def upload_experiments(
client: kfp.Client,
pipeline_name: str,
github_sha: str,
experiment_name: str = "",
) -> str:
"""Function to upload an experiment to Kubeflow Pipelines.
For clarity, the experiment will be registered to Kubeflow Pipelines named like below:
{pipeline_name}-{experiment_name}
If the experiment does not exist, it will be created newly with specified name.
If the experiment is not specified, {pipeline_name}-default will be used.
Args:
client (kfp.Client) : KFP client.
pipeline_name (str) : The name of the pipeline function.
github_sha (str) : GitHub SHA generated in GitHub Actions.
experiment_name (str) : The experiment name. (Optional)
Returns:
str : The ID of the experiment.
"""
register_name = (f"{pipeline_name}-{experiment_name}"
if experiment_name != "Default" else experiment_name)
try:
experiment_id = client.get_experiment(
experiment_name=register_name).to_dict()["id"]
except ValueError:
experiment_id = client.create_experiment(
name=register_name).to_dict()["id"]
logging.info(f"The experiment is newly registered : {register_name}")
return experiment_id
def check(self):
""" Check the pipeline running results of the notebook sample. """
test_cases = []
test_name = self._testname + ' Sample Test'
###### Write the script exit code log ######
utils.add_junit_test(
test_cases, 'test script execution', (self._exit_code == '0'),
'test script failure with exit code: ' + self._exit_code)
try:
with open(DEFAULT_CONFIG, 'r') as f:
raw_args = yaml.safe_load(f)
except yaml.YAMLError as yamlerr:
raise RuntimeError('Illegal default config:{}'.format(yamlerr))
except OSError as ose:
raise FileExistsError('Default config not found:{}'.format(ose))
else:
test_timeout = raw_args['test_timeout']
if self._run_pipeline:
experiment = self._experiment_name
###### Initialization ######
client = Client(host=self._host)
###### Get experiments ######
experiment_id = client.get_experiment(
experiment_name=experiment).id
###### Get runs ######
list_runs_response = client.list_runs(page_size=RUN_LIST_PAGE_SIZE,
experiment_id=experiment_id)
###### Check all runs ######
for run in list_runs_response.runs:
run_id = run.id
response = client.wait_for_run_completion(run_id, test_timeout)
succ = (response.run.status.lower() == 'succeeded')
utils.add_junit_test(test_cases, 'job completion', succ,
'waiting for job completion failure')
###### Output Argo Log for Debugging ######
workflow_json = client._get_workflow_json(run_id)
workflow_id = workflow_json['metadata']['name']
print("Argo Workflow Name: ", workflow_id)
argo_log, _ = utils.run_bash_command(
'argo logs {} -n {}'.format(workflow_id, self._namespace))
print("=========Argo Workflow Log=========")
print(argo_log)
if not succ:
utils.write_junit_xml(test_name, self._result, test_cases)
exit(1)
###### Write out the test result in junit xml ######
utils.write_junit_xml(test_name, self._result, test_cases)
def run_pipeline_func(client: kfp.Client,
pipeline_name: str,
pipeline_id: str,
pipeline_paramters_path: dict,
recurring_flag: bool = False,
cron_exp: str = ''):
pipeline_params = read_pipeline_params(
pipeline_paramters_path=pipeline_paramters_path)
pipeline_params = pipeline_params if pipeline_params is not None else {}
experiment_id = None
experiment_name = "{}-{}".format(pipeline_name,
os.environ["INPUT_EXPERIMENT_NAME"])
try:
experiment_id = client.get_experiment(
experiment_name=experiment_name).to_dict()["id"]
except ValueError:
experiment_id = client.create_experiment(
name=experiment_name).to_dict()["id"]
namespace = os.getenv("INPUT_PIPELINE_NAMESPACE") if not str.isspace(
os.getenv("INPUT_PIPELINE_NAMESPACE")) else None
job_name = 'Run {} on {}'.format(
pipeline_name,
