#
# 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 for DataprocSubmitJobOperator with pyspark job.
"""
from __future__ import annotations
import os
from datetime import datetime
from airflow import models
from airflow.decorators import task
from airflow.providers.google.cloud.operators.dataproc import (
DataprocCreateClusterOperator,
DataprocDeleteClusterOperator,
DataprocSubmitJobOperator,
)
from airflow.providers.google.cloud.operators.gcs import (
GCSCreateBucketOperator,
GCSDeleteBucketOperator,
)
from airflow.providers.google.cloud.transfers.local_to_gcs import LocalFilesystemToGCSOperator
from airflow.utils.trigger_rule import TriggerRule
[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID")
[docs]DAG_ID = "dataproc_pyspark"
[docs]PROJECT_ID = os.environ.get("SYSTEM_TESTS_GCP_PROJECT")
[docs]BUCKET_NAME = f"bucket_{DAG_ID}_{ENV_ID}"
[docs]CLUSTER_NAME = f"cluster-dataproc-pyspark-{ENV_ID}"
# Cluster definition
[docs]CLUSTER_CONFIG = {
"master_config": {
"num_instances": 1,
"machine_type_uri": "n1-standard-4",
"disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 1024},
},
"worker_config": {
"num_instances": 2,
"machine_type_uri": "n1-standard-4",
"disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 1024},
},
}
[docs]JOB_FILE_NAME = "dataproc-pyspark-job.py"
[docs]JOB_FILE_LOCAL_PATH = f"/tmp/{JOB_FILE_NAME}"
[docs]JOB_FILE_CONTENT = """from operator import add
from random import random
from pyspark.sql import SparkSession
def f(_: int) -> float:
x = random() * 2 - 1
y = random() * 2 - 1
return 1 if x**2 + y**2 <= 1 else 0
spark = SparkSession.builder.appName("PythonPi").getOrCreate()
partitions = 2
n = 100000 * partitions
count = spark.sparkContext.parallelize(range(1, n + 1), partitions).map(f).reduce(add)
print(f"Pi is roughly {4.0 * count / n:f}")
spark.stop()
"""
# Jobs definitions
# [START how_to_cloud_dataproc_pyspark_config]
[docs]PYSPARK_JOB = {
"reference": {"project_id": PROJECT_ID},
"placement": {"cluster_name": CLUSTER_NAME},
"pyspark_job": {"main_python_file_uri": f"gs://{BUCKET_NAME}/{JOB_FILE_NAME}"},
}
# [END how_to_cloud_dataproc_pyspark_config]
with models.DAG(
DAG_ID,
schedule="@once",
start_date=datetime(2021, 1, 1),
catchup=False,
tags=["example", "dataproc", "pyspark"],
) as dag:
[docs] create_bucket = GCSCreateBucketOperator(
task_id="create_bucket", bucket_name=BUCKET_NAME, project_id=PROJECT_ID
)
@task
def create_job_file():
with open(JOB_FILE_LOCAL_PATH, "w") as job_file:
job_file.write(JOB_FILE_CONTENT)
create_job_file_task = create_job_file()
upload_file = LocalFilesystemToGCSOperator(
task_id="upload_file",
src=JOB_FILE_LOCAL_PATH,
dst=JOB_FILE_NAME,
bucket=BUCKET_NAME,
)
create_cluster = DataprocCreateClusterOperator(
task_id="create_cluster",
project_id=PROJECT_ID,
cluster_config=CLUSTER_CONFIG,
region=REGION,
cluster_name=CLUSTER_NAME,
)
# [START how_to_cloud_dataproc_submit_job_to_cluster_operator]
pyspark_task = DataprocSubmitJobOperator(
task_id="pyspark_task", job=PYSPARK_JOB, region=REGION, project_id=PROJECT_ID
)
# [END how_to_cloud_dataproc_submit_job_to_cluster_operator]
delete_cluster = DataprocDeleteClusterOperator(
task_id="delete_cluster",
project_id=PROJECT_ID,
cluster_name=CLUSTER_NAME,
region=REGION,
trigger_rule=TriggerRule.ALL_DONE,
)
delete_bucket = GCSDeleteBucketOperator(
task_id="delete_bucket", bucket_name=BUCKET_NAME, trigger_rule=TriggerRule.ALL_DONE
)
@task(trigger_rule=TriggerRule.ALL_DONE)
def delete_job_file():
try:
os.remove(JOB_FILE_LOCAL_PATH)
except FileNotFoundError:
pass
return 0
delete_job_file_task = delete_job_file()
(
# TEST SETUP
[[create_job_file_task, create_bucket] >> upload_file, create_cluster]
# TEST BODY
>> pyspark_task
# TEST TEARDOWN
>> [delete_cluster, delete_bucket, delete_job_file_task]
)
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)
