PyPI - wsba-hockey - Versions diffs - 1.2.1__tar.gz → 1.2.3__tar.gz - Mend

wsba-hockey 1.2.1tar.gz → 1.2.3tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (22) hide show

{wsba_hockey-1.2.1/src/wsba_hockey.egg-info → wsba_hockey-1.2.3}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wsba_hockey
-Version: 1.2.1
+Version: 1.2.3
 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-1.2.1 → wsba_hockey-1.2.3}/pyproject.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [project]
 name = "wsba_hockey"
-version = "1.2.1"
+version = "1.2.3"
 authors = [
   { name="Owen Singh", email="owenbksingh@gmail.com" },
 ]

{wsba_hockey-1.2.1 → wsba_hockey-1.2.3}/src/wsba_hockey/__init__.py RENAMED Viewed

@@ -7,6 +7,8 @@ from wsba_hockey.wsba_main import (
     nhl_scrape_roster,
     nhl_scrape_draft_rankings,
     nhl_scrape_prospects,
+    nhl_scrape_player_info,
+    nhl_scrape_team_info,
     nhl_scrape_game_info,
     nhl_calculate_stats,
     nhl_apply_xG,

wsba_hockey-1.2.3/src/wsba_hockey/tools/columns.py ADDED Viewed

@@ -0,0 +1,281 @@
+### COLUMN NAMES ###
+# Provided in this file are dicts to standardize column names as necessary #
+def col_map():
+    return {
+        'schedule':{
+            'id':'game_id',
+            'game_date':'game_date',
+            'gameType':'season_type',
+            'neutralSite':'neutral_site',
+            'startTimeUTC':'start_time_utc',
+            'start_time_est':'start_time_est',
+            'easternUTCOffset':'eastern_utc',
+            'venueUTCOffset':'venue_utc',
+            'venueTimezone':'venue_timezone',
+            'gameState':'game_state',
+            'gameScheduleState':'game_schedule_state',
+            'tvBroadcasts':'tv_broadcasts',
+            'threeMinRecap':'three_min_recap',
+            'threeMinRecapFr':'three_min_recap_fr',
+            'condensedGame':'condensed_game',
+            'condensedGameFr':'condensed_game_fr',
+            'gameCenterLink':'gamecenter_link',
+            'venue.default':'venue',
+            'awayTeam.id':'away_team_id',
+            'homeTeam.id':'home_team_id',
+            'awayTeam.abbrev':'away_team_abbr',
+            'homeTeam.abbrev':'home_team_abbr',
+            'awayTeam.darkLogo':'away_team_logo',
+            'homeTeam.darkLogo':'home_team_logo',
+            'awayTeam.awaySplitSquad':'away_team_split_squad',
+            'homeTeam.homeSplitSquad':'home_team_split_squad',
+            'awayTeam.score':'away_score',
+            'homeTeam.score':'home_score',
+            'periodDescriptor.number':'period',
+            'periodDescriptor.maxRegulationPeriods':'period_max_regulation',
+            'periodDescriptor.periodType':'period_type',
+            'gameOutcome.lastPeriodType':'period_type_last',
+            'seriesUrl':'series_url',
+            'seriesStatus.round':'series_round',
+            'seriesStatus.seriesAbbrev':'series_abbr',
+            'seriesStatus.seriesTitle':'series_name',
+            'seriesStatus.seriesLetter':'series_letter',
+            'seriesStatus.neededToWin':'series_games_needed_to_win',
+            'seriesStatus.gameNumberOfSeries':'series_game_num',
+            'seriesStatus.topSeedTeamAbbrev':'top_seed_team_abbr',
+            'seriesStatus.bottomSeedTeamAbbrev':'bottom_seed_team_abbr',
+            'seriesStatus.topSeedWins':'top_seed_wins',
+            'seriesStatus.bottomSeedWins':'bottom_seed_wins'
+        },
+        'season_info':{
+            'id':'season',
+            'formattedSeasonId':'season_name',
+            'seasonOrdinal':'season_ordinal',
+            'startDate':'start_date',
+            'endDate':'end_date',
+            'numberOfGames':'games_num',
+            'totalRegularSeasonGames':'regular_season_total_games_num',
+            'totalPlayoffGames':'playoffs_total_games_num',
+            'regularSeasonStartDate':'regular_season_start_date',
+            'regularSeasonEndDate':'regular_season_end_date',
+            'standingsStart':'standings_start_date',
+            'standingsEnd':'standings_end_date',
+            'allStarGameInUse':'all_star_game',
+            'conferencesInUse':'conferences',
+            'divisionsInUse':'divisions',
+            'wildcardInUse':'wildcard',
+            'entryDraftInUse':'entry_draft',
+            'nhlStanleyCupOwner':'nhl_stanley_cup_owner',
+            'olympicsParticipation':'olympic_participation',
+            'tiesInUse':'ties',
+            'pointForOTLossInUse':'ot_loss_point',
+            'regulationWinsInUse':'reg_wins',
+            'rowInUse':'row',
+            'supplementalDraftInUse':'supplemental_draft'
+        },
+        'standings':{
+            "clinchIndicator": "clinch_indicator",
+            "conferenceAbbrev": "conference_abbr",
+            "conferenceHomeSequence": "conference_home_sequence",
+            "conferenceL10Sequence": "conference_l10_sequence",
+            "conferenceName": "conference_name",
+            "conferenceRoadSequence": "conference_road_sequence",
+            "conferenceSequence": "conference_sequence",
+            "date": "date",
+            "divisionAbbrev": "division_abbr",
+            "divisionHomeSequence": "division_home_sequence",
+            "divisionL10Sequence": "division_l10_sequence",
+            "divisionName": "division_name",
+            "divisionRoadSequence": "division_road_sequence",
+            "divisionSequence": "division_sequence",
+            "gameTypeId": "game_type_id",
+            "gamesPlayed": "GP",
+            "goalDifferential": "GD",
+            "goalDifferentialPctg": "GD%",
+            "goalAgainst": "GA",
+            "goalFor": "GF",
+            "goalsForPctg": "GF%",
+            "homeGamesPlayed": "HGP",
+            "homeGoalDifferential": "HGD",
+            "homeGoalsAgainst": "HGA",
+            "homeGoalsFor": "HGF",
+            "homeLosses": "HL",
+            "homeOtLosses": "HOL",
+            "homePoints": "HPTS",
+            "homeRegulationPlusOtWins": "HROW",
+            "homeRegulationWins": "HRW",
+            "homeTies": "HT",
+            "homeWins": "HW",
+            "l10GamesPlayed": "l10_GP",
+            "l10GoalDifferential": "l10_GD",
+            "l10GoalsAgainst": "l10_GA",
+            "l10GoalsFor": "l10_GF",
+            "l10Losses": "l10_L",
+            "l10OtLosses": "l10_OTL",
+            "l10Points": "l10_PTS",
+            "l10RegulationPlusOtWins": "l10_ROW",
+            "l10RegulationWins": "l10_RW",
+            "l10Ties": "l10_T",
+            "l10Wins": "l10_W",
+            "leagueHomeSequence": "league_home_sequence",
+            "leagueL10Sequence": "league_l10_sequence",
