bluecast.conformal_prediction.conformal_prediction_regression

Module Contents

Classes

ConformalPredictionRegressionWrapper

Calibrate a model instance given a calibration set.
class bluecast.conformal_prediction.conformal_prediction_regression.ConformalPredictionRegressionWrapper(model: Any, nonconformity_measure_scorer: Callable = absolute_error)

Bases: bluecast.conformal_prediction.base_classes.ConformalPredictionWrapperBaseClass

Calibrate a model instance given a calibration set.

Parameters:

  • model – An already fitted model instance of any type

  • nonconformity_measure_scorer – A function object to calculate nonconformity scores with args y_calibration, preds

plot_non_conformity_scores(nonconformity_scores: List[float]) → None

Plot the distribution of nonconformity scores. :param nonconformity_scores: List of nonconformity scores

calibrate(x_calibration, y_calibration)

Calibrate a model instance given a calibration set.

Parameters:

  • x_calibration – Calibration set features. Must be unseen data for the model

  • y_calibration – Calibration set labels or values

predict(x)
_calculate_intervals(y_hat: numpy.ndarray, quantiles: List[float], alphas: List[float]) → pandas.DataFrame

Add lower and upper prediction bands for every quantile in quantiles.

predict_interval(x: pandas.DataFrame, alphas: List[float]) → pandas.DataFrame