Update app.py

app.py

@@ -49,47 +49,32 @@ print('Starting Everything:')
 # pa_df = pd.read_csv('pa_df_all.csv',index_col=[0])
 # pa_df_full_na = pa_df.dropna()
 
-### Import Datasets
-dataset = load_dataset('nesticot/mlb_data', data_files=['mlb_pitch_data_2024.csv',
-                                                         ])
-dataset_train = dataset['train']
-exit_velo_df_mlb = dataset_train.to_pandas().set_index(list(dataset_train.features.keys())[0]).reset_index(drop=True)
+
+exit_velo_df_mlb = pl.read_parquet(f"hf://datasets/TJStatsApps/mlb_data/data/mlb_pitch_data_2025.parquet").to_pandas()
 #print(df_2023)
 exit_velo_df_mlb['level'] = 'MLB'
 
-### Import Datasets
-dataset = load_dataset('nesticot/mlb_data', data_files=['aaa_pitch_data_2024.csv',
-                                                         ])
-dataset_train = dataset['train']
-exit_velo_df_aaa = dataset_train.to_pandas().set_index(list(dataset_train.features.keys())[0]).reset_index(drop=True)
+
+exit_velo_df_aaa = pl.read_parquet(f"hf://datasets/TJStatsApps/mlb_data/data/aaa_pitch_data_2025.parquet").to_pandas()
 #print(df_2023)
 exit_velo_df_aaa['level'] = 'AAA'
 
-### Import Datasets
-dataset = load_dataset('nesticot/mlb_data', data_files=['aa_pitch_data_2024.csv',
-                                                        ])
-dataset_train = dataset['train']
-exit_velo_df_aa = dataset_train.to_pandas().set_index(list(dataset_train.features.keys())[0]).reset_index(drop=True)
+
+exit_velo_df_aa = pl.read_parquet(f"hf://datasets/TJStatsApps/mlb_data/data/aa_pitch_data_2025.parquet").to_pandas()
 #print(df_2023)
 exit_velo_df_aa['level'] = 'AA'
 
-### Import Datasets
-dataset = load_dataset('nesticot/mlb_data', data_files=['high_a_pitch_data_2024.csv',
-                                                         ])
-dataset_train = dataset['train']
-exit_velo_df_ha = dataset_train.to_pandas().set_index(list(dataset_train.features.keys())[0]).reset_index(drop=True)
+
+exit_velo_df_ha = pl.read_parquet(f"hf://datasets/TJStatsApps/mlb_data/data/hi_a_pitch_data_2025.parquet").to_pandas()
 #print(df_2023)
 exit_velo_df_ha['level'] = 'A+'
 
 ### Import Datasets
-dataset = load_dataset('nesticot/mlb_data', data_files=['a_pitch_data_2024.csv',
-                                                         ])
-dataset_train = dataset['train']
-exit_velo_df_a = dataset_train.to_pandas().set_index(list(dataset_train.features.keys())[0]).reset_index(drop=True)
+exit_velo_df_a = pl.read_parquet(f"hf://datasets/TJStatsApps/mlb_data/data/lo_a_pitch_data_2025.parquet").to_pandas()
 #print(df_2023)
 exit_velo_df_a['level'] = 'A'
 
-exit_velo_df = pd.concat([exit_velo_df_mlb,exit_velo_df_aaa,exit_velo_df_aa,exit_velo_df_ha,exit_velo_df_a])
+exit_velo_df = pl.concat([exit_velo_df_mlb,exit_velo_df_aaa,exit_velo_df_aa,exit_velo_df_ha,exit_velo_df_a])
 # exit_velo_df = pd.concat([exit_velo_df_mlb,exit_velo_df_aaa])
 # exit_velo_df_copy = exit_velo_df.copy()
 
@@ -107,191 +92,6 @@ def percentile(n):
 exit_velo_df_codes = df_update(exit_velo_df)
 