+            "leagueRoadSequence": "league_road_sequence",
+            "leagueSequence": "league_sequence",
+            "losses": "L",
+            "otLosses": "OTL",
+            "pointPctg": "PTS%",
+            "points": "PTS",
+            "regulationPlusOtWinPctg": "ROW%",
+            "regulationPlusOtWins": "ROW",
+            "regulationWinPctg": "RW%",
+            "regulationWins": "RW",
+            "roadGamesPlayed": "AGP",
+            "roadGoalDifferential": "AGD",
+            "roadGoalsAgainst": "AGA",
+            "roadGoalsFor": "AGF",
+            "roadLosses": "AL",
+            "roadOtLosses": "AOTL",
+            "roadPoints": "APTS",
+            "roadRegulationPlusOtWins": "AROW",
+            "roadRegulationWins": "ARW",
+            "roadTies": "AT",
+            "roadWins": "AW",
+            "seasonId": "season",
+            "shootoutLosses": "SOL",
+            "shootoutWins": "SOW",
+            "streakCode": "streak_code",
+            "streakCount": "streak_count",
+            "teamLogo": "team_logo",
+            "ties": "T",
+            "waiversSequence": "waivers_sequence",
+            "wildcardSequence": "wildcard_sequence",
+            "winPctg": "W%",
+            "wins": "W",
+            "placeName.default": "place_name",
+            "teamName.default": "team_name",
+            "teamCommonName.default": "team_common_name",
+            "teamAbbrev.default": "team_abbr"
+        },
+        'roster':{
+            "id": "player_id",
+            "team_abbr": "team_abbr",
+            "season": "season",
+            "headshot": "headshot",
+            "sweaterNumber": "sweater_number",
+            "positionCode": "position",
+            "heading_position": "heading_position",
+            "shootsCatches": "handedness",
+            "heightInInches": "height_in",
+            "weightInPounds": "weight_lbs",
+            "heightInCentimeters": "height_cm",
+            "weightInKilograms": "weight_kg",
+            "birthDate": "birth_date",
+            "birthCountry": "birth_country",
+            "player_name":"player_name",
+            "firstName.default": "player_first_name",
+            "lastName.default": "player_last_name",
+            "birthCity.default": "birth_city",
+            "birthStateProvince.default": "birth_state_province"
+            },
+        'prospects':{
+            "id": "player_id",
+            "headshot": "headshot",
+            "sweaterNumber": "sweater_number",
+            "positionCode": "position",
+            "shootsCatches": "handedness",
+            "heightInInches": "height_in",
+            "weightInPounds": "weight_lbs",
+            "heightInCentimeters": "height_cm",
+            "weightInKilograms": "weight_kg",
+            "birthDate": "birth_date",
+            "birthCountry": "birth_country",
+            "player_name":"player_name",
+            "firstName.default": "player_first_name",
+            "lastName.default": "player_last_name",
+            "birthCity.default": "birth_city",
+            "birthStateProvince.default": "birth_state_province",
+        },
+        'player_info':{
+            'playerId': 'player_id',
+            'player_name': 'player_name',
+            'isActive': 'is_active',
+            'currentTeamId': 'current_team_id',
+            'currentTeamAbbrev': 'current_team_abbr',
+            'badges': 'badges',
+            'teamLogo': 'team_logo',
+            'sweaterNumber': 'sweater_number',
+            'position': 'position',
+            'headshot': 'headshot',
+            'heroImage': 'hero_image',
+            'heightInInches': 'height_in',
+            'heightInCentimeters': 'height_cm',
+            'weightInPounds': 'weight_lbs',
+            'weightInKilograms': 'weight_kg',
+            'birthDate': 'birth_date',
+            'birthCountry': 'birth_country',
+            'shootsCatches': 'handedness',
+            'playerSlug': 'player_slug',
+            'inTop100AllTime': 'in_top_100_all_time',
+            'inHHOF': 'in_hhof',
+            'shopLink': 'shop_link',
+            'twitterLink': 'twitter_link',
+            'watchLink': 'watch_link',
+            'last5Games': 'last_5_games',
+            'seasonTotals': 'season_totals',
+            'awards': 'awards',
+            'currentTeamRoster': 'current_team_roster',
+            'fullTeamName.default': 'full_team_name',
+            'teamCommonName.default': 'team_common_name',
+            'teamPlaceNameWithPreposition.default': 'team_place_name_with_preposition',
+            'firstName.default': 'player_first_name',
+            'lastName.default': 'player_last_name',
+            'birthCity.default': 'birth_city',
+            'birthStateProvince.default': 'birth_state_province',
+            'draftDetails.year': 'draft_year',
+            'draftDetails.teamAbbrev': 'draft_team_abbr',
+            'draftDetails.round': 'draft_round',
+            'draftDetails.pickInRound': 'draft_pick_in_round',
+            'draftDetails.overallPick': 'draft_overall_pick',
+        },
+        'team_info':{
+            "id":"team_id",
+            "franchiseId":"franchise_id",
+            "fullName":"team_name",
+            "leagueId":"league_id",
+            "triCode":"team_abbr",
+            "logo_light":"logo_light",
+            "logo_dark":"logo_dark",
+            "country3Code":"country_abbr",
+            "countryCode":"country_abbr_2",
+            "countryName":"country_name",
+            "hasPlayerStats":"has_player_stats",
+            "imageUrl":"country_flag_large",
+            "isActive":"is_active",
+            "nationalityName":"nationality",
+            "olympicUrl":"olympic_url",
+            "thumbnailUrl":"thumbnail_url"
+        },
+        'draft_rankings':{
+            "id": "player_id",
+            "player_name":"player_name",
+            "firstName": "player_first_name",
+            "lastName": "player_last_name",
+            "headshot": "headshot",
+            "sweaterNumber": "sweater_number",
+            "positionCode": "position",
+            "shootsCatches": "handedness",
+            "heightInInches": "height_in",
+            "weightInPounds": "weight_lbs",
+            "heightInCentimeters": "height_cm",
+            "weightInKilograms": "weight_kg",
+            "birthDate": "birth_date",
+            "birthCity": "birth_city",
+            "birthCountry": "birth_country",
+            "birthStateProvince": "birth_state_province",
+            "lastAmateurClub": "last_amateur_club",
+            "lastAmateurLeague": "last_amateur_league",
+            "midtermRank":"midterm_rank",
+            "finalRank":"final_rank"
+        }
+    }

