#create_dataproc_cluster = dataproc_operator.DataprocClusterCreateOperator(
# task_id='create_dataproc_cluster',
# # Give the cluster a unique name by appending the date scheduled.
# # See https://airflow.apache.org/code.html#default-variables
# cluster_name='composer-hadoop-tutorial-cluster-{{ ds_nodash }}',
# num_workers=2,
# zone=models.Variable.get('gce_zone'),
# master_machine_type='n1-standard-1',
# worker_machine_type='n1-standard-1')
# Submit the PySpark job.
submit_pyspark1 = dataproc_operator.DataProcPySparkOperator(
task_id='submit_pyspark1',
main=PYSPARK_JOB,
# Obviously needs to match the name of cluster created in the prior Operator.
cluster_name='cicd-demo-cluster',
region='us-central1',
dataproc_jars='gs://spark-lib/bigquery/spark-bigquery-latest.jar',
dataproc_pyspark_jars=
'gs://spark-lib/bigquery/spark-bigquery-latest.jar')
submit_pyspark2 = dataproc_operator.DataProcPySparkOperator(
task_id='submit_pyspark2',
main=PYSPARK_JOB,
# Obviously needs to match the name of cluster created in the prior Operator.
cluster_name='cicd-demo-cluster',
region='us-central1',
dataproc_jars='gs://spark-lib/bigquery/spark-bigquery-latest.jar',
dataproc_pyspark_jars=
'gs://spark-lib/bigquery/spark-bigquery-latest.jar')
tags=['all-bastion-ssh', 'dataproc', 'cassandra'],
storage_bucket='hd-personalization-dev-batch',
properties={'dataproc:dataproc.allow.zero.workers': 'true'},
dag=dag)
dataproc_pyspark_submit = dataproc_operator.DataProcPySparkOperator(
task_id='pyspark_task',
main=
'gs://hd-personalization-dev-artifacts/releases/com.homedepot.recommendations/collections-model-training/python-scripts/v0.0.0+16/__main__.py',
pyfiles=[
'gs://hd-personalization-dev-artifacts/releases/com.homedepot.recommendations/collections-model-training/python-scripts/v0.0.0+16/collections_model_training-0.0.1-py3.7.egg'
],
arguments=[
'LSTM_DATAGEN', '--project', 'hd-personalization-dev', '--category',
'AreaRugs', '--dupletsData',
'gs://hd-personalization-dev-data/vdc2136/training/duplets/2020-06-01/',
'--featuresData',
'gs://hd-personalization-dev-data/vdc2136/training/data/AllFeatures.csv',
'--finalOutputPath',
'gs://hd-personalization-dev-data/vdc2136/training/lstm/2020-06-02/',
'--appName', 'LSTM_DATA_GEN', '--mode=cluster'
],
job_name='airflow_pyspark_job',
cluster_name='airflow-dataproc-cluster',
project_id='hd-personalization-dev',
dag=dag)
delete_dataproc_cluster = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc_cluster',
cluster_name='airflow-dataproc-cluster',
# Setting trigger_rule to ALL_DONE causes the cluster to be deleted
# BashOperator
# A simple print date
print_date = BashOperator(task_id='print_date', bash_command='date')
# dataproc_operator
# Create small dataproc cluster
create_dataproc = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc',
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
num_workers=2,
zone=models.Variable.get('dataproc_zone'),
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
# Run the PySpark job
run_spark = dataproc_operator.DataProcPySparkOperator(
task_id='run_spark',
main=SPARK_CODE,
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
job_name=dataproc_job_name)
# dataproc_operator
# Delete Cloud Dataproc cluster.
delete_dataproc = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc',
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
trigger_rule=trigger_rule.TriggerRule.ALL_DONE)
# STEP 6: Set DAGs dependencies
# Each task should run after have finished the task before.
print_date >> create_dataproc >> run_spark >> delete_dataproc
from airflow import models
from airflow.contrib.operators import dataproc_operator
from airflow.utils import trigger_rule
output_file = os.path.join(
models.Variable.get('gcs_bucket'), 'dataproc_simple',
datetime.datetime.now().strftime('%Y%m%d-%H%M%S')) + os.sep
yesterday = datetime.datetime.combine(
datetime.datetime.today() - datetime.timedelta(1),
datetime.datetime.min.time())
args = {
'start_date': yesterday,
'email_on_failure': False,
'email_on_retry': False,
'retries': 1,
'retry_delay': datetime.timedelta(minutes=5),
'project_id': models.Variable.get('gcp_project')
}
with models.DAG('spark_simple',
schedule_interval=datetime.timedelta(days=1),
default_args=args) as dag:
run_step = dataproc_operator.DataProcPySparkOperator(
task_id='run_spark',
cluster_name='cluster-9c11',
region='europe-west1',
main='gs://bigdataupv_code/compras_top_ten_countries.py',
files=['gs://bigdataupv_code/helpers.py'])
# [END composer_quickstart_schedule]
# Create a Cloud Dataproc cluster.
create_dataproc_cluster = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc_cluster',