datetime.now().strftime("%Y-%m-%d %H:%M:%S"))
logging.info(f"experiment_id: {experiment_id}, \
job_name: {job_name}, \
pipeline_params: {pipeline_params}, \
pipeline_id: {pipeline_id}, \
namespace: {namespace}, \
cron_exp: {cron_exp}")
if recurring_flag == "true":
client.create_recurring_run(experiment_id=experiment_id,
job_name=job_name,
params=pipeline_params,
pipeline_id=pipeline_id,
cron_expression=cron_exp)
logging.info(
"Successfully started the recurring pipeline, head over to kubeflow to check it out"
)
client.run_pipeline(experiment_id=experiment_id,
job_name=job_name,
params=pipeline_params,
pipeline_id=pipeline_id)
logging.info(
"Successfully started the pipeline, head over to kubeflow to check it out"
)
def main():
args = parse_arguments()
test_cases = []
test_name = args.testname + ' Sample Test'
###### Write the script exit code log ######
utils.add_junit_test(
test_cases, 'test script execution', (args.exit_code == '0'),
'test script failure with exit code: ' + args.exit_code)
if args.experiment is not None:
###### Initialization ######
host = 'ml-pipeline.%s.svc.cluster.local:8888' % args.namespace
client = Client(host=host)
###### Get experiments ######
experiment_id = client.get_experiment(
experiment_name=args.experiment).id
###### Get runs ######
list_runs_response = client.list_runs(page_size=1000,
experiment_id=experiment_id)
###### Check all runs ######
for run in list_runs_response.runs:
run_id = run.id
response = client.wait_for_run_completion(run_id, 1200)
succ = (response.run.status.lower() == 'succeeded')
utils.add_junit_test(test_cases, 'job completion', succ,
'waiting for job completion failure')
###### Output Argo Log for Debugging ######
workflow_json = client._get_workflow_json(run_id)
workflow_id = workflow_json['metadata']['name']
argo_log, _ = utils.run_bash_command(
'argo logs -n {} -w {}'.format(args.namespace, workflow_id))
print("=========Argo Workflow Log=========")
print(argo_log)
if not succ:
utils.write_junit_xml(test_name, args.result, test_cases)
exit(1)
###### Write out the test result in junit xml ######
utils.write_junit_xml(test_name, args.result, test_cases)
def check(self):
test_cases = []
test_name = self._testname + ' Sample Test'
###### Write the script exit code log ######
utils.add_junit_test(test_cases, 'test script execution',
(self._exit_code == '0'),
'test script failure with exit code: '
+ self._exit_code)
if self._experiment is not None: # Bypassing dsl type check sample.
###### Initialization ######
host = 'ml-pipeline.%s.svc.cluster.local:8888' % self._namespace
client = Client(host=host)
###### Get experiments ######
experiment_id = client.get_experiment(experiment_name=self._experiment).id
###### Get runs ######
list_runs_response = client.list_runs(page_size=_RUN_LIST_PAGE_SIZE,
experiment_id=experiment_id)
###### Check all runs ######
for run in list_runs_response.runs:
run_id = run.id
response = client.wait_for_run_completion(run_id, _TEST_TIMEOUT)
succ = (response.run.status.lower()=='succeeded')
utils.add_junit_test(test_cases, 'job completion',
succ, 'waiting for job completion failure')
###### Output Argo Log for Debugging ######
workflow_json = client._get_workflow_json(run_id)
workflow_id = workflow_json['metadata']['name']
argo_log, _ = utils.run_bash_command(
'argo logs -n {} -w {}'.format(self._namespace, workflow_id))
print("=========Argo Workflow Log=========")
print(argo_log)
if not succ:
utils.write_junit_xml(test_name, self._result, test_cases)
exit(1)
###### Write out the test result in junit xml ######
utils.write_junit_xml(test_name, self._result, test_cases)
class KubeflowClient(object):
log = logging.getLogger(__name__)
def __init__(self, config, project_name, context):
