predict_proba

MultiModalEndpoint.predict_proba(data: str | list[str] | DataFrame, *, include_predict: bool = True, **inference_kwargs: Any) → tuple[Series, DataFrame | Series] | DataFrame | Series[source]

Predict class probabilities for data with the deployed endpoint.

For regression, the probability result is identical to the prediction.

Parameters:

  • data (str | list[str] | pd.DataFrame) –

    Data to predict. One of:

    • a pd.DataFrame or a local path to a data file.

    • a local path to a single image file, or a list of local paths to image files.

  • include_predict (bool, default = True) – Whether to return the predictions along with the probabilities. Both are computed in the same request.

  • **inference_kwargs (Any) – Additional args passed to the predict_proba call of the AutoGluon predictor on the endpoint. If data has an image column, pass image_column to name the column with absolute paths to local images; the images are encoded and sent with the request.

Returns:

tuple[pd.Series, pd.DataFrame | pd.Series] | pd.DataFrame | pd.Series – (prediction, predict_probability) if include_predict is True, otherwise predict_probability.

SageMaker API

  • InvokeEndpoint: sends the data to the endpoint and returns the predictions. The payload is limited to 6 MB (4 MB for serverless endpoints).