_filter:
         human_filter = [GameRoster.human_id == human_id_filter]
 
-    # Filter games by status
-    game_status_filter = Game.status.like('Final%')
+    # Filter games by status - include both Final and NOEVENTS games
+    game_status_filter = (Game.status.like('Final%')) | (Game.status == 'NOEVENTS')
 
     # Aggregate skater games played
     skater_stats = session.query(

hockey_blast_common_lib/aggregate_referee_stats.py

@@ -17,6 +17,12 @@ from hockey_blast_common_lib.utils import get_start_datetime
 from hockey_blast_common_lib.stats_utils import ALL_ORGS_ID
 from hockey_blast_common_lib.progress_utils import create_progress_tracker
 
+# Import status constants for game filtering
+FINAL_STATUS = "Final"
+FINAL_SO_STATUS = "Final(SO)"
+FORFEIT_STATUS = "FORFEIT"
+NOEVENTS_STATUS = "NOEVENTS"
+
 def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregation_window=None):
     human_ids_to_filter = get_non_human_ids(session)
 
@@ -72,17 +78,26 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
 
     filter_condition = filter_condition & (Division.id == Game.division_id)
     # Aggregate games reffed for each referee
+    # games_participated: Count FINAL, FINAL_SO, FORFEIT, NOEVENTS
+    # games_with_stats: Count only FINAL, FINAL_SO (for per-game averages)
+    # Filter by game status upfront for performance
+    status_filter = Game.status.in_([FINAL_STATUS, FINAL_SO_STATUS, FORFEIT_STATUS, NOEVENTS_STATUS])
+
     games_reffed_stats = session.query(
         Game.referee_1_id.label('human_id'),
         func.count(Game.id).label('games_reffed'),
+        func.count(Game.id).label('games_participated'),  # Same as games_reffed after filtering
+        func.count(Game.id).label('games_with_stats'),  # Same as games_reffed after filtering
         func.array_agg(Game.id).label('game_ids')
-    ).filter(filter_condition).group_by(Game.referee_1_id).all()
+    ).filter(filter_condition, status_filter).group_by(Game.referee_1_id).all()
 
     games_reffed_stats_2 = session.query(
         Game.referee_2_id.label('human_id'),
         func.count(Game.id).label('games_reffed'),
+        func.count(Game.id).label('games_participated'),  # Same as games_reffed after filtering
+        func.count(Game.id).label('games_with_stats'),  # Same as games_reffed after filtering
         func.array_agg(Game.id).label('game_ids')
-    ).filter(filter_condition).group_by(Game.referee_2_id).all()
+    ).filter(filter_condition, status_filter).group_by(Game.referee_2_id).all()
 
     # Aggregate penalties given for each referee
     penalties_given_stats = session.query(
@@ -101,7 +116,9 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
         key = (aggregation_id, stat.human_id)
         if key not in stats_dict:
             stats_dict[key] = {
-                'games_reffed': 0,
+                'games_reffed': 0,  # DEPRECATED - for backward compatibility
+                'games_participated': 0,  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+                'games_with_stats': 0,  # Games with full stats: FINAL, FINAL_SO only
                 'penalties_given': 0,
                 'gm_given': 0,
                 'penalties_per_game': 0.0,
@@ -111,6 +128,8 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
                 'last_game_id': None
             }
         stats_dict[key]['games_reffed'] += stat.games_reffed
+        stats_dict[key]['games_participated'] += stat.games_participated
+        stats_dict[key]['games_with_stats'] += stat.games_with_stats
         stats_dict[key]['game_ids'].extend(stat.game_ids)
 
     for stat in games_reffed_stats_2:
@@ -119,7 +138,9 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
         key = (aggregation_id, stat.human_id)
         if key not in stats_dict:
             stats_dict[key] = {
-                'games_reffed': 0,
+                'games_reffed': 0,  # DEPRECATED - for backward compatibility
+                'games_participated': 0,  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+                'games_with_stats': 0,  # Games with full stats: FINAL, FINAL_SO only
                 'penalties_given': 0,
                 'gm_given': 0,
                 'penalties_per_game': 0.0,
@@ -129,6 +150,8 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
                 'last_game_id': None
             }
         stats_dict[key]['games_reffed'] += stat.games_reffed
+        stats_dict[key]['games_participated'] += stat.games_participated
+        stats_dict[key]['games_with_stats'] += stat.games_with_stats
         stats_dict[key]['game_ids'].extend(stat.game_ids)
 
     # Filter out entries with games_reffed less than min_games
@@ -149,11 +172,11 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
                 stats_dict[key]['gm_given'] += stat.gm_given / 2
                 stats_dict[key]['game_ids'].append(stat.game_id)
 
