diff --git a/data.py b/data.py
index f337df956409cac3e2661521458dc28063d0254e..e2a8f07279ed781d95b3589c9bc7bd2de6232344 100644
--- a/data.py
+++ b/data.py
@@ -1,5 +1,6 @@
-import pandas as pd
+# import pandas as pd
+import polars as pl
import numpy as np
from gradio_client import Client
from tqdm.auto import tqdm
@@ -10,69 +11,181 @@ import re
from translate import translate_pa_outcome, translate_pitch_outcome, jp_pitch_to_en_pitch, jp_pitch_to_pitch_code, translate_pitch_outcome, max_pitch_types
# load game data
-game_df = pd.read_csv('game.csv').drop_duplicates()
+# game_df = pd.read_csv('game.csv').drop_duplicates()
+game_df = pl.read_csv('game.csv').unique()
assert len(game_df) == len(game_df['game_pk'].unique())
# load pa data
pa_df = []
+# for game_pk in tqdm(game_df['game_pk']):
+# pa_df.append(pd.read_csv(os.path.join('pa', f'{game_pk}.csv'), dtype={'pa_pk': str}))
+# pa_df = pd.concat(pa_df, axis='rows')
for game_pk in tqdm(game_df['game_pk']):
- pa_df.append(pd.read_csv(os.path.join('pa', f'{game_pk}.csv'), dtype={'pa_pk': str}))
-pa_df = pd.concat(pa_df, axis='rows')
+ pa_df.append(pl.read_csv(os.path.join('pa', f'{game_pk}.csv'), schema_overrides={'pa_pk': str}))
+pa_df = pl.concat(pa_df)
# load pitch data
pitch_df = []
+# for game_pk in tqdm(game_df['game_pk']):
+# pitch_df.append(pd.read_csv(os.path.join('pitch', f'{game_pk}.csv'), dtype={'pa_pk': str}))
+# pitch_df = pd.concat(pitch_df, axis='rows')
for game_pk in tqdm(game_df['game_pk']):
- pitch_df.append(pd.read_csv(os.path.join('pitch', f'{game_pk}.csv'), dtype={'pa_pk': str}))
-pitch_df = pd.concat(pitch_df, axis='rows')
-pitch_df
+ pitch_df.append(pl.read_csv(os.path.join('pitch', f'{game_pk}.csv'), schema_overrides={'pa_pk': str, 'on_1b': pl.Int64, 'on_2b': pl.Int64, 'on_3b': pl.Int64}))
+pitch_df = pl.concat(pitch_df)
# load player data
-player_df = pd.read_csv('player.csv')
-player_df
+player_df = pl.read_csv('player.csv')
# translate pa data
-pa_df['_des'] = pa_df['des'].str.strip()
-pa_df['des'] = pa_df['des'].str.strip()
-pa_df['des_more'] = pa_df['des_more'].str.strip()
-pa_df.loc[pa_df['des'].isna(), 'des'] = pa_df[pa_df['des'].isna()]['des_more']
-pa_df.loc[:, 'des'] = pa_df['des'].apply(lambda item: item.split()[0] if (len(item.split()) > 1 and re.search(r'＋\d+点', item)) else item)
-non_home_plate_outcome = (pa_df['des'].isin(['ボール', '見逃し', '空振り'])) | (pa_df['des'].str.endswith('塁けん制'))
-pa_df.loc[non_home_plate_outcome, 'des'] = pa_df.loc[non_home_plate_outcome, 'des_more']
-pa_df['des'] = pa_df['des'].apply(translate_pa_outcome)
+# pa_df['_des'] = pa_df['des'].str.strip()
+# pa_df['des'] = pa_df['des'].str.strip()
+# pa_df['des_more'] = pa_df['des_more'].str.strip()
+# pa_df.loc[pa_df['des'].isna(), 'des'] = pa_df[pa_df['des'].isna()]['des_more']
+# pa_df.loc[:, 'des'] = pa_df['des'].apply(lambda item: item.split()[0] if (len(item.split()) > 1 and re.search(r'＋\d+点', item)) else item)
+# non_home_plate_outcome = (pa_df['des'].isin(['ボール', '見逃し', '空振り'])) | (pa_df['des'].str.endswith('塁けん制'))
+# pa_df.loc[non_home_plate_outcome, 'des'] = pa_df.loc[non_home_plate_outcome, 'des_more']
+# pa_df['des'] = pa_df['des'].apply(translate_pa_outcome)
+pa_df = (
+ pa_df
+ .with_columns(
+ pl.col('des').str.strip_chars().alias('_des'),
+ pl.col('des').str.strip_chars(),
+ pl.col('des_more').str.strip_chars()
+ )
+ .with_columns(
+ pl.col('des').fill_null(pl.col('des_more'))
+ )
+ .with_columns(
