GPy.testing package

Submodules

GPy.testing.examples_tests module

class GPy.testing.examples_tests.ExamplesTests(methodName='runTest')

Bases: unittest.case.TestCase

GPy.testing.examples_tests.flatten_nested(lst)

GPy.testing.examples_tests.model_checkgrads(model)

GPy.testing.examples_tests.model_instance(model)

GPy.testing.examples_tests.test_models()

GPy.testing.fitc module

class GPy.testing.fitc.FITCtest(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_fitc_1d()

test_fitc_2d()

GPy.testing.index_operations_tests module

class GPy.testing.index_operations_tests.Test(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_clear()

test_index_view()

test_indexview_remove()

test_misc()

test_print()

test_remove()

test_shift_left()

test_shift_right()

test_view_of_view()

GPy.testing.inference_tests module

The test cases for various inference algorithms

class GPy.testing.inference_tests.InferenceXTestCase(methodName='runTest')

Bases: unittest.case.TestCase

genData()

test_inferenceX_BGPLVM()

test_inferenceX_GPLVM()

GPy.testing.kernel_tests module

class GPy.testing.kernel_tests.Coregionalize_weave_test(methodName='runTest')

Bases: unittest.case.TestCase

Make sure that the coregionalize kernel work with and without weave enabled

setUp()

test_nonsym()

test_sym()

class GPy.testing.kernel_tests.Kern_check_dK_dX(kernel=None, dL_dK=None, X=None, X2=None)

Bases: GPy.testing.kernel_tests.Kern_check_model

This class allows gradient checks for the gradient of a kernel with respect to X.

parameters_changed()

class GPy.testing.kernel_tests.Kern_check_dK_dtheta(kernel=None, dL_dK=None, X=None, X2=None)

Bases: GPy.testing.kernel_tests.Kern_check_model

This class allows gradient checks for the gradient of a kernel with respect to parameters.

parameters_changed()

class GPy.testing.kernel_tests.Kern_check_dKdiag_dX(kernel=None, dL_dK=None, X=None, X2=None)

Bases: GPy.testing.kernel_tests.Kern_check_dK_dX

This class allows gradient checks for the gradient of a kernel diagonal with respect to X.

log_likelihood()

parameters_changed()

class GPy.testing.kernel_tests.Kern_check_dKdiag_dtheta(kernel=None, dL_dK=None, X=None)

Bases: GPy.testing.kernel_tests.Kern_check_model

This class allows gradient checks of the gradient of the diagonal of a kernel with respect to the parameters.

log_likelihood()

parameters_changed()

class GPy.testing.kernel_tests.Kern_check_model(kernel=None, dL_dK=None, X=None, X2=None)

Bases: GPy.core.model.Model

This is a dummy model class used as a base class for checking that the gradients of a given kernel are implemented correctly. It enables checkgrad() to be called independently on a kernel.

is_positive_semi_definite()

log_likelihood()

class GPy.testing.kernel_tests.KernelGradientTestsContinuous(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_Add()

test_Add_dims()

test_Linear()

test_LinearFull()

test_Matern32()

test_Matern52()

test_Prod()

test_Prod2()

test_Prod3()

test_RBF()

class GPy.testing.kernel_tests.KernelTestsMiscellaneous(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_which_parts()

class GPy.testing.kernel_tests.KernelTestsNonContinuous(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_Hierarchical()

test_IndependentOutputs()

test_ODE_UY()

GPy.testing.kernel_tests.check_kernel_gradient_functions(kern, X=None, X2=None, output_ind=None, verbose=False, fixed_X_dims=None)

This function runs on kernels to check the correctness of their implementation. It checks that the covariance function is positive definite for a randomly generated data set.

Parameters:

• kern (GPy.kern.Kernpart) – the kernel to be tested.
• X (ndarray) – X input values to test the covariance function.
• X2 (ndarray) – X2 input values to test the covariance function.