-    # Calculate per game stats
+    # Calculate per game stats (using games_with_stats as denominator for accuracy)
     for key, stat in stats_dict.items():
-        if stat['games_reffed'] > 0:
-            stat['penalties_per_game'] = stat['penalties_given'] / stat['games_reffed']
-            stat['gm_per_game'] = stat['gm_given'] / stat['games_reffed']
+        if stat['games_with_stats'] > 0:
+            stat['penalties_per_game'] = stat['penalties_given'] / stat['games_with_stats']
+            stat['gm_per_game'] = stat['gm_given'] / stat['games_with_stats']
 
     # Ensure all keys have valid human_id values
     stats_dict = {key: value for key, value in stats_dict.items() if key[1] is not None}
@@ -172,6 +195,8 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
 
     # Assign ranks
     assign_ranks(stats_dict, 'games_reffed')
+    assign_ranks(stats_dict, 'games_participated')  # Rank by total participation
+    assign_ranks(stats_dict, 'games_with_stats')  # Rank by games with full stats
     assign_ranks(stats_dict, 'penalties_given')
     assign_ranks(stats_dict, 'penalties_per_game')
     assign_ranks(stats_dict, 'gm_given')
@@ -185,7 +210,11 @@ def aggregate_referee_stats(session, aggregation_type, aggregation_id, aggregati
         referee_stat = StatsModel(
             aggregation_id=aggregation_id,
             human_id=human_id,
-            games_reffed=stat['games_reffed'],
+            games_reffed=stat['games_reffed'],  # DEPRECATED - for backward compatibility
+            games_participated=stat['games_participated'],  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+            games_participated_rank=stat['games_participated_rank'],
+            games_with_stats=stat['games_with_stats'],  # Games with full stats: FINAL, FINAL_SO only
+            games_with_stats_rank=stat['games_with_stats_rank'],
             penalties_given=stat['penalties_given'],
             penalties_per_game=stat['penalties_per_game'],
             gm_given=stat['gm_given'],

hockey_blast_common_lib/aggregate_scorekeeper_stats.py

@@ -17,6 +17,12 @@ from hockey_blast_common_lib.utils import get_start_datetime
 from hockey_blast_common_lib.stats_utils import ALL_ORGS_ID
 from hockey_blast_common_lib.progress_utils import create_progress_tracker
 
+# Import status constants for game filtering
+FINAL_STATUS = "Final"
+FINAL_SO_STATUS = "Final(SO)"
+FORFEIT_STATUS = "FORFEIT"
+NOEVENTS_STATUS = "NOEVENTS"
+
 def calculate_quality_score(avg_max_saves_5sec, avg_max_saves_20sec, peak_max_saves_5sec, peak_max_saves_20sec):
     """
     Calculate a quality score based on excessive clicking patterns.
@@ -89,9 +95,14 @@ def aggregate_scorekeeper_stats(session, aggregation_type, aggregation_id, aggre
 
 
     # Aggregate scorekeeper quality data for each human
+    # games_participated: Count FINAL, FINAL_SO, FORFEIT, NOEVENTS
+    # games_with_stats: Count only FINAL, FINAL_SO (for per-game averages)
+    # Filter by game status upfront for performance
     scorekeeper_quality_stats = session.query(
         ScorekeeperSaveQuality.scorekeeper_id.label('human_id'),
         func.count(ScorekeeperSaveQuality.game_id).label('games_recorded'),
+        func.count(ScorekeeperSaveQuality.game_id).label('games_participated'),  # Same as games_recorded after filtering
+        func.count(ScorekeeperSaveQuality.game_id).label('games_with_stats'),  # Same as games_recorded after filtering
         func.sum(ScorekeeperSaveQuality.total_saves_recorded).label('total_saves_recorded'),
         func.avg(ScorekeeperSaveQuality.total_saves_recorded).label('avg_saves_per_game'),
         func.avg(ScorekeeperSaveQuality.max_saves_per_5sec).label('avg_max_saves_per_5sec'),
@@ -99,7 +110,9 @@ def aggregate_scorekeeper_stats(session, aggregation_type, aggregation_id, aggre
         func.max(ScorekeeperSaveQuality.max_saves_per_5sec).label('peak_max_saves_per_5sec'),
         func.max(ScorekeeperSaveQuality.max_saves_per_20sec).label('peak_max_saves_per_20sec'),
         func.array_agg(ScorekeeperSaveQuality.game_id).label('game_ids')
-    ).join(Game, Game.id == ScorekeeperSaveQuality.game_id)
+    ).join(Game, Game.id == ScorekeeperSaveQuality.game_id).filter(
+        Game.status.in_([FINAL_STATUS, FINAL_SO_STATUS, FORFEIT_STATUS, NOEVENTS_STATUS])
+    )
 
 
     scorekeeper_quality_stats = scorekeeper_quality_stats.filter(filter_condition).group_by(ScorekeeperSaveQuality.scorekeeper_id).all()
@@ -120,7 +133,9 @@ def aggregate_scorekeeper_stats(session, aggregation_type, aggregation_id, aggre
         )
 
         stats_dict[key] = {
-            'games_recorded': stat.games_recorded,
+            'games_recorded': stat.games_recorded,  # DEPRECATED - for backward compatibility
+            'games_participated': stat.games_participated,  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+            'games_with_stats': stat.games_with_stats,  # Games with full stats: FINAL, FINAL_SO only
             'sog_given': stat.total_saves_recorded,  # Legacy field name mapping
             'sog_per_game': stat.avg_saves_per_game or 0.0,  # Legacy field name mapping
             'total_saves_recorded': stat.total_saves_recorded,
@@ -152,6 +167,8 @@ def aggregate_scorekeeper_stats(session, aggregation_type, aggregation_id, aggre
 
     # Assign ranks - note: for quality metrics, lower values are better (reverse_rank=True for avg and peak clicking)
     assign_ranks(stats_dict, 'games_recorded')
+    assign_ranks(stats_dict, 'games_participated')  # Rank by total participation
+    assign_ranks(stats_dict, 'games_with_stats')  # Rank by games with full stats
     assign_ranks(stats_dict, 'sog_given')  # Legacy field
     assign_ranks(stats_dict, 'sog_per_game')  # Legacy field
     assign_ranks(stats_dict, 'total_saves_recorded')
@@ -169,7 +186,11 @@ def aggregate_scorekeeper_stats(session, aggregation_type, aggregation_id, aggre
         scorekeeper_stat = StatsModel(
             aggregation_id=aggregation_id,
             human_id=human_id,
-            games_recorded=stat['games_recorded'],
+            games_recorded=stat['games_recorded'],  # DEPRECATED - for backward compatibility
+            games_participated=stat['games_participated'],  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+            games_participated_rank=stat['games_participated_rank'],
+            games_with_stats=stat['games_with_stats'],  # Games with full stats: FINAL, FINAL_SO only
+            games_with_stats_rank=stat['games_with_stats_rank'],
             sog_given=stat['sog_given'],  # Legacy field mapping
             sog_per_game=stat['sog_per_game'],  # Legacy field mapping
             total_saves_recorded=stat['total_saves_recorded'],

hockey_blast_common_lib/aggregate_skater_stats.py

@@ -18,50 +18,65 @@ from collections import defaultdict
 from hockey_blast_common_lib.stats_utils import ALL_ORGS_ID
 from hockey_blast_common_lib.progress_utils import create_progress_tracker
 
+# Import status constants for game filtering
+FINAL_STATUS = "Final"
+FINAL_SO_STATUS = "Final(SO)"
+FORFEIT_STATUS = "FORFEIT"
+NOEVENTS_STATUS = "NOEVENTS"
+
 def calculate_current_point_streak(session, human_id, filter_condition):
     """
     Calculate the current point streak for a player.
     A point streak is consecutive games (from the most recent game backward) where the player had at least one point.
     Returns a tuple: (streak_length, average_points_during_streak)
+
+    Optimized to use CASE statements for conditional aggregation in a single query.
     """
-    # Get all games for this player ordered by date/time descending (most recent first)
-    games = session.query(Game).join(GameRoster, Game.id == GameRoster.game_id).filter(
+    # Get all games with their point totals in ONE query using CASE for conditional counting
+    game_points = session.query(
+        Game.id,
+        Game.date,
+        Game.time,
+        func.sum(case((Goal.goal_scorer_id == human_id, 1), else_=0)).label('goals'),
+        func.sum(case(
+            ((Goal.assist_1_id == human_id) | (Goal.assist_2_id == human_id), 1),
+            else_=0
+        )).label('assists')
+    ).join(
+        GameRoster, Game.id == GameRoster.game_id
+    ).outerjoin(
+        Goal, Game.id == Goal.game_id
+    ).filter(
         GameRoster.human_id == human_id,
         ~GameRoster.role.ilike('g'),  # Exclude goalie games
         filter_condition,
-        Game.status.like('Final%')  # Only final games
-    ).order_by(Game.date.desc(), Game.time.desc()).all()
-    
-    if not games:
+        (Game.status.like('Final%')) | (Game.status == 'NOEVENTS')  # Include Final and NOEVENTS games
+    ).group_by(
+        Game.id, Game.date, Game.time
+    ).order_by(
+        Game.date.desc(), Game.time.desc()
+    ).all()
+
+    if not game_points:
         return 0, 0.0
-    
+
     current_streak = 0
     total_points_in_streak = 0
-    
-    for game in games:
-        # Check if the player had any points in this game
-        goals = session.query(Goal).filter(
-            Goal.game_id == game.id,
-            Goal.goal_scorer_id == human_id
-        ).count()
-        
-        assists = session.query(Goal).filter(
-            Goal.game_id == game.id,
-            ((Goal.assist_1_id == human_id) | (Goal.assist_2_id == human_id))
-        ).count()
-        
-        total_points = goals + assists
-        
+
+    # Iterate through games from most recent to oldest
+    for game in game_points:
+        total_points = (game.goals or 0) + (game.assists or 0)
+
         if total_points > 0:
             current_streak += 1
             total_points_in_streak += total_points
         else:
             # Streak is broken, stop counting
             break
-    
+
     # Calculate average points during streak
     avg_points_during_streak = total_points_in_streak / current_streak if current_streak > 0 else 0.0
-    
+
     return current_streak, avg_points_during_streak
 
 def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_human_id=None, aggregation_window=None):
@@ -123,7 +138,7 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
 
