def train(
# Use InputPath to get a locally accessible path for the input artifact
# of type `Dataset`.
dataset_one_path: InputPath('Dataset'),
# Use InputArtifact to get a metadata-rich handle to the input artifact
# of type `Dataset`.
dataset_two: InputArtifact(Dataset),
# An input parameter of type string.
message: str,
# Use OutputArtifact to get a metadata-rich handle to the output artifact
# of type `Dataset`.
model: OutputArtifact(Model),
# An input parameter of type int with a default value.
num_steps: int = 100):
'''Dummy Training step'''
with open(dataset_one_path, 'r') as input_file:
dataset_one_contents = input_file.read()
with open(dataset_two.path, 'r') as input_file:
dataset_two_contents = input_file.read()
line = "dataset_one_contents: {} || dataset_two_contents: {} || message: {}\n".format(
dataset_one_contents, dataset_two_contents, message)
with open(model.path, 'w') as output_file:
for i in range(num_steps):
output_file.write("Step {}\n{}\n=====\n".format(i, line))
# Use model.get() to get a Model artifact, which has a .metadata dictionary
# to store arbitrary metadata for the output artifact.
model.get().metadata['accuracy'] = 0.9
def test_func(input_artifact_one: InputArtifact(Dataset)):
self.assertEqual(input_artifact_one.uri,
'gs://some-bucket/input_artifact_one')
self.assertEqual(
input_artifact_one.path,
os.path.join(self._test_dir, 'some-bucket/input_artifact_one'))
self.assertEqual(input_artifact_one.get().name, 'input_artifact_one')
def train(dataset: InputArtifact(Dataset)) -> NamedTuple(
'Outputs', [
('scalar', str),
('model', Model),
]):
"""Dummy Training step."""
with open(dataset.path, 'r') as f:
data = f.read()
print('Dataset:', data)
scalar = '123'
model = 'My model trained using data: {}'.format(data)
from collections import namedtuple
output = namedtuple('Outputs', ['scalar', 'model'])
return output(scalar, model)
def output_named_tuple(artifact: InputArtifact(Dataset)) -> NamedTuple(
'Outputs', [
('scalar', str),
('metrics', Metrics),
('model', Model),
]):
scalar = "123"
import json
metrics = json.dumps({
'metrics': [{
'name': 'accuracy',
'numberValue': 0.9,
'format': "PERCENTAGE",
}]
})
with open(artifact.path, 'r') as f:
artifact_contents = f.read()
model = "Model contents: " + artifact_contents
from collections import namedtuple
output = namedtuple('Outputs', ['scalar', 'metrics', 'model'])
return output(scalar, metrics, model)
def _make_input_artifact(cls, runtime_artifact: Dict):
artifact = create_runtime_artifact(runtime_artifact)
return InputArtifact(artifact_type=type(artifact), artifact=artifact)
