def main(
tags: Iterable[str] = None,
env: str = None,
runner: str = None,
):
"""Application main entry point.
Args:
tags: An optional list of node tags which should be used to
filter the nodes of the ``Pipeline``. If specified, only the nodes
containing *any* of these tags will be added to the ``Pipeline``.
env: An optional parameter specifying the environment in which
the ``Pipeline`` should be run. If not specified defaults to "local".
runner: An optional parameter specifying the runner that you want to run
the pipeline with.
Raises:
KedroCliError: If the resulting ``Pipeline`` is empty.
"""
# Report project name
logging.info("** Kedro project {}".format(Path.cwd().name))
# Load Catalog
conf = get_config(project_path=str(Path.cwd()), env=env)
catalog = create_catalog(config=conf)
# Load the pipeline
pipeline = create_pipeline()
pipeline = pipeline.only_nodes_with_tags(*tags) if tags else pipeline
if not pipeline.nodes:
if tags:
raise KedroCliError("Pipeline contains no nodes with tags: " +
str(tags))
raise KedroCliError("Pipeline contains no nodes")
# Load the runner
# When either --parallel or --runner is used, class_obj is assigned to runner
runner = load_obj(runner, "kedro.runner") if runner else SequentialRunner
# Initialise SparkSession
spark = init_spark_session()
# Run the runner
#runner().run(pipeline, catalog)
# Run the pipeline
#io.add_feed_dict({'parameters': parameters}, replace=True)
SequentialRunner().run(pipeline, catalog)
def pipeline(self) -> Pipeline:
return create_pipeline()