     # Apply aggregation window filter
     if aggregation_window:
-        last_game_datetime_str = session.query(func.max(func.concat(Game.date, ' ', Game.time))).filter(filter_condition, Game.status.like('Final%')).scalar()
+        last_game_datetime_str = session.query(func.max(func.concat(Game.date, ' ', Game.time))).filter(filter_condition, (Game.status.like('Final%')) | (Game.status == 'NOEVENTS')).scalar()
         start_datetime = get_start_datetime(last_game_datetime_str, aggregation_window)
         if start_datetime:
             game_window_filter = func.cast(func.concat(Game.date, ' ', Game.time), sqlalchemy.types.TIMESTAMP).between(start_datetime, last_game_datetime_str)
@@ -138,16 +153,22 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
     #     human_filter = [GameRoster.human_id == debug_human_id]
 
     # Aggregate games played for each human in each division, excluding goalies
+    # Filter games by status upfront for performance (avoid CASE statements on 200K+ rows)
+    # Only count games with these statuses: FINAL, FINAL_SO, FORFEIT, NOEVENTS
     games_played_query = session.query(
         GameRoster.human_id,
         func.count(Game.id).label('games_played'),
+        func.count(Game.id).label('games_participated'),  # Same as games_played after filtering
+        func.count(Game.id).label('games_with_stats'),  # Same as games_played after filtering
         func.array_agg(Game.id).label('game_ids')
-    ).join(Game, Game.id == GameRoster.game_id)
-    
+    ).join(Game, Game.id == GameRoster.game_id).filter(
+        Game.status.in_([FINAL_STATUS, FINAL_SO_STATUS, FORFEIT_STATUS, NOEVENTS_STATUS])
+    )
+
     # Only join Division if not level aggregation (since we filter on Game.division_id directly for levels)
     if aggregation_type != 'level':
         games_played_query = games_played_query.join(Division, Game.division_id == Division.id)
-    
+
     games_played_stats = games_played_query.filter(filter_condition, ~GameRoster.role.ilike('g'), *human_filter).group_by(GameRoster.human_id).all()
 
     # Aggregate goals for each human in each division, excluding goalies
@@ -206,7 +227,9 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
         key = (aggregation_id, stat.human_id)
         if key not in stats_dict:
             stats_dict[key] = {
-                'games_played': 0,
+                'games_played': 0,  # DEPRECATED - for backward compatibility
+                'games_participated': 0,  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+                'games_with_stats': 0,  # Games with full stats: FINAL, FINAL_SO only
                 'goals': 0,
                 'assists': 0,
                 'penalties': 0,
@@ -224,6 +247,8 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
                 'last_game_id': None
             }
         stats_dict[key]['games_played'] += stat.games_played
+        stats_dict[key]['games_participated'] += stat.games_participated
+        stats_dict[key]['games_with_stats'] += stat.games_with_stats
         stats_dict[key]['game_ids'].extend(stat.game_ids)
 
     # Filter out entries with games_played less than min_games
@@ -253,34 +278,61 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
             stats_dict[key]['penalties'] += stat.penalties
             stats_dict[key]['gm_penalties'] += stat.gm_penalties  # Update GM penalties
 
-    # Calculate per game stats
+    # Calculate per game stats (using games_with_stats as denominator for accuracy)
     for key, stat in stats_dict.items():
-        if stat['games_played'] > 0:
-            stat['goals_per_game'] = stat['goals'] / stat['games_played']
-            stat['points_per_game'] = stat['points'] / stat['games_played']
-            stat['assists_per_game'] = stat['assists'] / stat['games_played']
-            stat['penalties_per_game'] = stat['penalties'] / stat['games_played']
-            stat['gm_penalties_per_game'] = stat['gm_penalties'] / stat['games_played']  # Calculate GM penalties per game
+        if stat['games_with_stats'] > 0:
+            stat['goals_per_game'] = stat['goals'] / stat['games_with_stats']
+            stat['points_per_game'] = stat['points'] / stat['games_with_stats']
+            stat['assists_per_game'] = stat['assists'] / stat['games_with_stats']
+            stat['penalties_per_game'] = stat['penalties'] / stat['games_with_stats']
+            stat['gm_penalties_per_game'] = stat['gm_penalties'] / stat['games_with_stats']  # Calculate GM penalties per game
 
     # Ensure all keys have valid human_id values
     stats_dict = {key: value for key, value in stats_dict.items() if key[1] is not None}
 
