Create odds_name_map.py

data/odds_name_map.py

@@ -0,0 +1,60 @@
+from __future__ import annotations
+
+import re
+import unicodedata
+
+
+NAME_ALIASES = {
+    "shohei ohtani": "shohei ohtani",
+    "shōhei ohtani": "shohei ohtani",
+    "seiya suzuki": "seiya suzuki",
+    "masataka yoshida": "masataka yoshida",
+    "mookie betts": "mookie betts",
+    "fernando tatis jr": "fernando tatis jr",
+    "fernando tatis jr.": "fernando tatis jr",
+    "vladimir guerrero jr": "vladimir guerrero jr",
+    "vladimir guerrero jr.": "vladimir guerrero jr",
+    "ronald acuña jr": "ronald acuna jr",
+    "ronald acuna jr": "ronald acuna jr",
+    "ronald acuña jr.": "ronald acuna jr",
+    "ronald acuna jr.": "ronald acuna jr",
+    "juan soto": "juan soto",
+    "julio rodriguez": "julio rodriguez",
+    "julio rodríguez": "julio rodriguez",
+    "jose ramirez": "jose ramirez",
+    "josé ramírez": "jose ramirez",
+    "yordan alvarez": "yordan alvarez",
+    "yordan álvarez": "yordan alvarez",
+    "luis robert jr": "luis robert jr",
+    "luis robert jr.": "luis robert jr",
+    "bo bichette": "bo bichette",
+    "manny machado": "manny machado",
+    "xander bogaerts": "xander bogaerts",
+    "rafael devers": "rafael devers",
+    "ketel marte": "ketel marte",
+    "isaac paredes": "isaac paredes",
+    "andy pages": "andy pages",
+}
+
+
+def _strip_accents(text: str) -> str:
+    normalized = unicodedata.normalize("NFKD", text)
+    return "".join(ch for ch in normalized if not unicodedata.combining(ch))
+
+
+def normalize_player_name(name: str) -> str:
+    text = str(name or "").strip().lower()
+    text = _strip_accents(text)
+    text = text.replace("’", "'")
+    text = text.replace(".", "")
+    text = re.sub(r"\s+", " ", text)
+
+    # Remove common suffix punctuation inconsistencies
+    text = text.replace(" jr ", " jr ")
+    text = text.replace(" sr ", " sr ")
+
+    return NAME_ALIASES.get(text, text)
+
+
+def map_odds_name_to_model_name(name: str) -> str:
+    return normalize_player_name(name)