40 lines
1.7 KiB
YAML
40 lines
1.7 KiB
YAML
# Licensed 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.
|
|
|
|
name: emr_submit_pyspark_job
|
|
description: >-
|
|
Submits an Elastic Map Reduce (EMR) PySpark application.
|
|
inputs:
|
|
- {name: region, description: 'The EMR region in which to handle the request.'}
|
|
- {name: jobflow_id, description: 'The cluster id to run the job.'}
|
|
- {name: job_name, description: 'The name of the spark job.'}
|
|
- {name: py_file, description: 'A path to a pyspark file run during the step.'}
|
|
- {name: input, description: 'File path of the dataset.'}
|
|
- {name: output, description: 'Output path of the result files.'}
|
|
outputs:
|
|
- {name: job_id, description: 'The id of the created job.'}
|
|
- {name: output_location, description: 'S3 URI of the training job results.'}
|
|
implementation:
|
|
container:
|
|
image: seedjeffwan/kubeflow-pipeline-aws-emr:20190507
|
|
command: ['python', 'submit_pyspark_job.py']
|
|
args: [
|
|
--region, {inputValue: region},
|
|
--jobflow_id, {inputValue: jobflow_id},
|
|
--job_name, {inputValue: job_name},
|
|
--py_file, {inputValue: py_file},
|
|
--input, {inputValue: input},
|
|
--output, {inputValue: output},
|
|
--output_file, {outputPath: output_location},
|
|
]
|
|
fileOutputs:
|
|
job_id: /output.txt |