token = AuthHandler().obtain_id_token()
self.host = config.host
self.client = Client(self.host, existing_token=token)
self.project_name = project_name
self.pipeline_description = config.run_config.description
self.generator = PipelineGenerator(config, project_name, context)
def list_pipelines(self):
pipelines = self.client.list_pipelines(page_size=30).pipelines
return tabulate(map(lambda x: [x.name, x.id], pipelines),
headers=["Name", "ID"])
def run_once(
self,
pipeline,
image,
experiment_name,
run_name,
wait,
image_pull_policy="IfNotPresent",
) -> None:
run = self.client.create_run_from_pipeline_func(
self.generator.generate_pipeline(pipeline, image,
image_pull_policy),
arguments={},
experiment_name=experiment_name,
run_name=run_name,
)
if wait:
run.wait_for_run_completion(timeout=WAIT_TIMEOUT)
def compile(self,
pipeline,
image,
output,
image_pull_policy="IfNotPresent"):
Compiler().compile(
self.generator.generate_pipeline(pipeline, image,
image_pull_policy),
output,
)
self.log.info("Generated pipeline definition was saved to %s" % output)
def upload(self, pipeline, image, image_pull_policy="IfNotPresent"):
pipeline = self.generator.generate_pipeline(pipeline, image,
image_pull_policy)
if self._pipeline_exists(self.project_name):
pipeline_id = self._get_pipeline_id(self.project_name)
version_id = self._upload_pipeline_version(pipeline, pipeline_id)
self.log.info("New version of pipeline created: %s", version_id)
else:
(pipeline_id, version_id) = self._upload_pipeline(pipeline)
self.log.info("Pipeline created")
self.log.info(
f"Pipeline link: {self.host}/#/pipelines/details/%s/version/%s",
pipeline_id,
version_id,
)
def _pipeline_exists(self, pipeline_name):
return self._get_pipeline_id(pipeline_name) is not None
def _get_pipeline_id(self, pipeline_name):
pipelines = self.client.pipelines.list_pipelines(filter=json.dumps({
"predicates": [{
"key": "name",
"op": 1,
"string_value": pipeline_name,
}]
})).pipelines
if pipelines:
return pipelines[0].id
def _upload_pipeline_version(self, pipeline_func, pipeline_id):
version_name = f"{clean_name(self.project_name)}-{uuid.uuid4()}"[:100]
with NamedTemporaryFile(suffix=".yaml") as f:
Compiler().compile(pipeline_func, f.name)
return self.client.pipeline_uploads.upload_pipeline_version(
f.name,
name=version_name,
pipelineid=pipeline_id,
_request_timeout=10000,
).id
def _upload_pipeline(self, pipeline_func):
with NamedTemporaryFile(suffix=".yaml") as f:
Compiler().compile(pipeline_func, f.name)
pipeline = self.client.pipeline_uploads.upload_pipeline(
f.name,
name=self.project_name,
description=self.pipeline_description,
_request_timeout=10000,
)
return (pipeline.id, pipeline.default_version.id)
def _ensure_experiment_exists(self, experiment_name):
try:
experiment = self.client.get_experiment(
experiment_name=experiment_name)
self.log.info(f"Existing experiment found: {experiment.id}")
except ValueError as e:
if not str(e).startswith("No experiment is found"):
raise
experiment = self.client.create_experiment(experiment_name)
self.log.info(f"New experiment created: {experiment.id}")
return experiment.id
def schedule(self, experiment_name, cron_expression):
experiment_id = self._ensure_experiment_exists(experiment_name)
pipeline_id = self._get_pipeline_id(self.project_name)
self._disable_runs(experiment_id, pipeline_id)
self.client.create_recurring_run(
experiment_id,
f"{self.project_name} on {cron_expression}",
cron_expression=cron_expression,
pipeline_id=pipeline_id,
)
self.log.info("Pipeline scheduled to %s", cron_expression)
def _disable_runs(self, experiment_id, pipeline_id):
runs = self.client.list_recurring_runs(experiment_id=experiment_id)
if runs.jobs is not None:
my_runs = [
