PlainLearner

class falcon.tabular.learners.PlainLearner(task: str, model_class: Optional[Type] = None, hyperparameters: Optional[Dict] = None, **kwargs: Any)

PlainLearner trains a model using provided or default hyperparameters.

__init__(task: str, model_class: Optional[Type] = None, hyperparameters: Optional[Dict] = None, **kwargs: Any) → None

Parameters

task (str) – ‘tabular_classification’ or ‘tabular_regression’
model_class (Optional[Type], optional) – the class of the model to train, by default None; if None, HistGradientBoosting is used
hyperparameters (Dict, optional) – the dictionary of hyperparameters for model training

fit(X: ndarray[Any, dtype[float32]], y: ndarray[Any, dtype[float32]], *args: Any, **kwargs: Any) → None

Fits the model and trains the final model using them. For classification tasks, the dataset will be balanced by upsampling the minority class(es).

Parameters

X (Float32Array) – features
y (Float32Array) – targets

fit_pipe(X: ndarray[Any, dtype[float32]], y: ndarray[Any, dtype[float32]], *args: Any, **kwargs: Any) → None

Equivalent to .fit(X, y)

Parameters

X (Float32Array) – features
y (Float32Array) – targets

forward(X: Any, *args: Any, **kwargs: Any) → Any

Equivalent of predict method that is used for elements chaining inside pipeline during inference.

Parameters: X (Any) – featrues
Returns: predictions
Return type: Any

get_input_type() → Type

Returns: Float32Array
Return type: Type

get_output_type() → Type

Returns: Float32Array for regression, Int64Array for classification
Return type: Type

predict(X: ndarray[Any, dtype[float32]], *args: Any, **kwargs: Any) → Union[ndarray[Any, dtype[float32]], ndarray[Any, dtype[int64]]]

Parameters: X (npt.NDArray) – features
Returns: predictions
Return type: npt.NDArray

to_onnx() → SerializedModelRepr

Serializes the underlying model to onnx by calling its .to_onnx() method.

Return type: SerializedModelRepr