(dataset_dir)
| 32 | |
| 33 | @pytest.mark.integration |
| 34 | def test_test_command(dataset_dir): |
| 35 | args = _TestCommandArgs(dataset=dataset_dir, all_configs=True, save_infos=True) |
| 36 | test_command = TestCommand(*args) |
| 37 | test_command.run() |
| 38 | dataset_readme_path = os.path.join(dataset_dir, "README.md") |
| 39 | assert os.path.exists(dataset_readme_path) |
| 40 | dataset_infos = DatasetInfosDict.from_directory(dataset_dir) |
| 41 | expected_dataset_infos = DatasetInfosDict( |
| 42 | { |
| 43 | "default": DatasetInfo( |
| 44 | features=Features( |
| 45 | { |
| 46 | "tokens": List(Value("string")), |
| 47 | "ner_tags": List( |
| 48 | ClassLabel(names=["O", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC"]) |
| 49 | ), |
| 50 | "langs": List(Value("string")), |
| 51 | "spans": List(Value("string")), |
| 52 | } |
| 53 | ), |
| 54 | splits=[ |
| 55 | { |
| 56 | "name": "train", |
| 57 | "num_bytes": 2351563, |
| 58 | "num_examples": 10000, |
| 59 | }, |
| 60 | { |
| 61 | "name": "validation", |
| 62 | "num_bytes": 238418, |
| 63 | "num_examples": 1000, |
| 64 | }, |
| 65 | ], |
| 66 | download_size=3940680, |
| 67 | dataset_size=2589981, |
| 68 | ) |
| 69 | } |
| 70 | ) |
| 71 | assert dataset_infos.keys() == expected_dataset_infos.keys() |
| 72 | for key in DatasetInfo._INCLUDED_INFO_IN_YAML: |
| 73 | result, expected = getattr(dataset_infos["default"], key), getattr(expected_dataset_infos["default"], key) |
| 74 | if key == "num_bytes": |
| 75 | assert is_1percent_close(result, expected) |
| 76 | elif key == "splits": |
| 77 | assert list(result) == list(expected) |
| 78 | for split in result: |
| 79 | assert result[split].name == expected[split].name |
| 80 | assert result[split].num_examples == expected[split].num_examples |
| 81 | assert is_1percent_close(result[split].num_bytes, expected[split].num_bytes) |
| 82 | else: |
| 83 | result == expected |
nothing calls this directly
no test coverage detected