+ pl.when(
+ (pl.col('des').str.split(' ').list.len() > 1) &
+ (pl.col('des').str.contains(r'＋\d+点'))
+ )
+ .then(pl.col('des').str.split(' ').list.first())
+ .otherwise(pl.col('des'))
+ .alias('des')
+ )
+ .with_columns(
+ pl.when(
+ pl.col('des').is_in(['ボール', '見逃し', '空振り']) |
+ pl.col('des').str.ends_with('塁けん制')
+ )
+ .then(
+ pl.col('des_more')
+ )
+ .otherwise(
+ pl.col('des')
+ )
+ .alias('des')
+ )
+ .with_columns(
+ pl.col('des').map_elements(translate_pa_outcome, return_dtype=str)
+ )
+)
# translate pitch data
-pitch_df = pitch_df[~pitch_df['pitch_name'].isna()]
-pitch_df['jp_pitch_name'] = pitch_df['pitch_name']
-pitch_df['pitch_name'] = pitch_df['jp_pitch_name'].apply(lambda pitch_name: jp_pitch_to_en_pitch[pitch_name])
-pitch_df['pitch_type'] = pitch_df['jp_pitch_name'].apply(lambda pitch_name: jp_pitch_to_pitch_code[pitch_name])
-pitch_df['description'] = pitch_df['description'].apply(lambda item: item.split()[0] if len(item.split()) > 1 else item)
-pitch_df['description'] = pitch_df['description'].apply(translate_pitch_outcome)
-pitch_df['release_speed'] = pitch_df['release_speed'].replace('-', np.nan)
-pitch_df.loc[~pitch_df['release_speed'].isna(), 'release_speed'] = pitch_df.loc[~pitch_df['release_speed'].isna(), 'release_speed'].str.removesuffix('km/h').astype(int)
-pitch_df['plate_x'] = (pitch_df['plate_x'] + 13) - 80
-pitch_df['plate_z'] = 200 - (pitch_df['plate_z'] + 13) - 100
+# pitch_df = pitch_df[~pitch_df['pitch_name'].isna()]
+# pitch_df['jp_pitch_name'] = pitch_df['pitch_name']
+# pitch_df['pitch_name'] = pitch_df['jp_pitch_name'].apply(lambda pitch_name: jp_pitch_to_en_pitch[pitch_name])
+# pitch_df['pitch_type'] = pitch_df['jp_pitch_name'].apply(lambda pitch_name: jp_pitch_to_pitch_code[pitch_name])
+# pitch_df['description'] = pitch_df['description'].apply(lambda item: item.split()[0] if len(item.split()) > 1 else item)
+# pitch_df['description'] = pitch_df['description'].apply(translate_pitch_outcome)
+# pitch_df['release_speed'] = pitch_df['release_speed'].replace('-', np.nan)
+# pitch_df.loc[~pitch_df['release_speed'].isna(), 'release_speed'] = pitch_df.loc[~pitch_df['release_speed'].isna(), 'release_speed'].str.removesuffix('km/h').astype(int)
+# pitch_df['plate_x'] = (pitch_df['plate_x'] + 13) - 80
+# pitch_df['plate_z'] = 200 - (pitch_df['plate_z'] + 13) - 100
+pitch_df = (
+ pitch_df
+ .filter(pl.col('pitch_name').is_not_null())
+ .with_columns(
+ pl.col('pitch_name').alias('jp_pitch_name')
+ )
+ .with_columns(
+ pl.col('jp_pitch_name').map_elements(lambda pitch_name: jp_pitch_to_en_pitch[pitch_name], return_dtype=str).alias('pitch_name'),
+ pl.col('jp_pitch_name').map_elements(lambda pitch_name: jp_pitch_to_pitch_code[pitch_name], return_dtype=str).alias('pitch_type'),
+ pl.col('description').str.split(' ').list.first().map_elements(translate_pitch_outcome, return_dtype=str),
+ pl.when(
+ pl.col('release_speed') != '-'
+ )
+ .then(
+ pl.col('release_speed').str.strip_suffix('km/h')
+ )
+ .otherwise(
+ None
+ )
+ .alias('release_speed'),
+ ((pl.col('plate_x') + 13) - 80).alias('plate_x'),
+ (200 - (pl.col('plate_z') + 13) - 100).alias('plate_z'),
+ )
+ .with_columns(
+ pl.col('release_speed').cast(int), # idk why I can't do this during the strip_suffix step
+ )
+)
# translate player data
client = Client("Ramos-Ramos/npb_name_translator")
+# en_names = client.predict(
+# jp_names='\n'.join(player_df.name.tolist()),
+# api_name="/predict"
