def main():
af.init_ai_flow_context()
with af.job_config('task_1'):
af.user_define_operation(BashProcessor("sleep 30"))
with af.job_config('task_2'):
af.user_define_operation(BashProcessor("sleep 60"))
with af.job_config('task_3'):
af.user_define_operation(BashProcessor("echo hello"))
af.action_on_job_status('task_2',
'task_1',
upstream_job_status=Status.RUNNING,
action=JobAction.START)
af.action_on_job_status('task_2',
'task_1',
upstream_job_status=Status.FINISHED,
action=JobAction.STOP)
af.action_on_job_status('task_3',
'task_1',
upstream_job_status=Status.RUNNING,
action=JobAction.START)
af.action_on_job_status('task_3',
'task_2',
upstream_job_status=Status.KILLED,
action=JobAction.RESTART)
workflow_name = af.current_workflow_config().workflow_name
stop_workflow_executions(workflow_name)
af.workflow_operation.submit_workflow(workflow_name)
af.workflow_operation.start_new_workflow_execution(workflow_name)
def main():
af.init_ai_flow_context()
with af.job_config('task_1'):
af.user_define_operation(BashProcessor("echo hello"))
with af.job_config('task_2'):
af.user_define_operation(BashProcessor("echo hello"))
af.action_on_job_status('task_2', 'task_1')
workflow_name = af.current_workflow_config().workflow_name
stop_workflow_executions(workflow_name)
af.workflow_operation.submit_workflow(workflow_name)
af.workflow_operation.start_new_workflow_execution(workflow_name)
def run_workflow():
# Init project
af.init_ai_flow_context()
artifact_prefix = af.current_project_config().get_project_name() + "."
# Training of model
with af.job_config('train'):
# Register metadata of training data(dataset) and read dataset(i.e. training dataset)
train_dataset = af.register_dataset(name=artifact_prefix + 'train_dataset',
uri=DATASET_URI.format('train'))
train_read_dataset = af.read_dataset(dataset_info=train_dataset,
read_dataset_processor=DatasetReader())
# Register model metadata and train model
train_model = af.register_model(model_name=artifact_prefix + 'KNN',
model_desc='KNN model')
train_channel = af.train(input=[train_read_dataset],
training_processor=ModelTrainer(),
model_info=train_model)
# Validation of model
with af.job_config('validate'):
# Read validation dataset
validate_dataset = af.register_dataset(name=artifact_prefix + 'validate_dataset',
uri=DATASET_URI.format('test'))
# Validate model before it is used to predict
validate_read_dataset = af.read_dataset(dataset_info=validate_dataset,
read_dataset_processor=ValidateDatasetReader())
validate_artifact_name = artifact_prefix + 'validate_artifact'
validate_artifact = af.register_artifact(name=validate_artifact_name,
uri=get_file_dir(__file__) + '/validate_result')
validate_channel = af.model_validate(input=[validate_read_dataset],
model_info=train_model,
model_validation_processor=ModelValidator(validate_artifact_name))
# Prediction(Inference) using flink
with af.job_config('predict'):
# Read test data and do prediction
predict_dataset = af.register_dataset(name=artifact_prefix + 'predict_dataset',
uri=DATASET_URI.format('test'))
predict_read_dataset = af.read_dataset(dataset_info=predict_dataset,
read_dataset_processor=Source())
predict_channel = af.predict(input=[predict_read_dataset],
model_info=train_model,
prediction_processor=Predictor())
# Save prediction result
write_dataset = af.register_dataset(name=artifact_prefix + 'write_dataset',
uri=get_file_dir(__file__) + '/predict_result.csv')
af.write_dataset(input=predict_channel,
dataset_info=write_dataset,
write_dataset_processor=Sink())
# Define relation graph connected by control edge: train -> validate -> predict
af.action_on_model_version_event(job_name='validate',
model_version_event_type=ModelVersionEventType.MODEL_GENERATED,
model_name=train_model.name)
af.action_on_model_version_event(job_name='predict',
model_version_event_type=ModelVersionEventType.MODEL_VALIDATED,
model_name=train_model.name)
# Submit workflow
af.workflow_operation.submit_workflow(af.current_workflow_config().workflow_name)
# Run workflow
af.workflow_operation.start_new_workflow_execution(af.current_workflow_config().workflow_name)
def setUp(self):
self.master._clear_db()
af.current_graph().clear_graph()
init_ai_flow_context()
def run_workflow():
af.init_ai_flow_context()
artifact_prefix = af.current_project_config().get_project_name() + "."
