Use short team names

app.py

@@ -5,6 +5,9 @@ from pitcher_overview import create_pitcher_overview
 from pitch_leaderboard import create_pitch_leaderboard
 
 updated = '2025-07-21'
+limitations = '''**General Limitations**
+- Foreign players names are in Hebpurn romanization. Contact me if you need a card for a foreign player.
+'''
 
 if __name__ == '__main__':
   with gr.Blocks() as app:
@@ -14,4 +17,5 @@ if __name__ == '__main__':
       create_pitch_leaderboard()
 
     gr.Markdown(f'Last updated: {updated}')
+    gr.Markdown(limitations)
   app.launch()

convert.py

@@ -338,12 +338,31 @@ ball_kind_code_to_color = {
 
 
 def get_text_color_from_color(color):
-  if color in ['gold', 'paleturquoise', 'turquoise']:
+  if color in ['gold', 'khaki', 'paleturquoise', 'turquoise']:
     return 'black'
   return 'white'
 
 ball_kind_to_color = {ball_kind: ball_kind_code_to_color[ball_kind_code[code]] for code, ball_kind in ball_kind.items()}
 
+team_name_short = {
+    'G': 'Yomiuri',
+    'S': 'Yakult',
+    'DB': 'DeNA',
+    'D': 'Chunichi',
+    'T': 'Hanshin',
+    'C': 'Hiroshima',
+    'F': 'Nipponham',
+    'E': 'Rakuten',
+    'L': 'Seibu',
+    'M': 'Lotte',
+    'B': 'ORIX',
+    'H': 'SoftBank',
+    'PL': 'Pacific League',
+    'CL': 'Central League',
+    'WL': 'Western League', # Why is this in the data?
+    'EL': 'Eastern League', # Same with this
+}
+
 team_to_color = {
     'G': '#f69727',
     'S': '#abcd05', 
@@ -356,11 +375,17 @@ team_to_color = {
     'L': '#00214b', 
     'M': '#efefef', 
     'B': '#baa834', 
-    'H': '#fcc700'
+    'H': '#fcc700',
+    'PL': '#01a9e4',
+    'CL': '#129144',
+    'WL': '#552a8d',
+    'EL': '#068ed9'
 }
 
+team_names_short_to_color = {team_name: team_to_color[team] for team, team_name in team_name_short.items()}
+
 def get_text_color_from_team(team):
-  if team in ['DB', 'F', 'L', 'E']:
+  if team in ['DB', 'F', 'L', 'E', 'DeNA', 'Nipponham', 'Seibu', 'Rakuten']:
     return 'white'
   else:
     return 'black'

data.py

@@ -6,6 +6,7 @@ from huggingface_hub import snapshot_download
 
 from convert import (
   aux_global_id_to_code, presult, 
+  team_name_short,
   ball_kind, ball_kind_code, general_ball_kind, general_ball_kind_code, lr, 
   game_kind
 )
@@ -180,7 +181,17 @@ data_df = (
         (pl.col('half_inning') + pl.col('new_batter')).alias('newFiveDigitSerialNumber')
     )
     .with_columns(pl.max('new_batter').cast(pl.Int32).over(['gameId', pl.col('newFiveDigitSerialNumber').str.slice(offset=0, length=3)]).alias('inning_pas'))
-    .join(sched_df[['GameID', 'HomeTeamNameES', 'VisitorTeamNameES']].rename({'GameID': 'gameId'}), on='gameId')
+    .join(
+      (
+        sched_df[['GameID', 'HomeTeamNameES', 'VisitorTeamNameES']]
+        .rename({'GameID': 'gameId'})
+        .with_columns(
+          pl.col('HomeTeamNameES').replace_strict(team_name_short).alias('home_team_name_short'),
+          pl.col('VisitorTeamNameES').replace_strict(team_name_short).alias('visitor_team_name_short')
+        )
+      ),
+      on='gameId'
+    )
     .with_columns(pl.col('UpdatedAt').dt.strftime('%Y%m%d').alias('date'))
     .with_columns(
         (pl.col('date') + '_' + pl.col('VisitorTeamNameES') + '_' + pl.col('HomeTeamNameES') + '_' + pl.col('newFiveDigitSerialNumber')).alias('universal_code') + '_' + pl.col('atBatBallCount'),
@@ -231,7 +242,8 @@ data_df = (
         .otherwise('GameKindName')
         .alias('coarse_game_kind'),
 
-        pl.when(pl.col('half_inning').str.ends_with(1)).then('HomeTeamNameES').otherwise('VisitorTeamNameES').alias('pitcher_team')
+        pl.when(pl.col('half_inning').str.ends_with(1)).then('HomeTeamNameES').otherwise('VisitorTeamNameES').alias('pitcher_team'),
+        pl.when(pl.col('half_inning').str.ends_with(1)).then('home_team_name_short').otherwise('visitor_team_name_short').alias('pitcher_team_name_short')
     )
     .with_columns(
         pl.col('presult_id').replace_strict(presult).alias('presult')

pitch_leaderboard.py

@@ -7,7 +7,7 @@ from datetime import datetime
 
 from data import data_df
 from stats import compute_pitch_stats, filter_data_by_date_and_game_kind
-from convert import ball_kind, ball_kind_to_color, get_text_color_from_color, team_to_color, get_text_color_from_team
+from convert import ball_kind, ball_kind_to_color, get_text_color_from_color, team_names_short_to_color, get_text_color_from_team
 from plotting import stat_cmap
 
