Add location stats

data.py

@@ -221,6 +221,7 @@ data_df = (
         pl.col('ballKind').replace_strict(general_ball_kind).alias('general_ballKind'),
         pl.col('ballKind').replace_strict(general_ball_kind_code).alias('general_ballKind_code'),
         pl.col('batLR').replace_strict(lr),
+        pl.col('pitLR').replace_strict(lr),
         pl.col('date').str.to_date('%Y%m%d'),
         
         pl.when(pl.col('GameKindName').str.contains('Regular Season') | (pl.col('GameKindName') == 'Interleague'))

pitch_leaderboard.py

@@ -8,9 +8,9 @@ from data import data_df
 from stats import compute_pitch_stats, filter_data_by_date_and_game_kind
 from convert import ball_kind
 
-STATS = ['Count', 'Usage', 'Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
-PCT_STATS = ['Usage', 'Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
-STATS_WITH_PCTLS = ['Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
+STATS = ['Count', 'Usage', 'Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%', 'Zone%', 'Arm%', 'Glove%', 'High%', 'Low%']
+PCT_STATS = ['Usage', 'Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%', 'Zone%', 'Arm%', 'Glove%', 'High%', 'Low%']
+STATS_WITH_PCTLS = ['Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%', 'Zone%']
 
 todo = '''
 **To-do**
@@ -56,7 +56,7 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr, i
           pl.col(stat).mul(100).round(1)
           for stat in PCT_STATS + [f'{stat} (Pctl)' for stat in STATS_WITH_PCTLS]
         )
-        [['Pitcher', 'Pitch', 'Pitch (General)', 'Count', 'Usage'] + STATS_WITH_PCTLS]
+        [['Pitcher', 'Pitch', 'Pitch (General)'] + STATS]
   )
   return pitch_stats
 

stats.py

@@ -52,48 +52,6 @@ def compute_team_games(data):
   )
 
 
-# def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
-  # assert player_type in ('pitcher', 'batter')
-  # assert pitch_class_type in ('general', 'specific')
-  # id_col = 'pitId' if player_type == 'pitcher' else 'batId'
-  # pitch_col = 'ballKind_code' if pitch_class_type == 'specific' else 'general_ballKind_code'
-  # pitch_name_col = 'ballKind' if pitch_class_type == 'specific' else 'general_ballKind'
-  # pitch_stats = (
-      # data
-      # .group_by(id_col, pitch_col)
-      # .agg(
-          # pl.first('pitcher_name'),
-          # *([pl.first('general_ballKind')] if pitch_class_type == 'specific' else []),
-          # pl.first(pitch_name_col),
-          # pl.len().alias('count'),
-          # pl.col('aux_bresult').struct.field('batType').drop_nulls().value_counts(normalize=True),
-          # (pl.col('whiff').sum() / pl.col('pitch').sum()).alias('SwStr%'),
-          # (pl.col('whiff').sum() / pl.col('swing').sum()).alias('Whiff%'),
-          # (pl.col('csw').sum() / pl.col('pitch').sum()).alias('CSW%')
-      # )
-      # .with_columns(
-          # (pl.col('count')/pl.sum('count').over('pitId')).alias('usage'),
-          # (pl.col('count') >= min_pitches).alias('qualified')
-      # )
-      # .explode('batType')
-      # .unnest('batType')
-      # .pivot(on='batType', values='proportion')
-      # .fill_null(0)
-      # .with_columns(
-          # (pl.col('G') + pl.col('B')).alias('GB%'),
-          # (pl.col('F') + pl.col('P')).alias('FB%'),
-          # pl.col('L').alias('LD%').round(2),
-      # )
-      # .drop('G', 'F', 'B', 'P', 'L', 'null')
-      # .with_columns(
-          # (pl.when(pl.col('qualified')).then(pl.col(stat)).rank()/pl.when(pl.col('qualified')).then(pl.col(stat)).count()).alias(f'{stat}_pctl')
-          # for stat in ['SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
-      # )
-      # .rename({pitch_col: 'ballKind_code', pitch_name_col: 'ballKind'} if pitch_class_type == 'general' else {})
-      # .sort(id_col, 'count', descending=[False, True])
-  # )
-  # return pitch_stats
-
 def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
   assert player_type in ('pitcher', 'batter')
   assert pitch_class_type in ('general', 'specific')
@@ -109,7 +67,6 @@ def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
           pl.first(pitch_name_col),
           pl.len().alias('count'),
           pl.col('aux_bresult').struct.field('batType').drop_nulls().value_counts(normalize=True),
-          (pl.col('zone').sum() / pl.col('pitch').sum()).alias('Zone%'),
           (pl.col('swing').sum() / pl.col('pitch').sum()).alias('Swing%'),
           ((pl.col('swing') & pl.col('zone')).sum() / pl.col('pitch').sum()).alias('Z-Swing%'),
           ((pl.col('swing') & ~pl.col('zone')).sum() / pl.col('pitch').sum()).alias('Chase%'),
@@ -119,6 +76,11 @@ def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
           (pl.col('whiff').sum() / pl.col('swing').sum()).alias('Whiff%'),
           (pl.col('whiff').sum() / pl.col('pitch').sum()).alias('SwStr%'),
           (pl.col('csw').sum() / pl.col('pitch').sum()).alias('CSW%'),
+          (pl.col('zone').sum() / pl.col('pitch').sum()).alias('Zone%'),
+          (pl.when(pl.col('pitLR') == 'r').then(pl.col('x') < 0).otherwise(pl.col('x') > 0)).mean().alias('Glove%'),
+          (pl.when(pl.col('pitLR') == 'r').then(pl.col('x') >= 0).otherwise(pl.col('x') <= 0)).mean().alias('Arm%'),
+          (pl.col('y') > 125).mean().alias('High%'),
+          (pl.col('y') <= 125).mean().alias('Low%')
       )
       .with_columns(
           (pl.col('count')/pl.sum('count').over('pitId')).alias('usage'),