def test_resolve_tags_no_arg(mock_run_context_providers):
assert resolve_tags() == {
"one": "override",
"two": "two-val",
"three": "three-val",
"new": "new-val"
}
def experiment(self) -> MlflowClient:
r"""
Actual MLflow object. To use MLflow features in your
:class:`~pytorch_lightning.core.lightning.LightningModule` do the following.
Example::
self.logger.experiment.some_mlflow_function()
"""
if self._experiment_id is None:
expt = self._mlflow_client.get_experiment_by_name(
self._experiment_name)
if expt is not None:
self._experiment_id = expt.experiment_id
else:
log.warning(
f'Experiment with name {self._experiment_name} not found. Creating it.'
)
self._experiment_id = self._mlflow_client.create_experiment(
name=self._experiment_name,
artifact_location=self._artifact_location,
)
if self._run_id is None:
run = self._mlflow_client.create_run(
experiment_id=self._experiment_id,
tags=resolve_tags(self.tags))
self._run_id = run.info.run_id
return self._mlflow_client
def test_resolve_tags(mock_run_context_providers):
tags_arg = {"two": "arg-override", "arg": "arg-val"}
assert resolve_tags(tags_arg) == {
"one": "override",
"two": "arg-override",
"three": "three-val",
"new": "new-val",
"arg": "arg-val"
}
def test_run_context_provider_registry_with_installed_plugin(tmp_wkdir):
"""This test requires the package in tests/resources/mlflow-test-plugin to be installed"""
reload(mlflow.tracking.context)
from mlflow_test_plugin import PluginRunContextProvider
assert PluginRunContextProvider in _currently_registered_run_context_provider_classes()
# The test plugin's context provider always returns False from in_context
# to avoid polluting tags in developers' environments. The following mock overrides this to
# perform the integration test.
with mock.patch.object(PluginRunContextProvider, "in_context", return_value=True):
assert resolve_tags()["test"] == "tag"
def experiment(self) -> MlflowClient:
r"""
Actual MLflow object. To use MLflow features in your
:class:`~pytorch_lightning.core.module.LightningModule` do the following.
Example::
self.logger.experiment.some_mlflow_function()
"""
if self._initialized:
return self._mlflow_client
if self._run_id is not None:
run = self._mlflow_client.get_run(self._run_id)
self._experiment_id = run.info.experiment_id
self._initialized = True
return self._mlflow_client
if self._experiment_id is None:
expt = self._mlflow_client.get_experiment_by_name(
self._experiment_name)
if expt is not None:
self._experiment_id = expt.experiment_id
else:
log.warning(
f"Experiment with name {self._experiment_name} not found. Creating it."
)
self._experiment_id = self._mlflow_client.create_experiment(
name=self._experiment_name,
artifact_location=self._artifact_location)
if self._run_id is None:
if self._run_name is not None:
self.tags = self.tags or {}
if MLFLOW_RUN_NAME in self.tags:
log.warning(
f"The tag {MLFLOW_RUN_NAME} is found in tags. The value will be overridden by {self._run_name}."
)
self.tags[MLFLOW_RUN_NAME] = self._run_name
run = self._mlflow_client.create_run(
experiment_id=self._experiment_id,
tags=resolve_tags(self.tags))
self._run_id = run.info.run_id
self._initialized = True
return self._mlflow_client
def start_run(run_id=None, experiment_id=None, run_name=None, nested=False):
"""
Start a new MLflow run, setting it as the active run under which metrics and parameters
will be logged. The return value can be used as a context manager within a ``with`` block;
otherwise, you must call ``end_run()`` to terminate the current run.
If you pass a ``run_id`` or the ``MLFLOW_RUN_ID`` environment variable is set,
``start_run`` attempts to resume a run with the specified run ID and
other parameters are ignored. ``run_id`` takes precedence over ``MLFLOW_RUN_ID``.
MLflow sets a variety of default tags on the run, as defined in
:ref:`MLflow system tags <system_tags>`.
:param run_id: If specified, get the run with the specified UUID and log parameters
and metrics under that run. The run's end time is unset and its status
is set to running, but the run's other attributes (``source_version``,
``source_type``, etc.) are not changed.
:param experiment_id: ID of the experiment under which to create the current run (applicable
only when ``run_id`` is not specified). If ``experiment_id`` argument
is unspecified, will look for valid experiment in the following order:
activated using ``set_experiment``, ``MLFLOW_EXPERIMENT_NAME``
environment variable, ``MLFLOW_EXPERIMENT_ID`` environment variable,
or the default experiment as defined by the tracking server.
:param run_name: Name of new run (stored as a ``mlflow.runName`` tag).
Used only when ``run_id`` is unspecified.
:param nested: Controls whether run is nested in parent run. ``True`` creates a nest run.
:return: :py:class:`mlflow.ActiveRun` object that acts as a context manager wrapping
the run's state.
"""
global _active_run_stack
# back compat for int experiment_id
experiment_id = str(experiment_id) if isinstance(experiment_id, int) else experiment_id
if len(_active_run_stack) > 0 and not nested:
raise Exception(("Run with UUID {} is already active. To start a nested " +
"run, call start_run with nested=True").format(
_active_run_stack[0].info.run_id))
if run_id:
existing_run_id = run_id
elif _RUN_ID_ENV_VAR in os.environ:
existing_run_id = os.environ[_RUN_ID_ENV_VAR]
del os.environ[_RUN_ID_ENV_VAR]
else:
existing_run_id = None
if existing_run_id:
_validate_run_id(existing_run_id)
active_run_obj = MlflowClient().get_run(existing_run_id)
if active_run_obj.info.lifecycle_stage == LifecycleStage.DELETED:
raise MlflowException("Cannot start run with ID {} because it is in the "
"deleted state.".format(existing_run_id))
else:
if len(_active_run_stack) > 0:
parent_run_id = _active_run_stack[-1].info.run_id
else:
parent_run_id = None
exp_id_for_run = experiment_id if experiment_id is not None else _get_experiment_id()
user_specified_tags = {}
if parent_run_id is not None:
user_specified_tags[MLFLOW_PARENT_RUN_ID] = parent_run_id
if run_name is not None:
user_specified_tags[MLFLOW_RUN_NAME] = run_name
tags = context.resolve_tags(user_specified_tags)
active_run_obj = MlflowClient().create_run(
experiment_id=exp_id_for_run,
tags=tags
)
_active_run_stack.append(ActiveRun(active_run_obj))
return _active_run_stack[-1]
def start_run(run_uuid=None,
experiment_id=None,
source_name=None,
source_version=None,
entry_point_name=None,
source_type=None,
run_name=None,
nested=False):
"""
Start a new MLflow run, setting it as the active run under which metrics and parameters
will be logged. The return value can be used as a context manager within a ``with`` block;
otherwise, you must call ``end_run()`` to terminate the current run.
If you pass a ``run_uuid`` or the ``MLFLOW_RUN_ID`` environment variable is set,
``start_run`` attempts to resume a run with the specified run ID and
other parameters are ignored. ``run_uuid`` takes precedence over ``MLFLOW_RUN_ID``.
:param run_uuid: If specified, get the run with the specified UUID and log parameters
and metrics under that run. The run's end time is unset and its status
is set to running, but the run's other attributes (``source_version``,
``source_type``, etc.) are not changed.
:param experiment_id: ID of the experiment under which to create the current run (applicable
only when ``run_uuid`` is not specified). If ``experiment_id`` argument
is unspecified, will look for valid experiment in the following order:
activated using ``set_experiment``, ``MLFLOW_EXPERIMENT_ID`` env variable,
or the default experiment.
:param source_name: Name of the source file or URI of the project to be associated with the run.
If none provided defaults to the current file.
:param source_version: Optional Git commit hash to associate with the run.
:param entry_point_name: Optional name of the entry point for the current run.
:param source_type: Integer :py:class:`mlflow.entities.SourceType` describing the type
of the run ("local", "project", etc.). Defaults to
:py:class:`mlflow.entities.SourceType.LOCAL` ("local").
:param run_name: Name of new run. Used only when ``run_uuid`` is unspecified.
:param nested: Parameter which must be set to ``True`` to create nested runs.
:return: :py:class:`mlflow.ActiveRun` object that acts as a context manager wrapping
the run's state.
"""
global _active_run_stack
# back compat for int experiment_id
experiment_id = str(experiment_id) if isinstance(experiment_id,
int) else experiment_id
if len(_active_run_stack) > 0 and not nested:
raise Exception(
("Run with UUID {} is already active. To start a nested " +
"run call start_run with nested=True").format(
_active_run_stack[0].info.run_uuid))
existing_run_uuid = run_uuid or os.environ.get(_RUN_ID_ENV_VAR, None)
if existing_run_uuid:
_validate_run_id(existing_run_uuid)
active_run_obj = MlflowClient().get_run(existing_run_uuid)
if active_run_obj.info.lifecycle_stage == LifecycleStage.DELETED:
raise MlflowException(
"Cannot start run with ID {} because it is in the "
"deleted state.".format(existing_run_uuid))
else:
if len(_active_run_stack) > 0:
parent_run_id = _active_run_stack[-1].info.run_uuid
else:
parent_run_id = None
exp_id_for_run = experiment_id if experiment_id is not None else _get_experiment_id(
)
user_specified_tags = {}
if parent_run_id is not None:
user_specified_tags[MLFLOW_PARENT_RUN_ID] = parent_run_id
if source_name is not None:
user_specified_tags[MLFLOW_SOURCE_NAME] = source_name
if source_type is not None:
user_specified_tags[MLFLOW_SOURCE_TYPE] = SourceType.to_string(
source_type)
if source_version is not None:
user_specified_tags[MLFLOW_GIT_COMMIT] = source_version
if entry_point_name is not None:
user_specified_tags[MLFLOW_PROJECT_ENTRY_POINT] = entry_point_name
tags = context.resolve_tags(user_specified_tags)
active_run_obj = MlflowClient().create_run(
experiment_id=exp_id_for_run, run_name=run_name, tags=tags)
_active_run_stack.append(ActiveRun(active_run_obj))
return _active_run_stack[-1]