 
-# end_codes = ['strikeout', 'field_out', 'single', 'walk', 'hit_by_pitch',
-#        'double', 'sac_fly', 'force_out', 'home_run',
-#        'grounded_into_double_play', 'fielders_choice', 'field_error',
-#        'triple', 'sac_bunt', 'double_play', 'intent_walk',
-#        'fielders_choice_out', 'strikeout_double_play',
-#        'sac_fly_double_play', 'catcher_interf', 'other_out']
-
-
-
-# exit_velo_df['pa'] = [1 if isinstance(x, str) else 0 for x in exit_velo_df.event_type]
-# #exit_velo_df['pa'] = 1
-# exit_velo_df['k'] = exit_velo_df.event_type.isin(list(filter(None, [x if 'strikeout' in x else '' for x in exit_velo_df.event_type.fillna('None').unique()])))
-# #exit_velo_df['bb'] = exit_velo_df.event_type.isin(list(filter(None, [x if 'walk' in x else '' for x in exit_velo_df.event_type.fillna('None').unique()])))
-# exit_velo_df['bb'] = exit_velo_df.event_type.isin(['walk','intent_walk'])
-
-# #exit_velo_df['k_minus_bb'] = exit_velo_df['k'].astype(np.float32)-exit_velo_df['bb'].astype(np.float32)
-# exit_velo_df['bb_minus_k'] = exit_velo_df['bb'].astype(np.float32)-exit_velo_df['k'].astype(np.float32)
-
-
-
-# exit_velo_df = exit_velo_df.drop_duplicates(subset=['play_id'])
-
-
-
-# swing_codes = ['Swinging Strike', 'In play, no out', 
-#         'Foul', 'In play, out(s)', 
-#        'In play, run(s)', 'Swinging Strike (Blocked)',
-#        'Foul Bunt','Foul Tip', 'Missed Bunt','Foul Pitchout','Swinging Pitchout']
-
-# swings_in = ['Swinging Strike', 'In play, no out', 
-#         'Foul', 'In play, out(s)', 
-#        'In play, run(s)', 'Swinging Strike (Blocked)',
-#        'Foul Bunt','Foul Tip', 'Missed Bunt','Foul Pitchout','Swinging Pitchout']       
-
-# swing_strike_codes = ['Swinging Strike',
-#  'Swinging Strike (Blocked)','Missed Bunt','Foul Tip','Swinging Pitchout']
-
-
-# contact_codes = ['In play, no out', 
-#         'Foul', 'In play, out(s)', 
-#        'In play, run(s)', 
-#        'Foul Bunt']
-
-# codes_in = ['In play, out(s)',
-# 'Swinging Strike',
-# 'Ball',
-# 'Foul',
-# 'In play, no out',
-# 'Called Strike',
-# 'Foul Tip',
-# 'In play, run(s)',
-# 'Hit By Pitch',
-# 'Ball In Dirt',
-# 'Pitchout',
-# 'Swinging Strike (Blocked)',
-# 'Foul Bunt',
-# 'Missed Bunt',
-# 'Foul Pitchout',
-# 'Intent Ball',
-# 'Swinging Pitchout']
-
-
-
-
-# exit_velo_df['in_zone'] = [x < 10 if x > 0 else np.nan for x in exit_velo_df['zone']]
-
-
-# if len(exit_velo_df.loc[(~exit_velo_df['x'].isnull())&(exit_velo_df['px'].isnull()),'px']) > 0:
-#     exit_velo_df.loc[(~exit_velo_df['x'].isnull())&(exit_velo_df['px'].isnull()),'px'] = px_model.predict(exit_velo_df.loc[(~exit_velo_df['x'].isnull())&(exit_velo_df['px'].isnull())][['x']])
-#     exit_velo_df.loc[(~exit_velo_df['y'].isnull())&(exit_velo_df['pz'].isnull()),'pz'] = px_model.predict(exit_velo_df.loc[(~exit_velo_df['y'].isnull())&(exit_velo_df['pz'].isnull())][['y']]) + 3.2
-
-
-# # exit_velo_df['in_zone'] =  [x < 10 if x > 0 else np.nan for x in exit_velo_df['zone']]
-# exit_velo_df.loc[(~exit_velo_df['px'].isna())&
-#                             (exit_velo_df['in_zone'].isna())&
-#                             (~exit_velo_df['sz_top'].isna())&
-#                             (~exit_velo_df['pz'].isna())&
-#                             (~exit_velo_df['sz_bot'].isna())
-#                             ,'in_zone'] = in_zone_model.predict(exit_velo_df.loc[(~exit_velo_df['px'].isna())&
-#                                                                 (exit_velo_df['in_zone'].isna())&
-#                                                                 (~exit_velo_df['sz_top'].isna())&
-#                                                                 (~exit_velo_df['pz'].isna())&
-#                                                                 (~exit_velo_df['sz_bot'].isna())][['px','pz','sz_top','sz_bot']].values)
-
-# exit_velo_df = exit_velo_df.drop_duplicates(subset=['play_id'])
-
-# exit_velo_df_codes = exit_velo_df[exit_velo_df.play_description.isin(codes_in)].dropna(subset=['in_zone'])
-
-# exit_velo_df_codes['bip'] = ~exit_velo_df_codes.launch_speed.isna()
-# conditions = [
-#     (exit_velo_df_codes['launch_speed'].isna()),