wsba_hockey-1.2.3/src/wsba_hockey/tools/game_pred.py ADDED Viewed

@@ -0,0 +1,33 @@
+import joblib
+import os
+import pandas as pd
+import numpy as np
+import xgboost as xgb
+import scipy.sparse as sp
+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
+### GAME PREDICTION MODEL FUNCTIONS ###
+# Provided in this file are functions vital to the game prediction model in the WSBA Hockey Python package. #
+## GLOBAL VARIABLES ##
+dir = os.path.dirname(os.path.realpath(__file__))
+roster_path = os.path.join(dir,'rosters\\nhl_rosters.csv')
+schedule_path = os.path.join(dir,'schedule/schedule.csv')
+def prep_game_data(pbp):
+    #Prepare schedule data for model development given full-season pbp
+    #Calculate necessary team stats (by game) for the prediction model
+    #The model will evaluate based on three different qualities for valid EV, PP, and SH strength
+    dfs = []
+    for strength in [['5v5'],['5v4'],['4v5']]:
+        team_games = wsba.nhl_calculate_stats(pbp,'team',[2,3],strength,True)
+        team_games['Year'] = team_games['Season'].str[0:4].astype(int)
+        dfs.append(team_games)
+    #Place the games in order and create sums for
+    df = pd.concat(dfs).sort_values(by=['Year','Game'])

{wsba_hockey-1.2.1 → wsba_hockey-1.2.3}/src/wsba_hockey/tools/plotting.py RENAMED Viewed

