Fix duplicate name translations

data.py

@@ -212,7 +212,9 @@ data_df = (
     .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'))
     .filter(pl.col('ballKind_code') != '-')
+    .unique()
 )
+bar = data_df
 
 
 def select_name(names):
@@ -328,9 +330,25 @@ players_df = (
     )
 )
 print(players_df.filter(pl.len().over('playerId', 'team', 'season') > 1))
-players_df = pl.concat((players_df.group_by('playerId').agg(pl.first('name_en')), manual_translated_df[['playerId', 'name_en']]))
+players_df = pl.concat((players_df.group_by('playerId').agg(pl.first('name_en')), manual_translated_df[['playerId', 'name_en']])).unique()
+print(players_df.filter(pl.len().over('playerId') > 1).sort('playerId'))
+players_df = players_df.group_by('playerId').agg(pl.first('name_en'))
 
 # join players to data
-data_df = data_df.join(players_df.rename({'name_en': 'pitcher_name'}), left_on='pitId', right_on='playerId', how='left')
+data_df = (
+  data_df
+  .join(
+    players_df.rename({'name_en': 'pitcher_name'})[['playerId', 'pitcher_name']], 
+    left_on='pitId', 
+    right_on='playerId', 
+    how='left'
+  )
+  .join(
+    players_df.rename({'name_en': 'batter_name'})[['playerId', 'batter_name']],
+    left_on='batId',
+    right_on='playerId',
+    how='left'
+  )
+)
 if __name__ == '__main__':
   breakpoint()

plotting.py

@@ -169,6 +169,7 @@ font = load_google_font('Saira Extra Condensed', weight='medium')
 
 def create_pitcher_overview_card(id, season, dpi=300):
   data = get_card_data(id, start_date=date(season, 1, 1), end_date=date(season, 12, 31), game_kind='Regular Season', min_pitches=100, pitch_class_type='general')
+  print(data)
 
   fig = plt.figure(figsize=(1080/300, 1350/300), dpi=dpi)
   gs = fig.add_gridspec(8, 6, height_ratios=[1, 1, 1.5, 6, 1, 3, 1, 0.5])

stats.py

@@ -67,13 +67,14 @@ 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'
+  name_col = 'pitcher_name' if player_type == 'pitcher' else 'batter_name'
   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, 'pitcher_team_name_short')
       .agg(
-          pl.first('pitcher_name'),
+          pl.first(name_col),
           *([pl.first('general_ballKind')] if pitch_class_type == 'specific' else []),
           pl.first(pitch_name_col),
           pl.len().alias('count'),
@@ -116,15 +117,14 @@ def compute_pitch_stats(data, player_type, pitch_class_type, min_pitches=1):
       .sort(id_col, 'count', descending=[False, True])
   )
   return pitch_stats
+  
 
-
-def compute_pitcher_stats(data, min_ip='qualified'):
-  data = data.filter(pl.col('ballKind') != '-')
+def compute_player_stats(data, player_type, min_ip='qualified'):
   data = (
       compute_team_games(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') # inaccurate
+          pl.col('inning_code').unique().len().over('pitId').alias('IP')
       )
   )
 
@@ -133,35 +133,37 @@ def compute_pitcher_stats(data, min_ip='qualified'):
   else:
     data = data.with_columns((pl.col('IP') >= min_ip).alias('qualified'))
 
-  pitcher_stats = (
-      data
-      .group_by('pitId', 'pitcher_team_name_short')
-      .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('whiff').sum().alias('Whiffs'),
-          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', 'null')
-      .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%']
-      )
+  assert player_type in ('pitcher', 'batter') 
+  id_col = 'pitId' if player_type == 'pitcher' else 'batId'
+  name_col = 'pitcher_name' if player_type == 'pitcher' else 'batter_name'
+  player_stats = (
+    data
+    .group_by(id_col)
+    .agg(
+        pl.col(name_col).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%']
+    )
   )
-  return pitcher_stats
-  
+  return player_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') != '-')
@@ -176,19 +178,6 @@ def get_pitcher_stats(id, lr=None, game_kind=None, start_date=None, end_date=Non
   source_data = data_df
   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)
 
@@ -206,32 +195,6 @@ def get_pitcher_stats(id, lr=None, game_kind=None, start_date=None, end_date=Non
       .with_columns((pl.col('ballSpeed')/1.609).alias('ballSpeed_mph'))
   )
 
-  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)
-  )
+  pitcher_stats = compute_player_stats(source_data, player_type='pitcher', min_ip=min_ip).filter(pl.col('pitId') == id)
 
   return SimpleNamespace(pitcher_stats=pitcher_stats, pitch_stats=pitch_stats, pitch_shapes=pitch_shapes)