def test_kedro_mlflow_config_setup_tracking_priority(kedro_project_with_mlflow_conf):
"""Test if the mlflow_tracking uri set is the one of mlflow.yml
if it also eist in credentials.
Args:
mocker ([type]): [description]
tmp_path ([type]): [description]
"""
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
(kedro_project_with_mlflow_conf / "conf/base/credentials.yml").write_text(
yaml.dump(dict(my_mlflow_creds=dict(mlflow_tracking_uri="mlruns2")))
)
config = KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf,
mlflow_tracking_uri="mlruns1",
credentials="my_mlflow_creds",
)
project_metadata = _get_project_metadata(kedro_project_with_mlflow_conf)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_mlflow_conf)
configure_project(project_metadata.package_name)
with KedroSession.create(
"fake_project", project_path=kedro_project_with_mlflow_conf
):
config.setup()
assert (
mlflow.get_tracking_uri()
== (kedro_project_with_mlflow_conf / "mlruns1").as_uri()
)
def test_kedro_mlflow_config_experiment_was_deleted(kedro_project_with_mlflow_conf):
# create an experiment with the same name and then delete it
mlflow_tracking_uri = (kedro_project_with_mlflow_conf / "mlruns").as_uri()
mlflow_client = MlflowClient(mlflow_tracking_uri)
mlflow_client.create_experiment("exp1")
mlflow_client.delete_experiment(
mlflow_client.get_experiment_by_name("exp1").experiment_id
)
# the config must restore properly the experiment
config = KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf,
mlflow_tracking_uri="mlruns",
experiment_opts=dict(name="exp1"),
)
project_metadata = _get_project_metadata(kedro_project_with_mlflow_conf)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_mlflow_conf)
configure_project(project_metadata.package_name)
with KedroSession.create(
"fake_project", project_path=kedro_project_with_mlflow_conf
):
config.setup()
assert "exp1" in [exp.name for exp in config.mlflow_client.list_experiments()]
def test_kedro_mlflow_config_setup_tracking_priority(mocker, tmp_path,
config_dir):
"""Test if the mlflow_tracking uri set is the one of mlflow.yml
if it also eist in credentials.
Args:
mocker ([type]): [description]
tmp_path ([type]): [description]
config_dir ([type]): [description]
"""
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
mocker.patch("kedro_mlflow.utils._is_kedro_project", lambda x: True)
(tmp_path / "conf/base/credentials.yml").write_text(
yaml.dump(dict(my_mlflow_creds=dict(mlflow_tracking_uri="mlruns2"))))
config = KedroMlflowConfig(
project_path=tmp_path,
mlflow_tracking_uri="mlruns1",
credentials="my_mlflow_creds",
)
context = load_context(tmp_path)
config.setup(context)
assert mlflow.get_tracking_uri() == (tmp_path / "mlruns1").as_uri()
def test_kedro_mlflow_config_validate_uri_local(mocker, tmp_path, uri):
mocker.patch("kedro_mlflow.utils._is_kedro_project", return_value=True)
mocker.patch("mlflow.tracking.MlflowClient", return_value=None)
mocker.patch(
"kedro_mlflow.framework.context.config.KedroMlflowConfig._get_or_create_experiment",
return_value=None,
)
config = KedroMlflowConfig(project_path=tmp_path)
assert config._validate_uri(uri=uri).startswith(r"file:///") # relative
def get_mlflow_config(context: KedroContext):
try:
conf_mlflow_yml = context.config_loader.get("mlflow*", "mlflow*/**")
except MissingConfigException:
raise KedroMlflowConfigError(
"No 'mlflow.yml' config file found in environment. Use ``kedro mlflow init`` command in CLI to create a default config file."
)
conf_mlflow = KedroMlflowConfig(context.project_path)
conf_mlflow.from_dict(conf_mlflow_yml)
return conf_mlflow
def get_mlflow_config(session: Optional[KedroSession] = None):
session = session or get_current_session()
context = session.load_context()
try:
conf_mlflow_yml = context.config_loader.get("mlflow*", "mlflow*/**")
except MissingConfigException:
raise KedroMlflowConfigError(
"No 'mlflow.yml' config file found in environment. Use ``kedro mlflow init`` command in CLI to create a default config file."