+# )
+# player_df['jp_name'] = player_df['name']
+# player_df['name'] = [name if name != 'nan' else np.nan for name in en_names.splitlines()]
en_names = client.predict(
- jp_names='\n'.join(player_df.name.tolist()),
+ jp_names='\n'.join(player_df['name'].to_list()),
api_name="/predict"
)
-player_df['jp_name'] = player_df['name']
-player_df['name'] = [name if name != 'nan' else np.nan for name in en_names.splitlines()]
+player_df = (
+ player_df
+ .with_columns(
+ pl.col('name').alias('jp_name'),
+ pl.Series('name', en_names.splitlines())
+ )
+ .with_columns(
+ pl.when(pl.col('name') == 'nan')
+ .then(None)
+ .otherwise(pl.col('name'))
+ .alias('name')
+ )
+)
-# merge pitch and pa data
-df = pd.merge(pitch_df, pa_df, 'inner', on=['game_pk', 'pa_pk'])
-df = pd.merge(df, player_df.rename(columns={'player_id': 'pitcher'}), 'inner', on='pitcher')
-df['whiff'] = df['description'].isin(['SS', 'K'])
-df['swing'] = ~df['description'].isin(['B', 'BB', 'LS', 'inv_K', 'bunt_K', 'HBP', 'SH', 'SH E', 'SH FC', 'obstruction', 'illegal_pitch', 'defensive_interference'])
-df['csw'] = df['description'].isin(['SS', 'K', 'LS', 'inv_K'])
-df['normal_pitch'] = ~df['description'].isin(['obstruction', 'illegal_pitch', 'defensive_interference']) # guess
+# # merge pitch and pa data
+# df = pd.merge(pitch_df, pa_df, 'inner', on=['game_pk', 'pa_pk'])
+# df = pd.merge(df, player_df.rename(columns={'player_id': 'pitcher'}), 'inner', on='pitcher')
+# df['whiff'] = df['description'].isin(['SS', 'K'])
+# df['swing'] = ~df['description'].isin(['B', 'BB', 'LS', 'inv_K', 'bunt_K', 'HBP', 'SH', 'SH E', 'SH FC', 'obstruction', 'illegal_pitch', 'defensive_interference'])
+# df['csw'] = df['description'].isin(['SS', 'K', 'LS', 'inv_K'])
+# df['normal_pitch'] = ~df['description'].isin(['obstruction', 'illegal_pitch', 'defensive_interference']) # guess
-df_by_player_pitch = df.groupby(['name', 'pitch_name'])
-whiff_rate = (df_by_player_pitch['whiff'].sum() / df_by_player_pitch['swing'].sum() * 100).round(1).rename('Whiff%')
-csw_rate = (df_by_player_pitch['csw'].sum() / df_by_player_pitch['normal_pitch'].sum() * 100).round(1).rename('CSW%')
-velo = df_by_player_pitch['release_speed'].apply(lambda x: round(x.mean(), 1)).rename('Velocity')
+df = (
+ (
+ pitch_df
+ .join(pa_df, on=['game_pk', 'pa_pk'], how='inner')
+ .join(player_df.rename({'player_id': 'pitcher'}), on='pitcher', how='inner')
+ )
+ .with_columns(
+ pl.col('description').is_in(['SS', 'K']).alias('whiff'),
+ ~pl.col('description').is_in(['B', 'BB', 'LS', 'inv_K', 'bunt_K', 'HBP', 'SH', 'SH E', 'SH FC', 'obstruction', 'illegal_pitch', 'defensive_interference']).alias('swing'),
+ pl.col('description').is_in(['SS', 'K', 'LS', 'inv_K']).alias('csw'),
+ ~pl.col('description').is_in(['obstruction', 'illegal_pitch', 'defensive_interference']).alias('normal_pitch') # guess
+ )
+)
-pitch_stats = pd.concat([whiff_rate, csw_rate, velo], axis=1)
-league_pitch_stats = pd.DataFrame(df.groupby('pitch_name')['release_speed'].apply(lambda x: round(x.mean(), 1)).rename('Velocity'))
+# df_by_player_pitch = df.groupby(['name', 'pitch_name'])
+# whiff_rate = (df_by_player_pitch['whiff'].sum() / df_by_player_pitch['swing'].sum() * 100).round(1).rename('Whiff%')
+# csw_rate = (df_by_player_pitch['csw'].sum() / df_by_player_pitch['normal_pitch'].sum() * 100).round(1).rename('CSW%')
+# velo = df_by_player_pitch['release_speed'].apply(lambda x: round(x.mean(), 1)).rename('Velocity')
