def test_deploy_with_requirements(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
sample_requirements = "\n".join(["pyspark=3.0.0", "xgboost=0.6.0"])
pathlib.Path("runtime_requirements.txt").write_text(sample_requirements)
deploy_result = invoke_cli_runner(
deploy,
[
"--environment",
"test",
"--requirements-file",
"runtime_requirements.txt",
],
)
self.assertEqual(deploy_result.exit_code, 0)
def test_deploy_non_existent_env(self, *args):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {
"misconfigured-environment": {
"dbfs": {},
"jobs": []
}
}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
deploy_result = invoke_cli_runner(deploy,
["--environment", "test"],
expected_error=True)
self.assertIsInstance(deploy_result.exception, NameError)
self.assertIn("non-existent in the deployment file",
str(deploy_result.exception))
def test_deploy_basic(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
with patch(
"mlflow.get_experiment_by_name",
return_value=Experiment("id", None,
f"dbfs:/dbx/{self.project_name}",
None, None),
):
deploy_result = invoke_cli_runner(deploy,
["--environment", "test"])
self.assertEqual(deploy_result.exit_code, 0)
def test_deploy_listed_jobs(self, *args):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {
"test": {
"jobs": [{
"name": "job-1"
}, {
"name": "job-2"
}]
}
}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
deploy_result = invoke_cli_runner(
deploy, ["--environment", "test", "--jobs", "job-1,job-2"])
self.assertEqual(deploy_result.exit_code, 0)
def test_trace_runs(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"dbfs": {}, "jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
deploy_result = invoke_cli_runner(
deploy, ["--environment", "test", "--tags", "cake=cheesecake"])
self.assertEqual(deploy_result.exit_code, 0)
launch_result = invoke_cli_runner(launch, [
"--environment", "test", "--job", "sample", "--tags",
"cake=cheesecake", "--trace"
])
self.assertEqual(launch_result.exit_code, 0)
def test_deploy_with_requirements_and_branch(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
sample_requirements = "\n".join(
["pyspark=3.0.0", "xgboost=0.6.0", "pyspark3d"])
pathlib.Path("runtime_requirements.txt").write_text(
sample_requirements)
with patch(
"mlflow.get_experiment_by_name",
return_value=Experiment("id", None,
f"dbfs:/dbx/{self.project_name}",
None, None),
):
deploy_result = invoke_cli_runner(
deploy,
[
"--environment",
"test",
"--requirements-file",
"runtime_requirements.txt",
"--branch-name",
"test-branch",
],
)
deleted_dependency_lines = [
line for line in deploy_result.stdout.splitlines()
if "pyspark dependency deleted" in line
]
self.assertEqual(len(deleted_dependency_lines), 1)
self.assertEqual(deploy_result.exit_code, 0)
def test_no_runs(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"dbfs": {}, "jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
with patch(
"mlflow.get_experiment_by_name",
return_value=Experiment("id", None,
f"dbfs:/dbx/{self.project_name}",
None, None),
):
deploy_result = invoke_cli_runner(
deploy,
["--environment", "test", "--tags", "cake=cheesecake"])
self.assertEqual(deploy_result.exit_code, 0)
launch_result = invoke_cli_runner(
launch,
[
"--environment",
"test",
"--job",
"sample",
"--tags",
"cake=cheesecake",
],
expected_error=True,
)
self.assertIsNotNone(launch_result.exception)
self.assertTrue("not found in underlying MLflow experiment" in
str(launch_result.exception))
def test_no_runs(self, *args):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"dbfs": {}, "jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
deploy_result = invoke_cli_runner(
deploy, ["--environment", "test", "--tags", "cake=cheesecake"]
)
self.assertEqual(deploy_result.exit_code, 0)
launch_result = invoke_cli_runner(
launch,
[
"--environment",
"test",
"--job",
"sample",
"--tags",
"cake=cheesecake",
],
expected_error=True
)
self.assertIsNotNone(launch_result.exception)
self.assertTrue("No runs provided per given set of filters" in str(launch_result.exception))
def test_deploy_incorrect_artifact_location(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
with patch(
"mlflow.get_experiment_by_name",
return_value=Experiment("id", None,
"dbfs:/some/correct-location",
None, None),
):
deployment_content = {"test": {"jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
sample_config = read_json(INFO_FILE_PATH)
sample_config["environments"]["test"][
"artifact_location"] = "dbfs:/some/another-location"
write_json(sample_config, INFO_FILE_PATH)
deploy_result = invoke_cli_runner(deploy,
["--environment", "test"],
expected_error=True)
self.assertIsInstance(deploy_result.exception, Exception)
self.assertIn(
"Please change the experiment name to create a new experiment",
str(deploy_result.exception))
def test_launch_with_parameters(self, *_):
with self.project_dir:
ws_dir = "/Shared/dbx/projects/%s" % self.project_name
configure_result = invoke_cli_runner(
configure,
[
"--environment",
"test",
"--profile",
self.profile_name,
"--workspace-dir",
ws_dir,
],
)
self.assertEqual(configure_result.exit_code, 0)
deployment_content = {"test": {"dbfs": {}, "jobs": []}}
write_json(deployment_content, DEFAULT_DEPLOYMENT_FILE_PATH)
with patch(
"mlflow.get_experiment_by_name",
return_value=Experiment("id", None,
f"dbfs:/dbx/{self.project_name}",
None, None),
):
deploy_result = invoke_cli_runner(
deploy,
["--environment", "test", "--tags", "cake=cheesecake"])
self.assertEqual(deploy_result.exit_code, 0)
launch_raw = invoke_cli_runner(
launch,
[
"--environment",
"test",
"--job",
"sample",
"--tags",
"cake=cheesecake",
"""--parameters-raw='{"key1": "value1", "key2": 2}'""",
],
)
self.assertEqual(launch_raw.exit_code, 0)
launch_with_params = invoke_cli_runner(
launch,
[
"--environment",
"test",
"--job",
"sample",
"--tags",
"cake=cheesecake",
"--parameters='cake=cheesecake'",
],
)
self.assertEqual(launch_with_params.exit_code, 0)