# Give the cluster a unique name by appending the date scheduled.
# See https://airflow.apache.org/code.html#default-variables
cluster_name='parquetconverter2',
num_workers=3,
zone='europe-west1-b',
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
# Run the pyspark CSV2PARQUET example
run_dataproc_csv2parquet = dataproc_operator.DataProcPySparkOperator(
task_id='run_dataproc_parquetconvert',
cluster_name='parquetconverter2',
main='gs://alex-code/convert.py')
# Delete Cloud Dataproc cluster.
delete_dataproc_cluster = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc_cluster',
cluster_name='parquetconverter2',
# Setting trigger_rule to ALL_DONE causes the cluster to be deleted
# even if the Dataproc job fails.
trigger_rule=trigger_rule.TriggerRule.ALL_DONE)
# [START composer_quickstart_steps]
# Define DAG dependencies.
create_dataproc_cluster >> run_dataproc_csv2parquet >> delete_dataproc_cluster
# [END composer_quickstart_steps]
},
optional_components=['ANACONDA', 'JUPYTER', 'ZEPPELIN'],
enable_optional_components=True,
enable_http_port_access=True,
zone="europe-west1-b",
storage_bucket="vf-polimi-batch-data",
idle_delete_ttl=3601,
internal_ip_only=False,
init_actions_uris=[
'gs://goog-dataproc-initialization-actions-europe-west1/python/pip-install.sh'
])
run_batch_kpi_scheduled = dataproc_operator.DataProcPySparkOperator(
task_id="submit_batch-kpi-scheduled",
cluster_name='vf-polimi-demo',
region='europe-west1',
main='gs://vf-polimi-batch-data/dev/compute-kpi-batch.py',
dataproc_pyspark_jars=
'gs://spark-lib/bigquery/spark-bigquery-latest.jar',
xcom_push=True)
remove_cluster = dataproc_operator.DataprocClusterDeleteOperator(
project_id=PROJECT,
task_id="delete_cluster",
cluster_name='vf-polimi-demo',
region='europe-west1')
def check_batch_kpi_scheduled_cluster_running(**kwargs):
ti = kwargs['ti']
xcom_value = ti.xcom_pull(task_ids='batch_kpi_scheduled_cluster')
if xcom_value == "vf-polimi-demo":
return 'delete_cluster'
with airflow.DAG('gcs_composer_trigger_dag',default_args=default_args, schedule_interval=None) as dag:
create_dataproc_cluster = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc_cluster',
cluster_name='composer-311-complaints-{{ ds_nodash }}',
num_workers=2,
region=models.Variable.get('region'),
zone=models.Variable.get('gce_zone'),
project_id=models.Variable.get('project_id'),
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
run_dataproc_job = dataproc_operator.DataProcPySparkOperator(
task_id="run_dataproc_job",
main="gs://311-complaints-spark_jobs/spark_job.py",
cluster_name='composer-311-complaints-{{ ds_nodash }}',
region=models.Variable.get('region'),
dataproc_pyspark_jars=['gs://spark-lib/bigquery/spark-bigquery-latest.jar'],
arguments=['gs://{{ dag_run.conf.get("bucket") }}/{{ dag_run.conf.get("name") }}'])
delete_dataproc_cluster = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc_cluster',
cluster_name='composer-311-complaints-{{ ds_nodash }}',
project_id=models.Variable.get('project_id'),
region=models.Variable.get('region'),
trigger_rule=trigger_rule.TriggerRule.ALL_DONE)
bigquery_transformations=BigQueryOperator(
sql='/sql/job.sql',
task_id='bigquery_transformations',
use_legacy_sql=False,
import logging
logging.info('Hello World!')