@@ -50,7 +50,7 @@ def prep_plot_data(pbp,events,strengths,marker_dict=event_markers):
         pbp = wsba_xG(pbp)
         pbp['xG'] = np.where(pbp['xG'].isna(),0,pbp['xG'])
-    pbp['WSBA'] = pbp['event_player_1_name']+pbp['season'].astype(str)+pbp['event_team_abbr']
+    pbp['WSBA'] = pbp['event_player_1_id'].astype(str)+pbp['season'].astype(str)+pbp['event_team_abbr']
     pbp['x_plot'] = np.where(pbp['x']<0,-pbp['y_adj'],pbp['y_adj'])
     pbp['y_plot'] = abs(pbp['x_adj'])
@@ -88,8 +88,8 @@ def plot_skater_shots(pbp, player, season, team, strengths, title = None, marker
     pbp = pbp.loc[(pbp['season'].astype(str)==season)&((pbp['away_team_abbr']==team)|(pbp['home_team_abbr']==team))]
     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]
+    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]
     if onice in ['for','against']:
         skater = pbp.loc[(pbp[f'onice_{onice}'].str.contains(player.upper()))]
@@ -123,8 +123,8 @@ def plot_game_events(pbp,game_id,events,strengths,marker_dict=event_markers,team
     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],
+        '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']}_color'])[0],
+        'home_color': list(team_data.loc[team_data['WSBA']==f'{home_abbr}{season}',f'{team_colors['home']}_color'])[0],
         'away_logo': f'tools/logos/png/{away_abbr}{season}.png',
         'home_logo': f'tools/logos/png/{home_abbr}{season}.png',
     }

{wsba_hockey-1.2.1 → wsba_hockey-1.2.3}/src/wsba_hockey/tools/xg_model.py RENAMED Viewed

@@ -90,18 +90,18 @@ def fix_players(pbp):
     print('Adding player info to pbp...')
     #Load roster and all players
-    roster = pd.read_csv(roster_path).drop_duplicates(['id'])[['fullName','id','shootsCatches']]
+    roster = pd.read_csv(roster_path).drop_duplicates(['player_id'])[['player_name','player_id','handedness']]
     #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())
+    miss = list(pbp.loc[~(pbp['event_player_1_id'].isin(list(roster['player_id'])))&(pbp['event_player_1_id'].notna()),'event_player_1_id'].drop_duplicates())
     if miss:
-        add = wsba.nhl_scrape_player_data(miss).rename(columns={'playerId':'id'})[['fullName','id','shootsCatches']]
+        add = wsba.nhl_scrape_player_info(miss)[['player_name','player_id','handedness']]
         roster = pd.concat([roster,add]).reset_index(drop=True)
     #Conversion dict
-    roster['id'] = roster['id'].astype(str)
-    roster_dict = roster.set_index('id').to_dict()['shootsCatches']
-    names_dict = roster.set_index('id').to_dict()['fullName']
+    roster['player_id'] = roster['player_id'].astype(str)
+    roster_dict = roster.set_index('player_id').to_dict()['handedness']
+    names_dict = roster.set_index('player_id').to_dict()['player_name']
     #Add player names
     for i in range(3):

{wsba_hockey-1.2.1 → wsba_hockey-1.2.3}/src/wsba_hockey/wsba_main.py RENAMED Viewed