     # Populate first_game_id and last_game_id
-    for key, stat in stats_dict.items():
-        all_game_ids = stat['game_ids']
-        if all_game_ids:
-            first_game = session.query(Game).filter(Game.id.in_(all_game_ids)).order_by(Game.date, Game.time).first()
-            last_game = session.query(Game).filter(Game.id.in_(all_game_ids)).order_by(Game.date.desc(), Game.time.desc()).first()
-            stat['first_game_id'] = first_game.id if first_game else None
-            stat['last_game_id'] = last_game.id if last_game else None
+    # Only show progress for "All Orgs" with no window (all-time stats) - the slowest case
+    total_players = len(stats_dict)
+    if aggregation_type == 'org' and aggregation_id == ALL_ORGS_ID and aggregation_window is None and total_players > 1000:
+        progress = create_progress_tracker(total_players, f"Processing {total_players} players for {aggregation_name}")
+        for idx, (key, stat) in enumerate(stats_dict.items()):
+            all_game_ids = stat['game_ids']
+            if all_game_ids:
+                first_game = session.query(Game).filter(Game.id.in_(all_game_ids)).order_by(Game.date, Game.time).first()
+                last_game = session.query(Game).filter(Game.id.in_(all_game_ids)).order_by(Game.date.desc(), Game.time.desc()).first()
+                stat['first_game_id'] = first_game.id if first_game else None
+                stat['last_game_id'] = last_game.id if last_game else None
+            if (idx + 1) % 100 == 0 or (idx + 1) == total_players:  # Update every 100 players
+                progress.update(idx + 1)
+    else:
+        # No progress tracking for all other cases
+        for key, stat in stats_dict.items():
+            all_game_ids = stat['game_ids']
+            if all_game_ids:
+                first_game = session.query(Game).filter(Game.id.in_(all_game_ids)).order_by(Game.date, Game.time).first()
+                last_game = session.query(Game).filter(Game.id.in_(all_game_ids)).order_by(Game.date.desc(), Game.time.desc()).first()
+                stat['first_game_id'] = first_game.id if first_game else None
+                stat['last_game_id'] = last_game.id if last_game else None
 
     # Calculate current point streak (only for all-time stats)
     if aggregation_window is None:
-        for key, stat in stats_dict.items():
-            aggregation_id, human_id = key
-            streak_length, avg_points = calculate_current_point_streak(session, human_id, filter_condition)
-            stat['current_point_streak'] = streak_length
-            stat['current_point_streak_avg_points'] = avg_points
+        total_players = len(stats_dict)
+        # Show progress for All Orgs - this is the slowest part
+        if aggregation_type == 'org' and aggregation_id == ALL_ORGS_ID and total_players > 1000:
+            progress = create_progress_tracker(total_players, f"Calculating point streaks for {total_players} players")
+            for idx, (key, stat) in enumerate(stats_dict.items()):
+                agg_id, human_id = key
+                streak_length, avg_points = calculate_current_point_streak(session, human_id, filter_condition)
+                stat['current_point_streak'] = streak_length
+                stat['current_point_streak_avg_points'] = avg_points
+                if (idx + 1) % 100 == 0 or (idx + 1) == total_players:
+                    progress.update(idx + 1)
+        else:
+            for key, stat in stats_dict.items():
+                agg_id, human_id = key
+                streak_length, avg_points = calculate_current_point_streak(session, human_id, filter_condition)
+                stat['current_point_streak'] = streak_length
+                stat['current_point_streak_avg_points'] = avg_points
 
     # Calculate total_in_rank
     total_in_rank = len(stats_dict)
@@ -292,6 +344,8 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
             stats_dict[key][f'{field}_rank'] = rank
 
     assign_ranks(stats_dict, 'games_played')
+    assign_ranks(stats_dict, 'games_participated')  # Rank by total participation
+    assign_ranks(stats_dict, 'games_with_stats')  # Rank by games with full stats
     assign_ranks(stats_dict, 'goals')
     assign_ranks(stats_dict, 'assists')
     assign_ranks(stats_dict, 'points')
@@ -330,7 +384,11 @@ def aggregate_skater_stats(session, aggregation_type, aggregation_id, debug_huma
         skater_stat = StatsModel(
             aggregation_id=aggregation_id,
             human_id=human_id,
-            games_played=stat['games_played'],
+            games_played=stat['games_played'],  # DEPRECATED - for backward compatibility
+            games_participated=stat['games_participated'],  # Total games: FINAL, FINAL_SO, FORFEIT, NOEVENTS
+            games_participated_rank=stat['games_participated_rank'],
+            games_with_stats=stat['games_with_stats'],  # Games with full stats: FINAL, FINAL_SO only
+            games_with_stats_rank=stat['games_with_stats_rank'],
             goals=stat['goals'],
             assists=stat['assists'],
             points=stat['goals'] + stat['assists'],

