def test_load_docker_project(tmpdir):
tmpdir.join("MLproject").write(
textwrap.dedent("""
docker_env:
image: some-image
"""))
project = _project_spec.load_project(tmpdir.strpath)
assert project._entry_points == {}
assert project.conda_env_path is None
assert project.docker_env.get("image") == "some-image"
def test_load_project(tmpdir, mlproject, conda_env_path, conda_env_contents,
mlproject_path):
"""
Test that we can load a project with various combinations of an MLproject / conda.yaml file
:param mlproject: Contents of MLproject file. If None, no MLproject file will be written
:param conda_env_path: Path to conda environment file. If None, no conda environment file will
be written.
:param conda_env_contents: Contents of conda environment file (written if conda_env_path is
not None)
"""
if mlproject:
tmpdir.join(mlproject_path).write(mlproject)
if conda_env_path:
tmpdir.join(conda_env_path).write(conda_env_contents)
project = _project_spec.load_project(tmpdir.strpath)
assert project._entry_points == {}
expected_env_path = \
os.path.abspath(os.path.join(tmpdir.strpath, conda_env_path)) if conda_env_path else None
assert project.conda_env_path == expected_env_path
if conda_env_path:
assert open(project.conda_env_path).read() == conda_env_contents
def test_load_invalid_project(tmpdir, invalid_project_contents,
expected_error_msg):
tmpdir.join("MLproject").write(invalid_project_contents)
with pytest.raises(ExecutionException) as e:
_project_spec.load_project(tmpdir.strpath)
assert expected_error_msg in str(e.value)
def _create_run(uri, experiment_id, work_dir, version, entry_point,
parameters):
"""
Create a ``Run`` against the current MLflow tracking server, logging metadata (e.g. the URI,
entry point, and parameters of the project) about the run. Return an ``ActiveRun`` that can be
used to report additional data about the run (metrics/params) to the tracking server.
"""
if _is_local_uri(uri):
source_name = tracking._tracking_service.utils._get_git_url_if_present(
_expand_uri(uri))
else:
source_name = _expand_uri(uri)
source_version = _get_git_commit(work_dir)
git_diff = _get_git_diff(work_dir)
existing_run = fluent.active_run()
if existing_run:
parent_run_id = existing_run.info.run_id
else:
parent_run_id = None
tags = {
MLFLOW_USER: _get_user(),
MLFLOW_SOURCE_NAME: source_name,
MLFLOW_SOURCE_TYPE: SourceType.to_string(SourceType.PROJECT),
MLFLOW_PROJECT_ENTRY_POINT: entry_point
}
# System tags - all include a string header, thus none of them is empty
tags[KIWI_SYSTEM_HW_CPU] = _get_cpu_info()
tags[KIWI_SYSTEM_HW_MEMORY] = _get_mem_info()
tags[KIWI_SYSTEM_HW_DISK] = _get_disk_info()
tags[KIWI_SYSTEM_HW_GPU] = _get_gpu_info()
tags[KIWI_SYSTEM_OS] = _get_os_info()
if source_version is not None:
tags[MLFLOW_GIT_COMMIT] = source_version
tags[MLFLOW_GIT_DIFF] = git_diff
if parent_run_id is not None:
tags[MLFLOW_PARENT_RUN_ID] = parent_run_id
repo_url = _get_git_repo_url(work_dir)
if repo_url is not None:
tags[MLFLOW_GIT_REPO_URL] = repo_url
tags[LEGACY_MLFLOW_GIT_REPO_URL] = repo_url
# Add branch name tag if a branch is specified through -version
if _is_valid_branch_name(work_dir, version):
tags[MLFLOW_GIT_BRANCH] = version
tags[LEGACY_MLFLOW_GIT_BRANCH_NAME] = version
active_run = tracking.MlflowClient().create_run(
experiment_id=experiment_id, tags=tags)
project = _project_spec.load_project(work_dir)
# Consolidate parameters for logging.
# `storage_dir` is `None` since we want to log actual path not downloaded local path
entry_point_obj = project.get_entry_point(entry_point)
final_params, extra_params = entry_point_obj.compute_parameters(
parameters, storage_dir=None)
params_list = [
Param(key, value) for key, value in list(final_params.items()) +
list(extra_params.items())
]
tracking.MlflowClient().log_batch(active_run.info.run_id,
params=params_list)
return active_run
def load_project():
""" Loads an example project for use in tests, returning an in-memory `Project` object. """
return _project_spec.load_project(TEST_PROJECT_DIR)
def load_project(work_dir):
return _project_spec.load_project(work_dir)
def fetch_and_validate_project(uri, version, entry_point, parameters):
parameters = parameters or {}
work_dir = _fetch_project(uri=uri, version=version)
project = _project_spec.load_project(work_dir)
project.get_entry_point(entry_point)._validate_parameters(parameters)
return work_dir
def test_docker_invalid_project_backend_local():
work_dir = "./examples/docker"
project = _project_spec.load_project(work_dir)
project.name = None
with pytest.raises(ExecutionException):
kiwi.projects._validate_docker_env(project)
def test_docker_valid_project_backend_local():
work_dir = "./examples/docker"
project = _project_spec.load_project(work_dir)
kiwi.projects._validate_docker_env(project)
def load_project():
return _project_spec.load_project(directory=TEST_PROJECT_DIR)