wsba-hockey 1.0.4__py3-none-any.whl → 1.0.6__py3-none-any.whl

wsba_hockey/__init__.py

@@ -1 +1 @@
-from .wsba_main import nhl_scrape_game,nhl_scrape_schedule,nhl_scrape_season,nhl_scrape_seasons_info,nhl_scrape_standings,nhl_scrape_roster,nhl_scrape_draft_rankings,nhl_scrape_prospects,nhl_calculate_stats,nhl_shooting_impacts,nhl_plot_skaters_shots,nhl_plot_games,repo_load_rosters,repo_load_schedule,repo_load_teaminfo,repo_load_pbp,repo_load_seasons
+from wsba_hockey.wsba_main import nhl_scrape_game,nhl_scrape_schedule,nhl_scrape_season,nhl_scrape_seasons_info,nhl_scrape_standings,nhl_scrape_roster,nhl_scrape_draft_rankings,nhl_scrape_prospects,nhl_calculate_stats,nhl_shooting_impacts,nhl_apply_xG,nhl_plot_skaters_shots,nhl_plot_games,repo_load_rosters,repo_load_schedule,repo_load_teaminfo,repo_load_pbp,repo_load_seasons

wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/game_stats/app.py

@@ -1,6 +1,5 @@
 import pandas as pd
 import numpy as np
-import wsba_hockey as wsba
 from urllib.parse import *
 from shiny import *
 from shinywidgets import output_widget, render_widget 

wsba_hockey/tools/agg.py

@@ -1,6 +1,6 @@
 import pandas as pd
 import numpy as np
-from .xg_model import *
+from wsba_hockey.tools.xg_model import *
 
 ## AGGREGATE FUNCTIONS ##
 

wsba_hockey/tools/plotting.py

@@ -1,14 +1,16 @@
 import matplotlib.pyplot as plt
-import matplotlib.image as mpimg
 import numpy as np
 import pandas as pd
-from scipy.interpolate import griddata
-from scipy.ndimage import gaussian_filter
-import urllib.request
-import PIL
-from .xg_model import *
 from hockey_rink import NHLRink
 from hockey_rink import CircularImage
+from scipy.interpolate import griddata
+from scipy.ndimage import gaussian_filter
+from wsba_hockey.tools.xg_model import *
+
+### PLOTTING FUNCTIONS ###
+# Provided in this file are basic plotting functions for the WSBA Hockey Python package. #
+
+## GLOBAL VARIABLES ##
 
 event_markers = {
     'faceoff':'X',
@@ -21,6 +23,10 @@ event_markers = {
     'takeaway':'2',
 }
 
+dir = os.path.dirname(os.path.realpath(__file__))
+info_path = os.path.join(dir,'teaminfo\\nhl_teaminfo.csv')
+img_path = os.path.join(dir,'utils\\wsba.png')
+
 def wsba_rink(display_range='offense',rotation = 0):
     img = 'tools/utils/wsba.png'
     rink = NHLRink(center_logo={
@@ -81,7 +87,7 @@ def plot_skater_shots(pbp, player, season, team, strengths, title = None, marker
     pbp = prep_plot_data(pbp,shots,strengths,marker_dict)
     pbp = pbp.loc[(pbp['season'].astype(str)==season)&((pbp['away_team_abbr']==team)|(pbp['home_team_abbr']==team))]
 
-    team_data = pd.read_csv('teaminfo/nhl_teaminfo.csv')
+    team_data = pd.read_csv(info_path)
     team_color = list(team_data.loc[team_data['WSBA']==f'{team}{season}','Primary Color'])[0]
     team_color_2nd = list(team_data.loc[team_data['WSBA']==f'{team}{season}','Secondary Color'])[0]
 
@@ -115,7 +121,7 @@ def plot_game_events(pbp,game_id,events,strengths,marker_dict=event_markers,team
     date = list(pbp['game_date'])[0]
     season = list(pbp['season'])[0]
 
-    team_data = pd.read_csv('teaminfo/nhl_teaminfo.csv')
+    team_data = pd.read_csv(info_path)
     team_info ={
         'away_color':'#000000' if list(team_data.loc[team_data['WSBA']==f'{away_abbr}{season}','Secondary Color'])[0]=='#FFFFFF' else list(team_data.loc[team_data['WSBA']==f'{away_abbr}{season}',f'{team_colors['away'].capitalize()} Color'])[0],
         'home_color': list(team_data.loc[team_data['WSBA']==f'{home_abbr}{season}',f'{team_colors['home'].capitalize()} Color'])[0],

wsba_hockey/tools/scraping.py

@@ -1,12 +1,12 @@
 import re
-from bs4 import BeautifulSoup
-import requests as rs
-import json as json_lib
-from .utils.shared import *
-import numpy as np
-import pandas as pd
 import warnings
 import os
+import numpy as np
+import pandas as pd
+import requests as rs
+import json as json_lib
+from bs4 import BeautifulSoup
+from wsba_hockey.tools.utils.shared import *
 warnings.filterwarnings('ignore')
 
