automatminer.featurization.tests package

Submodules

automatminer.featurization.tests.test_base module

Tests for the featurization base classes.

class automatminer.featurization.tests.test_base.TestAutoFeaturizer(methodName='runTest')

Bases: unittest.case.TestCase

test_fsets()

Test the base behavior of ABC FeaturizerSet.

automatminer.featurization.tests.test_core module

class automatminer.featurization.tests.test_core.TestAutoFeaturizer(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

Hook method for setting up the test fixture before exercising it.

tearDown()

Hook method for deconstructing the test fixture after testing it.

test_StructureFeaturizers_needs_fitting()
test_caching()
test_column_attr()

Test that the autofeaturizer object correctly takes in composition_col, structure_col, bandstruct_col, and dos_col, and checks that fit_and_transform() works correctly with the attributes.

test_exclude_by_users()

Test custom args for featurizers to use.

test_featurize_bsdos(refresh_df_init=False, limit=1)

Tests featurize_dos and featurize_bandstructure.

Parameters

  • refresh_df_init (bool) – for developers, if the test need to be updated set to True. Otherwise set to False to make the final test independent of MPRester and faster.

  • limit (int) – the maximum final number of entries.

Returns (None):

test_featurize_composition()

Test automatic featurization while only considering formula/composition.

test_featurize_structure()

Test automatic featurization while only considering structure. May automatically infer composition features.

test_featurizers_by_users()
test_functionalization()
test_prechecking()
test_presets()
test_sanity()
test_transferability()

Test that an autofeaturizer object is able to be fit on one dataset and applied to another.

automatminer.featurization.tests.test_sets module

class automatminer.featurization.tests.test_sets.TestAllFeaturizers(methodName='runTest')

Bases: unittest.case.TestCase

Class to ensure the featurizers available in featurizer files in matminer match exactly to those defined to AllFeaturizers class. This test is meant to catch events when a new featurizer is defined but not listed inside AllFeaturizers (e.g. by mistake).

static get_featurizers(module, ignore=None)

Get a list of featurizers class names defined in a module.

Parameters

  • module (module) – A python module.

  • ignore (list of str, optional) – Class names to ignore.

Returns

List of all featurizer class names.

Return type

(list of str)

setUp()

Hook method for setting up the test fixture before exercising it.

test_bandstructure_featurizers()
test_composition_featurizers()
test_dos_featurizers()
test_structure_featurizers()
class automatminer.featurization.tests.test_sets.TestFeaturizerSets(methodName='runTest')

Bases: unittest.case.TestCase

setUp()

Hook method for setting up the test fixture before exercising it.

test_sets_not_empty()

Module contents