# the config of train job is a periodic job which means it will
# run every `interval`(defined in workflow_config.yaml) seconds
with af.job_config('train'):
# Register metadata raw training data(dataset) and read dataset(i.e. training dataset)
train_dataset = af.register_dataset(name=artifact_prefix +
'train_dataset',
uri=DATASET_URI.format('train'))
train_read_dataset = af.read_dataset(
dataset_info=train_dataset, read_dataset_processor=DatasetReader())
# Transform(preprocessing) dataset
train_transform = af.transform(
input=[train_read_dataset],
transform_processor=DatasetTransformer())
# Register model metadata and train model
train_model = af.register_model(model_name=artifact_prefix +
'logistic-regression',
model_desc='logistic regression model')
train_channel = af.train(input=[train_transform],
training_processor=ModelTrainer(),
model_info=train_model)
with af.job_config('validate'):
# Validation of model
# Read validation dataset and validate model before it is used to predict
validate_dataset = af.register_dataset(
name=artifact_prefix + 'validate_dataset',
uri=DATASET_URI.format('evaluate'))
validate_read_dataset = af.read_dataset(
dataset_info=validate_dataset,
read_dataset_processor=ValidateDatasetReader())
validate_transform = af.transform(
input=[validate_read_dataset],
transform_processor=ValidateTransformer())
validate_artifact_name = artifact_prefix + 'validate_artifact'
validate_artifact = af.register_artifact(name=validate_artifact_name,
uri=get_file_dir(__file__) +
'/validate_result')
validate_channel = af.model_validate(
input=[validate_transform],
model_info=train_model,
model_validation_processor=ModelValidator(validate_artifact_name))
with af.job_config('push'):
# Push model to serving
# Register metadata of pushed model
push_model_artifact_name = artifact_prefix + 'push_model_artifact'
push_model_artifact = af.register_artifact(
name=push_model_artifact_name,
uri=get_file_dir(__file__) + '/pushed_model')
af.push_model(
model_info=train_model,
pushing_model_processor=ModelPusher(push_model_artifact_name))
with af.job_config('predict'):
# Prediction(Inference)
predict_dataset = af.register_dataset(
name=artifact_prefix + 'predict_dataset',
uri=DATASET_URI.format('predict'))
predict_read_dataset = af.read_dataset(
dataset_info=predict_dataset,
read_dataset_processor=PredictDatasetReader())
predict_transform = af.transform(
input=[predict_read_dataset],
transform_processor=PredictTransformer())
predict_channel = af.predict(input=[predict_transform],
model_info=train_model,
prediction_processor=ModelPredictor())
# Save prediction result
write_dataset = af.register_dataset(
name=artifact_prefix + 'write_dataset',
uri=get_file_dir(__file__) + '/predict_result')
af.write_dataset(input=predict_channel,
dataset_info=write_dataset,
write_dataset_processor=DatasetWriter())
# Define relation graph connected by control edge:
# Once a round of training is done, validator will be launched and
# pusher will be launched if the new model is better.
# Prediction will start once the first round of training is done and
# when pusher pushes(deploys) a new model, the predictor will use the latest deployed model as well.
af.action_on_model_version_event(
job_name='validate',
model_version_event_type=ModelVersionEventType.MODEL_GENERATED,
model_name=train_model.name)
af.action_on_model_version_event(
job_name='push',
model_version_event_type=ModelVersionEventType.MODEL_VALIDATED,
model_name=train_model.name)
# Run workflow
af.workflow_operation.submit_workflow(
af.current_workflow_config().workflow_name)
af.workflow_operation.start_new_workflow_execution(
af.current_workflow_config().workflow_name)
def run_workflow():
af.init_ai_flow_context()
artifact_prefix = af.current_project_config().get_project_name() + "."
