Toloka documentation

fit_predict_scores

crowdkit.aggregation.embeddings.hrrasa.HRRASA.fit_predict_scores | Source code

fit_predict_scores(
    self,
    data: DataFrame,
    true_embeddings: Optional[Series] = None
)

Fit the model and return scores.

Parameters Description

Parameters Type Description
data DataFrame

Workers' outputs with their embeddings. A pandas.DataFrame containing task, worker, output and embedding columns.

true_embeddings Optional[Series]

Tasks' embeddings. A pandas.Series indexed by task and holding corresponding embeddings.

  • Returns:

    Tasks' label scores. A pandas.DataFrame indexed by task such that result.loc[task, label] is the score of label for task.

  • Return type:

    DataFrame