#
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
"""
Example Airflow DAG that uses Google AutoML services.
"""
from __future__ import annotations
import os
from datetime import datetime
from google.cloud.aiplatform import schema
from google.protobuf.struct_pb2 import Value
from airflow.models.dag import DAG
from airflow.providers.google.cloud.hooks.automl import CloudAutoMLHook
from airflow.providers.google.cloud.operators.gcs import (
GCSCreateBucketOperator,
GCSDeleteBucketOperator,
GCSSynchronizeBucketsOperator,
)
from airflow.providers.google.cloud.operators.vertex_ai.auto_ml import (
CreateAutoMLTextTrainingJobOperator,
DeleteAutoMLTrainingJobOperator,
)
from airflow.providers.google.cloud.operators.vertex_ai.dataset import (
CreateDatasetOperator,
DeleteDatasetOperator,
ImportDataOperator,
)
from airflow.utils.trigger_rule import TriggerRule
[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID", "default")
[docs]GCP_PROJECT_ID = os.environ.get("SYSTEM_TESTS_GCP_PROJECT", "default")
[docs]DAG_ID = "example_automl_text_extr"
[docs]GCP_AUTOML_LOCATION = "us-central1"
[docs]RESOURCE_DATA_BUCKET = "airflow-system-tests-resources"
[docs]DATA_SAMPLE_GCS_BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}".replace("_", "-")
[docs]TEXT_EXTR_DISPLAY_NAME = f"{DAG_ID}-{ENV_ID}".replace("_", "-")
[docs]AUTOML_DATASET_BUCKET = f"gs://{DATA_SAMPLE_GCS_BUCKET_NAME}/automl/extraction.jsonl"
[docs]MODEL_NAME = f"{DAG_ID}-{ENV_ID}".replace("_", "-")
[docs]DATASET_NAME = f"ds_clss_{ENV_ID}".replace("-", "_")
[docs]DATASET = {
"display_name": DATASET_NAME,
"metadata_schema_uri": schema.dataset.metadata.text,
"metadata": Value(string_value="extr-dataset"),
}
[docs]DATA_CONFIG = [
{
"import_schema_uri": schema.dataset.ioformat.text.extraction,
"gcs_source": {"uris": [AUTOML_DATASET_BUCKET]},
},
]
# Example DAG for AutoML Natural Language Entities Extraction
with DAG(
DAG_ID,
schedule="@once", # Override to match your needs
start_date=datetime(2021, 1, 1),
catchup=False,
user_defined_macros={"extract_object_id": extract_object_id},
tags=["example", "automl", "text-extraction"],
) as dag:
[docs] create_bucket = GCSCreateBucketOperator(
task_id="create_bucket",
bucket_name=DATA_SAMPLE_GCS_BUCKET_NAME,
storage_class="REGIONAL",
location=GCP_AUTOML_LOCATION,
)
move_dataset_file = GCSSynchronizeBucketsOperator(
task_id="move_dataset_to_bucket",
source_bucket=RESOURCE_DATA_BUCKET,
source_object="vertex-ai/automl/datasets/text",
destination_bucket=DATA_SAMPLE_GCS_BUCKET_NAME,
destination_object="automl",
recursive=True,
)
create_extr_dataset = CreateDatasetOperator(
task_id="create_extr_dataset",
dataset=DATASET,
region=GCP_AUTOML_LOCATION,
project_id=GCP_PROJECT_ID,
)
extr_dataset_id = create_extr_dataset.output["dataset_id"]
import_extr_dataset = ImportDataOperator(
task_id="import_extr_data",
dataset_id=extr_dataset_id,
region=GCP_AUTOML_LOCATION,
project_id=GCP_PROJECT_ID,
import_configs=DATA_CONFIG,
)
# [START howto_cloud_create_text_extraction_training_job_operator]
create_extr_training_job = CreateAutoMLTextTrainingJobOperator(
task_id="create_extr_training_job",
display_name=TEXT_EXTR_DISPLAY_NAME,
prediction_type="extraction",
multi_label=False,
dataset_id=extr_dataset_id,
model_display_name=MODEL_NAME,
training_fraction_split=0.8,
validation_fraction_split=0.1,
test_fraction_split=0.1,
sync=True,
region=GCP_AUTOML_LOCATION,
project_id=GCP_PROJECT_ID,
)
# [END howto_cloud_create_text_extraction_training_job_operator]
delete_extr_training_job = DeleteAutoMLTrainingJobOperator(
task_id="delete_extr_training_job",
training_pipeline_id=create_extr_training_job.output["training_id"],
region=GCP_AUTOML_LOCATION,
project_id=GCP_PROJECT_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
delete_extr_dataset = DeleteDatasetOperator(
task_id="delete_extr_dataset",
dataset_id=extr_dataset_id,
region=GCP_AUTOML_LOCATION,
project_id=GCP_PROJECT_ID,
trigger_rule=TriggerRule.ALL_DONE,
)
delete_bucket = GCSDeleteBucketOperator(
task_id="delete_bucket",
bucket_name=DATA_SAMPLE_GCS_BUCKET_NAME,
trigger_rule=TriggerRule.ALL_DONE,
)
(
# TEST SETUP
[create_bucket >> move_dataset_file, create_extr_dataset]
# TEST BODY
>> import_extr_dataset
>> create_extr_training_job
# TEST TEARDOWN
>> delete_extr_training_job
>> delete_extr_dataset
>> delete_bucket
)
from tests.system.utils.watcher import watcher
# This test needs watcher in order to properly mark success/failure
# when "tearDown" task with trigger rule is part of the DAG
list(dag.tasks) >> watcher()
from tests.system.utils import get_test_run # noqa: E402
# Needed to run the example DAG with pytest (see: tests/system/README.md#run_via_pytest)
[docs]test_run = get_test_run(dag)