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 main(): # pragma: no cover
"""Main entry point. Look for a ``cli.py``, and, if found, add its
commands to `kedro`'s before invoking the CLI.
"""
_init_plugins()
global_groups = [cli]
global_groups.extend(load_entry_points("global"))
project_groups = []
cli_context = dict()
path = Path.cwd()
if _is_project(path):
# load project commands from cli.py
metadata = _get_project_metadata(path)
package_name = metadata.package_name
cli_context = dict(obj=metadata)
_add_src_to_path(metadata.source_dir, path)
configure_project(package_name)
project_groups.extend(load_entry_points("project"))
try:
project_cli = importlib.import_module(f"{package_name}.cli")
project_groups.append(project_cli.cli)
except Exception as exc:
raise KedroCliError(
f"Cannot load commands from {package_name}.cli") from exc
cli_collection = CommandCollection(
("Global commands", global_groups),
("Project specific commands", project_groups),
)
cli_collection(**cli_context)
def test_mlflow_pipeline_hook_with_copy_mode(
kedro_project_with_mlflow_conf,
dummy_pipeline_ml,
dummy_catalog,
dummy_run_params,
copy_mode,
expected,
):
# config_with_base_mlflow_conf is a conftest fixture
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(
package_name=project_metadata.package_name,
project_path=kedro_project_with_mlflow_conf,
):
pipeline_hook = MlflowPipelineHook()
runner = SequentialRunner()
pipeline_hook.after_catalog_created(
catalog=dummy_catalog,
# `after_catalog_created` is not using any of arguments bellow,
# so we are setting them to empty values.
conf_catalog={},
conf_creds={},
feed_dict={},
save_version="",
load_versions="",
run_id=dummy_run_params["run_id"],
)
pipeline_to_run = pipeline_ml_factory(
training=dummy_pipeline_ml.training,
inference=dummy_pipeline_ml.inference,
input_name=dummy_pipeline_ml.input_name,
conda_env={},
model_name=dummy_pipeline_ml.model_name,
copy_mode=copy_mode,
)
pipeline_hook.before_pipeline_run(
run_params=dummy_run_params, pipeline=pipeline_to_run, catalog=dummy_catalog
)
runner.run(pipeline_to_run, dummy_catalog)
run_id = mlflow.active_run().info.run_id
pipeline_hook.after_pipeline_run(
run_params=dummy_run_params, pipeline=pipeline_to_run, catalog=dummy_catalog
)
mlflow_tracking_uri = (kedro_project_with_mlflow_conf / "mlruns").as_uri()
mlflow.set_tracking_uri(mlflow_tracking_uri)
loaded_model = mlflow.pyfunc.load_model(model_uri=f"runs:/{run_id}/model")
actual_copy_mode = {
name: ds._copy_mode
for name, ds in loaded_model._model_impl.python_model.loaded_catalog._data_sets.items()
}
assert actual_copy_mode == expected
def test_get_current_session(self, fake_project, mock_package_name):
assert get_current_session(silent=True) is None # no sessions yet
pattern = "There is no active Kedro session"
with pytest.raises(RuntimeError, match=pattern):
get_current_session()
configure_project(mock_package_name)
session1 = KedroSession.create(mock_package_name, fake_project)
session2 = KedroSession.create(mock_package_name, fake_project)
with session1:
assert get_current_session() is session1
pattern = (
"Cannot activate the session as another active session already exists"
)
with pytest.raises(RuntimeError, match=pattern), session2:
pass # pragma: no cover
# session has been closed, so no current sessions should be available
assert get_current_session(silent=True) is None
with session2:
assert get_current_session() is session2
def test_mlflow_config_with_templated_config_loader(kedro_project_with_tcl, ):
_write_yaml(
kedro_project_with_tcl / "conf" / "local" / "mlflow.yml",
dict(
mlflow_tracking_uri="${mlflow_tracking_uri}",
credentials=None,
disable_tracking=dict(pipelines=["my_disabled_pipeline"]),
experiment=dict(name="fake_package", create=True),
run=dict(id="123456789", name="my_run", nested=True),
ui=dict(port="5151", host="localhost"),
hooks=dict(node=dict(
flatten_dict_params=True,
recursive=False,
sep="-",
long_parameters_strategy="truncate",
)),
),
)
_write_yaml(
kedro_project_with_tcl / "conf" / "local" / "globals.yml",
dict(mlflow_tracking_uri="dynamic_mlruns"),
)
expected = {
"mlflow_tracking_uri":
(kedro_project_with_tcl / "dynamic_mlruns").as_uri(),
"credentials": None,
"disable_tracking": {
"pipelines": ["my_disabled_pipeline"]
},
"experiments": {
"name": "fake_package",
"create": True
},
"run": {
"id": "123456789",
"name": "my_run",
"nested": True
},
"ui": {
"port": "5151",
"host": "localhost"
},
"hooks": {
"node": {
"flatten_dict_params": True,
"recursive": False,
"sep": "-",
"long_parameters_strategy": "truncate",
}
},
}
project_metadata = _get_project_metadata(kedro_project_with_tcl)
_add_src_to_path(project_metadata.source_dir, kedro_project_with_tcl)
configure_project(project_metadata.package_name)
with KedroSession.create(project_metadata.package_name,
kedro_project_with_tcl):
assert get_mlflow_config().to_dict() == expected
def run_package():