@@ -11,6 +11,7 @@ from wsba_hockey.tools.scraping import *
 from wsba_hockey.tools.xg_model import *
 from wsba_hockey.tools.agg import *
 from wsba_hockey.tools.plotting import *
+from wsba_hockey.tools.columns import col_map
 ### WSBA HOCKEY ###
 ## Provided below are all integral functions in the WSBA Hockey Python package. ##
@@ -105,7 +106,7 @@ KNOWN_PROBS = {
 SHOT_TYPES = ['wrist','deflected','tip-in','slap','backhand','snap','wrap-around','poke','bat','cradle','between-legs']
-NEW = 2024
+NEW = 2025
 EVENTS = ['faceoff','hit','giveaway','takeaway','blocked-shot','missed-shot','shot-on-goal','goal','penalty']
@@ -114,8 +115,19 @@ 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')
+#Load column names for standardization
+COL_MAP = col_map()
+DRAFT_CAT = {
+    0: 'All Prospects',
+    1: 'North American Skaters',
+    2: 'International Skater',
+    3: 'North American Goalies',
+    4: 'International Goalies'
+}
 ## SCRAPE FUNCTIONS ##
-def nhl_scrape_game(game_ids:list[int], split_shifts:bool = False, remove:list[str] = [], verbose:bool = False, sources:bool = False, errors:bool = False):
+def nhl_scrape_game(game_ids:int | list[int], split_shifts:bool = False, remove:list[str] = [], verbose:bool = False, sources:bool = False, errors:bool = False):
     """
     Given a set of game_ids (NHL API), return complete play-by-play information as requested.
@@ -319,24 +331,17 @@ def nhl_scrape_schedule(season:int, start:str = '', end:str = ''):
         if gameWeek.empty:
             game.append(gameWeek)
         else:
-            gameWeek['date'] = get['gameWeek'][0]['date']
-            gameWeek['season_type'] = gameWeek['gameType']
-            gameWeek['away_team_abbr'] = gameWeek['awayTeam.abbrev']
-            gameWeek['home_team_abbr'] = gameWeek['homeTeam.abbrev']
-            gameWeek['game_title'] = gameWeek['away_team_abbr'] + " @ " + gameWeek['home_team_abbr'] + " - " + gameWeek['date']
-            gameWeek['estStartTime'] = pd.to_datetime(gameWeek['startTimeUTC']).dt.tz_convert('US/Eastern').dt.strftime("%I:%M %p")
-            front_col = ['id','season','date','season_type','game_title','away_team_abbr','home_team_abbr','estStartTime']
-            gameWeek = gameWeek[front_col+[col for col in gameWeek.columns.to_list() if col not in front_col]]
+            gameWeek['game_date'] = get['gameWeek'][0]['date']
+            gameWeek['game_title'] = gameWeek['awayTeam.abbrev'] + " @ " + gameWeek['homeTeam.abbrev'] + " - " + gameWeek['game_date']
+            gameWeek['start_time_est'] = pd.to_datetime(gameWeek['startTimeUTC']).dt.tz_convert('US/Eastern').dt.strftime("%I:%M %p")
         game.append(gameWeek)
-    #Concatenate all games
-    df = pd.concat(game)
+    #Concatenate all games and standardize column naming
+    df = pd.concat(game).rename(columns=COL_MAP['schedule'],errors='ignore')
     #Return: specificed schedule data
-    return df
+    return df[[col for col in COL_MAP['schedule'].values() if col in df.columns]]
 def nhl_scrape_season(season:int, split_shifts:bool = False, season_types:list[int] = [2,3], remove:list[str] = [], start:str = '', end:str = '', local:bool=False, local_path:str = SCHEDULE_PATH, verbose:bool = False, sources:bool = False, errors:bool = False):
     """
@@ -399,13 +404,13 @@ def nhl_scrape_season(season:int, split_shifts:bool = False, season_types:list[i
         load = load.loc[(load['season']==season)&
                         (load['season_type'].isin(season_types))&
-                        (load['date']>=start)&(load['date']<=end)]
+                        (load['game_date']>=start)&(load['game_date']<=end)]
-        game_ids = load['id'].to_list()
+        game_ids = load['game_id'].to_list()
     else:
         load = nhl_scrape_schedule(season,start,end)
         load = load.loc[(load['season']==season)&(load['season_type'].isin(season_types))]
-        game_ids = load['id'].to_list()
+        game_ids = load['game_id'].to_list()
     #If no games found, terminate the process
     if not game_ids:
@@ -440,10 +445,9 @@ def nhl_scrape_seasons_info(seasons:list[int] = []):
             A DataFrame containing the information for requested seasons.
     """
-    #
-    # param 'season' - list of seasons to include
     print(f'Scraping info for seasons: {seasons}')
+    #Load two different data sources: general season info and standings data related to season
     api = "https://api.nhle.com/stats/rest/en/season"
     info = "https://api-web.nhle.com/v1/standings-season"
     data = rs.get(api).json()['data']
@@ -452,21 +456,26 @@ def nhl_scrape_seasons_info(seasons:list[int] = []):
     df = pd.json_normalize(data)
     df_2 = pd.json_normalize(data_2)
-    df = pd.merge(df,df_2,how='outer',on=['id'])
+    #Remove common columns
+    df_2 = df_2.drop(columns=['conferencesInUse', 'divisionsInUse', 'pointForOTlossInUse','rowInUse','tiesInUse','wildcardInUse'])
+    df = pd.merge(df,df_2,how='outer',on=['id']).rename(columns=COL_MAP['season_info'])
+    df = df[[col for col in COL_MAP['season_info'].values() if col in df.columns]]
     if len(seasons) > 0:
-        return df.loc[df['id'].astype(str).isin(seasons)].sort_values(by=['id'])
+        return df.loc[df['season'].isin(seasons)].sort_values(by=['season'])
     else:
-        return df.sort_values(by=['id'])
+        return df.sort_values(by=['season'])
-def nhl_scrape_standings(arg:str | int = "now", season_type:int = 2):
+def nhl_scrape_standings(arg:int | list[int] | Literal['now'] = 'now', season_type:int = 2):
     """
     Returns standings or playoff bracket
     Args:
-        arg (str or int, optional):
