`sklearn_rvm.em_rvm`.EMRVR¶

class sklearn_rvm.em_rvm.EMRVR(kernel='rbf', degree=3, gamma='auto_deprecated', coef0=0.0, tol=0.001, threshold_alpha=1000000000.0, beta_fixed='not_fixed', alpha_max=10000000000.0, init_alpha=None, bias_used=True, max_iter=5000, compute_score=False, epsilon=1e-08, verbose=False)[source]¶

Relevance Vector Regressor.

Implementation of the relevance vector regressor using the algorithm based on expectation maximization.

Parameters

kernelstring, optional (default=”rbf”)

Specifies the kernel type to be used in the algorithm. It must be one of “linear”, “poly”, “rbf”, “sigmoid” or “precomputed”. If none is given, “rbf” will be used.

degreeint, optional (default=3)

Degree of the polynomial kernel function (“poly”). Ignored by all other kernels.

gamma{“auto”, “scale”} or float, optional (default=”auto”)

Kernel coefficient for “rbf”, “poly” and “sigmoid”.

Current default is “auto” which uses 1 / n_features, if gamma="scale" is passed then it uses 1 / (n_features * X.var()) as value of gamma.

coef0float, optional (default=0.0)

Independent term in kernel function. It is only significant in “poly” and “sigmoid”.

tolfloat, optional (default=1e-6)

Tolerance for stopping criterion.

threshold_alphafloat, optional (default=1e5)

Threshold for alpha selection criterion.

beta_fixed{“not_fixed”} or float, optional (default=”not_fixed”)

Fixed value for beta. If “not_fixed” selected, the beta is updated at each iteration.

alpha_maxint, optional (default=1e9)

Basis functions associated with alpha value beyond this limit will be purged. Must be a positive and big number.

init_alphaarray-like of shape (n_sample) or None, optional (default=None)

Initial value for alpha. If None is selected, the initial value of alpha is defined by init_alpha = 1 / M ** 2.

bias_usedboolean, optional (default=False)

Specifies if a constant (a.k.a. bias) should be added to the decision function.

max_iterint, optional (default=5000)

Hard limit on iterations within solver.

compute_scoreboolean, optional (default=False)

Specifies if the objective function is computed at each step of the model.

verboseboolean, optional (default=False)

Enable verbose output.

See also

EMRVC: Relevant Vector Machine for Classification.

Notes

References: The relevance vector machine.

Attributes

relevance_array-like, shape (n_relevance): Indices of relevance vectors.
relevance_vectors_array-like, shape (n_relevance, n_features): Relevance vectors (equivalent to X[relevance_]).
alpha_array-like, shape (n_samples): Estimated alpha values.
gamma_array-like, shape (n_samples): Estimated gamma values.
Phi_array-like, shape (n_samples, n_features): Estimated phi values.
Sigma_array-like, shape (n_samples, n_features): Estimated covariance matrix of the weights.
mu_array-like, shape (n_relevance, n_features): Coefficients of the regression model (mean of posterior distribution)
coef_array, shape (n_class * (n_class-1) / 2, n_features): Coefficients of the regression model (mean of posterior distribution). Weights assigned to the features. This is only available in the case of a linear kernel. coef_ is a readonly property derived from mu and relevance_vectors_.

Methods

`compute_marginal_likelihood`(self, upper_inv, …)	Calculate marginal likelihood.
`fit`(self, X, y)	Fit the RVR model according to the given training data.
`get_params`(self[, deep])	Get parameters for this estimator.
`predict`(self, X[, return_std])	Predict using the RVR model.
`score`(self, X, y[, sample_weight])	Return the coefficient of determination R^2 of the prediction.
`set_params`(self, \\params)	Set the parameters of this estimator.

__init__(self, kernel='rbf', degree=3, gamma='auto_deprecated', coef0=0.0, tol=0.001, threshold_alpha=1000000000.0, beta_fixed='not_fixed', alpha_max=10000000000.0, init_alpha=None, bias_used=True, max_iter=5000, compute_score=False, epsilon=1e-08, verbose=False)[source]¶: Initialize self. See help(type(self)) for accurate signature.

compute_marginal_likelihood(self, upper_inv, ed, n_samples, y)[source]¶: Calculate marginal likelihood.

fit(self, X, y)[source]¶

Fit the RVR model according to the given training data.

Parameters

Xarray-like, shape (n_samples, n_features): Training vectors.
yarray-like, shape (n_samples,): Target values.

Returns

selfobject

get_params(self, deep=True)[source]¶

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

paramsmapping of string to any: Parameter names mapped to their values.

predict(self, X, return_std=False)[source]¶

Predict using the RVR model.

In addition to the mean of the predictive distribution, its standard deviation can also be returned.

Parameters

Xarray-like, shape (n_samples, n_features): Query points to be evaluate.
return_stdbool, optional (default=False): If True, the standard-deviation of the predictive distribution at the query points is returned along with the mean.

Returns

y_meanarray, shape (n_samples, n_output_dims): Mean of predictive distribution at query points
y_stdarray, shape (n_samples,), optional: Standard deviation of predictive distribution at query points. Only returned when return_std is True.

score(self, X, y, sample_weight=None)[source]¶

Return the coefficient of determination R^2 of the prediction.

The coefficient R^2 is defined as (1 - u/v), where u is the residual sum of squares ((y_true - y_pred) ** 2).sum() and v is the total sum of squares ((y_true - y_true.mean()) ** 2).sum(). The best possible score is 1.0 and it can be negative (because the model can be arbitrarily worse). A constant model that always predicts the expected value of y, disregarding the input features, would get a R^2 score of 0.0.

Parameters

Xarray-like of shape (n_samples, n_features): Test samples. For some estimators this may be a precomputed kernel matrix or a list of generic objects instead, shape = (n_samples, n_samples_fitted), where n_samples_fitted is the number of samples used in the fitting for the estimator.
yarray-like of shape (n_samples,) or (n_samples, n_outputs): True values for X.
sample_weightarray-like of shape (n_samples,), default=None: Sample weights.

Returns

scorefloat: R^2 of self.predict(X) wrt. y.

Notes

The R2 score used when calling score on a regressor will use multioutput='uniform_average' from version 0.23 to keep consistent with r2_score. This will influence the score method of all the multioutput regressors (except for MultiOutputRegressor). To specify the default value manually and avoid the warning, please either call r2_score directly or make a custom scorer with make_scorer (the built-in scorer 'r2' uses multioutput='uniform_average').

set_params(self, **params)[source]¶

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

**paramsdict: Estimator parameters.

Returns

selfobject: Estimator instance.

sklearn_rvm.em_rvm.EMRVR¶

`sklearn_rvm.em_rvm`.EMRVR¶