bqlearn.plugin.PluginCorrection

class bqlearn.plugin.PluginCorrection(estimator, *, prefit=False, transition_matrix='iterative', quantile=0.97, n_iter=100, noise_free_prior=0.0)

A Noise Corrected Plug-in Classifier.

PluginCorrection [1] learns a classifier on noisy data and uses a noise transition matrix \(\mathbf{T}\) at prediction time (plug-in) to correct the classifier.

\[\forall x \in \mathcal{X}, f_T(x)=(\mathbf{T}^{t})^{-1}\cdot f_U(x)\]

Parameters:

estimatorestimator object

An estimator object implementing fit and predict_proba.

prefitbool, default=False

Whether a prefit model is expected to be passed into the constructor directly or not. If True, estimator must be a fitted estimator. If False, estimator is fitted by calling fit.

transition_matrix{‘iterative’, ‘anchor’, ‘gold’, ‘confusion’} or array-like of shape (n_classes, n_classes), default=’iterative’

Algorithm to estimate the transition matrix. ‘gold’ and ‘confusion’ are only available on biquality data.

quantilefloat, default=0.97

Quantile used to select the anchor points. Only used when transition_matrix=’anchor’ or transition_matrix=’iterative’.

n_iterint, default=100

Number of iteratives to compute the transition matrix. Only used when transition_matrix=’iterative’.

noise_free_priorfloat, default=0.0

Factor for the convex combination between the estimated transition_matrix and the identity matrix to lower the condition number of the estimated transition matrix. It’s equivalent to take a more conservative noise-free prior.

random_stateint or RandomState, default=None

Controls the random seed given at base_estimator. Pass an int for reproducible output across multiple function calls.

Attributes:

estimator_classifier

The fitted estimator.

transition_matrix_: ndarray of shape (n_classes, n_classes)

Estimated transition matrix between untrusted and untrusted labels.

classes_ndarray of shape (n_classes,)

The classes labels.

n_classes_int

The number of classes.

n_features_in_int

Number of features seen during fit. Only defined if the underlying estimator exposes such an attribute when fit.

feature_names_in_ndarray of shape (n_features_in_,)

Names of features seen during fit. Only defined if the underlying estimator exposes such an attribute when fit.

References

[1]

13. Zhang, J. Lee, and S. Agarwal. “Learning from noisy labels with no change to the training process.”, ICML, 2021.

Methods

decision_function(X)	Noise-corrected plug-in of predicted probabilites from estimator.
fit(X, y[, sample_quality])	Fit the noise corrected plug-in classification model.
get_params([deep])	Get parameters for this estimator.
predict(X)	Predict the classes of X.
score(X, y[, sample_weight])	Return the mean accuracy on the given test data and labels.
set_params(**params)	Set the parameters of this estimator.

decision_function(X)

Noise-corrected plug-in of predicted probabilites from estimator.

For binary classification, the score is the margin between the two classes.

Parameters:

Xarray-like, shape (n_samples, n_features)

The input samples.

Returns:

yndarray, shape (n_samples, n_classes)

The predicted classes.

fit(X, y, sample_quality=None)

Fit the noise corrected plug-in classification model.

Parameters:

Xarray-like of shape (n_samples, n_features)

The samples.

yarray-like of shape (n_samples,)

The targets.

sample_qualityarray-like, shape (n_samples,)

Per-sample qualities.

Returns:

selfobject

Returns self.

get_params(deep=True)

Get parameters for this estimator.

Parameters:

deepbool, default=True

If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns:

paramsdict

Parameter names mapped to their values.

predict(X)

Predict the classes of X.

Parameters:

Xarray-like, shape (n_samples, n_features)

The input samples.

Returns:

yndarray, shape (n_samples,)

The predicted classes.

score(X, y, sample_weight=None)

Return the mean accuracy on the given test data and labels.

In multi-label classification, this is the subset accuracy which is a harsh metric since you require for each sample that each label set be correctly predicted.

Parameters:

Xarray-like of shape (n_samples, n_features)

Test samples.

yarray-like of shape (n_samples,) or (n_samples, n_outputs)

True labels for X.

sample_weightarray-like of shape (n_samples,), default=None

Sample weights.

Returns:

scorefloat

Mean accuracy of self.predict(X) w.r.t. y.

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as Pipeline). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**paramsdict

Estimator parameters.

Returns:

selfestimator instance

Estimator instance.