 ### SCRAPING FUNCTIONS ###

wsba_hockey/tools/xg_model.py

@@ -1,13 +1,14 @@
+import joblib
+import os
 import pandas as pd
 import numpy as np
 import xgboost as xgb
 import scipy.sparse as sp
-import joblib
-import wsba_main as wsba
-import tools.scraping as scraping
+import wsba_hockey.wsba_main as wsba
+import wsba_hockey.tools.scraping as scraping
+import matplotlib.pyplot as plt
 from sklearn.calibration import calibration_curve
 from sklearn.metrics import roc_curve, auc
-import matplotlib.pyplot as plt
 
 ### XG_MODEL FUNCTIONS ###
 # Provided in this file are functions vital to the goal prediction model in the WSBA Hockey Python package. #
@@ -78,12 +79,18 @@ strengths = ['3v3',
             '6v4',
             '6v5']
 
+dir = os.path.dirname(os.path.realpath(__file__))
+roster_path = os.path.join(dir,'rosters\\nhl_rosters.csv')
+xg_model_path = os.path.join(dir,'xg_model\\wsba_xg.joblib')
+test_path = os.path.join(dir,'xg_model\\testing\\xg_model_training_runs.csv')
+cv_path = os.path.join(dir,'xg_model\\testing\\xg_model_cv_runs.csv')
+
 def fix_players(pbp):
     #Add/fix player info for shooters and goaltenders
     print('Adding player info to pbp...')
 
     #Load roster and all players
-    roster = pd.read_csv('rosters/nhl_rosters.csv').drop_duplicates(['id'])[['fullName','id','shootsCatches']]
+    roster = pd.read_csv(roster_path).drop_duplicates(['id'])[['fullName','id','shootsCatches']]
 
     #Some players are missing from the roster file (generally in newer seasons); add these manually
     miss = list(pbp.loc[~(pbp['event_player_1_id'].isin(list(roster['id'])))&(pbp['event_player_1_id'].notna()),'event_player_1_id'].drop_duplicates())
@@ -111,6 +118,7 @@ def fix_players(pbp):
 
 def prep_xG_data(data):
     #Prep data for xG training and calculation
+    data = fix_players(data)
 
     #Informal groupby
     data = data.sort_values(by=['season','game_id','period','seconds_elapsed','event_num'])
@@ -168,7 +176,7 @@ def prep_xG_data(data):
     #Return: pbp data prepared to train and calculate the xG model
     return data
 
-def wsba_xG(pbp, hypertune = False, train = False, model_path = "tools/xg_model/wsba_xg.joblib", train_runs = 20, cv_runs = 20):
+def wsba_xG(pbp, hypertune = False, train = False, model_path = xg_model_path, train_runs = 20, cv_runs = 20):
     #Train and calculate the WSBA Expected Goals model
 
     #Add index for future merging
@@ -258,7 +266,7 @@ def wsba_xG(pbp, hypertune = False, train = False, model_path = "tools/xg_model/
             # Arrange to get best run
             best_all = best_all.sort_values(by="auc", ascending=False)
 
-            best_all.to_csv("tools/xg_model/testing/xg_model_training_runs.csv",index=False)
+            best_all.to_csv(test_path,index=False)
 
             # Final parameters
             param_7_EV = {
@@ -303,11 +311,11 @@ def wsba_xG(pbp, hypertune = False, train = False, model_path = "tools/xg_model/
 
             # Clean results and sort to find the number of rounds to use and seed
             cv_final = cv_test.sort_values(by="AUC", ascending=False)
-            cv_final.to_csv("tools/xg_model/testing/xg_model_cv_runs.csv",index=False)
+            cv_final.to_csv(cv_path,index=False)
         else:
             # Load previous parameters
-            best_all = pd.read_csv('tools/xg_model/testing/xg_model_training_runs.csv')
-            cv_final = pd.read_csv("tools/xg_model/testing/xg_model_cv_runs.csv")
+            best_all = pd.read_csv(test_path)
+            cv_final = pd.read_csv(cv_path)
 
             print('Loaded hyperparameters...')
             # Final parameters

wsba_hockey/wsba_main.py

@@ -1,12 +1,13 @@
+import random
+import os
 import requests as rs
 import pandas as pd
 import time
-import random
 from datetime import datetime, timedelta, date
-from tools.scraping import *
-from tools.xg_model import *
-from tools.agg import *
-from tools.plotting import *
+from .tools.scraping import *
+from .tools.xg_model import *
+from .tools.agg import *
+from .tools.plotting import *
 
