mars.learn.semi_supervised.LabelPropagation#

class mars.learn.semi_supervised.LabelPropagation(kernel='rbf', gamma=20, n_neighbors=7, max_iter=1000, tol=0.001)[source]#

Label Propagation classifier

Read more in the User Guide.

Parameters

  • kernel ({'knn', 'rbf', callable}) – String identifier for kernel function to use or the kernel function itself. Only ‘rbf’ and ‘knn’ strings are valid inputs. The function passed should take two inputs, each of shape [n_samples, n_features], and return a [n_samples, n_samples] shaped weight matrix.

  • gamma (float) – Parameter for rbf kernel

  • n_neighbors (integer > 0) – Parameter for knn kernel

  • max_iter (integer) – Change maximum number of iterations allowed

  • tol (float) – Convergence tolerance: threshold to consider the system at steady state

X_#

Input array.

Type

array, shape = [n_samples, n_features]

classes_#

The distinct labels used in classifying instances.

Type

array, shape = [n_classes]

label_distributions_#

Categorical distribution for each item.

Type

array, shape = [n_samples, n_classes]

transduction_#

Label assigned to each item via the transduction.

Type

array, shape = [n_samples]

n_iter_#

Number of iterations run.

Type

int

Examples

>>> import numpy as np
>>> from sklearn import datasets
>>> from mars.learn.semi_supervised import LabelPropagation
>>> label_prop_model = LabelPropagation()
>>> iris = datasets.load_iris()
>>> rng = np.random.RandomState(42)
>>> random_unlabeled_points = rng.rand(len(iris.target)) < 0.3
>>> labels = np.copy(iris.target)
>>> labels[random_unlabeled_points] = -1
>>> label_prop_model.fit(iris.data, labels)
LabelPropagation(...)

References

Xiaojin Zhu and Zoubin Ghahramani. Learning from labeled and unlabeled data with label propagation. Technical Report CMU-CALD-02-107, Carnegie Mellon University, 2002 http://pages.cs.wisc.edu/~jerryzhu/pub/CMU-CALD-02-107.pdf

See also

LabelSpreading

Alternate label propagation strategy more robust to noise

__init__(kernel='rbf', gamma=20, n_neighbors=7, max_iter=1000, tol=0.001)[source]#

Methods

__init__([kernel, gamma, n_neighbors, ...])

fit(X, y[, session, run_kwargs])

Fit a semi-supervised label propagation model based

get_params([deep])

Get parameters for this estimator.

predict(X[, session, run_kwargs])

Performs inductive inference across the model.

predict_proba(X[, session, run_kwargs])

Predict probability for each possible outcome.

score(X, y[, sample_weight, session, run_kwargs])

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

set_params(**params)

Set the parameters of this estimator.