create_dataproc_cluster = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc_cluster',
# Give the cluster a unique name by appending the date scheduled.
# See https://airflow.apache.org/code.html#default-variables
cluster_name='composer-dataproc-{{ ds_nodash }}',
num_workers=2,
region='asia-south1',
zone='asia-south1-a',
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
dataprod_pyspark = dataproc_operator.DataProcPySparkOperator(
task_id='pyspark',
main='gs://code_deploy/dataproc_read_bucket_to_bigquery.py',
cluster_name='composer-dataproc-{{ ds_nodash }}',
region='asia-south1',
dataproc_pyspark_jars=[])
delete_dataproc_cluster = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc_cluster',
cluster_name='composer-dataproc-{{ ds_nodash }}',
region='asia-south1',
# Setting trigger_rule to ALL_DONE causes the cluster to be deleted
# even if the Dataproc job fails.
trigger_rule=trigger_rule.TriggerRule.ALL_DONE)
# An instance of an operator is called a task. In this case, the
# hello_python task calls the "greeting" Python function.
hello_python = python_operator.PythonOperator(task_id='hello',
python_callable=greeting)
task_id='create_dataproc_cluster',
# Give the cluster a unique name by appending the date scheduled.
# See https://airflow.apache.org/code.html#default-variables
cluster_name=pipeline_cluster_name,
num_workers=2,
region='us-central1',
autoscaling_policy=
'projects/{}/regions/us-central1/autoscalingPolicies/ephimeral-scaling-policy'
.format(os.environ['PROJECT_ID']),
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
run_py_spark = dataproc_operator.DataProcPySparkOperator(
task_id='run_py_spark',
region='us-central1',
main='gs://{}/data/compute-pi-pipeline/calculate-pi.py'.format(
os.environ['COMPOSER_BUCKET']),
arguments=[models.Variable.get("NUM_SAMPLES")],
cluster_name=pipeline_cluster_name)
# Delete Cloud Dataproc cluster.
delete_dataproc_cluster = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc_cluster',
region='us-central1',
cluster_name=pipeline_cluster_name,
# Setting trigger_rule to ALL_DONE causes the cluster to be deleted
# even if the Dataproc job fails.
trigger_rule=trigger_rule.TriggerRule.ALL_DONE)
# Define DAG dependencies.
create_dataproc_cluster >> run_py_spark >> delete_dataproc_cluster
delete_ml_partition = bash_operator.BashOperator(
task_id='delete_ml_partition',
dag=dag,
bash_command=
'''bq rm -f -t 'dataops_demo_ml_dev.t_twitter_google${{ macros.ds_format(ds, "%Y-%m-%d", "%Y%m%d") }}' ''',
)
# Execute PySpark job
run_pyspark_job_splitting = dataproc_operator.DataProcPySparkOperator(
task_id='run_pyspark_job_splitting',
dag=dag,
main='gs://' + Variable.get('v_composer_bucket') +
'/dags/dataproc/twitterPySparkSplitting.py',
cluster_name='twitter-dataproc-mlanciau-{{ ds_nodash }}',
dataproc_pyspark_jars=[
'gs://spark-lib/bigquery/spark-bigquery-latest.jar'
],
arguments=[
"--dataproc=1.4", "--job_date={{ ds }}",
"--bucket=dataproc_dataops_tmp"
])
run_pyspark_job_frequency = dataproc_operator.DataProcPySparkOperator(
task_id='run_pyspark_job_frequency',
dag=dag,
main='gs://' + Variable.get('v_composer_bucket') +
'/dags/dataproc/twitterPySparkFrequency.py',
cluster_name='twitter-dataproc-mlanciau-{{ ds_nodash }}',
dataproc_pyspark_jars=[
'gs://spark-lib/bigquery/spark-bigquery-latest.jar'
# dataproc_operator
# Create small dataproc cluster
create_dataproc = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc',
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
num_workers=2,
zone=models.Variable.get('dataproc_zone'),
master_machine_type='e2-standard-4',
worker_machine_type='e2-standard-8')
# Run the PySpark job
run_spark0 = dataproc_operator.DataProcPySparkOperator(
task_id='run_spark0',
main=SPARK_CODE0,
dataproc_pyspark_jars=jarpath,
arguments=arglist,
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
job_name=dataproc_job_name + '0')
run_spark1 = dataproc_operator.DataProcPySparkOperator(
task_id='run_spark1',
main=SPARK_CODE1,
dataproc_pyspark_jars=jarpath,
arguments=arglist,
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
job_name=dataproc_job_name + '1')
run_spark2 = dataproc_operator.DataProcPySparkOperator(
task_id='run_spark2',
main=SPARK_CODE2,
# dataproc_operator
# Create small dataproc cluster
create_dataproc = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc',
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
num_workers=2,
zone=None,
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1',
region=models.Variable.get('dataproc_zone'))
# Run the PySpark job
run_spark = dataproc_operator.DataProcPySparkOperator(
task_id='run_spark',
main=SPARK_CODE,
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
job_name=dataproc_job_name,
region=models.Variable.get('dataproc_zone'))