-            Date formatted as 'YYYY-MM-DD' to scrape standings, NHL season such as "20242025", or 'now' for current standings. Default is 'now'.
+        arg (int or list[int] or str, optional):
+            Date formatted as 'YYYY-MM-DD' to scrape standings, NHL season such as "20242025", list of NHL seasons, or 'now' for current standings. Default is 'now'.
         season_type (int, optional):
-            Part of season to scrape.  If 3 (playoffs) then scrape the playoff bracket for the season implied by arg. When arg = 'now' this is ignored. Default is 2.
+            Part of season to scrape.  If 3 (playoffs) then scrape the playoff bracket for the season implied by arg. When arg = 'now' this is defaulted to the most recent playoff year.  Any dates passed through are parsed as seasons. Default is 2.
     Returns:
         pd.DataFrame:
@@ -475,31 +484,62 @@ def nhl_scrape_standings(arg:str | int = "now", season_type:int = 2):
     if season_type == 3:
         if arg == "now":
-            arg = NEW
+            arg = [NEW]
+        elif type(arg) == int:
+            #Find year from season
+            arg = [str(arg)[4:8]]
+        elif type(arg) == list:
+            #Find year from seasons
+            arg = [str(s)[4:8] for s in arg]
+        else:
+            #Find year from season from date
+            arg = [int(arg[0:4])+1 if (9 < int(arg[5:7]) < 13) else int(arg[0:4])]
-        print(f"Scraping playoff bracket for date: {arg}")
-        api = f"https://api-web.nhle.com/v1/playoff-bracket/{arg}"
+        print(f"Scraping playoff bracket for season{'s' if len(arg)>1 else ''}: {arg}")
+        dfs = []
+        for season in arg:
+            api = f"https://api-web.nhle.com/v1/playoff-bracket/{season}"
-        data = rs.get(api).json()['series']
+            data = rs.get(api).json()['series']
+            dfs.append(pd.json_normalize(data))
-        return pd.json_normalize(data)
+        #Return: playoff bracket
+        return pd.concat(dfs)
     else:
         if arg == "now":
             print("Scraping standings as of now...")
+            arg = [arg]
         elif arg in SEASONS:
             print(f'Scraping standings for season: {arg}')
+            arg = [arg]
+        elif type(arg) == list:
+            print(f'Scraping standings for seasons: {arg}')
         else:
             print(f"Scraping standings for date: {arg}")
+            arg = [arg]
+        dfs = []
+        for search in arg:
+            #If the end is an int then its a season otherwise it is either 'now' or a date as a string
+            if type(search) == int:
+                season_data = rs.get('https://api.nhle.com/stats/rest/en/season').json()['data']
+                season_data = [s for s in season_data if s['id'] == search][0]
+                end = season_data['regularSeasonEndDate'][0:10]
+            else:
+                end = search
+            api = f"https://api-web.nhle.com/v1/standings/{end}"
-        season_data = rs.get('https://api.nhle.com/stats/rest/en/season').json()['data']
-        season_data = [s for s in season_data if s['id'] == arg][0]
-        end = season_data['regularSeasonEndDate'][0:10]
+            data = rs.get(api).json()['standings']
+            dfs.append(pd.json_normalize(data))
-        api = f"https://api-web.nhle.com/v1/standings/{end}"
-        data = rs.get(api).json()['standings']
+        #Standardize columns
+        df = pd.concat(dfs).rename(columns=COL_MAP['standings'])
-        return pd.json_normalize(data)
+        #Return: standings data
+        return df[[col for col in COL_MAP['standings'].values() if col in df.columns]]
 def nhl_scrape_roster(season: int):
     """
@@ -514,33 +554,40 @@ def nhl_scrape_roster(season: int):
             A DataFrame containing the rosters for all teams in the specified season.
     """
-    print("Scrpaing rosters for the "+ season + "season...")
+    print(f'Scrpaing rosters for the {season} season...')
     teaminfo = pd.read_csv(info_path)
     rosts = []
-    for team in list(teaminfo['Team']):
+    for team in teaminfo['team_abbr'].drop_duplicates():
         try:
-            print("Scraping " + team + " roster...")
-            api = "https://api-web.nhle.com/v1/roster/"+team+"/"+season
+            print(f'Scraping {team} roster...')
+            api = f'https://api-web.nhle.com/v1/roster/{team}/{season}'
             data = rs.get(api).json()
             forwards = pd.json_normalize(data['forwards'])
-            forwards['headingPosition'] = "F"
+            forwards['heading_position'] = "F"
             dmen = pd.json_normalize(data['defensemen'])
-            dmen['headingPosition'] = "D"
+            dmen['heading_position'] = "D"
             goalies = pd.json_normalize(data['goalies'])
-            goalies['headingPosition'] = "G"
+            goalies['heading_position'] = "G"
             roster = pd.concat([forwards,dmen,goalies]).reset_index(drop=True)
-            roster['fullName'] = (roster['firstName.default']+" "+roster['lastName.default']).str.upper()
+            roster['player_name'] = (roster['firstName.default']+" "+roster['lastName.default']).str.upper()
             roster['season'] = str(season)
             roster['team_abbr'] = team
             rosts.append(roster)
         except:
-            print("No roster found for " + team + "...")
+            print(f'No roster found for {team}...')
+    #Combine rosters
+    df = pd.concat(rosts)
-    return pd.concat(rosts)
+    #Standardize columns
+    df = df.rename(columns=COL_MAP['roster'])
+    #Return: roster data for provided season
+    return df[[col for col in COL_MAP['roster'].values() if col in df.columns]]
