Update app.py

app.py

@@ -242,84 +242,84 @@ def server(input, output, session):
 
         return df_merge
 
-    @reactive.Calc
-    def ts_data():
-
-        df_spring = spring_data()
-
-        # 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(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
+    # @reactive.Calc
+    # def ts_data():
+
+    #     df_spring = spring_data()
+
+    #     # 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(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
 
     @reactive.Calc
     def ts_data_summ():
@@ -646,9 +646,9 @@ def server(input, output, session):
         df_last_game = df_spring_stuff.filter(pl.col("is_last_game"))
         df_prior_games = df_spring_stuff.filter(~pl.col("is_last_game"))
         
-        # Step 5: Apply feature engineering to both
-        df_last_group = stuff_apply.stuff_apply(fe.feature_engineering(df_last_game))
-        df_prior_group = stuff_apply.stuff_apply(fe.feature_engineering(df_prior_games))
+        # # Step 5: Apply feature engineering to both
+        # df_last_group = stuff_apply.stuff_apply(fe.feature_engineering(df_last_game))
+        # df_prior_group = stuff_apply.stuff_apply(fe.feature_engineering(df_prior_games))
         
         # Step 6: Group and aggregate both
         def group_by_pitch(df):