cvt.models package

Submodules

cvt.models.base_class module

Subspace Method Interface

class cvt.models.base_class.ConstrainedSMBase(n_subdims, n_gds_dims, normalize=False)

Bases: cvt.models.base_class.SMBase

Base class of Constrained Subspace Method

param_names = {'n_gds_dims', 'n_subdims', 'normalize'}

class cvt.models.base_class.KernelCSMBase(n_subdims, n_gds_dims, normalize=False, sigma=None)

Bases: cvt.models.base_class.SMBase

Base class of Kernel Constrained Subspace Method

param_names = {'n_gds_dims', 'n_subdims', 'normalize', 'sigma'}

class cvt.models.base_class.KernelSMBase(n_subdims, normalize=False, sigma=None, faster_mode=False)

Bases: cvt.models.base_class.SMBase

Base class of Kernel Subspace Method

param_names = {'n_subdims', 'normalize', 'sigma'}

class cvt.models.base_class.MSMInterface

Bases: object

Prediction interface of Mutual Subspace Method

predict_proba(X)

Predict class probabilities

X: list of 2d-arrays, (n_vector_sets, n_samples, n_dims)

List of input vector sets.

pred: array, (n_vector_sets)

Prediction array

property test_n_subdims

class cvt.models.base_class.SMBase(n_subdims, normalize=False, faster_mode=False)

Bases: sklearn.base.BaseEstimator, sklearn.base.ClassifierMixin

Base class of Subspace Method

fit(X, y)

Fit the model using the given data and parameters

Parameters

• X (list of 2d-arrays, (n_classes, n_samples, n_dims)) – Training vectors. n_classes is count of classes. n_samples is number of vectors of samples, this is variable across each classes. n_dims is number of dimentions of vectors.

• y (integer array, (n_classes)) –

  Class labels of training vectors. e.g.

  y = np.unique(labels).astype(int) y = range(len(X))

get_params(deep=True)

Get parameters for this estimator.

Parameters

deep (bool, default=True) – If True, will return the parameters for this estimator and contained subobjects that are estimators.

Returns

params – Parameter names mapped to their values.

Return type

mapping of string to any

param_names = {'n_subdims', 'normalize'}

predict(X)

Predict classes

X: list of 2d-arrays, (n_vector_sets, n_samples, n_dims)

List of input vector sets.

pred: array, (n_vector_sets)

Prediction array

predict_proba(X)

Predict class probabilities

X: 2d-array, (n_samples, n_dims)

Matrix of input vectors.

pred: array-like, shape: (n_samples)

Prediction array

proba2class(proba)

set_params(**parameters)

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.

Parameters

**params (dict) – Estimator parameters.

Returns

self – Estimator instance.

Return type

object

cvt.models.cmsm module

Constrained Mutual Subspace Method

class cvt.models.cmsm.ConstrainedMSM(n_subdims, n_gds_dims, normalize=False)

Bases: cvt.models.base_class.MSMInterface, cvt.models.base_class.ConstrainedSMBase

Constrained Mutual Subspace Method

cvt.models.kcmsm module

Kernel Constrained Mutual Subspace Method

class cvt.models.kcmsm.KernelCMSM(n_subdims, n_gds_dims, normalize=False, sigma=None)

Bases: cvt.models.base_class.MSMInterface, cvt.models.base_class.KernelCSMBase

Kernel Constrained Mutual Subspace Method

cvt.models.kmsm module

Kernel Mutual Subspace Method

class cvt.models.kmsm.KernelMSM(n_subdims, normalize=False, sigma=None, faster_mode=False)

Bases: cvt.models.base_class.MSMInterface, cvt.models.base_class.KernelSMBase

Kernel Mutual Subspace Method

fast_predict_proba(X)

Predict class probabilities

X: list of 2d-arrays, (n_vector_sets, n_samples, n_dims)

List of input vector sets.

pred: array, (n_vector_sets)

Prediction array

cvt.models.msm module

Mutual Subspace Method

class cvt.models.msm.MutualSubspaceMethod(n_subdims, normalize=False, faster_mode=False)

Bases: cvt.models.base_class.MSMInterface, cvt.models.base_class.SMBase

Mutual Subspace Method

cvt.models.sm module

Subspace Method

class cvt.models.sm.SubspaceMethod(n_subdims, normalize=False, faster_mode=False)

Bases: cvt.models.base_class.SMBase

Mutual Subspace Method

Module contents