+
+# pitch_stats = pd.concat([whiff_rate, csw_rate, velo], axis=1)
+# league_pitch_stats = pd.DataFrame(df.groupby('pitch_name')['release_speed'].apply(lambda x: round(x.mean(), 1)).rename('Velocity'))
+
+pitch_stats= (
+ df
+ .group_by(['name', 'pitch_name'])
+ .agg(
+ ((pl.col('whiff').sum() / pl.col('swing').sum()) * 100).round(1).alias('Whiff%'),
+ ((pl.col('csw').sum() / pl.col('normal_pitch').sum()) * 100).round(1).alias('CSW%'),
+ pl.col('release_speed').mean().round(1).alias('Velocity'),
+ pl.len().alias('Count')
+ )
+ .sort(['name', 'Count'], descending=[False, True])
+)
+league_pitch_stats = df.group_by('pitch_name').agg(pl.col('release_speed').mean().round(1).alias('Velocity'))
diff --git a/demo.py b/demo.py
index 19acf40b131eb0adb351fa415b67f707ced958d7..240264d11f1b7996d243fa1d6365acca6c24d771 100644
--- a/demo.py
+++ b/demo.py
@@ -1,6 +1,7 @@
import gradio as gr
-import pandas as pd
+# import pandas as pd
+import polars as pl
from math import ceil
import os
@@ -33,7 +34,8 @@ with gr.Blocks(css=css) as demo:
# NPB data visualization demo
[Data from SportsNavi](https://sports.yahoo.co.jp/)
''')
- player = gr.Dropdown(value=None, choices=sorted(player_df['name'].dropna().tolist()), label='Player')
+ # player = gr.Dropdown(value=None, choices=sorted(player_df['name'].dropna().tolist()), label='Player')
+ player = gr.Dropdown(value=None, choices=sorted(player_df.filter(pl.col('name').is_not_null())['name'].to_list()), label='Player')
player_info = gr.Markdown()
download_file = gr.DownloadButton(label='Download player data')
with gr.Group():
@@ -66,18 +68,17 @@ with gr.Blocks(css=css) as demo:
pitch_groups.append(pitch_group)
with pitch_group:
pitch_names.append(gr.Markdown(f'### Pitch {col+1}', visible=visible))
- pitch_infos.append(gr.DataFrame(pd.DataFrame([{'Whiff%': None, 'CSW%': None}]), interactive=False, visible=visible))
+ pitch_infos.append(gr.DataFrame(pl.DataFrame([{'Whiff%': None, 'CSW%': None}]), interactive=False, visible=visible))
pitch_velos.append(gr.Plot(show_label=False, elem_classes='pitch-velo', visible=visible))
pitch_maps.append(gr.Plot(label='Pitch Location', elem_classes='pitch-loc', visible=visible))
gr.Markdown('## Pitch Velocity')
- velo_stats = gr.DataFrame(pd.DataFrame([{'Avg. Velo': None, 'League Avg. Velo': None}]), interactive=False, label='Pitch Velocity')
+ velo_stats = gr.DataFrame(pl.DataFrame([{'Avg. Velo': None, 'League Avg. Velo': None}]), interactive=False, label='Pitch Velocity')
gr.Markdown('## Bugs and other notes')
with gr.Accordion('Click to open', open=False):
gr.Markdown('''
- Y axis ticks messy when no velocity distribution is plotted
- - Topmost distribution in summary velo distribution plot is clipped
- DataFrame precision inconsistent
'''
)
diff --git a/gradio_function.py b/gradio_function.py
index 4b0a7156a52d11d7699841f1973d687a7a894486..36903a48b19a183995414ec9b49ef3936c59b406 100644
--- a/gradio_function.py
+++ b/gradio_function.py
@@ -4,7 +4,8 @@ import plotly.graph_objects as go
import plotly.colors as pc
from scipy.stats import gaussian_kde
import numpy as np
-import pandas as pd
+# import pandas as pd
+import polars as pl
import gradio as gr
from translate import max_pitch_types
@@ -54,12 +55,14 @@ def plot_pitch_map(player=None, loc=None, pitch_type=None, pitch_name=None, all_
if loc is None and player is not None:
if all_pitches:
assert not (pitch_type is not None or pitch_name is not None), 'cannot have `pitch_type` or `pitch_name` when `all_pitches` is `True`'
- loc = df.sort_values('name').set_index('name').loc[player, ['plate_x', 'plate_z']]
+ # loc = df.set_index('name').sort_index().loc[player, ['plate_x', 'plate_z']]
+ loc = df.filter(pl.col('name') == player).select(['plate_x', 'plate_z'])
else:
assert not ((pitch_type is None and pitch_name is None) or (pitch_type is not None and pitch_name is not None)), 'exactly one of `pitch_type` or `pitch_name` must be specified'
pitch_val = pitch_type or pitch_name
pitch_col = 'pitch_type' if pitch_type else 'pitch_name'
- loc = df.sort_values('name').set_index(['name', pitch_col]).loc[(player, pitch_val), ['plate_x', 'plate_z']]
+ # loc = df.sort_index().set_index(['name', pitch_col]).sort_index().loc[(player, pitch_val), ['plate_x', 'plate_z']]
+ loc = df.filter((pl.col('name') == player) & (pl.col(pitch_col) == pitch_val)).select(['plate_x', 'plate_z'])
fig = go.Figure()
if len(loc) >= min_pitches:
@@ -85,7 +88,7 @@ def plot_pitch_map(player=None, loc=None, pitch_type=None, pitch_name=None, all_
contours={
'start': 1e-5,
'end': Z.max(),
- 'size': Z.max() / 6
+ 'size': Z.max() / 5
},
showscale=False
))
@@ -105,22 +108,6 @@ def plot_pitch_map(player=None, loc=None, pitch_type=None, pitch_name=None, all_
return fig
-# def plot_empty_pitch_map():
-# fig = go.Figure()
-# fig.add_annotation(
-# x=0,
-# y=0,
-# text='No visualization
as less than 10 pitches thrown',
-# showarrow=False
-# )
-# fig.update_layout(
-# xaxis=dict(range=[-plot_s/2, plot_s/2+1], showticklabels=False),
-# yaxis=dict(range=[-plot_s/2, plot_s/2+1], scaleanchor='x', scaleratio=1, showticklabels=False),
-# # width=384,
-# # height=384
-# )
-# return fig
-
# velo distribution
def plot_pitch_velo(player=None, velos=None, pitch_type=None, pitch_name=None, min_pitches=2):
assert not ((velos is None and player is None) or (velos is not None and player is not None)), 'exactly one of `player` or `loc` must be specified'
@@ -129,8 +116,9 @@ def plot_pitch_velo(player=None, velos=None, pitch_type=None, pitch_name=None, m
assert not ((pitch_type is None and pitch_name is None) or (pitch_type is not None and pitch_name is not None)), 'exactly one of `pitch_type` or `pitch_name` must be specified'
pitch_val = pitch_type or pitch_name
pitch_col = 'pitch_type' if pitch_type else 'pitch_name'
- velos = df.set_index(['name', pitch_col]).loc[(player, pitch_val), 'release_speed']
-
+ # velos = df.set_index(['name', pitch_col]).sort_index().loc[(player, pitch_val), 'release_speed']
+ velos = df.filter((pl.col('name') == player) & (pl.col(pitch_col) == pitch_val))['release_speed']
+
if isinstance(velos, int):
velos = [velos]
@@ -169,54 +157,29 @@ def plot_pitch_velo(player=None, velos=None, pitch_type=None, pitch_name=None, m
return fig
-# def plot_empty_pitch_velo():
-# fig = go.Figure()
-# fig.add_annotation(
-# x=(170+125)/2,
-# y=0.3/2,
-# text='No visualization
as less than 10 pitches thrown',
-# showarrow=False,
-# )
-# fig.update_layout(
-# xaxis=dict(
-# title='Velocity',
-# range=[125, 170],
-# scaleratio=2
-# ),
-# yaxis=dict(
-# title='Frequency',
-# range=[0, 0.3],
-# scaleanchor='x',
-# scaleratio=1,
-# # tickvals=np.linspace(0, 0.3, 3),
-# # ticktext=np.linspace(0, 0.3, 3),
-# tickvals=[0.15],
-# ticktext=[0.15]
-# ),
-# autosize=True,
-# # width=512,
-# # height=256,
-# modebar_remove=['zoom', 'autoScale', 'resetScale'],