 ### WSBA HOCKEY ###
 ## Provided below are all integral functions in the WSBA Hockey Python package. ##
@@ -62,7 +63,7 @@ per_sixty = ['Fi','xGi','Gi','A1','A2','P1','P','OZF','NZF','DZF','FF','FA','xGF
 
 #Some games in the API are specifically known to cause errors in scraping.
 #This list is updated as frequently as necessary
-known_probs ={
+known_probs = {
     '2007020011':'Missing shifts data for game between Chicago and Minnesota.',
     '2007021178':'Game between the Bruins and Sabres is missing data after the second period, for some reason.',
     '2008020259':'HTML data is completely missing for this game.',
@@ -105,6 +106,11 @@ standings_end = {
 
 events = ['faceoff','hit','giveaway','takeaway','blocked-shot','missed-shot','shot-on-goal','goal','penalty']
 
+dir = os.path.dirname(os.path.realpath(__file__))
+schedule_path = os.path.join(dir,'tools\\schedule\\schedule.csv')
+info_path = os.path.join(dir,'tools\\teaminfo\\nhl_teaminfo.csv')
+default_roster = os.path.join(dir,'tools\\rosters\\nhl_rosters.csv')
+
 ## SCRAPE FUNCTIONS ##
 def nhl_scrape_game(game_ids,split_shifts = False, remove = ['period-start','period-end','challenge','stoppage','shootout-complete','game-end'],verbose = False, sources = False, errors = False):
     #Given a set of game_ids (NHL API), return complete play-by-play information as requested
@@ -296,7 +302,7 @@ def nhl_scrape_schedule(season,start = "09-01", end = "08-01"):
     #Return: specificed schedule data
     return df
 
-def nhl_scrape_season(season,split_shifts = False, season_types = [2,3], remove = ['period-start','period-end','game-end','challenge','stoppage'], start = "09-01", end = "08-01", local=False, local_path = "schedule/schedule.csv", verbose = False, sources = False, errors = False):
+def nhl_scrape_season(season,split_shifts = False, season_types = [2,3], remove = ['period-start','period-end','game-end','challenge','stoppage'], start = "09-01", end = "08-01", local=False, local_path = schedule_path, verbose = False, sources = False, errors = False):
     #Given season, scrape all play-by-play occuring within the season
     # param 'season' - NHL season to scrape
     # param 'split_shifts' - boolean which splits pbp and shift events if true
@@ -402,7 +408,7 @@ def nhl_scrape_roster(season):
     #Given a nhl season, return rosters for all participating teams
     # param 'season' - NHL season to scrape
     print("Scrpaing rosters for the "+ season + "season...")
-    teaminfo = pd.read_csv("teaminfo/nhl_teaminfo.csv")
+    teaminfo = pd.read_csv(info_path)
 
     rosts = []
     for team in list(teaminfo['Team']):
@@ -503,8 +509,6 @@ def nhl_apply_xG(pbp):
     #param 'pbp' - play-by-play data
 
     print(f'Applying WSBA xG to model with seasons: {pbp['season'].drop_duplicates().to_list()}')
-    #Fix player data
-    #pbp = fix_players(pbp)
 
     #Apply xG model
     pbp = wsba_xG(pbp)
@@ -861,7 +865,7 @@ def nhl_shooting_impacts(agg,type):
         #Return: skater stats with shooting impacts
         return df
 
-def nhl_calculate_stats(pbp,type,season_types,game_strength,split_game=False,roster_path="rosters/nhl_rosters.csv",shot_impact=False):
+def nhl_calculate_stats(pbp,type,season_types,game_strength,split_game=False,roster_path=default_roster,shot_impact=False):
     #Given play-by-play, seasonal information, game_strength, rosters, and xG model, return aggregated stats
     # param 'pbp' - play-by-play dataframe
     # param 'type' - type of stats to calculate ('skater', 'goalie', or 'team')
@@ -1179,7 +1183,7 @@ def repo_load_rosters(seasons = []):
     #Returns roster data from repository
     # param 'seasons' - list of seasons to include
 