job for job in runs.jobs
if job.pipeline_spec.pipeline_id == pipeline_id
]
for job in my_runs:
self.client.jobs.delete_job(job.id)
self.log.info(f"Previous schedule deleted {job.id}")
class KubeflowClient(object):
log = logging.getLogger(__name__)
def __init__(self, config, project_name, context):
token = self.obtain_id_token()
self.host = config.host
self.client = Client(self.host, existing_token=token)
self.project_name = project_name
self.context = context
dsl.ContainerOp._DISABLE_REUSABLE_COMPONENT_WARNING = True
self.volume_meta = config.run_config.volume
def list_pipelines(self):
pipelines = self.client.list_pipelines(page_size=30).pipelines
return tabulate(map(lambda x: [x.name, x.id], pipelines),
headers=["Name", "ID"])
def run_once(
self,
pipeline,
image,
experiment_name,
run_name,
wait,
image_pull_policy="IfNotPresent",
) -> None:
run = self.client.create_run_from_pipeline_func(
self.generate_pipeline(pipeline, image, image_pull_policy),
arguments={},
experiment_name=experiment_name,
run_name=run_name,
)
if wait:
run.wait_for_run_completion(timeout=WAIT_TIMEOUT)
def obtain_id_token(self):
from google.auth.transport.requests import Request
from google.oauth2 import id_token
from google.auth.exceptions import DefaultCredentialsError
client_id = os.environ.get(IAP_CLIENT_ID, None)
jwt_token = None
if not client_id:
self.log.info(
"No IAP_CLIENT_ID provided, skipping custom IAP authentication"
)
return jwt_token
try:
self.log.debug("Obtaining JWT token for %s." + client_id)
jwt_token = id_token.fetch_id_token(Request(), client_id)
self.log.info("Obtained JWT token for MLFLOW connectivity.")
except DefaultCredentialsError as ex:
self.log.warning(
str(ex) +
(" Note that this authentication method does not work with default"
" credentials obtained via 'gcloud auth application-default login'"
" command. Refer to documentation on how to configure service account"
" locally"
" (https://cloud.google.com/docs/authentication/production#manually)"
))
except Exception as e:
self.log.error("Failed to obtain IAP access token. " + str(e))
finally:
return jwt_token
def generate_pipeline(self, pipeline, image, image_pull_policy):
@dsl.pipeline(
name=self.project_name,
description="Kubeflow pipeline for Kedro project",
)
def convert_kedro_pipeline_to_kfp() -> None:
"""Convert from a Kedro pipeline into a kfp container graph."""
node_volumes = (_setup_volumes()
if self.volume_meta is not None else {})
node_dependencies = self.context.pipelines.get(
pipeline).node_dependencies
kfp_ops = _build_kfp_ops(node_dependencies, node_volumes)
for node, dependencies in node_dependencies.items():
for dependency in dependencies:
kfp_ops[node.name].after(kfp_ops[dependency.name])
def _setup_volumes():
vop = dsl.VolumeOp(
name="data-volume-create",
resource_name="data-volume",
size=self.volume_meta.size,
modes=self.volume_meta.access_modes,
storage_class=self.volume_meta.storageclass,
)
if self.volume_meta.skip_init:
return {"/home/kedro/data": vop.volume}
else:
volume_init = dsl.ContainerOp(
name="data-volume-init",
image=image,
command=["sh", "-c"],
arguments=[
" ".join([
"cp",
"--verbose",
"-r",
"/home/kedro/data/*",
"/home/kedro/datavolume",
])
],
pvolumes={"/home/kedro/datavolume": vop.volume},
)
volume_init.container.set_image_pull_policy(image_pull_policy)
return {"/home/kedro/data": volume_init.pvolume}
def _build_kfp_ops(node_dependencies: Dict[Node, Set[Node]],
node_volumes: Dict) -> Dict[str, dsl.ContainerOp]:
"""Build kfp container graph from Kedro node dependencies. """
kfp_ops = {}
env = [
V1EnvVar(name=IAP_CLIENT_ID,
value=os.environ.get(IAP_CLIENT_ID, ""))
]
if is_mlflow_enabled():
kfp_ops["mlflow-start-run"] = dsl.ContainerOp(
name="mlflow-start-run",
