def compile_notebook(request, source_notebook_path,
notebook_metadata_overrides=None, debug=False):
"""Compile the notebook to KFP DSL."""
instance = Kale(source_notebook_path, notebook_metadata_overrides, debug)
instance.logger = request.log if hasattr(request, "log") else logger
pipeline_graph, pipeline_parameters = instance.notebook_to_graph()
script_path = instance.generate_kfp_executable(pipeline_graph,
pipeline_parameters)
pipeline_name = instance.pipeline_metadata["pipeline_name"]
package_path = kfputils.compile_pipeline(script_path, pipeline_name)
return {"pipeline_package_path": os.path.relpath(package_path),
"pipeline_metadata": instance.pipeline_metadata}
def main():
parser = argparse.ArgumentParser(description=ARGS_DESC, formatter_class=RawTextHelpFormatter)
general_group = parser.add_argument_group('General')
general_group.add_argument('--nb', type=str, help='Path to source JupyterNotebook', required=True)
# use store_const instead of store_true because we None instead of False in case the flag is missing
general_group.add_argument('--upload_pipeline', action='store_const', const=True)
general_group.add_argument('--run_pipeline', action='store_const', const=True)
general_group.add_argument('--debug', action='store_true')
metadata_group = parser.add_argument_group('Notebook Metadata Overrides', METADATA_GROUP_DESC)
metadata_group.add_argument('--experiment_name', type=str, help='Name of the created experiment')
metadata_group.add_argument('--pipeline_name', type=str, help='Name of the deployed pipeline')
metadata_group.add_argument('--pipeline_description', type=str, help='Description of the deployed pipeline')
metadata_group.add_argument('--docker_image', type=str, help='Docker base image used to build the pipeline steps')
metadata_group.add_argument('--kfp_host', type=str, help='KFP endpoint. Provide address as <host>:<port>.')
args = parser.parse_args()
# get the notebook metadata args group
metadata_overrides_group = next(filter(lambda x: x.title == 'Notebook Metadata Overrides', parser._action_groups))
# get the single args of that group
metadata_overrides_group_dict = {a.dest: getattr(args, a.dest, None) for a in metadata_overrides_group._group_actions}
kale = Kale(
source_notebook_path=args.nb,
notebook_metadata_overrides=metadata_overrides_group_dict,
debug=args.debug
)
pipeline_graph, pipeline_parameters = kale.notebook_to_graph()
script_path = kale.generate_kfp_executable(pipeline_graph, pipeline_parameters)
# compile the pipeline to kfp tar package
pipeline_package_path = kfp_utils.compile_pipeline(script_path, kale.pipeline_metadata['pipeline_name'])
if args.upload_pipeline:
kfp_utils.upload_pipeline(
pipeline_package_path=pipeline_package_path,
pipeline_name=kale.pipeline_metadata['pipeline_name'],
host=kale.pipeline_metadata.get('kfp_host', None)
)
if args.run_pipeline:
kfp_utils.run_pipeline(
run_name=kale.pipeline_metadata['pipeline_name'] + '_run',
experiment_name=kale.pipeline_metadata['experiment_name'],
pipeline_package_path=pipeline_package_path,
host=kale.pipeline_metadata.get('kfp_host', None)
)
def compile_notebook(source_notebook_path,
notebook_metadata_overrides=None,
debug=False,
auto_snapshot=False):
instance = Kale(source_notebook_path, notebook_metadata_overrides, debug,
auto_snapshot)
pipeline_graph, pipeline_parameters = instance.notebook_to_graph()
script_path = instance.generate_kfp_executable(pipeline_graph,
pipeline_parameters)
pipeline_name = instance.pipeline_metadata["pipeline_name"]
package_path = kfp_utils.compile_pipeline(script_path, pipeline_name)
return {
"pipeline_package_path": package_path,
"pipeline_metadata": instance.pipeline_metadata
}
def test_pipeline_generation_from_local(random_string, abs_working_dir):
"""Test code generation end to end from notebook to DSL."""
abs_working_dir.return_value = '/kale'
random_string.return_value = 'rnd'
notebook_path = "../assets/notebooks/pipeline_parameters_and_metrics.ipynb"
notebook_path = os.path.join(THIS_DIR, notebook_path)
kale = Kale(source_notebook_path=notebook_path)
kale.logger = logging.getLogger(__name__)
kale.logger.setLevel(logging.DEBUG)
pipeline_graph, pipeline_parameters = kale.notebook_to_graph()
script_path = kale.generate_kfp_executable(pipeline_graph,
pipeline_parameters,
save_to_tmp=True)
target_asset = os.path.join(THIS_DIR, '../assets/kfp_dsl/',
'pipeline_parameters_and_metrics.py')
expected_result = open(target_asset).read()
result = open(script_path).read()
assert result == expected_result
def test_pipeline_generation_from_gtihub(random_string, abs_working_dir):
"""Test code generation end to end from notebook to DSL."""
abs_working_dir.return_value = '/kale'
random_string.return_value = 'rnd'
notebook_url = EX_REPO + "titanic-ml-dataset/titanic_dataset_ml.ipynb"
# download notebook to tmp dir
notebook_path, response = urlretrieve(notebook_url)
kale = Kale(source_notebook_path=notebook_path)
kale.logger = logging.getLogger(__name__)
kale.logger.setLevel(logging.DEBUG)
pipeline_graph, pipeline_parameters = kale.notebook_to_graph()
script_path = kale.generate_kfp_executable(pipeline_graph,
pipeline_parameters,
save_to_tmp=True)
target_asset = os.path.join(THIS_DIR, '../assets/kfp_dsl/', 'titanic.py')
expected_result = open(target_asset).read()
result = open(script_path).read()
assert result == expected_result
def test_pipeline_generation_from_local(random_string, abs_working_dir):
"""Test code generation end to end from notebook to DSL."""
abs_working_dir.return_value = '/kale'
random_string.return_value = 'rnd'
notebook_path = "../assets/notebooks/pipeline_parameters_and_metrics.ipynb"
notebook_path = os.path.join(THIS_DIR, notebook_path)
kale = Kale(source_notebook_path=notebook_path)
pipeline_graph, pipeline_parameters = kale.notebook_to_graph()
script_path = kale.generate_kfp_executable(pipeline_graph,
pipeline_parameters,
save_to_tmp=True)
# TODO: Need to suppress log generation when running tests
os.remove(os.path.join(os.getcwd(), 'kale.log'))
target_asset = os.path.join(THIS_DIR, '../assets/kfp_dsl/',
'pipeline_parameters_and_metrics.py')
expected_result = open(target_asset).read()
result = open(script_path).read()
assert result == expected_result