# Entry point for running a Kedro project packaged with `kedro package`
# using `python -m <project_package>.run` command.
package_name = Path(__file__).resolve().parent.name
configure_project(package_name)
with KedroSession.create(package_name) as session:
session.run()
def test_get_current_session(self, fake_project, mocker):
assert get_current_session(silent=True) is None # no sessions yet
pattern = "There is no active Kedro session"
with pytest.raises(RuntimeError, match=pattern):
get_current_session()
mocker.patch("kedro.framework.project._validate_module")
configure_project(_FAKE_PACKAGE_NAME)
session1 = KedroSession.create(_FAKE_PACKAGE_NAME, fake_project)
session2 = KedroSession.create(_FAKE_PACKAGE_NAME, fake_project)
with session1:
assert get_current_session() is session1
pattern = (
"Cannot activate the session as another active session already exists"
)
with pytest.raises(RuntimeError, match=pattern), session2:
pass # pragma: no cover
# session has been closed, so no current sessions should be available
assert get_current_session(silent=True) is None
with session2:
assert get_current_session() is session2
def test_pipeline_run_hook_getting_configs(
kedro_project,
dummy_run_params,
dummy_pipeline,
dummy_catalog,
):
_write_yaml(
kedro_project / "conf" / "local" / "mlflow.yml",
dict(hooks=dict(
node=dict(flatten_dict_params=True, recursive=False, sep="-")), ),
),
project_metadata = _get_project_metadata(kedro_project)
_add_src_to_path(project_metadata.source_dir, kedro_project)
configure_project(project_metadata.package_name)
with KedroSession.create(
package_name=project_metadata.package_name,
project_path=kedro_project,
):
mlflow_node_hook = MlflowNodeHook()
mlflow_node_hook.before_pipeline_run(run_params=dummy_run_params,
pipeline=dummy_pipeline,
catalog=dummy_catalog)
assert (
mlflow_node_hook.flatten,
mlflow_node_hook.recursive,
mlflow_node_hook.sep,
) == (True, False, "-")
def test_register_pipelines_is_called(self, mock_session_with_hooks,
dummy_dataframe, caplog):
# not sure why this test needs this line here too
# and not just in the session fixture
configure_project(MOCK_PACKAGE_NAME)
context = mock_session_with_hooks.load_context()
catalog = context.catalog
catalog.save("cars", dummy_dataframe)
catalog.save("boats", dummy_dataframe)
mock_session_with_hooks.run()
register_pipelines_calls = [
record for record in caplog.records
if record.funcName == "register_pipelines"
]
assert len(register_pipelines_calls) == 1
call_record = register_pipelines_calls[0]
_assert_hook_call_record_has_expected_parameters(call_record, [])
expected_pipelines = {
"__default__": CONTEXT_PIPELINE,
"de": CONTEXT_PIPELINE,
"pipe": CONTEXT_PIPELINE,
}
assert context.pipelines == expected_pipelines
def ui(env, port, host):
"""Opens the mlflow user interface with the
project-specific settings of mlflow.yml. This interface
enables to browse and compares runs.
