Add team filtering after percentile computation in pitch leaderboard

pitch_leaderboard.py

@@ -43,9 +43,6 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr='B
   data = filter_data_by_date_and_game_kind(data, start_date=start_date, end_date=end_date, game_kind='Regular Season')
   if pitcher_lr != 'Both':
     data = data.filter(pl.col('batLR') == pitcher_lr[0].lower())
-
-  if include_teams is not None:
-    data = data.filter(pl.col('pitcher_team_name_short').is_in(include_teams))
     
   # both, left, right = [
     # (
@@ -80,6 +77,9 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr='B
         # [['Pitcher', 'Team', 'Pitch', 'Pitch (General)'] + STATS + [f'{stat}_pctl' for stat in STATS_WITH_PCTLS]]
   )
 
+  if include_teams is not None:
+    pitch_stats = pitch_stats.filter(pl.col('Team').is_in(include_teams))
+
   styling = []
   for i, row in enumerate(pitch_stats[COLUMNS].iter_rows()):
     styling_row = []
@@ -143,8 +143,8 @@ def create_pitch_leaderboard():
       pl.DataFrame({'Pitcher': [], 'Pitch': []}),
       column_widths=[200, 100, 200, 200] + [100]*len(STATS),
       show_copy_button=True,
-      show_search=True,
-      pinned_columns=3
+      show_search='filter',
+      pinned_columns=3,
     )
 
     gr.Markdown(notes)
@@ -152,7 +152,11 @@ def create_pitch_leaderboard():
     search.click(gr_create_pitch_leaderboard, inputs=[start_date, end_date, min_pitches, pitcher_lr, include_pitches, include_teams], outputs=leaderboard)
     all_pitches.click(lambda _pitch_types : [] if _pitch_types == PITCH_TYPES else PITCH_TYPES, inputs=include_pitches, outputs=include_pitches)
     all_teams.click(lambda _teams : [] if _teams == TEAMS else TEAMS, inputs=include_teams, outputs=include_teams)
-    # pin_columns.input(lambda _pin_columns : (gr.update(pinned_columns=None if _pin_columns else 3), not _pin_columns), inputs=pin_columns, outputs=[leaderboard, pin_columns])
+    # pin_columns.input(
+      # lambda _pin_columns : gr.update(pinned_columns=None if _pin_columns else 3),
+      # inputs=pin_columns,
+      # outputs=leaderboard
+    # )
     
   return app
 

plotting.py

@@ -10,86 +10,13 @@ import numpy as np
 from types import SimpleNamespace
 from datetime import date
 
-from data import data_df
 from convert import ball_kind_code_to_color, get_text_color_from_color
-from stats import filter_data_by_date_and_game_kind, compute_team_games, compute_pitch_stats
+from stats import get_pitcher_stats
 
 
 mpl.use('Agg')
 
 
-def get_pitcher_stats(id, lr=None, game_kind=None, start_date=None, end_date=None, min_ip=1, min_pitches=1, pitch_class_type='specific'):
-  source_data = data_df.filter(pl.col('ballKind_code') != '-')
-
-  # if start_date is not None:
-    # source_data = source_data.filter(pl.col('date') >= start_date)
-  # if end_date is not None:
-    # source_data = source_data.filter(pl.col('date') <= end_date)
-# 
-  # if game_kind is not None:
-    # source_data = source_data.filter(pl.col('coarse_game_kind') == game_kind)
-  source_data = filter_data_by_date_and_game_kind(source_data, start_date=start_date, end_date=end_date, game_kind=game_kind)
-
-  source_data = (
-      compute_team_games(source_data)
-      .with_columns(
-          pl.when(pl.col('half_inning').str.ends_with('1')).then('home_games').otherwise('visitor_games').first().over('pitId').alias('games'),
-          pl.col('inning_code').unique().len().over('pitId').alias('IP')
-      )
-  )
-
-  if min_ip == 'qualified':
-    source_data = source_data.with_columns((pl.col('IP') >= pl.col('games')).alias('qualified'))
-  else:
-    source_data = source_data.with_columns((pl.col('IP') >= min_ip).alias('qualified'))
-
-  if lr is not None:
-    source_data = source_data.filter(pl.col('batLR') == lr)
-
-  pitch_stats = compute_pitch_stats(source_data, player_type='pitcher', pitch_class_type=pitch_class_type, min_pitches=min_pitches).filter(pl.col('pitId') == id)
-
-  pitch_shapes = (
-      source_data
-      .filter(
-          (pl.col('pitId') == id) &
-          pl.col('x').is_not_null() &
-          pl.col('y').is_not_null() &
-          (pl.col('ballSpeed') > 0)
-      )
-      [['pitId', 'general_ballKind_code', 'ballKind_code', 'ballSpeed', 'x', 'y']]
-  )
-
-  pitcher_stats = (
-      source_data
-      .group_by('pitId')
-      .agg(
-          pl.col('pitcher_name').first(),
-          (pl.when(pl.col('presult').str.contains('strikeout')).then(1).otherwise(0).sum() / pl.col('pa_code').unique().len()).alias('K%'),
-          (pl.when(pl.col('presult') == 'Walk').then(1).otherwise(0).sum() / pl.col('pa_code').unique().len()).alias('BB%'),
-          (pl.col('csw').sum() / pl.col('pitch').sum()).alias('CSW%'),
-          pl.col('aux_bresult').struct.field('batType').drop_nulls().value_counts(normalize=True),
-          pl.first('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%'),
-      )
-      .drop('G', 'F', 'B', 'P', 'L')
-      .with_columns(
-          (pl.when(pl.col('qualified')).then(pl.col(stat)).rank(descending=(stat == 'BB%'))/pl.when(pl.col('qualified')).then(pl.col(stat)).count()).alias(f'{stat}_pctl')
-          for stat in ['CSW%', 'K%', 'BB%', 'GB%']
-      )
-      .filter(pl.col('pitId') == id)
-  )
-
-  return SimpleNamespace(pitcher_stats=pitcher_stats, pitch_stats=pitch_stats, pitch_shapes=pitch_shapes)
-
-
 def get_card_data(id, **kwargs):
   both, left, right = get_pitcher_stats(id, **kwargs), get_pitcher_stats(id, 'l', **kwargs), get_pitcher_stats(id, 'r', **kwargs)
   pitcher_stats = both.pitcher_stats.join(left.pitcher_stats, on='pitId', suffix='_left').join(right.pitcher_stats, on='pitId', suffix='_right')