)
conf_mlflow = KedroMlflowConfig(context.project_path)
conf_mlflow.from_dict(conf_mlflow_yml)
return conf_mlflow
def test_kedro_mlflow_config_init(kedro_project_with_mlflow_conf):
# kedro_project_with_mlflow_conf is a global fixture in conftest
config = KedroMlflowConfig(project_path=kedro_project_with_mlflow_conf)
assert config.to_dict() == dict(
mlflow_tracking_uri=(kedro_project_with_mlflow_conf / "mlruns").as_uri(),
credentials=None,
disable_tracking=KedroMlflowConfig.DISABLE_TRACKING_OPTS,
experiments=KedroMlflowConfig.EXPERIMENT_OPTS,
run=KedroMlflowConfig.RUN_OPTS,
ui=KedroMlflowConfig.UI_OPTS,
hooks=dict(node=KedroMlflowConfig.NODE_HOOK_OPTS),
)
def test_kedro_mlflow_config_init(tmp_path):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
(tmp_path / ".kedro.yml").write_text(
yaml.dump(dict(context_path="fake/path")))
config = KedroMlflowConfig(project_path=tmp_path)
assert config.to_dict() == dict(
mlflow_tracking_uri=(tmp_path / "mlruns").as_uri(),
experiments=KedroMlflowConfig.EXPERIMENT_OPTS,
run=KedroMlflowConfig.RUN_OPTS,
ui=KedroMlflowConfig.UI_OPTS,
hooks=dict(node=KedroMlflowConfig.NODE_HOOK_OPTS),
)
def get_mlflow_config(project_path=None, env="local"):
if project_path is None:
project_path = Path.cwd()
project_path = Path(project_path)
conf_paths = [
str(project_path / "conf" / "base"),
str(project_path / "conf" / env),
]
config_loader = ConfigLoader(conf_paths=conf_paths)
conf_mlflow_yml = config_loader.get("mlflow*", "mlflow*/**")
conf_mlflow = KedroMlflowConfig(project_path=project_path)
conf_mlflow.from_dict(conf_mlflow_yml)
return conf_mlflow
def test_kedro_mlflow_config_new_experiment_does_not_exists(
mocker, tmp_path, config_dir):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
mocker.patch("kedro_mlflow.utils._is_kedro_project", return_value=True)
config = KedroMlflowConfig(
project_path=tmp_path,
mlflow_tracking_uri="mlruns",
experiment_opts=dict(name="exp1"),
)
context = load_context(tmp_path)
config.setup(context)
assert "exp1" in [
exp.name for exp in config.mlflow_client.list_experiments()
]
def test_kedro_mlflow_config_setup_export_credentials(mocker, tmp_path,
config_dir):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
mocker.patch("kedro_mlflow.utils._is_kedro_project", lambda x: True)
(tmp_path / "conf/base/credentials.yml").write_text(
yaml.dump(dict(my_mlflow_creds=dict(fake_mlflow_cred="my_fake_cred"))))
# the config must restore properly the experiment
config = KedroMlflowConfig(project_path=tmp_path,
credentials="my_mlflow_creds")
context = load_context(tmp_path)
config.setup(context)
assert os.environ["fake_mlflow_cred"] == "my_fake_cred"
def test_kedro_mlflow_config_setup_set_tracking_uri(mocker, tmp_path,
config_dir):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
mocker.patch("kedro_mlflow.utils._is_kedro_project", lambda x: True)
# create an experiment with the same name and then delete it
mlflow_tracking_uri = (tmp_path / "awesome_tracking").as_uri()
# the config must restore properly the experiment
config = KedroMlflowConfig(
project_path=tmp_path,
mlflow_tracking_uri="awesome_tracking",
experiment_opts=dict(name="exp1"),
)
context = load_context(tmp_path)
config.setup(context)
assert mlflow.get_tracking_uri() == mlflow_tracking_uri
def test_kedro_mlflow_config_new_experiment_does_not_exists(
kedro_project_with_mlflow_conf,
):
config = KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf,
mlflow_tracking_uri="mlruns",
experiment_opts=dict(name="exp1"),
)
project_metadata = _get_project_metadata(kedro_project_with_mlflow_conf)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_mlflow_conf)
configure_project(project_metadata.package_name)
with KedroSession.create(
"fake_project", project_path=kedro_project_with_mlflow_conf
):
config.setup()
assert "exp1" in [exp.name for exp in config.mlflow_client.list_experiments()]
def test_kedro_mlflow_config_bad_long_parameters_strategy(tmp_path):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
(tmp_path / ".kedro.yml").write_text(
yaml.dump(dict(context_path="fake/path")))
with pytest.raises(KedroMlflowConfigError,
match="'long_parameters_strategy' must be one of "):
KedroMlflowConfig(
project_path=tmp_path,
node_hook_opts=dict(long_parameters_strategy="does_not_exist"),
)
def test_kedro_mlflow_config_setup_export_credentials(kedro_project_with_mlflow_conf):
(kedro_project_with_mlflow_conf / "conf/base/credentials.yml").write_text(
yaml.dump(dict(my_mlflow_creds=dict(fake_mlflow_cred="my_fake_cred")))
)
# the config must restore properly the experiment
config = KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf, credentials="my_mlflow_creds"