image=image,
command=["kedro"],
arguments=[
"kubeflow",
"mlflow-start",
dsl.RUN_ID_PLACEHOLDER,
],
file_outputs={"mlflow_run_id": "/tmp/mlflow_run_id"},
)
kfp_ops["mlflow-start-run"].container.set_image_pull_policy(
image_pull_policy)
env.append(
V1EnvVar(
name="MLFLOW_RUN_ID",
value=kfp_ops["mlflow-start-run"].output,
))
for node in node_dependencies:
name = _clean_name(node.name)
kfp_ops[node.name] = dsl.ContainerOp(
name=name,
image=image,
command=["kedro"],
arguments=["run", "--node", node.name],
pvolumes=node_volumes,
container_kwargs={"env": env},
)
kfp_ops[node.name].container.set_image_pull_policy(
image_pull_policy)
return kfp_ops
return convert_kedro_pipeline_to_kfp
def compile(self,
pipeline,
image,
output,
image_pull_policy="IfNotPresent"):
Compiler().compile(
self.generate_pipeline(pipeline, image, image_pull_policy), output)
self.log.info("Generated pipeline definition was saved to %s" % output)
def upload(self, pipeline, image, image_pull_policy="IfNotPresent"):
pipeline = self.generate_pipeline(pipeline, image, image_pull_policy)
if self._pipeline_exists(self.project_name):
pipeline_id = self._get_pipeline_id(self.project_name)
version_id = self._upload_pipeline_version(pipeline, pipeline_id,
self.project_name)
self.log.info("New version of pipeline created: %s", version_id)
else:
(pipeline_id,
version_id) = self._upload_pipeline(pipeline, self.project_name)
self.log.info("Pipeline created")
self.log.info(
f"Pipeline link: {self.host}/#/pipelines/details/%s/version/%s",
pipeline_id,
version_id,
)
def _pipeline_exists(self, pipeline_name):
return self._get_pipeline_id(pipeline_name) is not None
def _get_pipeline_id(self, pipeline_name):
pipelines = self.client.pipelines.list_pipelines(filter=json.dumps({
"predicates": [{
"key": "name",
"op": 1,
"string_value": pipeline_name,
}]
})).pipelines
if pipelines:
return pipelines[0].id
def _upload_pipeline_version(self, pipeline_func, pipeline_id,
pipeline_name):
version_name = f"{_clean_name(pipeline_name)}-{uuid.uuid4()}"[:100]
with NamedTemporaryFile(suffix=".yaml") as f:
Compiler().compile(pipeline_func, f.name)
return self.client.pipeline_uploads.upload_pipeline_version(
f.name, name=version_name, pipelineid=pipeline_id).id
def _upload_pipeline(self, pipeline_func, pipeline_name):
with NamedTemporaryFile(suffix=".yaml") as f:
Compiler().compile(pipeline_func, f.name)
pipeline = self.client.pipeline_uploads.upload_pipeline(
f.name, name=pipeline_name)
return (pipeline.id, pipeline.default_version.id)
def _ensure_experiment_exists(self, experiment_name):
try:
experiment = self.client.get_experiment(
experiment_name=experiment_name)
self.log.info(f"Existing experiment found: {experiment.id}")
except ValueError as e:
if not str(e).startswith("No experiment is found"):
raise
experiment = self.client.create_experiment(experiment_name)
self.log.info(f"New experiment created: {experiment.id}")
return experiment.id
def schedule(self, experiment_name, cron_expression):
experiment_id = self._ensure_experiment_exists(experiment_name)
pipeline_id = self._get_pipeline_id(self.project_name)
self._disable_runs(experiment_id, pipeline_id)
self.client.create_recurring_run(
experiment_id,
f"{self.project_name} on {cron_expression}",
cron_expression=cron_expression,
pipeline_id=pipeline_id,
)
self.log.info("Pipeline scheduled to %s", cron_expression)
def _disable_runs(self, experiment_id, pipeline_id):
runs = self.client.list_recurring_runs(experiment_id=experiment_id)
if runs.jobs is not None:
my_runs = [
job for job in runs.jobs
if job.pipeline_spec.pipeline_id == pipeline_id
]
for job in my_runs:
self.client.jobs.delete_job(job.id)
self.log.info(f"Previous schedule deleted {job.id}")
