Spaces:
Running
Running
File size: 7,900 Bytes
d1369a2 9eda2f5 d1369a2 9eda2f5 d1369a2 65fefb5 d1369a2 65fefb5 f89cae0 8fe9801 d1369a2 65fefb5 56c6bd4 d1369a2 9eda2f5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 |
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:
data = data.filter(pl.col('date') >= start_date)
if end_date is not None:
data = data.filter(pl.col('date') <= end_date)
if game_kind is not None:
data = data.filter(pl.col('coarse_game_kind') == game_kind)
return data
def compute_team_games(data):
data = (
data
.with_columns(
pl.col('gameId').unique().len().over('HomeTeamNameES').alias('home_games'),
pl.col('gameId').unique().len().over('VisitorTeamNameES').alias('visitor_games')
)
)
game_data = (
data
.group_by('HomeTeamNameES')
.first()
[['HomeTeamNameES', 'home_games']]
.rename({'HomeTeamNameES': 'team'})
.join(
(
data
.group_by('VisitorTeamNameES')
.first()
[['VisitorTeamNameES', 'visitor_games']]
.rename({'VisitorTeamNameES': 'team'})
),
on='team',
)
.with_columns((pl.col('home_games')+pl.col('visitor_games')).alias('games'))
)
return (
data
.drop('home_games', 'visitor_games')
.join(
game_data[['team', 'games']].rename({'games': 'home_games'}),
left_on='HomeTeamNameES',
right_on='team'
)
.join(
game_data[['team', 'games']].rename({'games': 'visitor_games'}),
left_on='VisitorTeamNameES',
right_on='team'
)
)
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, 'pitcher_team_name_short')
.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('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('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%'),
(pl.col('x').is_between(-20, 20) & pl.col('y').is_between(100, 100+50)).mean().alias('MM%')
)
.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(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 ['Swing%', 'Z-Swing%', 'Chase%', 'Contact%', 'Z-Contact%', 'O-Contact%', 'SwStr%', 'Whiff%', 'CSW%', 'GB%', 'FB%', 'LD%', 'Zone%']
)
.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 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)
|