-#     (exit_velo_df_codes['launch_speed']*1.5 - exit_velo_df_codes['launch_angle'] >= 117 ) & (exit_velo_df_codes['launch_speed'] + exit_velo_df_codes['launch_angle'] >= 124) & (exit_velo_df_codes['launch_speed'] > 98) & (exit_velo_df_codes['launch_angle'] >= 8) & (exit_velo_df_codes['launch_angle'] <= 50)
-# ]
-
-# choices = [False,True]
-# exit_velo_df_codes['barrel'] = np.select(conditions, choices, default=np.nan)
-
-# conditions_ss = [
-#     (exit_velo_df_codes['launch_angle'].isna()),
-#     (exit_velo_df_codes['launch_angle'] >= 8 ) * (exit_velo_df_codes['launch_angle'] <= 32 ) 
-# ]
-
-# choices_ss = [False,True]
-# exit_velo_df_codes['sweet_spot'] = np.select(conditions_ss, choices_ss, default=np.nan)
-
-
-# conditions_hh = [
-#     (exit_velo_df_codes['launch_speed'].isna()),
-#     (exit_velo_df_codes['launch_speed'] >= 94.5 ) 
-# ]
-
-# choices_hh = [False,True]
-# exit_velo_df_codes['hard_hit'] = np.select(conditions_hh, choices_hh, default=np.nan)
-
-
-# conditions_tb = [
-#     (exit_velo_df_codes['event_type']=='single'),
-#     (exit_velo_df_codes['event_type']=='double'),
-#     (exit_velo_df_codes['event_type']=='triple'),
-#     (exit_velo_df_codes['event_type']=='home_run'),
-# ]
-
-# choices_tb = [1,2,3,4]
-
-# exit_velo_df_codes['tb'] = np.select(conditions_tb, choices_tb, default=np.nan)
-
-# conditions_woba = [
-#     (exit_velo_df_codes['event_type']=='walk'),
-#     (exit_velo_df_codes['event_type']=='hit_by_pitch'),    
-#     (exit_velo_df_codes['event_type']=='single'),
-#     (exit_velo_df_codes['event_type']=='double'),
-#     (exit_velo_df_codes['event_type']=='triple'),
-#     (exit_velo_df_codes['event_type']=='home_run'),
-# ]
-
-# choices_woba = [0.705,
-#                 0.688,
-#                 0.897,
-#                 1.233,
-#                 1.612,
-#                 2.013]
-
-# exit_velo_df_codes['woba'] = np.select(conditions_woba, choices_woba, default=np.nan)
-
-
-# woba_codes = ['strikeout', 'field_out', 'single', 'walk', 'hit_by_pitch',
-#        'double', 'sac_fly', 'force_out', 'home_run',
-#        'grounded_into_double_play', 'fielders_choice', 'field_error',
-#        'triple', 'sac_bunt', 'double_play',
-#        'fielders_choice_out', 'strikeout_double_play',
-#        'sac_fly_double_play', 'other_out']
-
-
-
-
-
-# conditions_woba_code = [
-#     (exit_velo_df_codes['event_type'].isin(woba_codes))
-# ]
-
-# choices_woba_code = [1]
-
-# exit_velo_df_codes['woba_codes'] = np.select(conditions_woba_code, choices_woba_code, default=np.nan)
-
-
-# #exit_velo_df_codes['barrel']  = (exit_velo_df_codes.launch_speed >= 98) & (exit_velo_df_codes.launch_angle >= (26 - (-98 + exit_velo_df_codes.launch_speed))) & (exit_velo_df_codes.launch_angle <= 30 + (-98 + exit_velo_df_codes.launch_speed)) & (exit_velo_df_codes.launch_angle >= 8) & (exit_velo_df_codes.launch_angle <= 50)
-
-
-
-
-
-# #exit_velo_df_codes['barrel']  = (exit_velo_df_codes.launch_speed >= 98) & (exit_velo_df_codes.launch_angle >= (26 - (-98 + exit_velo_df_codes.launch_speed))) & (exit_velo_df_codes.launch_angle <= 30 + (-98 + exit_velo_df_codes.launch_speed)) & (exit_velo_df_codes.launch_angle >= 8) & (exit_velo_df_codes.launch_angle <= 50)
-# exit_velo_df_codes['pitches'] = 1
-# exit_velo_df_codes['whiffs'] = [1 if ((x == 'S')|(x == 'W')|(x =='T')) else 0 for x in exit_velo_df_codes.play_code]
-# exit_velo_df_codes['csw'] = [1 if ((x == 'S')|(x == 'W')|(x =='T')|(x == 'C')) else 0 for x in exit_velo_df_codes.play_code]
-# exit_velo_df_codes['swings'] = [1 if x in swings_in else 0 for x in exit_velo_df_codes.play_description]
-
-# exit_velo_df_codes['out_zone'] = exit_velo_df_codes.in_zone == False
-# exit_velo_df_codes['zone_swing'] = (exit_velo_df_codes.in_zone == True)&(exit_velo_df_codes.swings == 1)
-# exit_velo_df_codes['zone_contact'] = (exit_velo_df_codes.in_zone == True)&(exit_velo_df_codes.swings == 1)&(exit_velo_df_codes.whiffs == 0)
-# exit_velo_df_codes['ozone_swing'] = (exit_velo_df_codes.in_zone==False)&(exit_velo_df_codes.swings == 1)
-# exit_velo_df_codes['ozone_contact'] = (exit_velo_df_codes.in_zone==False)&(exit_velo_df_codes.swings == 1)&(exit_velo_df_codes.whiffs == 0)
-
-
-
 exit_velo_df_codes_summ = exit_velo_df_codes.groupby(['batter_id','batter_name','level']).agg(
     pa = ('pa','sum'), 
     k = ('k','sum'),