hockey_blast_common_lib/models.py

@@ -99,6 +99,7 @@ class Goal(db.Model):
     sequence_number = db.Column(db.Integer)
     __table_args__ = (
         db.UniqueConstraint('game_id', 'scoring_team_id', 'sequence_number', name='_goal_team_sequence_uc'),
+        db.UniqueConstraint('game_id', 'period', 'time', 'goal_scorer_id', 'scoring_team_id', name='uq_goals_no_duplicates'),
     )
 
 class Human(db.Model):

hockey_blast_common_lib/progress_utils.py

@@ -4,26 +4,34 @@ from datetime import datetime, timedelta
 class ProgressTracker:
     """
     Reusable progress tracker with ETA calculation for stats aggregation processes.
+    Supports optional custom counters for tracking additional metrics.
     """
-    
-    def __init__(self, total_items, description="Processing"):
+
+    def __init__(self, total_items, description="Processing", custom_counters=None):
         self.total_items = total_items
         self.description = description
         self.start_time = time.time()
         self.processed_items = 0
         self.last_update_time = self.start_time
+        self.custom_counters = custom_counters if custom_counters else {}
         
-    def update(self, processed_count=None):
+    def update(self, processed_count=None, **kwargs):
         """
         Update progress. If processed_count is None, increment by 1.
+        kwargs can be used to update custom counters.
         """
         if processed_count is not None:
             self.processed_items = processed_count
         else:
             self.processed_items += 1
-            
+
+        # Update custom counters
+        for key, value in kwargs.items():
+            if key in self.custom_counters:
+                self.custom_counters[key] = value
+
         current_time = time.time()
-        
+
         # Only update display if at least 0.1 seconds have passed (to avoid spamming)
         if current_time - self.last_update_time >= 0.1 or self.processed_items == self.total_items:
             self._display_progress()
@@ -52,10 +60,15 @@ class ProgressTracker:
                 eta_str = self._format_time(eta_seconds)
         
         elapsed_str = self._format_time(elapsed_time)
-        
+
         progress_msg = f"\r{self.description}: {self.processed_items}/{self.total_items} ({percentage:.1f}%) | "
         progress_msg += f"Elapsed: {elapsed_str} | ETA: {eta_str}"
-        
+
+        # Add custom counters to the display
+        if self.custom_counters:
+            counter_parts = [f"{key}: {value}" for key, value in self.custom_counters.items()]
+            progress_msg += " | " + ", ".join(counter_parts)
+
         print(progress_msg, end="", flush=True)
         
         # Add newline when complete
@@ -84,8 +97,9 @@ class ProgressTracker:
         self.processed_items = self.total_items
         self._display_progress()
 
-def create_progress_tracker(total_items, description="Processing"):
+def create_progress_tracker(total_items, description="Processing", custom_counters=None):
     """
     Factory function to create a progress tracker.
+    custom_counters: dict of counter_name: initial_value for additional metrics to track
     """
-    return ProgressTracker(total_items, description)
+    return ProgressTracker(total_items, description, custom_counters)