)
project_metadata = _get_project_metadata(kedro_project_with_mlflow_conf)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_mlflow_conf)
configure_project(project_metadata.package_name)
with KedroSession.create(
"fake_project", project_path=kedro_project_with_mlflow_conf
):
config.setup()
assert os.environ["fake_mlflow_cred"] == "my_fake_cred"
def test_kedro_mlflow_config_bad_long_parameters_strategy(
kedro_project_with_mlflow_conf,
):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
with pytest.raises(
KedroMlflowConfigError, match="'long_parameters_strategy' must be one of "
):
KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf,
node_hook_opts=dict(long_parameters_strategy="does_not_exist"),
)
def test_kedro_mlflow_config_setup_set_tracking_uri(kedro_project_with_mlflow_conf):
# create an experiment with the same name and then delete it
mlflow_tracking_uri = (kedro_project_with_mlflow_conf / "awesome_tracking").as_uri()
# the config must restore properly the experiment
config = KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf,
mlflow_tracking_uri="awesome_tracking",
experiment_opts=dict(name="exp1"),
)
project_metadata = _get_project_metadata(kedro_project_with_mlflow_conf)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_mlflow_conf)
configure_project(project_metadata.package_name)
with KedroSession.create(
"fake_project", project_path=kedro_project_with_mlflow_conf
):
config.setup()
assert mlflow.get_tracking_uri() == mlflow_tracking_uri
def test_kedro_mlflow_config_experiment_exists(mocker, kedro_project_with_mlflow_conf):
# create an experiment with the same name
mlflow_tracking_uri = (
kedro_project_with_mlflow_conf / "conf" / "local" / "mlruns"
).as_uri()
MlflowClient(mlflow_tracking_uri).create_experiment("exp1")
config = KedroMlflowConfig(
project_path=kedro_project_with_mlflow_conf,
mlflow_tracking_uri="mlruns",
experiment_opts=dict(name="exp1"),
)
project_metadata = _get_project_metadata(kedro_project_with_mlflow_conf)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_mlflow_conf)
configure_project(project_metadata.package_name)
with KedroSession.create(
"fake_project", project_path=kedro_project_with_mlflow_conf
):
config.setup()
assert "exp1" in [exp.name for exp in config.mlflow_client.list_experiments()]
def test_kedro_mlflow_config_experiment_was_deleted(mocker, tmp_path,
config_dir):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
mocker.patch("kedro_mlflow.utils._is_kedro_project", lambda x: True)
# create an experiment with the same name and then delete it
mlflow_tracking_uri = (tmp_path / "mlruns").as_uri()
mlflow_client = MlflowClient(mlflow_tracking_uri)
mlflow_client.create_experiment("exp1")
mlflow_client.delete_experiment(
mlflow_client.get_experiment_by_name("exp1").experiment_id)
# the config must restore properly the experiment
config = KedroMlflowConfig(
project_path=tmp_path,
mlflow_tracking_uri="mlruns",
experiment_opts=dict(name="exp1"),
)
context = load_context(tmp_path)
config.setup(context)
assert "exp1" in [
exp.name for exp in config.mlflow_client.list_experiments()
]
def test_kedro_mlflow_config_experiment_exists(mocker, tmp_path):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
mocker.patch("kedro_mlflow.utils._is_kedro_project", return_value=True)
# create an experiment with the same name
mlflow_tracking_uri = (tmp_path / "mlruns").as_uri()
MlflowClient(mlflow_tracking_uri).create_experiment("exp1")
config = KedroMlflowConfig(
project_path=tmp_path,
mlflow_tracking_uri="mlruns",
experiment_opts=dict(name="exp1"),
)
assert "exp1" in [
exp.name for exp in config.mlflow_client.list_experiments()
]
def test_from_dict_to_dict_idempotent(mocker, kedro_project_with_mlflow_conf):
mocker.patch("mlflow.tracking.MlflowClient", return_value=None)
mocker.patch(
"kedro_mlflow.framework.context.config.KedroMlflowConfig._get_or_create_experiment",
return_value=None,
)
config = KedroMlflowConfig(project_path=kedro_project_with_mlflow_conf)
original_config_dict = config.to_dict()
# modify config
config.from_dict(original_config_dict)
assert config.to_dict() == original_config_dict
def get_mlflow_config(context: KedroContext):
conf_mlflow_yml = context.config_loader.get("mlflow*", "mlflow*/**")
conf_mlflow = KedroMlflowConfig(context.project_path)
conf_mlflow.from_dict(conf_mlflow_yml)
return conf_mlflow
def test_kedro_mlflow_config_init_wrong_path(tmp_path):
# create a ".kedro.yml" file to identify "tmp_path" as the root of a kedro project
with pytest.raises(KedroMlflowConfigError,
match="not a valid path to a kedro project"):
KedroMlflowConfig(project_path=tmp_path)