feat(03-02): add WNBA to canonicalization pipeline

- Import WNBA_TEAMS from wnba module
- Add WNBA_DIVISIONS dict (single league structure, no divisions)
- Add WNBA to sport_mappings for team canonicalization
- Update arena_key to use 'arena' for WNBA (like NBA/NHL)
- Add WNBA team abbreviation aliases (LV, LAS, NYL, PHX, etc.)
- Add WNBA stadium aliases (Michelob Ultra Arena, Gateway Center, etc.)

Total teams: 167 (13 WNBA teams added)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Scripts/canonicalize_games.py

@@ -109,6 +109,14 @@ TEAM_ABBREV_ALIASES = {
     ('MLS', 'FCD'): 'team_mls_dal',    # FC Dallas
     ('MLS', 'MON'): 'team_mls_mtl',    # Montreal
     ('MLS', 'LAF'): 'team_mls_lafc',   # LAFC alt
+
+    # WNBA
+    ('WNBA', 'LV'): 'team_wnba_lva',    # Las Vegas Aces
+    ('WNBA', 'LAS'): 'team_wnba_la',    # LA Sparks
+    ('WNBA', 'NYL'): 'team_wnba_ny',    # New York Liberty
+    ('WNBA', 'PHX'): 'team_wnba_pho',   # Phoenix Mercury
+    ('WNBA', 'CONN'): 'team_wnba_con',  # Connecticut Sun
+    ('WNBA', 'WSH'): 'team_wnba_was',   # Washington Mystics
 }
 
 

Scripts/canonicalize_stadiums.py

@@ -233,6 +233,20 @@ HISTORICAL_STADIUM_ALIASES = {
         {'alias_name': 'lower.com field', 'valid_from': '2021-07-01'},  # Current name with period
         {'alias_name': 'new crew stadium', 'valid_from': '2021-07-01', 'valid_until': '2021-07-01'},
     ],
+
+    # WNBA (most share NBA/NHL arenas with existing aliases; these are WNBA-specific arenas)
+    'stadium_wnba_michelob_ultra_arena': [
+        {'alias_name': 'mandalay bay events center', 'valid_from': '1999-03-01', 'valid_until': '2021-01-01'},
+    ],
+    'stadium_wnba_gateway_center_arena': [
+        # Gateway Center Arena opened 2018, WNBA-specific venue
+    ],
+    'stadium_wnba_wintrust_arena': [
+        # Wintrust Arena opened 2017, WNBA-specific venue
+    ],
+    'stadium_wnba_college_park_center': [
+        # College Park Center opened 2012, university venue
+    ],
 }
 
 

Scripts/canonicalize_teams.py

@@ -20,6 +20,7 @@ from typing import Optional
 # Import team mappings from scraper
 from scrape_schedules import NBA_TEAMS, MLB_TEAMS, NHL_TEAMS, NFL_TEAMS
 from mls import MLS_TEAMS
+from wnba import WNBA_TEAMS
 
 
 # =============================================================================
@@ -252,6 +253,23 @@ MLS_DIVISIONS = {
     'VAN': ('mls_western', None),
 }
 
+WNBA_DIVISIONS = {
+    # WNBA has no divisions (single league structure)
+    'ATL': ('wnba', None),
+    'CHI': ('wnba', None),
+    'CON': ('wnba', None),
+    'DAL': ('wnba', None),
+    'GSV': ('wnba', None),
+    'IND': ('wnba', None),
+    'LVA': ('wnba', None),
+    'LA': ('wnba', None),
+    'MIN': ('wnba', None),
+    'NY': ('wnba', None),
+    'PHO': ('wnba', None),
+    'SEA': ('wnba', None),
+    'WAS': ('wnba', None),
+}
+
 
 # =============================================================================
 # FUZZY MATCHING
@@ -402,7 +420,7 @@ def canonicalize_teams(
     warnings = []
 
     # Determine arena key based on sport
-    arena_key = 'arena' if sport in ['NBA', 'NHL'] else 'stadium'
+    arena_key = 'arena' if sport in ['NBA', 'NHL', 'WNBA'] else 'stadium'
 
     # Get division structure
     division_map = {
@@ -411,6 +429,7 @@ def canonicalize_teams(
         'NHL': NHL_DIVISIONS,
         'NFL': NFL_DIVISIONS,
         'MLS': MLS_DIVISIONS,
+        'WNBA': WNBA_DIVISIONS,
     }.get(sport, {})
 
     for abbrev, info in team_mappings.items():
@@ -485,6 +504,7 @@ def canonicalize_all_teams(
         ('NHL', NHL_TEAMS),
         ('NFL', NFL_TEAMS),
         ('MLS', MLS_TEAMS),
+        ('WNBA', WNBA_TEAMS),
     ]
 
     for sport, team_map in sport_mappings: