Update app.py

app.py

@@ -60,6 +60,7 @@ app_ui = ui.page_fluid(
         ),
         ui.navset_tab(
             ui.nav("All Pitches",
+                ui.download_button("download_all", "Download Data", class_="btn-sm mb-3"),
                 output_tabulator("table_all")
             ),
             ui.nav("Daily Pitches",
@@ -77,6 +78,109 @@ app_ui = ui.page_fluid(
 )
 
 def server(input, output, session):
+
+
+    @reactive.Calc
+    def ts_data():
+
+        import polars as pl
+        df_spring = pl.read_parquet(f"hf://datasets/TJStatsApps/mlb_data/data/mlb_pitch_data_2025_spring.parquet")
+
+
+        date = (datetime.datetime.now() - datetime.timedelta(hours=8)).date()
+        print(datetime.datetime.now())
+        date_str = date.strftime('%Y-%m-%d')
+        # Initialize the scraper
+
+
+        game_list_input = (scraper.get_schedule(year_input=[int(date_str[0:4])], sport_id=[1], game_type=['S'])
+                    .filter(pl.col('date') == date)['game_id'])
+
+        data = scraper.get_data(game_list_input)
+        df = scraper.get_data_df(data)
+
+        df_spring = pl.concat([df_spring, df]).sort('game_date', descending=True)
+
+
+
+        # df_year_old = stuff_apply.stuff_apply(fe.feature_engineering(pl.concat([df_mlb,df_aaa,df_a,df_afl])))
+        # df_year_2old = stuff_apply.stuff_apply(fe.feature_engineering(pl.concat([df_mlb_2023])))
+        df_spring_stuff = stuff_apply.stuff_apply(fe.feature_engineering(pl.concat([df_spring])))
+
+
+
+        import polars as pl
+
+        # Compute total pitches for each pitcher
+        df_pitcher_totals = df_spring_stuff.group_by("pitcher_id").agg(
+            pl.col("start_speed").count().alias("pitcher_total")
+        )
+
+        df_spring_group = df_spring_stuff.group_by(['pitcher_id', 'pitcher_name', 'pitch_type']).agg([
+            pl.col('start_speed').count().alias('count'),
+            pl.col('start_speed').mean().alias('start_speed'),
+            pl.col('start_speed').max().alias('max_start_speed'),
+            pl.col('ivb').mean().alias('ivb'),
+            pl.col('hb').mean().alias('hb'),
+            pl.col('release_pos_z').mean().alias('release_pos_z'),
+            pl.col('release_pos_x').mean().alias('release_pos_x'),
+            pl.col('extension').mean().alias('extension'),
+            pl.col('tj_stuff_plus').mean().alias('tj_stuff_plus'),
+            (pl.col('start_speed').filter(pl.col('batter_hand')=='L').count()).alias('rhh_count'),
+            (pl.col('start_speed').filter(pl.col('batter_hand')=='R').count()).alias('lhh_count')
+        ])
+
+        # Join total pitches per pitcher to the grouped DataFrame on pitcher_id
+        df_spring_group = df_spring_group.join(df_pitcher_totals, on="pitcher_id", how="left")
+
+        # Now calculate the pitch percent for each pitcher/pitch_type combination
+        df_spring_group = df_spring_group.with_columns(
+            (pl.col("count") / pl.col("pitcher_total")).alias("pitch_percent")
+        )
+
+        # Optionally, if you want the percentage of left/right-handed batters within the group:
+        df_spring_group = df_spring_group.with_columns([
+            (pl.col("rhh_count") / pl.col("pitcher_total")).alias("rhh_percent"),
+            (pl.col("lhh_count") / pl.col("pitcher_total")).alias("lhh_percent")
+        ])
+
+        df_merge = df_spring_group.join(df_year_old_group,on=['pitcher_id','pitch_type'],how='left',suffix='_old')
+
+
+        df_merge = df_merge.with_columns(
+            pl.col('pitcher_id').is_in(df_year_old_group['pitcher_id']).alias('exists_in_old')
+        )
+
+        df_merge = df_merge.with_columns(
+            pl.when(pl.col('start_speed_old').is_null() & pl.col('exists_in_old'))
+            .then(pl.lit(True))
+            .otherwise(pl.lit(None))
+            .alias("new_pitch")
+        )
+
+        df_merge = df_merge.select([
+            'pitcher_id',
+            'pitcher_name',
+            'pitch_type',
+            'count',
+            'pitch_percent',
+            'rhh_percent',
+            'lhh_percent',
+            'start_speed',
+            'max_start_speed',
+            'ivb',
+            'hb',
+            'release_pos_z',
+            'release_pos_x',
+            'extension',
+            'tj_stuff_plus',
+        ])
+
+        return df_merge
+
+    @session.download(filename="data.csv")
+    def download_all():
+        yield ts_data().write_csv()
     @output
     @render_tabulator
     @reactive.event(input.refresh)