Loading...

vastorbit.machine_learning.vast.feature_extraction.text.TfidfVectorizer.fit

TfidfVectorizer.fit(input_relation: Annotated[str | VastFrame, ''], index: str, x: str, return_report: bool = False) → None

Applies basic pre-processing. Creates table with fitted vocabulary and idf values.

Parameters:

  • input_relation (SQLRelation) – Training relation.

  • index (str) – Column name of the document id.

  • x (str) – Column name which contains the text.