"""
project_path = Path().cwd()
project_metadata = _get_project_metadata(project_path)
_add_src_to_path(project_metadata.source_dir, project_path)
configure_project(project_metadata.package_name)
with KedroSession.create(
package_name=project_metadata.package_name,
project_path=project_path,
env=env,
):
mlflow_conf = get_mlflow_config()
host = host or mlflow_conf.ui_opts.get("host")
port = port or mlflow_conf.ui_opts.get("port")
# call mlflow ui with specific options
# TODO : add more options for ui
subprocess.call(
[
"mlflow",
"ui",
"--backend-store-uri",
mlflow_conf.mlflow_tracking_uri,
"--host",
host,
"--port",
port,
]
)
def fake_project_cli(fake_repo_path: Path, dummy_config: Path):
old_settings = settings.as_dict()
starter_path = Path(__file__).parents[3].resolve()
starter_path = starter_path / "features" / "steps" / "test_starter"
# This is needed just for the tests, those CLI groups are merged in our
# code when invoking `kedro` but when imported, they still need to be merged
kedro_cli = click.CommandCollection(name="Kedro",
sources=[cli, create_cli])
CliRunner().invoke(
kedro_cli,
["new", "-c",
str(dummy_config), "--starter",
str(starter_path)],
)
# NOTE: Here we load a couple of modules, as they would be imported in
# the code and tests.
# It's safe to remove the new entries from path due to the python
# module caching mechanism. Any `reload` on it will not work though.
old_path = sys.path.copy()
sys.path = [str(fake_repo_path / "src")] + sys.path
import_module(PACKAGE_NAME)
configure_project(PACKAGE_NAME)
yield import_module(f"{PACKAGE_NAME}.cli")
# reset side-effects of configure_project
pipelines.clear()
for key, value in old_settings.items():
settings.set(key, value)
sys.path = old_path
del sys.modules[PACKAGE_NAME]
def fake_project_cli(
fake_repo_path: Path, dummy_config: Path, fake_kedro_cli: click.CommandCollection
):
old_settings = settings.as_dict()
starter_path = Path(__file__).parents[3].resolve()
starter_path = starter_path / "features" / "steps" / "test_starter"
CliRunner().invoke(
fake_kedro_cli, ["new", "-c", str(dummy_config), "--starter", str(starter_path)]
)
# NOTE: Here we load a couple of modules, as they would be imported in
# the code and tests.
# It's safe to remove the new entries from path due to the python
# module caching mechanism. Any `reload` on it will not work though.
old_path = sys.path.copy()
sys.path = [str(fake_repo_path / "src")] + sys.path
import_module(PACKAGE_NAME)
configure_project(PACKAGE_NAME)
yield fake_kedro_cli
# reset side-effects of configure_project
pipelines._clear(PACKAGE_NAME) # this resets pipelines loading state
for key, value in old_settings.items():
settings.set(key, value)
sys.path = old_path
del sys.modules[PACKAGE_NAME]
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 bootstrap_project(project_path: Path) -> ProjectMetadata:
"""Run setup required at the beginning of the workflow
when running in project mode, and return project metadata.
"""
metadata = _get_project_metadata(project_path)
_add_src_to_path(metadata.source_dir, project_path)
configure_project(metadata.package_name)
return metadata
def reload_kedro(path, line=None):
"""Line magic which reloads all Kedro default variables."""
global startup_error
global context
global catalog
global session
try:
import kedro.config.default_logger
from kedro.framework.hooks import get_hook_manager
from kedro.framework.project import configure_project
from kedro.framework.session import KedroSession
from kedro.framework.session.session import _activate_session
from kedro.framework.cli.jupyter import collect_line_magic
except ImportError:
logging.error(
"Kedro appears not to be installed in your current environment "
"or your current IPython session was not started in a valid Kedro project."
)
raise
try:
path = path or project_path
# clear hook manager
hook_manager = get_hook_manager()
name_plugin_pairs = hook_manager.list_name_plugin()
for name, plugin in name_plugin_pairs:
hook_manager.unregister(name=name, plugin=plugin)
# remove cached user modules
metadata = _get_project_metadata(path)
to_remove = [
mod for mod in sys.modules if mod.startswith(metadata.package_name)
]