-    data = pd.read_csv("rosters/nhl_rosters.csv")
+    data = pd.read_csv(default_roster)
     if len(seasons)>0:
         data = data.loc[data['season'].isin(seasons)]
 
@@ -1189,7 +1193,7 @@ def repo_load_schedule(seasons = []):
     #Returns schedule data from repository
     # param 'seasons' - list of seasons to include
 
-    data = pd.read_csv("schedule/schedule.csv")
+    data = pd.read_csv(schedule_path)
     if len(seasons)>0:
         data = data.loc[data['season'].isin(seasons)]
 
@@ -1198,7 +1202,7 @@ def repo_load_schedule(seasons = []):
 def repo_load_teaminfo():
     #Returns team data from repository
 
-    return pd.read_csv("teaminfo/nhl_teaminfo.csv")
+    return pd.read_csv(info_path)
 
 def repo_load_pbp(seasons = []):
     #Returns play-by-play data from repository

{wsba_hockey-1.0.4.dist-info → wsba_hockey-1.0.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wsba_hockey
-Version: 1.0.4
+Version: 1.0.6
 Summary: WeakSide Breakout's complete Python package of access to hockey data, primairly including the scraping of National Hockey League schedule, play-by-play, and shifts information.
 Author-email: Owen Singh <owenbksingh@gmail.com>
 Project-URL: Homepage, https://github.com/owensingh38/wsba_hockey/

