wsba-hockey 1.0.2__py3-none-any.whl → 1.0.4__py3-none-any.whl

wsba_hockey/workspace.py

@@ -1,114 +1,35 @@
 import numpy as np
 import pandas as pd
-import matplotlib
-matplotlib.use('agg')
-import matplotlib.pyplot as plt
-import wsba_hockey as wsba
-from gspread_pandas import Spread, Client
-import urllib.request
-from wand.color import Color
-from wand.image import Image
+import wsba_main as wsba
+import data_pipelines as data
+import numpy as np
 
 season_load = wsba.repo_load_seasons()
 
-def workspace(seasons,type,arg = '',start='',end=''):
-    if type == 'pbp':
-        #Scrape pbp
-        errors=[]
-        for season in seasons:
-            data = wsba.nhl_scrape_season(season,remove=[],local=True,errors=True)
-            errors.append(data['errors'])
-            data['pbp'].to_csv(f'pbp/nhl_pbp_{season}.csv',index=False)
-        print(f'Errors: {errors}')
-
-    elif type == 'convert':
-        for season in seasons:
-            data = pd.read_csv(f"pbp/nhl_pbp_{season}.csv")
-            data = wsba.wsba_main.moneypuck_xG(data)
-            data.to_parquet(f'pbp/parquet/nhl_pbp_{season}.parquet',index=False)
-
-    elif type == 'team_info':
-        #Scrape team info
-        stand = [wsba.nhl_scrape_standings(season) for season in seasons]
-        standings = pd.concat(stand)
-        
-        colors = pd.read_csv('teaminfo/nhl_colors.csv')
-        data = pd.merge(colors,standings,how='right',left_on='triCode',right_on='teamAbbrev.default').sort_values(by=['seasonId','triCode'])
-        data['WSBA'] = data['teamAbbrev.default']+data['seasonId'].astype(str)
-
-        data.to_csv('teaminfo/nhl_teaminfo.csv',index=False)
-    
-    elif type == 'stats':
-        #Stats building
-        stats = []
-        for season in seasons:
-            for group in ['skater','team']:
-                pbp = pd.read_parquet(f'pbp/parquet/nhl_pbp_{season}.parquet')
-                stat = wsba.nhl_calculate_stats(pbp,group,[2],['5v5'],shot_impact=True)
-                stat.to_csv(f'stats/{group}/wsba_nhl_{season}_{group}.csv',index=False)
-                stats.append(stat)
-            pd.concat(stats).to_csv(f'stats/db/wsba_nhl_{group}_db.csv',index=False)
-    
-    elif type == 'plot_game':
-        for season in seasons:
-            pbp = wsba.nhl_scrape_season(season,remove=[],start=start,end=end)
-
-            plots = wsba.nhl_plot_games(pbp,wsba.wsba_main.fenwick_events,['5v5'],'all',team_colors=arg,legend=True)
-
-            games = list(pbp['game_id'].astype(str).drop_duplicates())
-            i = 1
-            for plot, game_id in zip(plots,games):
-                plot.savefig(f'plots/games/{game_id[0:4]}{int(game_id[0:4])+1}/{game_id[5:6]}/{game_id}_shotplot.png',bbox_inches='tight',transparent=True)
-                i += 1
-    
-    elif type == 'plot_skater':
-        for season in seasons:
-            pbp = pd.read_parquet(f'pbp/parquet/nhl_pbp_{season}.parquet')
+select = season_load[3:18]
 
-            skaters={}
+#data.pbp(select)
+#data.pbp_db(select)
 
-            for shooter,season,team in zip(pbp['event_player_1_name'],pbp['season'].astype(str),pbp['event_team_abbr']):    
-                if shooter is None:
-                    continue
-                else:
-                    skaters.update({
-                        shooter:[season,team]
-                    })
+#pbp = data.load_pbp_db(select)
 
-            plots = wsba.nhl_plot_skaters_shots(pbp,skaters,['5v5'],onice='indv',title=False,legend=True)
+#wsba.wsba_xG(pbp,hypertune=True,train=True,train_runs=30,cv_runs=30)
+#for season in select:
+#    wsba.nhl_apply_xG(data.load_pbp([season])).to_parquet(f'pbp/parquet/nhl_pbp_{season}.parquet',index=False)
+#data.pbp_db(select)
+test = pd.read_parquet('backblaze_pbp/20242025.parquet')
+test.loc[(test['event_goalie_id']==8476945)].to_csv('Hellebuyck.csv',index=False)
 
-            items = list(skaters.items())
-            for plot,skater in zip(plots,items):
-                plot.savefig(f'plots/{skater[1][0]}/{skater[0]}{skater[1][0]}{skater[1][1]}_indv.png',bbox_inches='tight',transparent=True)
-    
-    elif type == 'logos':
-        data = pd.read_csv('teaminfo/nhl_teaminfo.csv')
-        for url, id in zip(data['teamLogo'],data['WSBA']):
-            print(url)
-            urllib.request.urlretrieve(url,f'tools/logos/svg/{id}.svg')
-            with Image(filename=f'tools/logos/svg/{id}.svg') as img:
-                img.format = 'png32'
-                img.background_color = Color('transparent')  
-                img.alpha_channel = 'activate'    
-                img.save(filename=f'tools/logos/png/{id}.png')
-                
-    else:
-        print('Nothing here.')
+mp = pd.read_csv('shots_2024.csv')
+mp.loc[(mp['goalieIdForShot']==8476945)].to_csv('mfreally.csv',index=False)
+#wsba.roc_auc_curve(test,'tools/xg_model/wsba_xg.joblib')
+#wsba.feature_importance('tools/xg_model/wsba_xg.joblib')
+#wsba.reliability(test,'tools/xg_model/wsba_xg.joblib')
 
-def push_to_sheet():
-    spread = Spread('WSBA - NHL 5v5 Shooting Metrics Public v2.0')
+## UPLOAD TO BACKBLAZE ##
 
-    #Tables
-    skater = pd.read_csv('stats/db/wsba_nhl_skater_db.csv')
-    team = pd.read_csv('stats/db/wsba_nhl_team_db.csv')
-    team_info = pd.read_csv('teaminfo/nhl_teaminfo.csv')
-    country = pd.read_csv('teaminfo/nhl_countryinfo.csv')
-    schedule = pd.read_csv('schedule/schedule.csv')
+#data.stats(['goalie'],select)
+#data.game_log(['goalie'],select)
 
-    spread.df_to_sheet(skater,index=False,sheet='Skaters DB')
-    spread.df_to_sheet(team,index=False,sheet='Teams DB')
-    spread.df_to_sheet(team_info,index=False,sheet='Team Info')
-    spread.df_to_sheet(country,index=False,sheet='Country Info')
-    spread.df_to_sheet(schedule,index=False,sheet='Schedule')
+#data.push_to_sheet(select,['skaters','team','info'])
 
-workspace(['20242025'],'plot_game',arg={'away':'secondary','home':'primary'}, start='04-20',end='04-20')