hockey_blast_common_lib/stats_models.py

@@ -52,8 +52,12 @@ class BaseStatsSkater(db.Model):
     __abstract__ = True
     id = db.Column(db.Integer, primary_key=True)
     human_id = db.Column(db.Integer, db.ForeignKey('humans.id'), nullable=False)
-    games_played = db.Column(db.Integer, default=0)
+    games_played = db.Column(db.Integer, default=0)  # DEPRECATED - use games_participated instead
     games_played_rank = db.Column(db.Integer, default=0)
+    games_participated = db.Column(db.Integer, default=0)  # Count FINAL, FINAL_SO, FORFEIT, NOEVENTS
+    games_participated_rank = db.Column(db.Integer, default=0)
+    games_with_stats = db.Column(db.Integer, default=0)  # Count only FINAL, FINAL_SO
+    games_with_stats_rank = db.Column(db.Integer, default=0)
     goals = db.Column(db.Integer, default=0)
     goals_rank = db.Column(db.Integer, default=0)
     assists = db.Column(db.Integer, default=0)
@@ -104,8 +108,12 @@ class BaseStatsGoalie(db.Model):
     __abstract__ = True
     id = db.Column(db.Integer, primary_key=True)
     human_id = db.Column(db.Integer, db.ForeignKey('humans.id'), nullable=False)
-    games_played = db.Column(db.Integer, default=0)
+    games_played = db.Column(db.Integer, default=0)  # DEPRECATED - use games_participated instead
     games_played_rank = db.Column(db.Integer, default=0)
+    games_participated = db.Column(db.Integer, default=0)  # Count FINAL, FINAL_SO, FORFEIT, NOEVENTS
+    games_participated_rank = db.Column(db.Integer, default=0)
+    games_with_stats = db.Column(db.Integer, default=0)  # Count only FINAL, FINAL_SO
+    games_with_stats_rank = db.Column(db.Integer, default=0)
     goals_allowed = db.Column(db.Integer, default=0)
     goals_allowed_rank = db.Column(db.Integer, default=0)
     goals_allowed_per_game = db.Column(db.Float, default=0.0)
@@ -137,8 +145,12 @@ class BaseStatsReferee(db.Model):
     __abstract__ = True
     id = db.Column(db.Integer, primary_key=True)
     human_id = db.Column(db.Integer, db.ForeignKey('humans.id'), nullable=False)
-    games_reffed = db.Column(db.Integer, default=0)
+    games_reffed = db.Column(db.Integer, default=0)  # DEPRECATED - use games_participated instead
     games_reffed_rank = db.Column(db.Integer, default=0)
+    games_participated = db.Column(db.Integer, default=0)  # Count FINAL, FINAL_SO, FORFEIT, NOEVENTS
+    games_participated_rank = db.Column(db.Integer, default=0)
+    games_with_stats = db.Column(db.Integer, default=0)  # Count only FINAL, FINAL_SO (for per-game averages)
+    games_with_stats_rank = db.Column(db.Integer, default=0)
     penalties_given = db.Column(db.Integer, default=0)
     penalties_given_rank = db.Column(db.Integer, default=0)
     penalties_per_game = db.Column(db.Float, default=0.0)
@@ -170,8 +182,12 @@ class BaseStatsScorekeeper(db.Model):
     __abstract__ = True
     id = db.Column(db.Integer, primary_key=True)
     human_id = db.Column(db.Integer, db.ForeignKey('humans.id'), nullable=False)
-    games_recorded = db.Column(db.Integer, default=0)
+    games_recorded = db.Column(db.Integer, default=0)  # DEPRECATED - use games_participated instead
     games_recorded_rank = db.Column(db.Integer, default=0)
+    games_participated = db.Column(db.Integer, default=0)  # Count FINAL, FINAL_SO, FORFEIT, NOEVENTS
+    games_participated_rank = db.Column(db.Integer, default=0)
+    games_with_stats = db.Column(db.Integer, default=0)  # Count only FINAL, FINAL_SO (for per-game averages)
+    games_with_stats_rank = db.Column(db.Integer, default=0)
     sog_given = db.Column(db.Integer, default=0)
     sog_given_rank = db.Column(db.Integer, default=0)
     sog_per_game = db.Column(db.Float, default=0.0)

{hockey_blast_common_lib-0.1.61.dist-info → hockey_blast_common_lib-0.1.63.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: hockey-blast-common-lib
-Version: 0.1.61
+Version: 0.1.63
 Summary: Common library for shared functionality and DB models
 Author: Pavel Kletskov
 Author-email: kletskov@gmail.com

{hockey_blast_common_lib-0.1.61.dist-info → hockey_blast_common_lib-0.1.63.dist-info}/RECORD

