def end_run(status="FINISHED"):
global _active_run
if _active_run:
get_service().set_terminated(_active_run.info.run_uuid, status)
# Clear out the global existing run environment variable as well.
env.unset_variable(_RUN_ID_ENV_VAR)
_active_run = None
def set_tag(key, value):
"""
Sets the passed-in tag under the current run, creating a run if necessary.
:param key: Tag name (string)
:param value: Tag value (string, but will be string-ified if not)
"""
run_id = _get_or_start_run().info.run_uuid
get_service().set_tag(run_id, key, value)
def log_param(key, value):
"""
Log the passed-in parameter under the current run, creating a run if necessary.
:param key: Parameter name (string)
:param value: Parameter value (string, but will be string-ified if not)
"""
run_id = _get_or_start_run().info.run_uuid
get_service().log_param(run_id, key, value)
def log_artifacts(local_dir, artifact_path=None):
"""
Log all the contents of a local directory as artifacts of the run.
:param local_dir: Path to the directory of files to write.
:param artifact_path: If provided, the directory in ``artifact_uri`` to write to.
"""
run_id = _get_or_start_run().info.run_uuid
get_service().log_artifacts(run_id, local_dir, artifact_path)
def log_artifact(local_path, artifact_path=None):
"""
Log a local file or directory as an artifact of the currently active run.
:param local_path: Path to the file to write.
:param artifact_path: If provided, the directory in ``artifact_uri`` to write to.
"""
run_id = _get_or_start_run().info.run_uuid
get_service().log_artifact(run_id, local_path, artifact_path)
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):
"""
Start a new MLflow run, setting it as the active run under which metrics and params
will be logged. The return value can be used as a context manager within a ``with`` block;
otherwise, ``end_run()`` must be called to terminate the current run. If ``run_uuid``
is passed or the ``MLFLOW_RUN_ID`` environment variable is set, ``start_run`` attempts to
resume a run with the specified run ID (with ``run_uuid`` taking precedence over
``MLFLOW_RUN_ID``), and other parameters are ignored.
:param run_uuid: If specified, get the run with the specified UUID and log metrics
and params under that run. The run's end time is unset and its status
is set to running, but the run's other attributes remain unchanged
(the run's ``source_version``, ``source_type``, etc. are not changed).
:param experiment_id: Used only when ``run_uuid`` is unspecified. ID of the experiment under
which to create the current run. If unspecified, the run is created under
a new experiment with a randomly generated name.
:param source_name: Name of the source file or URI of the project to be associated with the run.
Defaults to the current file if none provided.
:param source_version: Optional Git commit hash to associate with the run.
:param entry_point_name: Optional name of the entry point for to the current run.
:param source_type: Integer enum value describing the type of the run
("local", "project", etc.). Defaults to
``mlflow.entities.SourceType.LOCAL``.
:return: :py:class:`mlflow.ActiveRun` object that acts as a context manager wrapping
the run's state.
"""
global _active_run
if _active_run:
raise Exception(
"Run with UUID %s is already active, unable to start nested "
"run" % _active_run.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 = get_service().get_run(existing_run_uuid)
else:
exp_id_for_run = experiment_id or _get_experiment_id()
active_run_obj = get_service().create_run(
experiment_id=exp_id_for_run,
run_name=run_name,
source_name=source_name or _get_source_name(),
source_version=source_version or _get_source_version(),
entry_point_name=entry_point_name,
source_type=source_type or _get_source_type())
_active_run = ActiveRun(active_run_obj)
return _active_run
def log_metric(key, value):
"""
Log the passed-in metric under the current run, creating a run if necessary.
:param key: Metric name (string).
:param value: Metric value (float).
"""
if not isinstance(value, numbers.Number):
print("WARNING: The metric {}={} was not logged because the value is not a number.".format(
key, value), file=sys.stderr)
return
run_id = _get_or_start_run().info.run_uuid
get_service().log_metric(run_id, key, value, int(time.time()))
def create_experiment(name, artifact_location=None):
"""
Creates an experiment.
:param name: must be unique
:param artifact_location: If not provided, the server will pick an appropriate default.
:return: integer id of the created experiment
"""
return get_service().create_experiment(name, artifact_location)
def create_experiment(name, artifact_location=None):
"""
Create an experiment.
:param name: The experiment name. Must be unique.
:param artifact_location: The location to store run artifacts.
If not provided, the server picks an appropriate default.
:return: Integer ID of the created experiment.
"""
return get_service().create_experiment(name, artifact_location)
def create_experiment(name, artifact_location=None):
return get_service().create_experiment(name, artifact_location)
def log_artifacts(local_dir, artifact_path=None):
"""Log all the contents of a local directory as artifacts of the run."""
artifact_uri = _get_or_start_run().info.artifact_uri
get_service().log_artifacts(artifact_uri, local_dir, artifact_path)
def log_artifact(local_path, artifact_path=None):
"""Log a local file or directory as an artifact of the currently active run."""
artifact_uri = _get_or_start_run().info.artifact_uri
get_service().log_artifact(artifact_uri, local_path, artifact_path)
def __exit__(self, exc_type, exc_val, exc_tb):
status = "FINISHED" if exc_type is None else "FAILED"
get_service().set_terminated(self.info.run_uuid, status)
global _active_run
_active_run = None
return exc_type is None
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):
"""
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.
Used only when ``run_uuid`` is unspecified. If unspecified,
the run is created under 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.
:return: :py:class:`mlflow.ActiveRun` object that acts as a context manager wrapping
the run's state.
"""
global _active_run
if _active_run:
raise Exception(
"Run with UUID %s is already active, unable to start nested "
"run" % _active_run.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 = get_service().get_run(existing_run_uuid)
else:
exp_id_for_run = experiment_id or _get_experiment_id()
if is_in_databricks_notebook():
databricks_tags = {}
notebook_id = get_notebook_id()
notebook_path = get_notebook_path()
webapp_url = get_webapp_url()
if notebook_id is not None:
databricks_tags[MLFLOW_DATABRICKS_NOTEBOOK_ID] = notebook_id
if notebook_path is not None:
databricks_tags[
MLFLOW_DATABRICKS_NOTEBOOK_PATH] = notebook_path
if webapp_url is not None:
databricks_tags[MLFLOW_DATABRICKS_WEBAPP_URL] = webapp_url
active_run_obj = get_service().create_run(
experiment_id=exp_id_for_run,
run_name=run_name,
source_name=notebook_path,
source_version=source_version or _get_source_version(),
entry_point_name=entry_point_name,
source_type=SourceType.NOTEBOOK,
tags=databricks_tags)
else:
active_run_obj = get_service().create_run(
experiment_id=exp_id_for_run,
run_name=run_name,
source_name=source_name or _get_source_name(),
source_version=source_version or _get_source_version(),
entry_point_name=entry_point_name,
source_type=source_type or _get_source_type())
_active_run = ActiveRun(active_run_obj)
return _active_run
def log_artifacts(local_dir, artifact_path=None):
"""Log all the contents of a local directory as artifacts of the run."""
run_id = _get_or_start_run().info.run_uuid
get_service().log_artifacts(run_id, local_dir, artifact_path)
def log_artifact(local_path, artifact_path=None):
"""Log a local file or directory as an artifact of the currently active run."""
run_id = _get_or_start_run().info.run_uuid
get_service().log_artifact(run_id, local_path, artifact_path)
