def _testDo(self, exec_properties):
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create output dict.
self.examples = standard_artifacts.Examples()
self.examples.uri = output_data_dir
self.examples.split_names = artifact_utils.encode_split_names(
['train', 'eval'])
output_dict = {utils.EXAMPLES_KEY: [self.examples]}
# Run executor.
import_example_gen = executor.Executor()
import_example_gen.Do({}, output_dict, exec_properties)
# Check import_example_gen outputs.
train_output_file = os.path.join(self.examples.uri, 'train',
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(self.examples.uri, 'eval',
'data_tfrecord-00000-of-00001.gz')
# Check import_example_gen outputs.
train_output_file = os.path.join(self.examples.uri, 'train',
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(self.examples.uri, 'eval',
'data_tfrecord-00000-of-00001.gz')
self.assertTrue(tf.io.gfile.exists(train_output_file))
self.assertTrue(tf.io.gfile.exists(eval_output_file))
self.assertGreater(
tf.io.gfile.GFile(train_output_file).size(),
tf.io.gfile.GFile(eval_output_file).size())
def testDo(self):
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create output dict.
train_examples = types.TfxArtifact(type_name='ExamplesPath',
split='train')
train_examples.uri = os.path.join(output_data_dir, 'train')
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
eval_examples.uri = os.path.join(output_data_dir, 'eval')
output_dict = {'examples': [train_examples, eval_examples]}
# Create exec proterties.
exec_properties = {
'input':
json_format.MessageToJson(
example_gen_pb2.Input(splits=[
example_gen_pb2.Input.Split(name='tfrecord',
pattern='tfrecord/*'),
])),
'output':
json_format.MessageToJson(
example_gen_pb2.Output(
split_config=example_gen_pb2.SplitConfig(splits=[
example_gen_pb2.SplitConfig.Split(name='train',
hash_buckets=2),
example_gen_pb2.SplitConfig.Split(name='eval',
hash_buckets=1)
])))
}
# Run executor.
import_example_gen = executor.Executor()
import_example_gen.Do(self._input_dict, output_dict, exec_properties)
# Check import_example_gen outputs.
train_output_file = os.path.join(train_examples.uri,
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(eval_examples.uri,
'data_tfrecord-00000-of-00001.gz')
self.assertTrue(tf.gfile.Exists(train_output_file))
self.assertTrue(tf.gfile.Exists(eval_output_file))
self.assertGreater(
tf.gfile.GFile(train_output_file).size(),
tf.gfile.GFile(eval_output_file).size())
def testDo(self):
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create output dict.
examples = standard_artifacts.Examples()
examples.uri = output_data_dir
examples.split_names = artifact_utils.encode_split_names(
['train', 'eval'])
output_dict = {'examples': [examples]}
# Create exec proterties.
exec_properties = {
'input_config':
json_format.MessageToJson(example_gen_pb2.Input(splits=[
example_gen_pb2.Input.Split(name='tfrecord',
pattern='tfrecord/*'),
]),
preserving_proto_field_name=True),
'output_config':
json_format.MessageToJson(example_gen_pb2.Output(
split_config=example_gen_pb2.SplitConfig(splits=[
example_gen_pb2.SplitConfig.Split(name='train',
hash_buckets=2),
example_gen_pb2.SplitConfig.Split(name='eval',
hash_buckets=1)
])),
preserving_proto_field_name=True)
}
# Run executor.
import_example_gen = executor.Executor()
import_example_gen.Do(self._input_dict, output_dict, exec_properties)
# Check import_example_gen outputs.
train_output_file = os.path.join(examples.uri, 'train',
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(examples.uri, 'eval',
'data_tfrecord-00000-of-00001.gz')
self.assertTrue(tf.io.gfile.exists(train_output_file))
self.assertTrue(tf.io.gfile.exists(eval_output_file))
self.assertGreater(
tf.io.gfile.GFile(train_output_file).size(),
tf.io.gfile.GFile(eval_output_file).size())
def _testDo(self, payload_format):
exec_properties = {
utils.INPUT_BASE_KEY: self._input_data_dir,
utils.INPUT_CONFIG_KEY: self._input_config,
utils.OUTPUT_CONFIG_KEY: self._output_config,
utils.OUTPUT_DATA_FORMAT_KEY: payload_format,
}
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create output dict.
self.examples = standard_artifacts.Examples()
self.examples.uri = output_data_dir
output_dict = {utils.EXAMPLES_KEY: [self.examples]}
# Run executor.
import_example_gen = executor.Executor()
import_example_gen.Do({}, output_dict, exec_properties)
self.assertEqual(
artifact_utils.encode_split_names(['train', 'eval']),
self.examples.split_names)
# Check import_example_gen outputs.
train_output_file = os.path.join(self.examples.uri, 'train',
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(self.examples.uri, 'eval',
'data_tfrecord-00000-of-00001.gz')
# Check import_example_gen outputs.
train_output_file = os.path.join(self.examples.uri, 'train',
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(self.examples.uri, 'eval',
'data_tfrecord-00000-of-00001.gz')
self.assertTrue(fileio.exists(train_output_file))
self.assertTrue(fileio.exists(eval_output_file))
self.assertGreater(
fileio.open(train_output_file).size(),
fileio.open(eval_output_file).size())