 def nhl_scrape_prospects(team:str):
     """
@@ -558,16 +605,21 @@ def nhl_scrape_prospects(team:str):
     api = f'https://api-web.nhle.com/v1/prospects/{team}'
     data = rs.get(api).json()
+    print(f'Scraping {team} prospects...')
     #Iterate through positions
     players = [pd.json_normalize(data[pos]) for pos in ['forwards','defensemen','goalies']]
     prospects = pd.concat(players)
     #Add name columns
-    prospects['fullName'] = (prospects['firstName.default']+" "+prospects['lastName.default']).str.upper()
+    prospects['player_name'] = (prospects['firstName.default']+" "+prospects['lastName.default']).str.upper()
+    #Standardize columns
+    prospects = prospects.rename(columns=COL_MAP['prospects'])
     #Return: team prospects
-    return prospects
+    return prospects[[col for col in COL_MAP['prospects'].values() if col in prospects.columns]]
 def nhl_scrape_team_info(country:bool = False):
     """
@@ -592,9 +644,13 @@ def nhl_scrape_team_info(country:bool = False):
         data['logo_light'] = 'https://assets.nhle.com/logos/nhl/svg/'+data['triCode']+'_light.svg'
         data['logo_dark'] = 'https://assets.nhle.com/logos/nhl/svg/'+data['triCode']+'_dark.svg'
-    return data.sort_values(by=(['country3Code','countryCode','iocCode','countryName'] if country else ['fullName','triCode','id']))
+    #Standardize columns
+    data = data.rename(columns=COL_MAP['team_info'])
+    #Return: team or country info
+    return data[[col for col in COL_MAP['team_info'].values() if col in data.columns]].sort_values(by=(['country_abbr','country_name'] if country else ['team_abbr','team_name']))
-def nhl_scrape_player_data(player_ids:list[int]):
+def nhl_scrape_player_info(player_ids:list[int]):
     """
     Returns player data for specified players.
@@ -607,6 +663,7 @@ def nhl_scrape_player_data(player_ids:list[int]):
             A DataFrame containing player data for specified players.
     """
+    print(f'Retreiving player information for {player_ids}...')
     infos = []
     for player_id in player_ids:
         player_id = int(player_id)
@@ -614,7 +671,7 @@ def nhl_scrape_player_data(player_ids:list[int]):
         data = pd.json_normalize(rs.get(api).json())
         #Add name column
-        data['fullName'] = (data['firstName.default'] + " " + data['lastName.default']).str.upper()
+        data['player_name'] = (data['firstName.default'] + " " + data['lastName.default']).str.upper()
         #Append
         infos.append(data)
@@ -622,12 +679,15 @@ def nhl_scrape_player_data(player_ids:list[int]):
     if infos:
         df = pd.concat(infos)
+        #Standardize columns
+        df = df.rename(columns=COL_MAP['player_info'])
         #Return: player data
-        return df
+        return df[[col for col in COL_MAP['player_info'].values() if col in df.columns]]
     else:
         return pd.DataFrame()
-def nhl_scrape_draft_rankings(arg:str = 'now', category:int = 0):
+def nhl_scrape_draft_rankings(arg:str | Literal['now'] = 'now', category:int = 0):
     """
     Returns draft rankings
     Args:
@@ -638,8 +698,8 @@ def nhl_scrape_draft_rankings(arg:str = 'now', category:int = 0):
             - Category 1 is North American Skaters.
             - Category 2 is International Skaters.
-            - Category 3 is North American Goalie.
-            - Category 4 is International Goalie
+            - Category 3 is North American Goalies.
+            - Category 4 is International Goalies
             Default is 0 (all prospects).
     Returns:
@@ -647,15 +707,26 @@ def nhl_scrape_draft_rankings(arg:str = 'now', category:int = 0):
             A DataFrame containing draft rankings.
     """
+    print(f'Scraping draft rankings for {arg}...\nCategory: {DRAFT_CAT[category]}...')
     #Player category only applies when requesting a specific season
     api = f"https://api-web.nhle.com/v1/draft/rankings/{arg}/{category}" if category > 0 else f"https://api-web.nhle.com/v1/draft/rankings/{arg}"
     data = pd.json_normalize(rs.get(api).json()['rankings'])
     #Add player name columns
-    data['fullName'] = (data['firstName']+" "+data['lastName']).str.upper()
+    data['player_name'] = (data['firstName']+" "+data['lastName']).str.upper()
+    #Fix positions
+    data['positionCode'] = data['positionCode'].replace({
+        'LW':'L',
+        'RW':'R'
+    })
+    #Standardize columns
+    data = data.rename(columns=COL_MAP['draft_rankings'])
     #Return: prospect rankings
-    return data
+    return data[[col for col in COL_MAP['draft_rankings'].values() if col in data.columns]]
 def nhl_scrape_game_info(game_ids:list[int]):
     """
@@ -670,6 +741,9 @@ def nhl_scrape_game_info(game_ids:list[int]):
             An DataFrame containing information for each game.
     """
+    #Wrap game_id in a list if only a single game_id is provided
+    game_ids = [game_ids] if type(game_ids) != list else game_ids
     print(f'Finding game information for games: {game_ids}')
     link = 'https://api-web.nhle.com/v1/gamecenter'
@@ -678,18 +752,15 @@ def nhl_scrape_game_info(game_ids:list[int]):
     df = pd.concat([pd.json_normalize(rs.get(f'{link}/{game_id}/landing').json()) for game_id in game_ids])
     #Add extra info
-    df['date'] = df['gameDate']
-    df['season_type'] = df['gameType']
-    df['away_team_abbr'] = df['awayTeam.abbrev']
-    df['home_team_abbr'] = df['homeTeam.abbrev']
-    df['game_title'] = df['away_team_abbr'] + " @ " + df['home_team_abbr'] + " - " + df['date']
-    df['estStartTime'] = pd.to_datetime(df['startTimeUTC']).dt.tz_convert('US/Eastern').dt.strftime("%I:%M %p")
+    df['game_date'] = df['gameDate']