@@ -1,28 +1,28 @@
 hockey_blast_common_lib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hockey_blast_common_lib/aggregate_all_stats.py,sha256=QhuSvGjuk4jVywNRcgxB-9ooJAoAbZRkaLjLe9Q1hEM,1363
-hockey_blast_common_lib/aggregate_goalie_stats.py,sha256=WmKqGdM0SZLYXailCsBM4Wdpy8kOcmPtF9JOxLxzmRc,13217
+hockey_blast_common_lib/aggregate_goalie_stats.py,sha256=J0hY5mK6UATScjqtPqbTfEeApnZy6lC3qlMGN02qhpY,14831
 hockey_blast_common_lib/aggregate_h2h_stats.py,sha256=dC5TcJZGkpIQTiq3z40kOX6EjEhFbGv5EL0P1EClBQ0,11117
-hockey_blast_common_lib/aggregate_human_stats.py,sha256=JZcXJofF1wmFPcLbalM_GiXrq22eUJO28R_xyypw4rI,25456
-hockey_blast_common_lib/aggregate_referee_stats.py,sha256=oX9UgD_mvvDJv4Sy1jJemUKWNi3N-1sOjfHNSg4VzOE,13351
+hockey_blast_common_lib/aggregate_human_stats.py,sha256=wRw0X_57-AUWHHn5SXRLovC7KQwQtTJm7Twb7XIQv_M,25560
+hockey_blast_common_lib/aggregate_referee_stats.py,sha256=zwMpQxq-tONNKSv87hwM_l94L1wBpu2ZVW-bvyV-zjY,15561
 hockey_blast_common_lib/aggregate_s2s_stats.py,sha256=urYN0Q06twwLO-XWGlSMVAVOTVR_D2AWdmoGsxIYHXE,6737
-hockey_blast_common_lib/aggregate_scorekeeper_stats.py,sha256=_SWt7qqUl31As1pkEJ40YLh9ItXdBuen3RjtSzHGP8U,11997
-hockey_blast_common_lib/aggregate_skater_stats.py,sha256=Y3zDeyEWuEae-PdnFMz7aGRzP4BnYNTut_zqRgR56yI,22715
+hockey_blast_common_lib/aggregate_scorekeeper_stats.py,sha256=SBwZ6kBMbgsBgyiLIuCTmgRHpseqjIlqjvR63rBvyiY,13500
+hockey_blast_common_lib/aggregate_skater_stats.py,sha256=d_4PRCZw458FMp6Yv4_QM8hbkXAH_dkX5O3_jMtaoU8,26547
 hockey_blast_common_lib/assign_skater_skill.py,sha256=Asq6iRMPsCMDnvuNSd-M3s4Gee4kDocP9Eznwju_9kA,2749
 hockey_blast_common_lib/db_connection.py,sha256=HvPxDvOj7j5H85RfslGvHVNevfg7mKCd0syJ6NX21mU,1890
 hockey_blast_common_lib/dump_sample_db.sh,sha256=MY3lnzTXBoWd76-ZlZr9nWsKMEVgyRsUn-LZ2d1JWZs,810
 hockey_blast_common_lib/h2h_models.py,sha256=0st4xoJO0U6ONfx3BV03BQvHjZE31e_PqZfphAJMoSU,7968
-hockey_blast_common_lib/hockey_blast_sample_backup.sql.gz,sha256=vJK83rusOv9VoljFTC03-0leXhGBHa1WV0XvM2ri870,4648906
-hockey_blast_common_lib/models.py,sha256=ccM886RcSFDiJ3yj2l9OqRi_PwR1L6WU8AsqzgV3_t0,19598
+hockey_blast_common_lib/hockey_blast_sample_backup.sql.gz,sha256=u5lGgEUTbJddCd-y2hu8LsMRoZW0Ox_jNzWYqNR1sbc,4648908
+hockey_blast_common_lib/models.py,sha256=rbpgLI6iol_Eh-zvL1jSVqA7t08H6aFQoSJvMzjp81U,19724
 hockey_blast_common_lib/options.py,sha256=XecGGlizbul7BnMePrvIqvEq5_w49UoG3Yu9iv961gg,1499
-hockey_blast_common_lib/progress_utils.py,sha256=H_zRFOsb2qQQpGw56wJghZ1nUe_m6zqGeR9hZ33Y1Uo,3229
+hockey_blast_common_lib/progress_utils.py,sha256=7cqyUTMmW3xAIh5JKFlhnBiybCJ9WvGDz7ihH59Lc_0,3953
 hockey_blast_common_lib/restore_sample_db.sh,sha256=7W3lzRZeu9zXIu1Bvtnaw8EHc1ulHmFM4mMh86oUQJo,2205
 hockey_blast_common_lib/skills_in_divisions.py,sha256=m-UEwMwn1KM7wOYvDstgsOEeH57M9V6yrkBoghzGYKE,7005
 hockey_blast_common_lib/skills_propagation.py,sha256=nUxntyK8M4xWjHpkfze8f0suaBeunxicgDCduGmNJ-A,18468
-hockey_blast_common_lib/stats_models.py,sha256=64sUq_iWhNXi_b_V_1INuQ1RusKaTASjurkRo5gQOs4,26703
+hockey_blast_common_lib/stats_models.py,sha256=yLfsR0RhSc95-8ULdJ8tuvLd6RjIFkgZ74ejubJYVUw,28187
 hockey_blast_common_lib/stats_utils.py,sha256=DXsPO4jw8XsdRUN46TGF_IiBAfz3GCIVBswCGp5ELDk,284
 hockey_blast_common_lib/utils.py,sha256=1YJRAj1lhftjIAM2frFi4A4K90kCJaxWlgBQ1-77xZY,6486
 hockey_blast_common_lib/wsgi.py,sha256=y3NxoJfWjdzX3iP7RGvDEer6zcnPyCanpqSgW1BlXgg,779
-hockey_blast_common_lib-0.1.61.dist-info/METADATA,sha256=AtOG9FeESKu9wi75z2Q9cOctyOnmyoNYfu6hkiCFn0c,318
-hockey_blast_common_lib-0.1.61.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
-hockey_blast_common_lib-0.1.61.dist-info/top_level.txt,sha256=wIR4LIkE40npoA2QlOdfCYlgFeGbsHR8Z6r0h46Vtgc,24
-hockey_blast_common_lib-0.1.61.dist-info/RECORD,,
+hockey_blast_common_lib-0.1.63.dist-info/METADATA,sha256=VFQNc4UUo8qUlyk2Bd_kykrsxVYwclpckA2eq2OCTgc,318
+hockey_blast_common_lib-0.1.63.dist-info/WHEEL,sha256=PZUExdf71Ui_so67QXpySuHtCi3-J3wvF4ORK6k_S8U,91
+hockey_blast_common_lib-0.1.63.dist-info/top_level.txt,sha256=wIR4LIkE40npoA2QlOdfCYlgFeGbsHR8Z6r0h46Vtgc,24
+hockey_blast_common_lib-0.1.63.dist-info/RECORD,,