from google.cloud import dataproc_v1 as dataproc
def instantiate_inline_workflow_template(project_id, region):
"""This sample walks a user through submitting a workflow
for a Cloud Dataproc using the Python client library.
Args:
project_id (string): Project to use for running the workflow.
region (string): Region where the workflow resources should live.
"""
# Create a client with the endpoint set to the desired region.
workflow_template_client = dataproc.WorkflowTemplateServiceClient(
client_options={"api_endpoint": f"{region}-dataproc.googleapis.com:443"}
)
parent = f"projects/{project_id}/regions/{region}"
template = {
"jobs": [
{
"hadoop_job": {
"main_jar_file_uri": "file:///usr/lib/hadoop-mapreduce/"
"hadoop-mapreduce-examples.jar",
"args": ["teragen", "1000", "hdfs:///gen/"],
},
"step_id": "teragen",
},
{
"hadoop_job": {
"main_jar_file_uri": "file:///usr/lib/hadoop-mapreduce/"
"hadoop-mapreduce-examples.jar",
"args": ["terasort", "hdfs:///gen/", "hdfs:///sort/"],
},
"step_id": "terasort",
"prerequisite_step_ids": ["teragen"],
},
],
"placement": {
"managed_cluster": {
"cluster_name": "my-managed-cluster",
"config": {
"gce_cluster_config": {
# Leave 'zone_uri' empty for 'Auto Zone Placement'
# 'zone_uri': ''
"zone_uri": "us-central1-a"
}
},
}
},
}
# Submit the request to instantiate the workflow from an inline template.
operation = workflow_template_client.instantiate_inline_workflow_template(
request={"parent": parent, "template": template}
)
operation.result()
# Output a success message.
print("Workflow ran successfully.")
[[["わかりやすい","easyToUnderstand","thumb-up"],["問題の解決に役立った","solvedMyProblem","thumb-up"],["その他","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["翻訳に関する問題","translationIssue","thumb-down"],["その他","otherDown","thumb-down"]],["最終更新日 2024-04-18 UTC。"],[],[]]