nonconformist.icp.IcpClassifier

class nonconformist.icp.IcpClassifier(nc_function, condition=None, smoothing=True)

Inductive conformal classifier.

Parameters:

nc_function : BaseScorer

Nonconformity scorer object used to calculate nonconformity of calibration examples and test patterns. Should implement fit(x, y) and calc_nc(x, y).

smoothing : boolean

Decides whether to use stochastic smoothing of p-values.

See also

IcpRegressor

References

[R55]Papadopoulos, H., & Haralambous, H. (2011). Reliable prediction intervals with regression neural networks. Neural Networks, 24(8), 842-851.

Examples

>>> import numpy as np
>>> from sklearn.datasets import load_iris
>>> from sklearn.tree import DecisionTreeClassifier
>>> from nonconformist.icp import IcpClassifier
>>> from nonconformist.nc import ClassifierNc, MarginErrFunc
>>> iris = load_iris()
>>> idx = np.random.permutation(iris.target.size)
>>> train = idx[:int(idx.size / 3)]
>>> cal = idx[int(idx.size / 3):int(2 * idx.size / 3)]
>>> test = idx[int(2 * idx.size / 3):]
>>> nc = ProbEstClassifierNc(DecisionTreeClassifier, MarginErrFunc())
>>> icp = IcpClassifier(nc)
>>> icp.fit(iris.data[train, :], iris.target[train])
>>> icp.calibrate(iris.data[cal, :], iris.target[cal])
>>> icp.predict(iris.data[test, :], significance=0.10)
...             
array([[ True, False, False],
        [False,  True, False],
        ...,
        [False,  True, False],
        [False,  True, False]], dtype=bool)

Attributes

cal_x (numpy array of shape [n_cal_examples, n_features]) Inputs of calibration set.
cal_y (numpy array of shape [n_cal_examples]) Outputs of calibration set.
nc_function (BaseScorer) Nonconformity scorer object used to calculate nonconformity scores.
__init__(nc_function, condition=None, smoothing=True)
calibrate(x, y, increment=False)

Calibrate conformal predictor based on underlying nonconformity scorer.

Parameters:

x : numpy array of shape [n_samples, n_features]

Inputs of examples for calibrating the conformal predictor.

y : numpy array of shape [n_samples, n_features]

Outputs of examples for calibrating the conformal predictor.

increment : boolean

If True, performs an incremental recalibration of the conformal predictor. The supplied x and y are added to the set of previously existing calibration examples, and the conformal predictor is then calibrated on both the old and new calibration examples.
Returns:

None
fit(x, y)

Fit underlying nonconformity scorer.

Parameters:

x : numpy array of shape [n_samples, n_features]

Inputs of examples for fitting the nonconformity scorer.

y : numpy array of shape [n_samples]

Outputs of examples for fitting the nonconformity scorer.
Returns:

None
get_params(deep=True)

Get parameters for this estimator.

Parameters:

deep : boolean, optional

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

params : mapping of string to any

Parameter names mapped to their values.
predict(x, significance=None)

Predict the output values for a set of input patterns.

Parameters:

x : numpy array of shape [n_samples, n_features]

Inputs of patters for which to predict output values.

significance : float or None

Significance level (maximum allowed error rate) of predictions. Should be a float between 0 and 1. If None, then the p-values are output rather than the predictions.
Returns:

p : numpy array of shape [n_samples, n_classes]

If significance is None, then p contains the p-values for each sample-class pair; if significance is a float between 0 and 1, then p is a boolean array denoting which labels are included in the prediction sets.
predict_conf(x)

Predict the output values for a set of input patterns, using the confidence-and-credibility output scheme.

Parameters:

x : numpy array of shape [n_samples, n_features]

Inputs of patters for which to predict output values.
Returns:

p : numpy array of shape [n_samples, 3]

p contains three columns: the first column contains the most likely class for each test pattern; the second column contains the confidence in the predicted class label, and the third column contains the credibility of the prediction.
set_params(**params)

Set the parameters of this estimator.

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

Returns:self