def test_write_mnist(orca_context_fixture):
sc = orca_context_fixture
temp_dir = tempfile.mkdtemp()
try:
train_image_file = os.path.join(temp_dir, "train-images")
train_label_file = os.path.join(temp_dir, "train-labels")
output_path = os.path.join(temp_dir, "output_dataset")
images = np.array([[i] * 16 for i in range(20)]).reshape(
(20, 4, 4)).astype(np.uint8)
labels = np.array(list(range(20))).reshape((20, )).astype(np.uint8)
_images_to_mnist_file(images, train_image_file)
_labels_to_mnist_file(labels, train_label_file)
write_mnist(image_file=train_image_file,
label_file=train_label_file,
output_path=output_path)
data, schema = ParquetDataset._read_as_dict_rdd(output_path)
data = data.sortBy(lambda x: x['label']).collect()
images_load = np.reshape(np.stack([d['image'] for d in data]),
(-1, 4, 4))
labels_load = np.stack([d['label'] for d in data])
assert np.all(images_load == images)
assert np.all(labels_load == labels_load)
finally:
shutil.rmtree(temp_dir)
def test_write_parquet_simple(orca_context_fixture):
sc = orca_context_fixture
temp_dir = tempfile.mkdtemp()
def generator(num):
for i in range(num):
yield {"id": i, "feature": np.zeros((10,)), "label": np.ones((4,))}
schema = {
"id": SchemaField(feature_type=FeatureType.SCALAR, dtype=DType.INT32, shape=()),
"feature": SchemaField(feature_type=FeatureType.NDARRAY, dtype=DType.FLOAT32, shape=(10,)),
"label": SchemaField(feature_type=FeatureType.NDARRAY, dtype=DType.FLOAT32, shape=(4,))
}
try:
ParquetDataset.write("file://" + temp_dir, generator(100), schema)
data, schema = ParquetDataset._read_as_dict_rdd("file://" + temp_dir)
data = data.collect()[0]
assert data['id'] == 0
assert np.all(data['feature'] == np.zeros((10,), dtype=np.float32))
assert np.all(data['label'] == np.ones((4,), dtype=np.float32))
finally:
shutil.rmtree(temp_dir)
def test_write_parquet_images(orca_context_fixture):
sc = orca_context_fixture
temp_dir = tempfile.mkdtemp()
def generator():
dataset_path = os.path.join(resource_path, "cat_dog")
for root, dirs, files in os.walk(os.path.join(dataset_path, "cats")):
for name in files:
image_path = os.path.join(root, name)
yield {"image": image_path, "label": 1, "id": image_path}
for root, dirs, files in os.walk(os.path.join(dataset_path, "dogs")):
for name in files:
image_path = os.path.join(root, name)
yield {"image": image_path, "label": 0, "id": image_path}
schema = {
"image": SchemaField(feature_type=FeatureType.IMAGE, dtype=DType.FLOAT32, shape=(10,)),
"label": SchemaField(feature_type=FeatureType.NDARRAY, dtype=DType.FLOAT32, shape=(4,)),
"id": SchemaField(feature_type=FeatureType.SCALAR, dtype=DType.STRING, shape=())
}
try:
ParquetDataset.write("file://" + temp_dir, generator(), schema)
data, schema = ParquetDataset._read_as_dict_rdd("file://" + temp_dir)
data = data.collect()[0]
image_path = data['id']
with open(image_path, "rb") as f:
image_bytes = f.read()
assert image_bytes == data['image']
finally:
shutil.rmtree(temp_dir)
def test_write_voc(orca_context_fixture):
sc = orca_context_fixture
temp_dir = tempfile.mkdtemp()
try:
from zoo.orca.data import SparkXShards
dataset_path = os.path.join(resource_path, "VOCdevkit")
output_path = os.path.join(temp_dir, "output_dataset")
write_voc(dataset_path, splits_names=[(2007, "trainval")],
output_path="file://" + output_path)
data, schema = ParquetDataset._read_as_dict_rdd("file://" + output_path)
data = data.collect()[0]
image_path = data["image_id"]
with open(image_path, "rb") as f:
image_bytes = f.read()
assert image_bytes == data['image']
finally:
shutil.rmtree(temp_dir)
