wsba-hockey 1.1.5__tar.gz → 1.1.7__tar.gz

{wsba_hockey-1.1.5/src/wsba_hockey.egg-info → wsba_hockey-1.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: wsba_hockey
-Version: 1.1.5
+Version: 1.1.7
 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-1.1.5 → wsba_hockey-1.1.7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "wsba_hockey"
-version = "1.1.5"
+version = "1.1.7"
 authors = [
   { name="Owen Singh", email="owenbksingh@gmail.com" },
 ]
@@ -18,4 +18,18 @@ keywords = ["wsba","hockey","scraping","NHL","analytics"]
 Homepage = "https://github.com/owensingh38/wsba_hockey/"
 
 [tool.setuptools]
-include-package-data = true
+include-package-data = true
+
+[tool.setuptools.exclude-package-data]
+wsba_hockey = [
+    "api/*",
+    "aws_pbp/*",
+    "pbp/*",
+    "sources/*",
+    "stats/*",
+    "evidence/*",
+    "flask/*",
+    "__pycache__/*",
+    "_vscode/*",
+    ".gitattributes"
+]

{wsba_hockey-1.1.5 → wsba_hockey-1.1.7}/src/wsba_hockey/__init__.py

@@ -1 +1 @@
-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
+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_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-1.1.5 → wsba_hockey-1.1.7}/src/wsba_hockey/api/api/index.py

@@ -90,14 +90,7 @@ def schedule_info(season: int):
 
 @app.get("/nhl/games/{game_id}")
 def pbp(game_id: int):
-    info = rs.get(f'https://api-web.nhle.com/v1/gamecenter/{game_id}/play-by-play').json()
-
-    season = info['season']
-    dataset = ds.dataset(f's3://weakside-breakout/pbp/parquet/nhl_pbp_{season}.parquet', format='parquet')
-    filter_expr = (ds.field('game_id')==game_id)
-
-    table = dataset.to_table(use_threads=True,filter=filter_expr)
-    df = table.to_pandas()
+    df = pd.read_csv(f'data/sources/20242025/{game_id}.csv')
 
     df = df.fillna('')
 

{wsba_hockey-1.1.5 → wsba_hockey-1.1.7}/src/wsba_hockey/tools/agg.py

@@ -89,6 +89,7 @@ def calc_indv(pbp,game_strength,second_group):
 
         shot = shot.rename(columns={
             'Gi':f'{type.capitalize()}Gi',
+            'Si':f'{type.capitalize()}Si',
             'Fi':f'{type.capitalize()}Fi',
             'xGi':f'{type.capitalize()}xGi',
         })

{wsba_hockey-1.1.5 → wsba_hockey-1.1.7}/src/wsba_hockey/tools/scraping.py

@@ -1,6 +1,7 @@
 import re
 import warnings
 import os
+import asyncio
 import numpy as np
 import pandas as pd
 import requests as rs
@@ -179,7 +180,7 @@ def get_game_info(game_id):
             'coaches':get_game_coaches(game_id),
             'json_shifts':json_shifts}
 
-def parse_json(info):
+async def parse_json(info):
     #Given game info, return JSON document
 
     #Retreive data
@@ -340,7 +341,7 @@ def clean_html_pbp(info):
 
     return cleaned_html
 
-def parse_html(info):
+async def parse_html(info):
     #Given game info, return HTML event data
 
     #Retreive game information and html events
@@ -561,7 +562,7 @@ def espn_game_id(date,away,home):
     #Return: ESPN game id
     return game_id
 
-def parse_espn(date,away,home):
+async def parse_espn(date,away,home):
     #Given a date formatted as YYYY-MM-DD and teams, return game events
     game_id = espn_game_id(date,away,home)
     url = f'https://www.espn.com/nhl/playbyplay/_/gameId/{game_id}'
@@ -711,15 +712,24 @@ def assign_target(data):
     #Revert sort and return dataframe
     return data.reset_index()
 
-def combine_pbp(info,sources):
+async def combine_pbp(info,sources):
     #Given game info, return complete play-by-play data for provided game
 
-    html_pbp = parse_html(info)
+    #Create tasks
+    html_task = asyncio.create_task(parse_html(info))
+    if info['season'] in [20052006, 20062007, 20072008, 20082009, 20092010]:
+        json_task = asyncio.create_task(parse_espn(str(info['game_date']),info['away_team_abbr'],info['home_team_abbr']))
+        json_type = 'espn'
+    else:
+        json_task = asyncio.create_task(parse_json(info))
+        json_type = 'nhl'
 
+    html_pbp, json_pbp = await asyncio.gather(html_task, json_task)
+    
     #Route data combining - json if season is after 2009-2010:
-    if str(info['season']) in ['20052006','20062007','20072008','20082009','20092010']:
+    if json_type == 'espn':
         #ESPN x HTML
-        espn_pbp = parse_espn(str(info['game_date']),info['away_team_abbr'],info['home_team_abbr']).rename(columns={'coords_x':'x',"coords_y":'y'}).sort_values(['period','seconds_elapsed']).reset_index()
+        espn_pbp = json_pbp.rename(columns={'coords_x':'x',"coords_y":'y'}).sort_values(['period','seconds_elapsed']).reset_index()
         merge_col = ['period','seconds_elapsed','event_type','event_team_abbr']
 
         #Merge pbp
@@ -727,8 +737,6 @@ def combine_pbp(info,sources):
 
     else:
         #JSON x HTML
-        json_pbp = parse_json(info)
-
         if sources:
             dirs_html = f'sources/{info['season']}/HTML/'
             dirs_json = f'sources/{info['season']}/JSON/'
@@ -1077,12 +1085,10 @@ def combine_shifts(info,sources):
     #Return: full shifts data converted to play-by-play format
     return full_shifts
 
-def combine_data(info,sources):
+async def combine_data(info,sources):
     #Given game info, return complete play-by-play data
 
-    game_id = info['game_id']
-
-    pbp = combine_pbp(info,sources)
+    pbp = await combine_pbp(info,sources)
     shifts = combine_shifts(info,sources)
 
     #Combine data