with af.job_config('train'):
# Register metadata raw training data(dataset) and read dataset(i.e. training dataset)
train_dataset = af.register_dataset(name=artifact_prefix +
'train_dataset',
uri=DATASET_URI.format('train'))
train_read_dataset = af.read_dataset(
dataset_info=train_dataset,
read_dataset_processor=TrainDatasetReader())
train_transform = af.transform(
input=[train_read_dataset],
transform_processor=TrainDatasetTransformer())
train_model = af.register_model(model_name=artifact_prefix +
'logistic-regression',
model_desc='logistic regression model')
train_channel = af.train(input=[train_transform],
training_processor=ModelTrainer(),
model_info=train_model)
with af.job_config('validate'):
validate_dataset = af.register_dataset(
name=artifact_prefix + 'validate_dataset',
uri=DATASET_URI.format('evaluate'))
validate_read_dataset = af.read_dataset(
dataset_info=validate_dataset,
read_dataset_processor=ValidateDatasetReader())
validate_transform = af.transform(
input=[validate_read_dataset],
transform_processor=ValidateTransformer())
validate_artifact_name = artifact_prefix + 'validate_artifact'
validate_artifact = af.register_artifact(name=validate_artifact_name,
uri=get_file_dir(__file__) +
'/validate_result')
validate_channel = af.model_validate(
input=[validate_transform],
model_info=train_model,
model_validation_processor=ModelValidator(validate_artifact_name))
with af.job_config('push'):
# Push model to serving
# Register metadata of pushed model
push_model_artifact_name = artifact_prefix + 'push_model_artifact'
push_model_artifact = af.register_artifact(
name=push_model_artifact_name,
uri=get_file_dir(__file__) + '/pushed_model')
af.push_model(
model_info=train_model,
pushing_model_processor=ModelPusher(push_model_artifact_name))
with af.job_config('predict'):
predict_dataset = af.register_dataset(
name=artifact_prefix + 'predict_dataset',
uri=DATASET_URI.format('predict'))
predict_read_dataset = af.read_dataset(
dataset_info=predict_dataset,
read_dataset_processor=PredictDatasetReader())
predict_transform = af.transform(
input=[predict_read_dataset],
transform_processor=PredictTransformer())
predict_channel = af.predict(input=[predict_transform],
model_info=train_model,
prediction_processor=ModelPredictor())
write_dataset = af.register_dataset(
name=artifact_prefix + 'export_dataset',
uri=get_file_dir(__file__) + '/predict_result')
af.write_dataset(input=predict_channel,
dataset_info=write_dataset,
write_dataset_processor=DatasetWriter())
af.action_on_model_version_event(
job_name='validate',
model_version_event_type=ModelVersionEventType.MODEL_GENERATED,
model_name=train_model.name)
af.action_on_model_version_event(
job_name='push',
model_version_event_type=ModelVersionEventType.MODEL_VALIDATED,
model_name=train_model.name)
# Run workflow
af.workflow_operation.submit_workflow(
af.current_workflow_config().workflow_name)
af.workflow_operation.start_new_workflow_execution(
af.current_workflow_config().workflow_name)
def run_workflow():
af.init_ai_flow_context()
artifact_prefix = af.current_project_config().get_project_name() + "."
