8 lines
213 B
Python
8 lines
213 B
Python
import re
|
|
|
|
from good_ai.utilities.lemmatize_text import lemmatize_text
|
|
|
|
|
|
def preprocess(text: str) -> str:
|
|
lemmas = [re.sub(r"\d+", "NUM", lemma) for lemma in lemmatize_text(text)]
|
|
return " ".join(lemmas)
|