Spaces:
Build error
Build error
File size: 6,042 Bytes
ff762e8 |
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 |
import gradio as gr
# import pandas as pd
import polars as pl
from math import ceil
import os
from data import df, pitch_stats, league_pitch_stats, player_df
from gradio_function import *
from translate import jp_pitch_to_en_pitch, max_pitch_types
os.makedirs('files', exist_ok=True)
css = '''
.pitch-usage {height: 256px}
.pitch-usage .js-plotly-plot {height: 100%}
.pitch-velo {height: 100px}
.pitch-velo .js-plotly-plot {height: 100%}
.pitch-loc {height: 320px}
.pitch-loc .js-plotly-plot {height: 100%}
.pitch-velo-summary div.plotly-notifier {visibility: hidden}
'''
with gr.Blocks(
css=css
) as demo:
gr.Markdown('''
# NPB data visualization demo
[Data from SportsNavi](https://sports.yahoo.co.jp/)
''')
source_df = gr.State(df)
app_df = gr.State(df)
app_league_df = gr.State(df)
app_pitch_stats = gr.State(pitch_stats)
app_league_pitch_stats = gr.State(league_pitch_stats)
with gr.Tab('Pitcher Dashboard'):
with gr.Row():
player = gr.Dropdown(value=None, choices=sorted(player_df.filter(pl.col('name').is_not_null())['name'].to_list()), label='Player')
handedness = gr.Radio(value='Both', choices=['Both', 'Left', 'Right'], type='value', interactive=False, label='Batter Handedness')
# preview = gr.DataFrame()
download_file = gr.DownloadButton(label='Download player data')
with gr.Group():
with gr.Row():
usage = gr.Plot(label='Pitch usage')
velo_summary = gr.Plot(label='Velocity summary', elem_classes='pitch-velo-summary')
loc_summary = gr.Plot(label='Overall location')
max_locs = len(jp_pitch_to_en_pitch)
locs_per_row = 4
max_rows = ceil(max_locs/locs_per_row)
gr.Markdown('''
## Pitch Locations
Pitcher's persective
<br>
`NPB` refers to the top 10% of pitches thrown across the league with the current search constraints e.g. handedness
<br>
Note: To speed up the KDE, we restrict the league-wide pitches to 5,000 pitches
''')
pitch_rows = []
pitch_groups = []
pitch_names = []
pitch_infos = []
pitch_velos = []
pitch_locs = []
for row in range(max_rows):
visible = row==0
pitch_row = gr.Row(visible=visible)
pitch_rows.append(pitch_row)
with pitch_row:
_locs_per_row = locs_per_row if row < max_rows-1 else max_locs - locs_per_row * (max_rows - 1)
for col in range(_locs_per_row):
with gr.Column(min_width=256):
pitch_group = gr.Group(visible=visible)
pitch_groups.append(pitch_group)
with pitch_group:
pitch_names.append(gr.Markdown(f'### Pitch {col+1}', 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_locs.append(gr.Plot(label='Pitch Location', elem_classes='pitch-loc', visible=visible))
gr.Markdown('## Pitch Velocity')
velo_stats = gr.DataFrame(pl.DataFrame([{'Avg. Velo': None, 'League Avg. Velo': None}]), interactive=False, label='Pitch Velocity')
(
player
.input(update_dfs, inputs=[player, handedness, source_df], outputs=[app_df, app_league_df, app_pitch_stats, app_league_pitch_stats])
.then(lambda : gr.update(value='Both', interactive=True), outputs=handedness)
)
handedness.input(update_dfs, inputs=[player, handedness, source_df], outputs=[app_df, app_league_df, app_pitch_stats, app_league_pitch_stats])
# app_df.change(preview_df, inputs=app_df, outputs=preview)
# app_df.change(set_download_file, inputs=app_df, outputs=download_file)
# app_df.change(plot_usage, inputs=[app_df, player], outputs=usage)
# app_df.change(plot_velo_summary, inputs=[app_df, app_league_df, player], outputs=velo_summary)
# app_df.change(lambda df: plot_loc(df), inputs=app_df, outputs=loc_summary)
# app_df.change(plot_pitch_cards, inputs=[app_df, app_pitch_stats], outputs=pitch_rows+pitch_groups+pitch_names+pitch_infos+pitch_velos+pitch_locs)
app_pitch_stats.change(update_velo_stats, inputs=[app_pitch_stats, app_league_pitch_stats], outputs=velo_stats)
(
app_df
.change(create_set_download_file_fn('files/player.csv'), inputs=app_df, outputs=download_file)
.then(plot_usage, inputs=[app_df, player], outputs=usage)
.then(plot_velo_summary, inputs=[app_df, app_league_df, player], outputs=velo_summary)
.then(lambda df: plot_loc(df), inputs=app_df, outputs=loc_summary)
.then(plot_pitch_cards, inputs=[app_df, app_league_df, app_pitch_stats], outputs=pitch_rows+pitch_groups+pitch_names+pitch_infos+pitch_velos+pitch_locs)
)
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
- DataFrame precision inconsistent
'''
)
with gr.Tab('Pitch Leaderboard'):
def filter_pitch_leaderboard(min_pitches):
return pitch_stats.filter(pl.col('Count') >= min_pitches).sort('CSW%', descending=True)
init_min_pitches = 100
pitch_stats.write_csv('pitch_leaderboard.csv')
pitch_leaderboard_df = gr.State(filter_pitch_leaderboard(init_min_pitches))
min_pitches = gr.Number(init_min_pitches, precision=0, label='Min. Pitches')
pitch_leaderboard_download_file = gr.DownloadButton(value='pitch_leaderboard.csv', label='Download leaderboard')
pitch_leaderboard = gr.Dataframe(value=pitch_leaderboard_df.value)
min_pitches.change(filter_pitch_leaderboard, inputs=min_pitches, outputs=pitch_leaderboard_df)
(
pitch_leaderboard_df
.change(create_set_download_file_fn('files/pitch_leaderboard.csv'), inputs=pitch_leaderboard_df, outputs=pitch_leaderboard_download_file)
.then(lambda df: df, inputs=pitch_leaderboard_df, outputs=pitch_leaderboard)
)
demo.launch(
share=True,
debug=True
)
|