with af.job_config('train'):
# Training of model
# Register metadata raw training data(dataset) and read dataset(i.e. training dataset)
train_dataset = af.register_dataset(name=artifact_prefix +
'train_dataset',
uri=DATASET_URI.format('train'))
train_read_dataset = af.read_dataset(
dataset_info=train_dataset, read_dataset_processor=DatasetReader())
# Transform(preprocessing) dataset
train_transform = af.transform(
input=[train_read_dataset],
transform_processor=DatasetTransformer())
# Register model metadata and train model
train_model = af.register_model(model_name=artifact_prefix +
'logistic-regression',
model_desc='logistic regression model')
train_channel = af.train(input=[train_transform],
training_processor=ModelTrainer(),
model_info=train_model)
with af.job_config('evaluate'):
# Evaluation of model
evaluate_dataset = af.register_dataset(
name=artifact_prefix + 'evaluate_dataset',
uri=DATASET_URI.format('evaluate'))
evaluate_read_dataset = af.read_dataset(
dataset_info=evaluate_dataset,
read_dataset_processor=EvaluateDatasetReader())
evaluate_transform = af.transform(
input=[evaluate_read_dataset],
transform_processor=EvaluateTransformer())
# Register disk path used to save evaluate result
evaluate_artifact_name = artifact_prefix + 'evaluate_artifact'
evaluate_artifact = af.register_artifact(name=evaluate_artifact_name,
uri=get_file_dir(__file__) +
'/evaluate_result')
# Evaluate model
evaluate_channel = af.evaluate(
input=[evaluate_transform],
model_info=train_model,
evaluation_processor=ModelEvaluator(evaluate_artifact_name))
with af.job_config('validate'):
# Validation of model
# Read validation dataset and validate model before it is used to predict
validate_dataset = af.register_dataset(
name=artifact_prefix + 'validate_dataset',
uri=DATASET_URI.format('evaluate'))
validate_read_dataset = af.read_dataset(
dataset_info=validate_dataset,
read_dataset_processor=ValidateDatasetReader())
validate_transform = af.transform(
input=[validate_read_dataset],
transform_processor=ValidateTransformer())
validate_artifact_name = artifact_prefix + 'validate_artifact'
validate_artifact = af.register_artifact(name=validate_artifact_name,
uri=get_file_dir(__file__) +
'/validate_result')
validate_channel = af.model_validate(
input=[validate_transform],
model_info=train_model,
model_validation_processor=ModelValidator(validate_artifact_name))
with af.job_config('push'):
# Push model to serving
# Register metadata of pushed model
push_model_artifact_name = artifact_prefix + 'push_model_artifact'
push_model_artifact = af.register_artifact(
name=push_model_artifact_name,
uri=get_file_dir(__file__) + '/pushed_model')
af.push_model(
model_info=train_model,
pushing_model_processor=ModelPusher(push_model_artifact_name))
with af.job_config('predict'):
# Prediction(Inference)
predict_dataset = af.register_dataset(
name=artifact_prefix + 'predict_dataset',
uri=DATASET_URI.format('predict'))
predict_read_dataset = af.read_dataset(
dataset_info=predict_dataset,
read_dataset_processor=PredictDatasetReader())
predict_transform = af.transform(
input=[predict_read_dataset],
transform_processor=PredictTransformer())
predict_channel = af.predict(input=[predict_transform],
model_info=train_model,
prediction_processor=ModelPredictor())
# Save prediction result
write_dataset = af.register_dataset(
name=artifact_prefix + 'write_dataset',
uri=get_file_dir(__file__) + '/predict_result')
af.write_dataset(input=predict_channel,
dataset_info=write_dataset,
write_dataset_processor=DatasetWriter())
# Define relation graph connected by control edge: train -> evaluate -> validate -> push -> predict
af.action_on_job_status('evaluate', 'train')
af.action_on_job_status('validate', 'evaluate')
af.action_on_job_status('push', 'validate')
af.action_on_job_status('predict', 'push')
# Run workflow
af.workflow_operation.submit_workflow(
af.current_workflow_config().workflow_name)
af.workflow_operation.start_new_workflow_execution(
af.current_workflow_config().workflow_name)
def setUp(self):
airflow_db_utils.clear_all()
self.master._clear_db()
af.current_graph().clear_graph()
init_ai_flow_context()
