def test_download_artifact_from_absolute_uri_persists_data_to_specified_output_directory(
tmpdir):
artifact_file_name = "artifact.txt"
artifact_text = "Sample artifact text"
local_artifact_path = tmpdir.join(artifact_file_name).strpath
with open(local_artifact_path, "w") as out:
out.write(artifact_text)
logged_artifact_subdir = "logged_artifact"
with mlflow.start_run():
mlflow.log_artifact(local_path=local_artifact_path,
artifact_path=logged_artifact_subdir)
artifact_uri = mlflow.get_artifact_uri(
artifact_path=logged_artifact_subdir)
artifact_output_path = tmpdir.join("artifact_output").strpath
os.makedirs(artifact_output_path)
_download_artifact_from_uri(artifact_uri=artifact_uri,
output_path=artifact_output_path)
assert logged_artifact_subdir in os.listdir(artifact_output_path)
assert artifact_file_name in os.listdir(
os.path.join(artifact_output_path, logged_artifact_subdir))
with open(
os.path.join(artifact_output_path, logged_artifact_subdir,
artifact_file_name), "r") as f:
assert f.read() == artifact_text
def test_artifact_can_be_downloaded_from_absolute_uri_successfully(tmpdir):
artifact_file_name = "artifact.txt"
artifact_text = "Sample artifact text"
local_artifact_path = tmpdir.join(artifact_file_name).strpath
with open(local_artifact_path, "w") as out:
out.write(artifact_text)
logged_artifact_path = "artifact"
with mlflow.start_run():
mlflow.log_artifact(local_path=local_artifact_path, artifact_path=logged_artifact_path)
artifact_uri = mlflow.get_artifact_uri(artifact_path=logged_artifact_path)
downloaded_artifact_path = os.path.join(
_download_artifact_from_uri(artifact_uri), artifact_file_name)
assert downloaded_artifact_path != local_artifact_path
assert downloaded_artifact_path != logged_artifact_path
with open(downloaded_artifact_path, "r") as f:
assert f.read() == artifact_text
def _save_model_with_class_artifacts_params(path,
python_model,
artifacts=None,
conda_env=None,
code_paths=None,
mlflow_model=Model()):
"""
:param path: The path to which to save the Python model.
:param python_model: An instance of a subclass of :class:`~PythonModel`. ``python_model``
defines how the model loads artifacts and how it performs inference.
:param artifacts: A dictionary containing ``<name, artifact_uri>`` entries. Remote artifact URIs
will be resolved to absolute filesystem paths, producing a dictionary of
``<name, absolute_path>`` entries. ``python_model`` can reference these
resolved entries as the ``artifacts`` property of the ``context`` attribute.
If *None*, no artifacts will be added to the model.
:param conda_env: Either a dictionary representation of a Conda environment or the path to a
Conda environment yaml file. If provided, this decribes the environment
this model should be run in. At minimum, it should specify the dependencies
contained in :data:`mlflow.pyfunc.DEFAULT_CONDA_ENV`. If `None`, the default
:data:`mlflow.pyfunc.DEFAULT_CONDA_ENV` environment will be added to the
model.
:param code_paths: A list of local filesystem paths to Python file dependencies (or directories
containing file dependencies). These files will be *prepended* to the system
path before the model is loaded.
:param mlflow_model: The model configuration to which to add the ``mlflow.pyfunc`` flavor.
"""
if os.path.exists(path):
raise MlflowException(message="Path '{}' already exists".format(path),
error_code=RESOURCE_ALREADY_EXISTS)
os.makedirs(path)
custom_model_config_kwargs = {}
if isinstance(python_model, PythonModel):
saved_python_model_subpath = "python_model.pkl"
with open(os.path.join(path, saved_python_model_subpath), "wb") as out:
cloudpickle.dump(python_model, out)
custom_model_config_kwargs[
CONFIG_KEY_PYTHON_MODEL] = saved_python_model_subpath
else:
raise MlflowException(message=(
"`python_model` must be a subclass of `PythonModel`. Instead, found an"
" object of type: {python_model_type}".format(
python_model_type=type(python_model))),
error_code=INVALID_PARAMETER_VALUE)
if artifacts:
saved_artifacts_config = {}
with TempDir() as tmp_artifacts_dir:
tmp_artifacts_config = {}
saved_artifacts_dir_subpath = "artifacts"
for artifact_name, artifact_uri in artifacts.items():
tmp_artifact_path = _download_artifact_from_uri(
artifact_uri=artifact_uri,
output_path=tmp_artifacts_dir.path())
tmp_artifacts_config[artifact_name] = tmp_artifact_path
saved_artifact_subpath = os.path.join(
saved_artifacts_dir_subpath,
os.path.relpath(path=tmp_artifact_path,
start=tmp_artifacts_dir.path()))
saved_artifacts_config[artifact_name] = {
CONFIG_KEY_ARTIFACT_RELATIVE_PATH: saved_artifact_subpath,
CONFIG_KEY_ARTIFACT_URI: artifact_uri,
}
shutil.move(tmp_artifacts_dir.path(),
os.path.join(path, saved_artifacts_dir_subpath))
custom_model_config_kwargs[
CONFIG_KEY_ARTIFACTS] = saved_artifacts_config
conda_env_subpath = "conda.yaml"
if conda_env is None:
conda_env = DEFAULT_CONDA_ENV
elif not isinstance(conda_env, dict):
with open(conda_env, "r") as f:
conda_env = yaml.safe_load(f)
with open(os.path.join(path, conda_env_subpath), "w") as f:
yaml.safe_dump(conda_env, stream=f, default_flow_style=False)
saved_code_subpath = None
if code_paths is not None:
saved_code_subpath = "code"
for code_path in code_paths:
_copy_file_or_tree(src=code_path,
dst=path,
dst_dir=saved_code_subpath)
mlflow.pyfunc.add_to_model(model=mlflow_model,
loader_module=__name__,
code=saved_code_subpath,
env=conda_env_subpath,
**custom_model_config_kwargs)
mlflow_model.save(os.path.join(path, 'MLmodel'))