GPy.testing.likelihood_tests module

class GPy.testing.likelihood_tests.LaplaceTests(methodName='runTest')

Bases: unittest.case.TestCase

Specific likelihood tests, not general enough for the above tests

setUp()

tearDown()

test_gaussian_d2logpdf_df2_2()

test_laplace_log_likelihood()

class GPy.testing.likelihood_tests.TestNoiseModels

Bases: object

Generic model checker

setUp()

t_d2logpdf2_df2_dparams(model, Y, f, params, params_names, param_constraints)

t_d2logpdf2_dlink2_dparams(model, Y, f, params, param_names, param_constraints)

t_d2logpdf_df2(model, Y, f)

t_d2logpdf_dlink2(model, Y, f, link_f_constraints)

t_d3logpdf_df3(model, Y, f)

t_d3logpdf_dlink3(model, Y, f, link_f_constraints)

t_dlogpdf_df(model, Y, f)

t_dlogpdf_df_dparams(model, Y, f, params, params_names, param_constraints)

t_dlogpdf_dlink(model, Y, f, link_f_constraints)

t_dlogpdf_dlink_dparams(model, Y, f, params, param_names, param_constraints)

t_dlogpdf_dparams(model, Y, f, params, params_names, param_constraints)

t_dlogpdf_link_dparams(model, Y, f, params, param_names, param_constraints)

t_ep_fit_rbf_white(model, X, Y, f, step, param_vals, param_names, constraints)

t_laplace_fit_rbf_white(model, X, Y, f, step, param_vals, param_names, constraints)

t_logpdf(model, Y, f)

tearDown()

test_scale2_models()

GPy.testing.likelihood_tests.dparam_checkgrad(func, dfunc, params, params_names, args, constraints=None, randomize=False, verbose=False)

checkgrad expects a f: R^N -> R^1 and df: R^N -> R^N However if we are holding other parameters fixed and moving something else We need to check the gradient of each of the fixed parameters (f and y for example) seperately, whilst moving another parameter. Otherwise f: gives back R^N and

df: gives back R^NxM where M is

The number of parameters and N is the number of data Need to take a slice out from f and a slice out of df

GPy.testing.likelihood_tests.dparam_partial(inst_func, *args)

If we have a instance method that needs to be called but that doesn’t take the parameter we wish to change to checkgrad, then this function will change the variable using set params.

inst_func: should be a instance function of an object that we would like

to change

param: the param that will be given to set_params args: anything else that needs to be given to the function (for example

the f or Y that are being used in the function whilst we tweak the param

GPy.testing.model_tests module

class GPy.testing.model_tests.GradientTests(methodName='runTest')

Bases: unittest.case.TestCase

check_model(kern, model_type='GPRegression', dimension=1, uncertain_inputs=False)

setUp()

test_GPLVM_rbf_bias_white_kern_2D()

Testing GPLVM with rbf + bias kernel

test_GPLVM_rbf_linear_white_kern_2D()

Testing GPLVM with rbf + bias kernel

test_GPRegression_bias_kern_1D()

Testing the GP regression with bias kernel on 1d data

test_GPRegression_bias_kern_2D()

Testing the GP regression with bias kernel on 2d data

test_GPRegression_exponential_1D()

Testing the GP regression with exponential kernel on 1d data

test_GPRegression_exponential_2D()

Testing the GP regression with exponential kernel on 2d data

test_GPRegression_exponential_ARD_2D()

Testing the GP regression with exponential kernel on 2d data

test_GPRegression_linear_kern_1D()

Testing the GP regression with linear kernel on 1d data

test_GPRegression_linear_kern_1D_ARD()

Testing the GP regression with linear kernel on 1d data

test_GPRegression_linear_kern_2D()

Testing the GP regression with linear kernel on 2d data

test_GPRegression_linear_kern_2D_ARD()

Testing the GP regression with linear kernel on 2d data

test_GPRegression_matern32_1D()

Testing the GP regression with matern32 kernel on 1d data

test_GPRegression_matern32_2D()

Testing the GP regression with matern32 kernel on 2d data

test_GPRegression_matern32_ARD_2D()

Testing the GP regression with matern32 kernel on 2d data

test_GPRegression_matern52_1D()

Testing the GP regression with matern52 kernel on 1d data

test_GPRegression_matern52_2D()

Testing the GP regression with matern52 kernel on 2d data

test_GPRegression_matern52_ARD_2D()

Testing the GP regression with matern52 kernel on 2d data

test_GPRegression_mlp_1d()

Testing the GP regression with mlp kernel with white kernel on 1d data

test_GPRegression_rbf_1d()