# dataproc_operator
# Delete Cloud Dataproc cluster.
delete_dataproc = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc',
cluster_name='dataproc-cluster-demo-{{ ds_nodash }}',
trigger_rule=trigger_rule.TriggerRule.ALL_DONE,
region=models.Variable.get('dataproc_zone'))
# STEP 6: Set DAGs dependencies
# Each task should run after have finished the task before.
print_date >> create_dataproc >> run_spark >> delete_dataproc
# See https://airflow.apache.org/code.html#default-variables
cluster_name='accomodation-cluster-{{ ds_nodash }}',
num_workers=2,
init_actions_uris=['gs://able-cogency-234306/tmp/cloud-sql-proxy.sh'],
service_account_scopes=['https://www.googleapis.com/auth/cloud-platform','https://www.googleapis.com/auth/sqlservice.admin'],
metadata={'enable-cloud-sql-hive-metastore':'false','additional-cloud-sql-instances':'able-cogency-234306:us-central1:testddd'},
region='us-central1',
zone=models.Variable.get('gce_zone'),
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
# Run the Hadoop wordcount example installed on the Cloud Dataproc cluster
# master node.
csv_import_job = dataproc_operator.DataProcPySparkOperator(
task_id='csv_import_job',
main=CSVIMPORTPY,
cluster_name='accomodation-cluster-{{ ds_nodash }}',
job_name='csv_import_job',
region='us-central1')
# Run the Hadoop wordcount example installed on the Cloud Dataproc cluster
# master node.
accomodation_model_job = dataproc_operator.DataProcPySparkOperator(
task_id='accomodation_model_job',
main=MODELPY,
cluster_name='accomodation-cluster-{{ ds_nodash }}',
job_name='accomodation_model_job',
region='us-central1')
# Delete Cloud Dataproc cluster.
delete_dataproc_cluster = dataproc_operator.DataprocClusterDeleteOperator(
task_id='delete_dataproc_cluster',
# Give the cluster a unique name by appending the date scheduled.
# See https://airflow.apache.org/code.html#default-variables
cluster_name='composer-hadoop-tutorial-cluster-{{ ds_nodash }}',
num_workers=2,
zone=models.Variable.get('gce_zone'),
master_machine_type='n1-standard-1',
worker_machine_type='n1-standard-1')
# Submit the PySpark job.
submit_pyspark1 = dataproc_operator.DataProcPySparkOperator(
task_id='submit_pyspark1',
main=PYSPARK_JOB,
# Obviously needs to match the name of cluster created in the prior Operator.
cluster_name='composer-hadoop-tutorial-cluster-{{ ds_nodash }}',
dataproc_jars = 'gs://spark-lib/bigquery/spark-bigquery-latest.jar',
dataproc_pyspark_jars ='gs://spark-lib/bigquery/spark-bigquery-latest.jar')
submit_pyspark2 = dataproc_operator.DataProcPySparkOperator(
task_id='submit_pyspark2',
main=PYSPARK_JOB,
# Obviously needs to match the name of cluster created in the prior Operator.
cluster_name='composer-hadoop-tutorial-cluster-{{ ds_nodash }}',
dataproc_jars = 'gs://spark-lib/bigquery/spark-bigquery-latest.jar',
dataproc_pyspark_jars ='gs://spark-lib/bigquery/spark-bigquery-latest.jar')
create_dataproc_cluster = dataproc_operator.DataprocClusterCreateOperator(
task_id='create_dataproc_cluster',
project_id='dataproc-300110',
cluster_name='cluster-58-wb',
num_workers=2,
region='us-east1',
init_actions_uris=['gs://worldbank2021/code/init_cluster.sh'],
master_machine_type='n1-standard-2',
worker_machine_type='n1-standard-2')
dataproc_pyspark_1 = dataproc_operator.DataProcPySparkOperator(
task_id='Load_BQ_spark_job_1',
# call the py file for processing
# main='gs://dataproc-nyc-taxi-2020/code_deploy/dataproc_wb.py',
main='gs://worldbank2021/code/dataproc_load_bq.py',
cluster_name='cluster-58-wb',
region='us-east1',
arguments=['wb_country_series_definition'],
dataproc_pyspark_jars=[
'gs://spark-lib/bigquery/spark-bigquery-latest.jar'
])
dataproc_pyspark_2 = dataproc_operator.DataProcPySparkOperator(
task_id='Load_BQ_spark_job_2',
main='gs://worldbank2021/code/dataproc_load_bq.py',
cluster_name='cluster-58-wb',
region='us-east1',
arguments=['wb_country_summary'],
dataproc_pyspark_jars=[
'gs://spark-lib/bigquery/spark-bigquery-latest.jar'
])
