Function test_dataset

python/pyarrow/tests/test_feather.py:149–169

(version)

@pytest.mark.numpy
def test_dataset(version):
    num_values = (100, 100)
    num_files = 5
    paths = [random_path() for i in range(num_files)]
    data = {
        "col_" + str(i): np.random.randn(num_values[0])
        for i in range(num_values[1])
    }
    table = pa.table(data)

    TEST_FILES.extend(paths)
    for index, path in enumerate(paths):
        rows = (
            index * (num_values[0] // num_files),
            (index + 1) * (num_values[0] // num_files),
        )

        write_feather(table[rows[0]: rows[1]], path, version=version)

    data = FeatherDataset(paths).read_table()
    assert data.equals(table)


@pytest.mark.pandas