def test_hierarchical_dataset_invalid_json_fail(hierarchical_dataset_fields): with pytest.raises(JSONDecodeError): HierarchicalDataset.from_json( INVALID_JSON, hierarchical_dataset_fields, HierarchicalDataset.get_default_dict_parser("children"), )
def test_hierarchical_dataset_json_root_element_not_list_fail( hierarchical_dataset_fields, ): with pytest.raises(ValueError): HierarchicalDataset.from_json( JSON_ROOT_NOT_LIST, hierarchical_dataset_fields, HierarchicalDataset.get_default_dict_parser("children"), )
def hierarchical_dataset_2(hierarchical_dataset_fields, hierarchical_dataset_parser): dataset = HierarchicalDataset.from_json( HIERARCHIAL_DATASET_JSON_EXAMPLE_2, hierarchical_dataset_fields, hierarchical_dataset_parser, ) return dataset
def hierarchical_dataset(hierarchical_dataset_fields, hierarchical_dataset_parser): return HierarchicalDataset.from_json( dataset=HIERARCHIAL_DATASET_JSON_EXAMPLE, fields=hierarchical_dataset_fields, parser=hierarchical_dataset_parser, )
def hierarchical_dataset(hierarchical_dataset_fields, hierarchical_dataset_parser): dataset = HierarchicalDataset.from_json( HIERARCHIAL_DATASET_JSON_EXAMPLE, hierarchical_dataset_fields, hierarchical_dataset_parser, ) dataset.finalize_fields() return dataset
def test_hierarchical_dataset_finalize_fields(hierarchical_dataset_parser): name_vocab = Vocab() number_vocab = Vocab() name_field = Field("name", keep_raw=True, tokenizer=None, numericalizer=name_vocab) number_field = Field("number", keep_raw=True, tokenizer=None, numericalizer=number_vocab) fields = {"name": name_field, "number": number_field} dataset = HierarchicalDataset.from_json( dataset=HIERARCHIAL_DATASET_JSON_EXAMPLE, fields=fields, parser=hierarchical_dataset_parser, ) dataset.finalize_fields() assert name_vocab.is_finalized assert number_vocab.is_finalized