 STATS = ['Count', 'Usage', 'Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%', 'Zone%', 'Arm%', 'Glove%', 'High%', 'Low%', 'MM%']
@@ -16,12 +16,22 @@ STATS_WITH_PCTLS = ['Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O
 COLUMNS = ['Pitcher', 'Team', 'Pitch', 'Pitch (General)'] + STATS
 
 PITCH_TYPES = [pitch_type for pitch_type in ball_kind.values() if pitch_type != '-']
-TEAMS  = ['G', 'S', 'DB', 'D', 'T', 'C', 'F', 'E', 'L', 'M', 'B', 'H']
+TEAMS  = [
+    'Yomiuri',
+    'Yakult',
+    'DeNA',
+    'Chunichi',
+    'Hanshin',
+    'Hiroshima',
+    'Nipponham',
+    'Rakuten',
+    'Seibu',
+    'Lotte',
+    'ORIX',
+    'SoftBank'
+]
 notes = '''**Limitations**
-- Foreign players names are in Hebpurn romanization.
-
-**To-do**
-- Color cells according to percentiles
+- [Column widths get messed up when filtering](https://github.com/gradio-app/gradio/issues/11564)
 '''
 
 
@@ -35,7 +45,7 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr='B
     data = data.filter(pl.col('batLR') == pitcher_lr[0].lower())
 
   if include_teams is not None:
-    data = data.filter(pl.col('pitcher_team').is_in(include_teams))
+    data = data.filter(pl.col('pitcher_team_name_short').is_in(include_teams))
     
   # both, left, right = [
     # (
@@ -62,11 +72,11 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr='B
         compute_pitch_stats(data, player_type='pitcher', min_pitches=min_pitches, pitch_class_type='specific')
         .filter(pl.col('qualified') & (pl.col('ballKind').is_in(include_pitches)))
         .drop('pitId', 'ballKind_code', 'qualified')
-        .rename({'pitcher_name': 'Pitcher', 'pitcher_team': 'Team', 'count': 'Count', 'usage': 'Usage', 'ballKind': 'Pitch', 'general_ballKind': 'Pitch (General)'})
-        # .with_columns(
-          # pl.col(stat).mul(100).round(1)
-          # for stat in PCT_STATS + [f'{stat}_pctl' for stat in STATS_WITH_PCTLS]
-        # )
+        .rename({'pitcher_name': 'Pitcher', 'pitcher_team_name_short': 'Team', 'count': 'Count', 'usage': 'Usage', 'ballKind': 'Pitch', 'general_ballKind': 'Pitch (General)'})
+        .with_columns(
+          pl.col(stat).mul(100)
+          for stat in PCT_STATS
+        )
         # [['Pitcher', 'Team', 'Pitch', 'Pitch (General)'] + STATS + [f'{stat}_pctl' for stat in STATS_WITH_PCTLS]]
   )
 
@@ -78,7 +88,7 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr='B
         r, g, b = (stat_cmap([pitch_stats[f'{col}_pctl'][i]])[0, :3]*255).astype(np.uint8)
         styling_row.append(f'background-color: rgba({r}, {g}, {b})')
       elif col == 'Team':
-        styling_row.append(f'color: {get_text_color_from_team(item)}; background-color: {team_to_color[item]}')
+        styling_row.append(f'color: {get_text_color_from_team(item)}; background-color: {team_names_short_to_color[item]}')
       elif col in ['Pitch', 'Pitch (General)']:
         color = ball_kind_to_color[item]
         styling_row.append(f'color: {get_text_color_from_color(color)}; background-color: {color}')
@@ -91,7 +101,7 @@ def gr_create_pitch_leaderboard(start_date, end_date, min_pitches, pitcher_lr='B
     display_value_row = []
     for item in row:
       if isinstance(item, float):
-        display_value_row.append(f'{item:.1%}')
+        display_value_row.append(f'{item:.1f}%')
       else:
         display_value_row.append(item)
     display_value.append(display_value_row)
@@ -131,7 +141,7 @@ def create_pitch_leaderboard():
     # pin_columns = gr.Checkbox(True, 'Pin columns')
     leaderboard = gr.DataFrame(
       pl.DataFrame({'Pitcher': [], 'Pitch': []}),
-      column_widths=[200, 60, 200, 200] + [100]*len(STATS),
+      column_widths=[200, 100, 200, 200] + [100]*len(STATS),
       show_copy_button=True,
       show_search=True,
       pinned_columns=3

pitcher_overview.py

@@ -7,7 +7,7 @@ from data import SEASONS, data_df
 from plotting import create_pitcher_overview_card
 
 notes = '''**Limitations**
-- Foreign players names are in Hebpurn romanization. Contact me if you need a card for a foreign player.
+- Only supports regular season data
 
 **To-do**
 - Fix names of foreign players

stats.py

@@ -1,4 +1,7 @@
 import polars as pl
+from data import data_df
+
+from types import SimpleNamespace
 
 def filter_data_by_date_and_game_kind(data, start_date=None, end_date=None, game_kind=None):
   if start_date is not None:
@@ -60,7 +63,7 @@ def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
   pitch_name_col = 'ballKind' if pitch_class_type == 'specific' else 'general_ballKind'
   pitch_stats = (
       data
-      .group_by(id_col, pitch_col, 'pitcher_team')
+      .group_by(id_col, pitch_col, 'pitcher_team_name_short')
       .agg(
           pl.first('pitcher_name'),
           *([pl.first('general_ballKind')] if pitch_class_type == 'specific' else []),
@@ -105,3 +108,75 @@ def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
       .sort(id_col, 'count', descending=[False, True])
   )
   return pitch_stats
+
+
+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)