Testing the GP regression with rbf kernel with white kernel on 1d data

test_GPRegression_rbf_2D()

Testing the GP regression with rbf kernel on 2d data

test_GPRegression_rbf_ARD_2D()

Testing the GP regression with rbf kernel on 2d data

test_GP_EP_probit()

test_SparseGPRegression_rbf_linear_white_kern_1D()

Testing the sparse GP regression with rbf kernel on 2d data

test_SparseGPRegression_rbf_linear_white_kern_1D_uncertain_inputs()

Testing the sparse GP regression with rbf, linear kernel on 1d data with uncertain inputs

test_SparseGPRegression_rbf_linear_white_kern_2D()

Testing the sparse GP regression with rbf kernel on 2d data

test_SparseGPRegression_rbf_linear_white_kern_2D_uncertain_inputs()

Testing the sparse GP regression with rbf, linear kernel on 2d data with uncertain inputs

test_SparseGPRegression_rbf_white_kern_1d()

Testing the sparse GP regression with rbf kernel with white kernel on 1d data

test_SparseGPRegression_rbf_white_kern_2D()

Testing the sparse GP regression with rbf kernel on 2d data

test_generalized_FITC(*args, **kwargs)

test_gp_VGPC()

test_gp_heteroscedastic_regression()

test_gp_kronecker_gaussian()

test_multioutput_regression_1D(*args, **kwargs)

test_multioutput_sparse_regression_1D(*args, **kwargs)

test_sparse_EP_DTC_probit()

test_sparse_gp_heteroscedastic_regression()

class GPy.testing.model_tests.MiscTests(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_big_model()

test_likelihood_replicate()

test_likelihood_replicate_kern()

test_likelihood_set()

test_missing_data()

test_model_optimize()

test_model_set_params()

test_raw_predict()

test_sparse_raw_predict()

GPy.testing.observable_tests module

class GPy.testing.observable_tests.ParamTestParent(name=None, parameters=[], *a, **kw)

Bases: GPy.core.parameterization.parameterized.Parameterized

parameters_changed()

parent_changed_count = -1

class GPy.testing.observable_tests.ParameterizedTest(name=None, parameters=[], *a, **kw)

Bases: GPy.core.parameterization.parameterized.Parameterized

parameters_changed()

params_changed_count = -1

class GPy.testing.observable_tests.Test(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_observable()

test_priority()

test_priority_notify()

test_set_params()

GPy.testing.parameterized_tests module

Created on Feb 13, 2014

@author: maxzwiessele

class GPy.testing.parameterized_tests.ArrayCoreTest(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_init()

test_slice()

class GPy.testing.parameterized_tests.ParameterizedTest(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

test_add_parameter()

test_add_parameter_already_in_hirarchy()

test_add_parameter_in_hierarchy()

test_constraints()

test_constraints_in_init()

test_constraints_link_unlink()

test_constraints_views()

test_default_constraints()

test_fix_unfix()

test_fixes()

test_fixing_optimize()

test_fixing_randomize()

test_fixing_randomize_parameter_handling()

test_parameter_modify_in_init()

test_printing()

test_randomize()

test_regular_expression_misc()

test_remove_parameter()

test_remove_parameter_param_array_grad_array()

test_updates()

GPy.testing.pickle_tests module

Created on 13 Mar 2014

@author: maxz

class GPy.testing.pickle_tests.ListDictTestCase(methodName='runTest')

Bases: unittest.case.TestCase

assertArrayListEquals(l1, l2)

assertListDictEquals(d1, d2, msg=None)

class GPy.testing.pickle_tests.Test(methodName='runTest')

Bases: GPy.testing.pickle_tests.ListDictTestCase

test_add_observer(test_item)

test_model()

test_model_concat()

test_modelrecreation()

test_observable_array()

test_param()

test_parameter_index_operations()

test_parameterized()

test_posterior()

GPy.testing.pickle_tests.toy_model()

GPy.testing.prior_tests module

class GPy.testing.prior_tests.PriorTests(methodName='runTest')

Bases: unittest.case.TestCase

test_Gamma()

test_fixed_domain_check()

test_fixed_domain_check1()

test_incompatibility()

test_lognormal()

test_set_gaussian_for_reals()

test_set_prior()

Module contents

MaxZ

GPy.testing.deepTest(reason)