+    df['game_title'] = df['awayTeam.abbrev'] + " @ " + df['homeTeam.abbrev'] + " - " + df['game_date']
+    df['start_time_est'] = pd.to_datetime(df['startTimeUTC']).dt.tz_convert('US/Eastern').dt.strftime("%I:%M %p")
-    front_col = ['id','season','date','season_type','game_title','away_team_abbr','home_team_abbr','estStartTime']
-    df = df[front_col+[col for col in df.columns.to_list() if col not in front_col]]
+    #Standardize columns
+    df = df.rename(columns=COL_MAP['schedule'])
     #Return: game information
-    return df
+    return df[[col for col in COL_MAP['schedule'].values() if col in df.columns]]
 def nhl_apply_xG(pbp: pd.DataFrame):
@@ -1144,23 +1215,23 @@ def nhl_calculate_stats(pbp:pd.DataFrame, type:Literal['skater','goalie','team']
         #Import rosters and player info
         rosters = pd.read_csv(roster_path)
-        names = rosters[['id','fullName',
-                            'headshot','positionCode','shootsCatches',
-                            'heightInInches','weightInPounds',
-                            'birthDate','birthCountry']].drop_duplicates(subset=['id','fullName'],keep='last')
+        names = rosters[['player_id','player_name',
+                            'headshot','position','handedness',
+                            'height_in','weight_lbs',
+                            'birth_date','birth_country']].drop_duplicates(subset=['player_id','player_name'],keep='last')
         #Add names
-        complete = pd.merge(complete,names,how='left',left_on='ID',right_on='id')
+        complete = pd.merge(complete,names,how='left',left_on='ID',right_on='player_id')
         #Rename if there are no missing names
-        complete = complete.rename(columns={'fullName':'Goalie',
+        complete = complete.rename(columns={'player_name':'Goalie',
                                             'headshot':'Headshot',
-                                            'positionCode':'Position',
-                                            'shootsCatches':'Handedness',
-                                            'heightInInches':'Height (in)',
-                                            'weightInPounds':'Weight (lbs)',
-                                            'birthDate':'Birthday',
-                                            'birthCountry':'Nationality'})
+                                            'position':'Position',
+                                            'handedness':'Handedness',
+                                            'height_in':'Height (in)',
+                                            'weight_lbs':'Weight (lbs)',
+                                            'birth_date':'Birthday',
+                                            'birth_country':'Nationality'})
         #WSBA
         complete['WSBA'] = complete['ID'].astype(str).str.replace('.0','')+complete['Team']+complete['Season'].astype(str)
@@ -1272,23 +1343,23 @@ def nhl_calculate_stats(pbp:pd.DataFrame, type:Literal['skater','goalie','team']
         #Import rosters and player info
         rosters = pd.read_csv(roster_path)
-        names = rosters[['id','fullName',
-                            'headshot','positionCode','shootsCatches',
-                            'heightInInches','weightInPounds',
-                            'birthDate','birthCountry']].drop_duplicates(subset=['id','fullName'],keep='last')
+        names = rosters[['player_id','player_name',
+                            'headshot','position','handedness',
+                            'height_in','weight_lbs',
+                            'birth_date','birth_country']].drop_duplicates(subset=['player_id','player_name'],keep='last')
         #Add names
-        complete = pd.merge(complete,names,how='left',left_on='ID',right_on='id')
+        complete = pd.merge(complete,names,how='left',left_on='ID',right_on='player_id')
         #Rename if there are no missing names
-        complete = complete.rename(columns={'fullName':'Player',
+        complete = complete.rename(columns={'player_name':'Player',
                                             'headshot':'Headshot',
-                                            'positionCode':'Position',
-                                            'shootsCatches':'Handedness',
-                                            'heightInInches':'Height (in)',
-                                            'weightInPounds':'Weight (lbs)',
-                                            'birthDate':'Birthday',
-                                            'birthCountry':'Nationality'})
+                                            'position':'Position',
+                                            'handedness':'Handedness',
+                                            'height_in':'Height (in)',
+                                            'weight_lbs':'Weight (lbs)',
+                                            'birth_date':'Birthday',
+                                            'birth_country':'Nationality'})
         #Set TOI to minute
         complete['TOI'] = complete['TOI']/60

{wsba_hockey-1.2.1 → wsba_hockey-1.2.3/src/wsba_hockey.egg-info}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wsba_hockey
-Version: 1.2.1
+Version: 1.2.3
 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-1.2.1 → wsba_hockey-1.2.3}/src/wsba_hockey.egg-info/SOURCES.txt RENAMED Viewed

@@ -9,6 +9,8 @@ src/wsba_hockey.egg-info/dependency_links.txt
 src/wsba_hockey.egg-info/top_level.txt
 src/wsba_hockey/tools/__init__.py
 src/wsba_hockey/tools/agg.py
+src/wsba_hockey/tools/columns.py
+src/wsba_hockey/tools/game_pred.py
 src/wsba_hockey/tools/plotting.py
 src/wsba_hockey/tools/scraping.py
 src/wsba_hockey/tools/xg_model.py