def test_array_xd_with_none():
# Fixed shape
features = datasets.Features(
{"foo": datasets.Array2D(dtype="int32", shape=(2, 2))})
dummy_array = np.array([[1, 2], [3, 4]], dtype="int32")
dataset = datasets.Dataset.from_dict(
{"foo": [dummy_array, None, dummy_array]}, features=features)
arr = NumpyArrowExtractor().extract_column(dataset._data)
assert isinstance(
arr, np.ndarray) and arr.dtype == np.float64 and arr.shape == (3, 2, 2)
assert np.allclose(arr[0], dummy_array) and np.allclose(
arr[2], dummy_array)
assert np.all(np.isnan(arr[1])) # broadcasted np.nan - use np.all
# Dynamic shape
features = datasets.Features(
{"foo": datasets.Array2D(dtype="int32", shape=(None, 2))})
dummy_array = np.array([[1, 2], [3, 4]], dtype="int32")
dataset = datasets.Dataset.from_dict(
{"foo": [dummy_array, None, dummy_array]}, features=features)
arr = NumpyArrowExtractor().extract_column(dataset._data)
assert isinstance(
arr, np.ndarray) and arr.dtype == np.object and arr.shape == (3, )
np.testing.assert_equal(arr[0], dummy_array)
np.testing.assert_equal(arr[2], dummy_array)
assert np.isnan(arr[1]) # a single np.nan value - np.all not needed
def test_numpy_extractor(self):
pa_table = self._create_dummy_table()
extractor = NumpyArrowExtractor()
row = extractor.extract_row(pa_table)
np.testing.assert_equal(row, {"a": _COL_A[0], "b": _COL_B[0], "c": np.array(_COL_C[0])})
col = extractor.extract_column(pa_table)
np.testing.assert_equal(col, np.array(_COL_A))
batch = extractor.extract_batch(pa_table)
np.testing.assert_equal(batch, {"a": np.array(_COL_A), "b": np.array(_COL_B), "c": np.array(_COL_C)})
def test_numpy_extractor_np_array_kwargs(self):
pa_table = self._create_dummy_table().drop(["b"])
extractor = NumpyArrowExtractor(dtype=np.float16)
row = extractor.extract_row(pa_table)
self.assertEqual(row["c"].dtype, np.dtype(np.float16))
col = extractor.extract_column(pa_table)
self.assertEqual(col.dtype, np.float16)
batch = extractor.extract_batch(pa_table)
self.assertEqual(batch["a"].dtype, np.dtype(np.float16))
self.assertEqual(batch["c"].dtype, np.dtype(np.float16))
def test_array_xd_numpy_arrow_extractor(dtype, dummy_value):
features = datasets.Features(
{"foo": datasets.Array2D(dtype=dtype, shape=(2, 2))})
dataset = datasets.Dataset.from_dict({"foo": [[[dummy_value] * 2] * 2]},
features=features)
arr = NumpyArrowExtractor().extract_column(dataset._data)
assert isinstance(arr, np.ndarray)
np.testing.assert_equal(
arr, np.array([[[dummy_value] * 2] * 2], dtype=np.dtype(dtype)))
