def test_get_experiment_id_in_databricks_with_active_experiment_returns_active_experiment_id(
):
with TempDir(chdr=True):
exp_name = "random experiment %d" % random.randint(1, 1e6)
exp_id = kiwi.create_experiment(exp_name)
kiwi.set_experiment(exp_name)
notebook_id = str(int(exp_id) + 73)
with mock.patch("mlflow.tracking.fluent.is_in_databricks_notebook") as notebook_detection_mock,\
mock.patch("mlflow.tracking.fluent.get_notebook_id") as notebook_id_mock:
notebook_detection_mock.return_value = True
notebook_id_mock.return_value = notebook_id
assert _get_experiment_id() != notebook_id
assert _get_experiment_id() == exp_id
def test_get_experiment_id_in_databricks_with_experiment_defined_in_env_returns_env_experiment_id(
):
with TempDir(chdr=True):
exp_name = "random experiment %d" % random.randint(1, 1e6)
exp_id = kiwi.create_experiment(exp_name)
notebook_id = str(int(exp_id) + 73)
HelperEnv.set_values(experiment_id=exp_id)
with mock.patch("mlflow.tracking.fluent.is_in_databricks_notebook") as notebook_detection_mock,\
mock.patch("mlflow.tracking.fluent.get_notebook_id") as notebook_id_mock:
notebook_detection_mock.side_effect = lambda *args, **kwargs: True
notebook_id_mock.side_effect = lambda *args, **kwargs: notebook_id
assert _get_experiment_id() != notebook_id
assert _get_experiment_id() == exp_id
def _resolve_experiment_id(experiment_name=None, experiment_id=None):
"""
Resolve experiment.
Verifies either one or other is specified - cannot be both selected.
If ``experiment_name`` is provided and does not exist, an experiment
of that name is created and its id is returned.
:param experiment_name: Name of experiment under which to launch the run.
:param experiment_id: ID of experiment under which to launch the run.
:return: str
"""
if experiment_name and experiment_id:
raise MlflowException(
"Specify only one of 'experiment_name' or 'experiment_id'.")
if experiment_id:
return str(experiment_id)
if experiment_name:
client = tracking.MlflowClient()
exp = client.get_experiment_by_name(experiment_name)
if exp:
return exp.experiment_id
else:
print(
"INFO: '{}' does not exist. Creating a new experiment".format(
experiment_name))
return client.create_experiment(experiment_name)
return _get_experiment_id()
def test_get_experiment_id_in_databricks_detects_notebook_id_by_default():
notebook_id = 768
with mock.patch("mlflow.tracking.fluent.is_in_databricks_notebook") as notebook_detection_mock,\
mock.patch("mlflow.tracking.fluent.get_notebook_id") as notebook_id_mock:
notebook_detection_mock.return_value = True
notebook_id_mock.return_value = notebook_id
assert _get_experiment_id() == notebook_id
def test_get_experiment_id_with_active_experiment_returns_active_experiment_id(
):
# Create a new experiment and set that as active experiment
with TempDir(chdr=True):
name = "Random experiment %d" % random.randint(1, 1e6)
exp_id = kiwi.create_experiment(name)
assert exp_id is not None
kiwi.set_experiment(name)
assert _get_experiment_id() == exp_id
def _already_ran(entry_point_name, parameters, git_commit, experiment_id=None):
"""Best-effort detection of if a run with the given entrypoint name,
parameters, and experiment id already ran. The run must have completed
successfully and have at least the parameters provided.
"""
experiment_id = experiment_id if experiment_id is not None else _get_experiment_id(
)
client = kiwi.tracking.MlflowClient()
all_run_infos = reversed(client.list_run_infos(experiment_id))
for run_info in all_run_infos:
full_run = client.get_run(run_info.run_id)
tags = full_run.data.tags
if tags.get(mlflow_tags.MLFLOW_PROJECT_ENTRY_POINT,
None) != entry_point_name:
continue
match_failed = False
for param_key, param_value in six.iteritems(parameters):
run_value = full_run.data.params.get(param_key)
if run_value != param_value:
match_failed = True
break
if match_failed:
continue
if run_info.to_proto().status != RunStatus.FINISHED:
eprint(("Run matched, but is not FINISHED, so skipping "
"(run_id=%s, status=%s)") %
(run_info.run_id, run_info.status))
continue
previous_version = tags.get(mlflow_tags.MLFLOW_GIT_COMMIT, None)
if git_commit != previous_version:
eprint((
"Run matched, but has a different source version, so skipping "
"(found=%s, expected=%s)") % (previous_version, git_commit))
continue
return client.get_run(run_info.run_id)
eprint("No matching run has been found.")
return None
def test_get_experiment_id_with_no_active_experiments_returns_zero():
assert _get_experiment_id() == "0"