# `del` is used instead of `reload()` because: If the new version of a module does not
# define a name that was defined by the old version, the old definition remains.
for module in to_remove:
del sys.modules[module]
configure_project(metadata.package_name)
session = KedroSession.create(metadata.package_name, path)
_activate_session(session, force=True)
logging.debug("Loading the context from %s", str(path))
context = session.load_context()
catalog = context.catalog
logging.info("** Kedro project %s", str(metadata.project_name))
logging.info("Defined global variable `context` and `catalog`")
for line_magic in collect_line_magic():
register_line_magic(needs_local_scope(line_magic))
logging.info("Registered line magic `%s`", line_magic.__name__)
except Exception as err:
startup_error = err
logging.exception("Kedro's ipython session startup script failed:\n%s",
str(err))
raise err
def _bootstrap_subprocess(package_name: str, conf_logging: Dict[str, Any]):
# pylint: disable=import-outside-toplevel,protected-access,cyclic-import
from kedro.framework.project import configure_project
from kedro.framework.session.session import _register_all_project_hooks
hook_manager = get_hook_manager()
configure_project(package_name)
_register_all_project_hooks(hook_manager)
logging.config.dictConfig(conf_logging)
def mock_session_with_hooks(tmp_path, mock_settings_with_logging_hooks,
logging_hooks, mocker): # pylint: disable=unused-argument
mocker.patch("kedro.framework.project._validate_module")
logging_hooks.queue_listener.start()
configure_project(MOCK_PACKAGE_NAME)
yield KedroSession.create(MOCK_PACKAGE_NAME,
tmp_path,
extra_params={"params:key": "value"})
logging_hooks.queue_listener.stop()
def test_node_hook_logging_above_limit_tag_strategy(kedro_project,
dummy_run_params,
param_length):
_write_yaml(
kedro_project / "conf" / "local" / "mlflow.yml",
dict(hooks=dict(node=dict(long_parameters_strategy="tag")), ),
)
mlflow_tracking_uri = (kedro_project / "mlruns").as_uri()
mlflow.set_tracking_uri(mlflow_tracking_uri)
mlflow_node_hook = MlflowNodeHook()
param_value = param_length * "a"
node_inputs = {"params:my_param": param_value}
project_metadata = _get_project_metadata(kedro_project)
_add_src_to_path(project_metadata.source_dir, kedro_project)
configure_project(project_metadata.package_name)
with KedroSession.create(
package_name=project_metadata.package_name,
project_path=kedro_project,
):
with mlflow.start_run():
mlflow_node_hook.before_pipeline_run(
run_params=dummy_run_params,
pipeline=Pipeline([]),
catalog=DataCatalog(),
)
# IMPORTANT: Overpassing the parameters limit
# should raise an error for all mlflow backend
# but it does not on FileStore backend :
# https://github.com/mlflow/mlflow/issues/2814#issuecomment-628284425
# Since we use FileStore system for simplicty for tests logging works
# But we have enforced failure (which is slightly different from mlflow
# behaviour)
mlflow_node_hook.before_node_run(
node=node(func=lambda x: x, inputs=dict(x="a"), outputs=None),
catalog=DataCatalog(), # can be empty
inputs=node_inputs,
is_async=False,
run_id="132",
)
run_id = mlflow.active_run().info.run_id
mlflow_client = MlflowClient(mlflow_tracking_uri)
current_run = mlflow_client.get_run(run_id)
assert current_run.data.params == {}
assert {
k: v
for k, v in current_run.data.tags.items()
if not k.startswith("mlflow")
} == {
"my_param": param_value
}
def dummy_context(tmp_path, prepare_project_dir, env, extra_params, mocker): # pylint: disable=unused-argument
mocker.patch("kedro.framework.project._validate_module")
configure_project(MOCK_PACKAGE_NAME)
context = KedroContext(MOCK_PACKAGE_NAME,
str(tmp_path),
env=env,
extra_params=extra_params)
return context
def _load_project(project_path): # pragma: no cover
# TODO: This one can potentially become project bootstrap and will be
# tested there
if not _is_project(project_path):
return None
metadata = _get_project_metadata(project_path)
_add_src_to_path(metadata.source_dir, project_path)
configure_project(metadata.package_name)
return metadata
def test_get_mlflow_config_in_uninitialized_project(kedro_project):
# config_with_base_mlflow_conf is a pytest.fixture in conftest
with pytest.raises(
KedroMlflowConfigError,
match="No 'mlflow.yml' config file found in environment"):
project_metadata = _get_project_metadata(kedro_project)
_add_src_to_path(project_metadata.source_dir, kedro_project)
configure_project(project_metadata.package_name)
with KedroSession.create(project_metadata.package_name, kedro_project):
get_mlflow_config()
def dummy_context(
tmp_path, prepare_project_dir, env, extra_params, mocker
): # pylint: disable=unused-argument
configure_project(MOCK_PACKAGE_NAME)
context = KedroContext(
MOCK_PACKAGE_NAME, str(tmp_path), env=env, extra_params=extra_params
)
yield context
pipelines._clear(MOCK_PACKAGE_NAME)
def test_configure_project_should_not_raise_for_unimportable_pipelines(
mock_package_name_with_unimportable_pipelines_file, ):
# configure_project should not raise error for unimportable pipelines
# since pipelines loading is lazy
configure_project(mock_package_name_with_unimportable_pipelines_file)
# accessing data should raise for unimportable pipelines
with pytest.raises(ModuleNotFoundError,
match="No module named 'this_is_not_a_real_thing'"):
_ = pipelines["new_pipeline"]
def get_session():
"Get kedro session"
cur_path = os.getcwd()
os.chdir(Path(__file__).parents[2])
configure_project("kedro_171_package")
session = KedroSession.create(Path(__file__).resolve().parent.name)
_activate_session(session, force=True)
os.chdir(cur_path)
return session
def test_mlflow_pipeline_hook_with_pipeline_ml_signature(
kedro_project_with_mlflow_conf,
env_from_dict,
dummy_pipeline,
dummy_catalog,
dummy_run_params,
model_signature,
expected_signature,
):
# config_with_base_mlflow_conf is a conftest fixture
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(
package_name=project_metadata.package_name,
project_path=kedro_project_with_mlflow_conf,
):
pipeline_hook = MlflowPipelineHook()
runner = SequentialRunner()
pipeline_to_run = pipeline_ml_factory(
training=dummy_pipeline.only_nodes_with_tags("training"),
inference=dummy_pipeline.only_nodes_with_tags("inference"),
input_name="raw_data",
conda_env=env_from_dict,
model_name="model",
model_signature=model_signature,
)
pipeline_hook.after_catalog_created(
catalog=dummy_catalog,
# `after_catalog_created` is not using any of arguments bellow,
# so we are setting them to empty values.
conf_catalog={},
conf_creds={},
feed_dict={},
save_version="",
load_versions="",
run_id=dummy_run_params["run_id"],
)
pipeline_hook.before_pipeline_run(
run_params=dummy_run_params, pipeline=pipeline_to_run, catalog=dummy_catalog
)
runner.run(pipeline_to_run, dummy_catalog)
run_id = mlflow.active_run().info.run_id
pipeline_hook.after_pipeline_run(
run_params=dummy_run_params, pipeline=pipeline_to_run, catalog=dummy_catalog
)
# test : parameters should have been logged
trained_model = mlflow.pyfunc.load_model(f"runs:/{run_id}/model")
assert trained_model.metadata.signature == expected_signature
def init(env, force, silent):
"""Updates the template of a kedro project.
Running this command is mandatory to use kedro-mlflow.
This adds "conf/base/mlflow.yml": This is a configuration file
used for run parametrization when calling "kedro run" command.
See INSERT_DOC_URL for further details.
"""
# get constants
mlflow_yml = "mlflow.yml"
project_path = Path().cwd()
project_metadata = _get_project_metadata(project_path)
_add_src_to_path(project_metadata.source_dir, project_path)
configure_project(project_metadata.package_name)
session = KedroSession.create(
project_metadata.package_name, project_path=project_path
)
context = session.load_context()
mlflow_yml_path = project_path / context.CONF_ROOT / env / mlflow_yml
# mlflow.yml is just a static file,
# but the name of the experiment is set to be the same as the project
if mlflow_yml_path.is_file() and not force:
click.secho(
click.style(
f"A 'mlflow.yml' already exists at '{mlflow_yml_path}' You can use the ``--force`` option to override it.",
fg="red",
)
)
else:
try:
write_jinja_template(
src=TEMPLATE_FOLDER_PATH / mlflow_yml,
is_cookiecutter=False,
dst=mlflow_yml_path,
python_package=project_metadata.package_name,
)
except FileNotFoundError:
click.secho(
click.style(
f"No env '{env}' found. Please check this folder exists inside '{context.CONF_ROOT}' folder.",
fg="red",
)
)
if not silent:
click.secho(
click.style(
f"'{context.CONF_ROOT}/{env}/{mlflow_yml}' successfully updated.",
fg="green",
)
)
def mock_session(
mocker, mock_settings_with_mlflow_hooks, kedro_project_path
): # pylint: disable=unused-argument
# we need to patch "kedro.framework.session.session.validate_settings" instead of
# "kedro.framework.project.validate_settings" because it is imported
mocker.patch("kedro.framework.session.session.validate_settings")
# idem, we patch we need to patch "kedro.framework.session.session._register_hooks_setuptools" instead of
# "kedro.framework.hooks.manager._register_hooks_setuptools" because it is imported
mocker.patch(
"kedro.framework.session.session._register_hooks_setuptools"
) # prevent registering the one of the plugins which are already installed
configure_project(MOCK_PACKAGE_NAME)
return KedroSession.create(MOCK_PACKAGE_NAME, kedro_project_path)
def test_register_pipelines_with_duplicate_entries(self, tmp_path,
mock_pipelines, mocker):
mocker.patch("kedro.framework.project._validate_module")
pattern = ("Found duplicate pipeline entries. The following "
"will be overwritten: __default__")
with pytest.warns(UserWarning, match=re.escape(pattern)):
configure_project(MOCK_PACKAGE_NAME)
session = KedroSession.create(MOCK_PACKAGE_NAME, tmp_path)
context = session.load_context()
# check that all pipeline dictionaries merged together correctly
expected_pipelines = {
key: CONTEXT_PIPELINE
for key in ("__default__", "de", "pipe")
}
assert mock_pipelines == expected_pipelines
assert context.pipelines == expected_pipelines
def test_on_pipeline_error(kedro_project_with_mlflow_conf):
tracking_uri = (kedro_project_with_mlflow_conf / "mlruns").as_uri()
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(
package_name=project_metadata.package_name,
project_path=kedro_project_with_mlflow_conf,
):
def failing_node():
mlflow.start_run(nested=True)
raise ValueError("Let's make this pipeline fail")
class DummyContextWithHook(KedroContext):
project_name = "fake project"
package_name = "fake_project"
project_version = "0.16.5"
hooks = (MlflowPipelineHook(),)
def _get_pipeline(self, name: str = None) -> Pipeline:
return Pipeline(
[
node(
func=failing_node,
inputs=None,
outputs="fake_output",
)
]
)
with pytest.raises(ValueError):
failing_context = DummyContextWithHook(
"fake_package", kedro_project_with_mlflow_conf.as_posix()
)
failing_context.run()
# the run we want is the last one in Default experiment
failing_run_info = MlflowClient(tracking_uri).list_run_infos("0")[0]
assert mlflow.active_run() is None # the run must have been closed
assert failing_run_info.status == RunStatus.to_string(
RunStatus.FAILED
) # it must be marked as failed
def test_node_hook_logging_above_limit_truncate_strategy(
kedro_project, dummy_run_params, param_length):
_write_yaml(
kedro_project / "conf" / "local" / "mlflow.yml",
dict(hooks=dict(node=dict(long_parameters_strategy="truncate")), ),
)
mlflow_tracking_uri = (kedro_project / "mlruns").as_uri()
mlflow.set_tracking_uri(mlflow_tracking_uri)
mlflow_node_hook = MlflowNodeHook()
param_value = param_length * "a"
node_inputs = {"params:my_param": param_value}
project_metadata = _get_project_metadata(kedro_project)
_add_src_to_path(project_metadata.source_dir, kedro_project)
configure_project(project_metadata.package_name)
with KedroSession.create(
package_name=project_metadata.package_name,
project_path=kedro_project,
):
with mlflow.start_run():
mlflow_node_hook.before_pipeline_run(
run_params=dummy_run_params,
pipeline=Pipeline([]),
catalog=DataCatalog(),
)
mlflow_node_hook.before_node_run(
node=node(func=lambda x: x, inputs=dict(x="a"), outputs=None),
catalog=DataCatalog(), # can be empty
inputs=node_inputs,
is_async=False,
run_id="132",
)
run_id = mlflow.active_run().info.run_id
mlflow_client = MlflowClient(mlflow_tracking_uri)
current_run = mlflow_client.get_run(run_id)
assert current_run.data.params == {
"my_param": param_value[0:MAX_PARAM_VAL_LENGTH]
}
