fix: incorrect parameters for tokenize

This commit is contained in:
2026-02-01 18:13:44 +00:00
parent 319f9276a6
commit fe257ece5c

View File

@@ -39,7 +39,7 @@ class StatGen:
df["hour"] = df["dt"].dt.hour
df["weekday"] = df["dt"].dt.day_name()
def _tokenize(text: str):
def _tokenize(self, text: str):
tokens = re.findall(r"\b[a-z]{3,}\b", text)
return [t for t in tokens if t not in EXCLUDE_WORDS]