def _before_run_validations(tracking_uri, cluster_spec):
"""Validations to perform before running a project on Databricks."""
_check_databricks_auth_available()
if cluster_spec is None:
raise ExecutionException("Cluster spec must be provided when launching MLflow project runs "
"on Databricks.")
if tracking.is_local_uri(tracking_uri):
raise ExecutionException(
"When running on Databricks, the MLflow tracking URI must be set to a remote URI "
"accessible to both the current client and code running on Databricks. Got local "
"tracking URI %s." % tracking_uri)
def _create_databricks_run(tracking_uri, experiment_id, source_name,
source_version, entry_point_name):
"""
Make an API request to the specified tracking server to create a new run with the specified
attributes. Return an ``ActiveRun`` that can be used to query the tracking server for the run's
status or log metrics/params for the run.
"""
if tracking.is_local_uri(tracking_uri):
eprint(
"WARNING: MLflow tracking URI is set to a local URI (%s), so results from "
"Databricks will not be logged permanently." % tracking_uri)
return tracking._create_run(experiment_id=experiment_id,
source_name=source_name,
source_version=source_version,
entry_point_name=entry_point_name,
source_type=SourceType.PROJECT)
def test_uri_types():
assert tracking.is_local_uri("mlruns")
assert tracking.is_local_uri("./mlruns")
assert tracking.is_local_uri("file:///foo/mlruns")
assert not tracking.is_local_uri("https://whatever")
assert not tracking.is_local_uri("http://whatever")
assert not tracking.is_local_uri("databricks")
assert not tracking.is_local_uri("databricks:whatever")
assert not tracking.is_local_uri("databricks://whatever")
assert tracking._is_databricks_uri("databricks")
assert tracking._is_databricks_uri("databricks:whatever")
assert tracking._is_databricks_uri("databricks://whatever")
assert not tracking._is_databricks_uri("mlruns")
assert not tracking._is_databricks_uri("http://whatever")
assert tracking._is_http_uri("http://whatever")
assert tracking._is_http_uri("https://whatever")
assert not tracking._is_http_uri("file://whatever")
assert not tracking._is_http_uri("databricks://whatever")
assert not tracking._is_http_uri("mlruns")
def _create_databricks_run(tracking_uri, experiment_id, source_name,
source_version, entry_point_name):
"""
Makes an API request to the specified tracking server to create a new run with the specified
attributes. Returns an `ActiveRun` that can be used to query the tracking server for the run's
status or log metrics/params for the run.
"""
if tracking.is_local_uri(tracking_uri):
# TODO: we'll actually use the Databricks deployment's tracking URI here in the future
eprint(
"WARNING: MLflow tracking URI is set to a local URI (%s), so results from "
"Databricks will not be logged permanently." % tracking_uri)
return None
else:
# Assume non-local tracking URIs are accessible from Databricks (won't work for e.g.
# localhost)
return tracking._create_run(experiment_id=experiment_id,
source_name=source_name,
source_version=source_version,
entry_point_name=entry_point_name,
source_type=SourceType.PROJECT)