{wsba_hockey-1.0.4.dist-info → wsba_hockey-1.0.6.dist-info}/RECORD

@@ -1,7 +1,7 @@
-wsba_hockey/__init__.py,sha256=QXyc8FFlCDWQuECyyEbj80ASHEbTFj4R13DOFOY9nJg,353
+wsba_hockey/__init__.py,sha256=yfr8z5PA503iaIQv30ngancwT_WnsuK-tZETKlHcI0M,377
 wsba_hockey/data_pipelines.py,sha256=tqAnUL8xf-K2jYG1zeuau5GzRlgTiaHkXwER481Jkb4,7952
 wsba_hockey/workspace.py,sha256=B--BrXrY5BL3AXQYnsy4pHQGv2LG_82VtqZT0ANab30,1088
-wsba_hockey/wsba_main.py,sha256=DOFS1isNEDGUU-kehoH56ieVOmd7yNCTv2M8I5GBu5o,54103
+wsba_hockey/wsba_main.py,sha256=NPZvcL3VTi3pMq2jd9rlgyfVgXetrwSpRJehbvldWr8,54247
 wsba_hockey/evidence/weakside-breakout/node_modules/duckdb/vendor.py,sha256=lmu0TB0rIYkAuV9-csFJgW-1hJojso_-EZpEoorUUKM,4949
 wsba_hockey/evidence/weakside-breakout/node_modules/flatted/python/flatted.py,sha256=ke8FuEflns-WlphCcQ9CC0qJqWqX3zEEuak74o6rgE8,3879
 wsba_hockey/evidence/weakside-breakout/node_modules/flatted/python/test.py,sha256=uTOn6HJd7KeY_PTRvvufv60dmvON3KWp3nnqACj8IlA,2129
@@ -104,7 +104,7 @@ wsba_hockey/evidence/weakside-breakout/node_modules/sqlite3/node_modules/node-gy
 wsba_hockey/evidence/weakside-breakout/node_modules/sqlite3/node_modules/node-gyp/gyp/tools/pretty_sln.py,sha256=b_Fxm-SXUCPL3Tix4EyNwZNmQ-zkeRIFFmuL0R5wFhw,5482
 wsba_hockey/evidence/weakside-breakout/node_modules/sqlite3/node_modules/node-gyp/gyp/tools/pretty_vcproj.py,sha256=AwQrxK1F-jhjsbbT35XQjrvWNbc3IBFaKXoJogqMh_o,10633
 wsba_hockey/evidence/weakside-breakout/node_modules/sqlite3/node_modules/node-gyp/test/fixtures/test-charmap.py,sha256=5raXzaQnO2eJnrlFtlDtWftryhZX7Fj0amFW3hdSnhE,547
-wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/game_stats/app.py,sha256=YTXM8XzpUVf5N6X5XBcNSU2cK7zp_vs1ZczVufhLe3I,12647
+wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/game_stats/app.py,sha256=ay8NzjfC_2bZ38tOlXKDNpF35_KPGsl6Adx13ls6yWg,12619
 wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/game_stats/name_fix.py,sha256=v7IN4JWrudeFuIsBdjLLlHsr9wU65jYi9-34pI_ZpoM,1488
 wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/heatmaps/app.py,sha256=53jaUv8LOerKHWD-0d-EoxogEb83YFVm6KiRdbSLlVA,4254
 wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/heatmaps/plot.py,sha256=nTVk41u8l6M3czVeyJ-3edmiIAzXY-By7meGfl5C_kE,4505
@@ -119,17 +119,17 @@ wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/skater/app.py
 wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/skater/plot.py,sha256=xDHLM_jcXSi5NBcQ7tWeF9yzcjNiOrHYD7C8sBfynFo,1860
 wsba_hockey/evidence/weakside-breakout/wsba_nhl_apps/wsba_nhl_apps/skater/rink_plot.py,sha256=bvU7enxqxGwo2QThNabSo1qB2vltS_0HjF95ZOYZ98I,11993
 wsba_hockey/tools/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-wsba_hockey/tools/agg.py,sha256=SqYExI1OJGQKxKizsM6I9GhBzee7OQDz144FDbSXuFI,21392
-wsba_hockey/tools/plotting.py,sha256=1hyf3uyjPFOVmexolWcHJpYk6dNbRnHfdcTM0-v1oxk,5826
-wsba_hockey/tools/scraping.py,sha256=dmT4RymMq-TXKhcp_I8U6P8lnqRbB5R8UNw2d3RkkRk,45244
-wsba_hockey/tools/xg_model.py,sha256=eWEX8d_8Vj1SGyPwzQj0TDAPXrwSOwpymkon0EwBW5Q,18144
+wsba_hockey/tools/agg.py,sha256=SYZDykUQFygDfRaazlBMKcfs_1eYP7GTJNpUnNKHH-8,21409
+wsba_hockey/tools/plotting.py,sha256=LJ62FvqCmY2C_tbNR3NedVWy37tN_FaWmWSZ2xmhjiM,6047
+wsba_hockey/tools/scraping.py,sha256=rmypleknqfS9gU-JuB5VQn5yDVwnNastoDL3YDeUCVk,45261
+wsba_hockey/tools/xg_model.py,sha256=nOr_2RBijLgPmJ0TTs4wbSsORYmRqWCKRjLKDm7sAhI,18342
 wsba_hockey/tools/archive/old_scraping.py,sha256=hEjMI1RtfeZnf0RBiJFI38oXkLZ3WofeH5xqcF4pzgM,49585
 wsba_hockey/tools/utils/__init__.py,sha256=vccXhOtzARoR99fmEWU1OEI3qCIdQ9Z42AlRA_BUhrs,114
 wsba_hockey/tools/utils/config.py,sha256=D3Uk05-YTyrhfReMTTLfNI3HN_rON2uo_CDE9oER3Lg,351
 wsba_hockey/tools/utils/save_pages.py,sha256=CsyL_0n-b-4pJoUauwU3HpnCO6n69-RlBMJQBd_qGDc,4979
 wsba_hockey/tools/utils/shared.py,sha256=dH_JwZfia5fib8rksy5sW-mBp0pluBPvw37Vdr8Kap0,14211
-wsba_hockey-1.0.4.dist-info/licenses/LICENSE,sha256=Nr_Um1Pd5FQJTWWgm7maZArdtYMbDhzXYSwyJIZDGik,1114
-wsba_hockey-1.0.4.dist-info/METADATA,sha256=5oQ7ledqHC51MxvTjENNFus_etzB2NwkDCz5XvpxMhI,3542
-wsba_hockey-1.0.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-wsba_hockey-1.0.4.dist-info/top_level.txt,sha256=acU7s3x-RZC1zGiqCOmO0g267iqCg34lzIfdmYxxGmQ,12
-wsba_hockey-1.0.4.dist-info/RECORD,,
+wsba_hockey-1.0.6.dist-info/licenses/LICENSE,sha256=Nr_Um1Pd5FQJTWWgm7maZArdtYMbDhzXYSwyJIZDGik,1114
+wsba_hockey-1.0.6.dist-info/METADATA,sha256=NHJh3evFLJ5IFGbm44LhWZ3DkqvwNLsxTNuhOi9ZzTU,3542
+wsba_hockey-1.0.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+wsba_hockey-1.0.6.dist-info/top_level.txt,sha256=acU7s3x-RZC1zGiqCOmO0g267iqCg34lzIfdmYxxGmQ,12
+wsba_hockey-1.0.6.dist-info/RECORD,,