-# )
-# return fig
-
-
def plot_all_pitch_velo(player=None, player_df=None, pitch_counts=None, min_pitches=2):
# assert not ((player is None and player_df is None) or (player is not None and player_df is not None)), 'exactly one of `player` or `player_df` must be specified'
if player_df is None and player is not None:
assert pitch_counts is None, '`pitch_counts` must be `None` if `player_df` is None'
- player_df = df.sort_values('name').set_index('name').loc[player].sort_values('pitch_name').set_index('pitch_name')
- pitch_counts = player_df.index.value_counts(ascending=True)
+ # player_df = df.set_index('name').sort_index().loc[player].sort_values('pitch_name').set_index('pitch_name')
+ # pitch_counts = player_df.index.value_counts(ascending=True)
+ player_df = df.filter((pl.col('name') == player) & (pl.col('release_speed').is_not_null()))
+ pitch_counts = player_df['pitch_name'].value_counts().sort('count')
+
- league_df = df.set_index('pitch_name')
+ # league_df = df.set_index('pitch_name').sort_index()
+ league_df = df.filter(pl.col('release_speed').is_not_null())
fig = go.Figure()
velo_center = (player_df['release_speed'].min() + player_df['release_speed'].max()) / 2
- for i, (pitch_name, count) in enumerate(pitch_counts.items()):
- velos = player_df.loc[pitch_name, 'release_speed']
- league_velos = league_df.loc[pitch_name, 'release_speed']
+ # for i, (pitch_name, count) in enumerate(pitch_counts.items()):
+ for i, (pitch_name, count) in enumerate(pitch_counts.iter_rows()):
+ # velos = player_df.loc[pitch_name, 'release_speed']
+ # league_velos = league_df.loc[pitch_name, 'release_speed']
+ velos = player_df.filter(pl.col('pitch_name') == pitch_name)['release_speed']
+ league_velos = league_df.filter(pl.col('pitch_name') == pitch_name)['release_speed']
fig.add_trace(go.Violin(
x=league_velos,
y=[pitch_name]*len(league_velos),
@@ -280,7 +243,8 @@ def plot_all_pitch_velo(player=None, player_df=None, pitch_counts=None, min_pitc
name=player
))
- fig.update_xaxes(title='Velocity', range=[player_df['release_speed'].dropna().min() - 2, player_df['release_speed'].dropna().max() + 2])
+ # fig.update_xaxes(title='Velocity', range=[player_df['release_speed'].dropna().min() - 2, player_df['release_speed'].dropna().max() + 2])
+ fig.update_xaxes(title='Velocity', range=[player_df['release_speed'].min() - 2, player_df['release_speed'].max() + 2])
fig.update_yaxes(range=[0, len(pitch_counts)+1-0.25], visible=False)
fig.update_layout(violingap=0, violingroupgap=0, legend=dict(orientation='h', y=-0.15, yanchor='top'))
@@ -290,37 +254,44 @@ def plot_all_pitch_velo(player=None, player_df=None, pitch_counts=None, min_pitc
def get_data(player):
player_name = f'# {player}'
- _df = df.sort_values('name').set_index('name').loc[player]
- _df.to_csv(f'files/npb.csv', index=False)
- _df_by_pitch_name = _df.set_index('pitch_name').sort_values('pitch_name')
+ # _df = df.set_index('name').sort_index().loc[player]
+ # _df.to_csv(f'files/npb.csv', index=False)
+ # _df_by_pitch_name = _df.set_index('pitch_name').sort_index()
+ _df = df.filter(pl.col('name') == player)
+
+ # usage_fig = px.pie(_df['pitch_name'], names='pitch_name')
+ usage_fig = px.pie(_df.select('pitch_name'), names='pitch_name')
- usage_fig = px.pie(_df['pitch_name'], names='pitch_name')
usage_fig.update_traces(texttemplate='%{percent:.1%}', hovertemplate=f'{player}
' + 'threw a %{label}
%{percent:.1%} of the time (%{value}