Add more pitch stats

data.py

@@ -241,6 +241,10 @@ data_df = (
         (pl.col('pitch') & pl.col('presult').is_in(['Hit by pitch', 'Sacrifice bunt', 'Sacrifice fly', 'Looking strike', 'Ball', 'Walk', 'Looking strikeout', 'Sacrifice hit error', 'Sacrifice fly error', "Sacrifice fielder's choice", 'Bunt strikeout']).not_()).alias('swing'),
         (pl.col('whiff') | pl.col('presult').is_in(['Looking strike', 'Uncaught third strike', 'Looking strikeout'])).alias('csw')
     )
+    .with_columns((pl.col('x').is_between(-60, 60) & pl.col('y').is_between(50, 50+150)).alias('zone'))
+    .with_columns((pl.col('x').is_between(-40, 40) & pl.col('y').is_between(75, 75+100)).alias('heart'))
+    .with_columns((pl.col('x').is_between(-80, 80) & pl.col('y').is_between(25, 25+200)  & ~pl.col('heart')).alias('shadow'))
+    .with_columns((pl.col('x').is_between(-100, 101) & pl.col('y').is_between(0, 0+251) & ~pl.col('heart') & ~pl.col('shadow')).alias('chase'))
 )
 
 if __name__ == '__main__':

pitch_leaderboard.py

@@ -2,15 +2,15 @@ import gradio as gr
 import polars as pl
 
 from datetime import datetime
-from itertools import chain
+# from itertools import chain
 
 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', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
-PCT_STATS = ['Usage', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
-STATS_WITH_PCTLS = ['SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%']
+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%']
 
 todo = '''
 **To-do**

stats.py

@@ -52,6 +52,48 @@ 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')
@@ -67,9 +109,16 @@ 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('whiff').sum() / pl.col('pitch').sum()).alias('SwStr%'),
+          (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%'),
+          ((pl.col('swing') & ~pl.col('whiff')).sum()/pl.col('swing').sum()).alias('Contact%'),
+          ((pl.col('zone') & pl.col('swing') & ~pl.col('whiff')).sum()/(pl.col('zone') & pl.col('swing')).sum()).alias('Z-Contact%'),
+          ((~pl.col('zone') & pl.col('swing') & ~pl.col('whiff')).sum()/(~pl.col('zone') & pl.col('swing')).sum()).alias('O-Contact%'),
           (pl.col('whiff').sum() / pl.col('swing').sum()).alias('Whiff%'),
-          (pl.col('csw').sum() / pl.col('pitch').sum()).alias('CSW%')
+          (pl.col('whiff').sum() / pl.col('pitch').sum()).alias('SwStr%'),
+          (pl.col('csw').sum() / pl.col('pitch').sum()).alias('CSW%'),
       )
       .with_columns(
           (pl.col('count')/pl.sum('count').over('pitId')).alias('usage'),
@@ -86,8 +135,8 @@ def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
       )
       .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%']
+          (pl.when(pl.col('qualified')).then(pl.col(stat)).rank(descending=((stat in ['FB%', 'LD%'] or 'Contact%' in stat)))/pl.when(pl.col('qualified')).then(pl.col(stat)).count()).alias(f'{stat}_pctl')
+          for stat in ['Zone%', 'Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', '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])