Change implementation of player- and league-level stats

daily_pitcher_leaderboard.py

@@ -103,8 +103,8 @@ def create_daily_pitcher_leaderboard():
                 min_width=50
             )
             top_players = gr.Number(10, label='# Top players', scale=1, min_width=100)
-            strict = gr.Checkbox(False, label='Strict', info='Ignore ties and restrict to # top players', scale=1.5, min_width=100)
-            ignore_zero_whiffs = gr.Checkbox(False, label='Ignore zero whiffs', info='Ignore zero whiff players if in top ranked', scale=1.5, min_width=100)
+            strict = gr.Checkbox(False, label='Strict', info='Ignore ties and restrict to # top players', scale=2, min_width=100)
+            ignore_zero_whiffs = gr.Checkbox(False, label='Ignore zero whiffs', info='Ignore zero whiff players if in top ranked', scale=2, min_width=100)
             show_rank = gr.Checkbox(False, label='Show rank', scale=1, min_width=100)
             debug = gr.Checkbox(False, label='Debug', info='Show dates', scale=1, min_width=100)
             search_btn = gr.Button('Search', scale=1, min_width=100)

data.py

@@ -2,7 +2,7 @@
 # import pandas as pd
 import polars as pl
 import numpy as np
-from gradio_client import Client
+# from gradio_client import Client
 from tqdm.auto import tqdm
 
 import os
@@ -159,32 +159,53 @@ df = (
 # unfortunately we have pas that don't show up in the pitch data, so this would be useful for
 pa_df = pa_df.join(player_df.rename({'player_id': 'pitcher'}), on='pitcher', how='inner')
 
-pitch_stats, rhb_pitch_stats, lhb_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])
-        # .rename({'name': 'Player', 'pitch_name': 'Pitch'})
-    )
-    for _df
-    in (
-        df,
-        df.filter(pl.col('stand') == 'R'),
-        df.filter(pl.col('stand') == 'L'),
-    )
-]
-league_pitch_stats, rhb_league_pitch_stats, lhb_league_pitch_stats = [
-    _df.group_by('pitch_name').agg(pl.col('release_speed').mean().round(1).alias('Velocity'))
-    for _df
-    in (
-        df,
-        df.filter(pl.col('stand') == 'R'),
-        df.filter(pl.col('stand') == 'L'),
-    )
-]
+# pitch_stats, rhb_pitch_stats, lhb_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])
+#         # .rename({'name': 'Player', 'pitch_name': 'Pitch'})
+#     )
+#     for _df
+#     in (
+#         df,
+#         df.filter(pl.col('stand') == 'R'),
+#         df.filter(pl.col('stand') == 'L'),
+#     )
+# ]
+# league_pitch_stats, rhb_league_pitch_stats, lhb_league_pitch_stats = [
+#     _df.group_by('pitch_name').agg(pl.col('release_speed').mean().round(1).alias('Velocity'))
+#     for _df
+#     in (
+#         df,
+#         df.filter(pl.col('stand') == 'R'),
+#         df.filter(pl.col('stand') == 'L'),
+#     )
+# ]
+
+def compute_pitch_stats(df):
+  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])
+  )
+  return pitch_stats
+
+pitch_stats = compute_pitch_stats(df)
+
+def compute_league_pitch_stats(df):
+  return df.group_by('pitch_name').agg(pl.col('release_speed').mean().round(1).alias('Velocity'))
+
+league_pitch_stats = compute_league_pitch_stats(df)

gradio_function.py

@@ -12,8 +12,9 @@ from math import ceil
 from translate import max_pitch_types, jp_pitch_to_en_pitch
 from data import (
     df,
-    pitch_stats, rhb_pitch_stats,lhb_pitch_stats,
-    league_pitch_stats, rhb_league_pitch_stats, lhb_league_pitch_stats
+    # pitch_stats, rhb_pitch_stats,lhb_pitch_stats,
+    # league_pitch_stats, rhb_league_pitch_stats, lhb_league_pitch_stats
+    compute_pitch_stats, compute_league_pitch_stats
 )
 
 
@@ -315,19 +316,27 @@ def plot_velo_summary(df, league_df, player):
 def update_dfs(player, handedness, df):
   if handedness == 'Both':
     handedness_filter = pl.col('stand').is_in(['R', 'L'])
-    _pitch_stats = pitch_stats
-    _league_pitch_stats = league_pitch_stats
+    # _pitch_stats = pitch_stats
+    # _league_pitch_stats = league_pitch_stats
   elif handedness == 'Right':
     handedness_filter = pl.col('stand') == 'R'
-    _pitch_stats = rhb_pitch_stats
-    _league_pitch_stats = rhb_league_pitch_stats
+    # _pitch_stats = rhb_pitch_stats
+    # _league_pitch_stats = rhb_league_pitch_stats
   elif handedness == 'Left':
     handedness_filter = pl.col('stand') == 'L'
-    _pitch_stats = lhb_pitch_stats
-    _league_pitch_stats = lhb_league_pitch_stats
+    # _pitch_stats = lhb_pitch_stats
+    # _league_pitch_stats = lhb_league_pitch_stats
   player_filter = pl.col('name') == player
   final_filter = player_filter & handedness_filter
-  return df.filter(final_filter), df.filter(handedness_filter), _pitch_stats.filter(player_filter), _league_pitch_stats,
+  _df = df.filter(final_filter)
+  _league_df = df.filter(handedness_filter)
+
+  return (
+    _df,
+    _league_df, 
+    compute_pitch_stats(_df), 
+    compute_league_pitch_stats(_league_df),
+  )
 
 def create_set_download_file_fn(filepath):
   def set_download_file(df):