pycalib.calibration_methods Module

Calibration Methods.

Classes

BayesianBinningQuantiles([C, input_range])	Probability calibration using Bayesian binning into quantiles
BetaCalibration([params])	Probability calibration using Beta calibration
CalibrationMethod()	A generic class for probability calibration
GPCalibration(n_classes[, logits, …])	Probability calibration using a latent Gaussian process
HistogramBinning([mode, n_bins, input_range])	Probability calibration using histogram binning
IsotonicRegression([out_of_bounds])	Probability calibration using Isotonic Regression
LabelBinarizer([neg_label, pos_label, …])	Binarize labels in a one-vs-all fashion
NoCalibration([logits])	A class that performs no calibration.
OneVsRestCalibrator(calibrator[, n_jobs])	One-vs-the-rest (OvR) multiclass strategy Also known as one-vs-all, this strategy consists in fitting one calibrator per class.
Parallel([n_jobs, backend, verbose, …])	Helper class for readable parallel mapping.
PlattScaling([regularization, random_state])	Probability calibration using Platt scaling
TemperatureScaling([T_init, verbose])	Probability calibration using temperature scaling