sklearn_lvq.MrslvqModel

class sklearn_lvq.MrslvqModel(prototypes_per_class=1, initial_prototypes=None, initial_matrix=None, regularization=0.0, dim=None, sigma=1, max_iter=1000, gtol=1e-05, display=False, random_state=None)

Matrix Robust Soft Learning Vector Quantization

Parameters:

prototypes_per_class : int or list of int, optional (default=1)

Number of prototypes per class. Use list to specify different numbers per class.

initial_prototypes : array-like,

shape = [n_prototypes, n_features + 1], optional

Prototypes to start with. If not given initialization near the class means. Class label must be placed as last entry of each prototype

initial_matrix : array-like, shape = [dim, n_features], optional

Relevance matrix to start with. If not given random initialization for rectangular matrix and unity for squared matrix.

regularization : float, optional (default=0.0)

Value between 0 and 1. Regularization is done by the log determinant of the relevance matrix. Without regularization relevances may degenerate to zero.

dim : int, optional (default=nb_features)

Maximum rank or projection dimensions

sigma : float, optional (default=0.5)

Variance for the distribution.

max_iter : int, optional (default=500)

The maximum number of iterations.

gtol : float, optional (default=1e-5)

Gradient norm must be less than gtol before successful termination of l-bfgs-b.

display : boolean, optional (default=False)

Print information about the bfgs steps.

random_state : int, RandomState instance or None, optional (default=None)

If int, random_state is the seed used by the random number generator; If RandomState instance, random_state is the random number generator; If None, the random number generator is the RandomState instance used by np.random.

Attributes:

w_ : array-like, shape = [n_prototypes, n_features]

Prototype vector, where n_prototypes in the number of prototypes and n_features is the number of features

c_w_ : array-like, shape = [n_prototypes]

Prototype classes

classes_ : array-like, shape = [n_classes]

Array containing labels.

dim_ : int

Maximum rank or projection dimensions

omega_ : array-like, shape = [dim, n_features]

Relevance matrix

See also

RslvqModel, LmrslvqModel

Methods

fit(x, y)	Fit the LVQ model to the given training data and parameters using l-bfgs-b.
get_params([deep])	Get parameters for this estimator.
posterior(y, x)	calculate the posterior for x:
predict(x)	Predict class membership index for each input sample.
project(x, dims[, print_variance_covered])	Projects the data input data X using the relevance matrix of trained model to dimension dim
score(X, y[, sample_weight])	Returns the mean accuracy on the given test data and labels.
set_params(**params)	Set the parameters of this estimator.

__init__(prototypes_per_class=1, initial_prototypes=None, initial_matrix=None, regularization=0.0, dim=None, sigma=1, max_iter=1000, gtol=1e-05, display=False, random_state=None)

x.__init__(…) initializes x; see help(type(x)) for signature

fit(x, y)

Fit the LVQ model to the given training data and parameters using l-bfgs-b.

Parameters:

x : array-like, shape = [n_samples, n_features]

Training vector, where n_samples in the number of samples and n_features is the number of features.

y : array, shape = [n_samples]

Target values (integers in classification, real numbers in regression)

Returns:

self

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.

posterior(y, x)

calculate the posterior for x:

p(y|x)

Parameters:

y: class

label

x: array-like, shape = [n_features]

sample

Returns:

posterior

:return: posterior

predict(x)

Predict class membership index for each input sample.

This function does classification on an array of test vectors X.

Parameters:

x : array-like, shape = [n_samples, n_features]

Returns:

C : array, shape = (n_samples,)

Returns predicted values.

project(x, dims, print_variance_covered=False)

Projects the data input data X using the relevance matrix of trained model to dimension dim

Parameters:

x : array-like, shape = [n,n_features]

input data for project

dims : int

dimension to project to

print_variance_covered : boolean

flag to print the covered variance of the projection

Returns:

C : array, shape = [n,n_features]

Returns predicted values.

score(X, y, sample_weight=None)

Returns 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:

X : array-like, shape = (n_samples, n_features)

Test samples.

y : array-like, shape = (n_samples) or (n_samples, n_outputs)

True labels for X.

sample_weight : array-like, shape = [n_samples], optional

Sample weights.

Returns:

score : float

Mean accuracy of self.predict(X) wrt. y.

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