def run_project(project_root_path):
af.set_project_config_file(project_root_path + '/project.yaml')
# Config command line job, we set platform to local and engine to cmd_line here
cmd_job_config = af.BaseJobConfig(platform=LocalPlatform.platform(), engine=CMDEngine().engine())
with af.config(cmd_job_config):
# Command line job executor
cmd_job = af.user_define_operation(executor=CmdExecutor(cmd_line="echo Start AI flow"))
# Config python job, we set platform to local and engine to python here
python_job_config = af.BaseJobConfig(platform=LocalPlatform.platform(), engine=PythonEngine.engine())
# Set execution mode of this python job to BATCH,
# which indicates jobs with this config is running in the form of batch.
python_job_config.exec_mode = af.ExecutionMode.BATCH
with af.config(python_job_config):
# Path of Source data(under '..../simple_transform_airflow' dir)
source_path = os.path.dirname(os.path.abspath(__file__)) + '/source_data.csv'
# Path of Sink data
sink_path = os.path.dirname(os.path.abspath(__file__)) + '/sink_data.csv'
# To make the project replaceable, we register the example in metadata service
read_example_meta = af.register_example(name='read_example', support_type=ExampleSupportType.EXAMPLE_BATCH,
data_format='csv', data_type='pandas', batch_uri=source_path)
# Read training example using af.read_example()
# example_info is the meta information of the example
read_example_channel = af.read_example(example_info=read_example_meta, exec_args=ExecuteArgs(
batch_properties=Args(header=None, names=["a", "b", "c"])))
# Transform examples using af.transform()
transform_channel = af.transform(input_data_list=[read_example_channel],
executor=PythonObjectExecutor(python_object=SimpleTransform()))
write_example_meta = af.register_example(name='write_example', support_type=ExampleSupportType.EXAMPLE_BATCH,
data_format='csv', data_type='pandas', batch_uri=sink_path)
# Write example to specific path
write = af.write_example(input_data=transform_channel, example_info=write_example_meta,
exec_args=ExecuteArgs(batch_properties=Args(sep=',', header=False, index=False)))
# Add control dependency, which means read_example job will start right after command line job finishes.
af.stop_before_control_dependency(read_example_channel, cmd_job)
transform_dag = 'simple_transform'
af.deploy_to_airflow(project_root_path, dag_id=transform_dag)
context = af.run(project_path=project_root_path,
dag_id=transform_dag,
scheduler_type=SchedulerType.AIRFLOW)
def __init__(self):
super().__init__(platform=LocalPlatform.platform(),
engine=CMDEngine.engine())
def __init__(self):
super().__init__(engine=CMDEngine.engine())