Updated the "Basic - Parallel execution" sample (#1110)

Modernized the sample pipeline code.

samples/basic/parallel_join.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright 2018 Google LLC
+# Copyright 2019 Google LLC
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -14,38 +14,44 @@
 # limitations under the License.
 
 
-import kfp.dsl as dsl
+import kfp
+from kfp import dsl
+
+def gcs_download_op(url):
+    return dsl.ContainerOp(
+        name='GCS - Download',
+        image='google/cloud-sdk:216.0.0',
+        command=['sh', '-c'],
+        arguments=['gsutil cat $0 | tee $1', url, '/tmp/results.txt'],
+        file_outputs={
+            'data': '/tmp/results.txt',
+        }
+    )
+
+
+def echo2_op(text1, text2):
+    return dsl.ContainerOp(
+        name='echo',
+        image='library/bash:4.4.23',
+        command=['sh', '-c'],
+        arguments=['echo "Text 1: $0"; echo "Text 2: $1"', text1, text2]
+    )
 
 
 @dsl.pipeline(
-  name='Parallel_and_Join',
-  description='Download two messages in parallel and print the concatenated result.'
+  name='Parallel pipeline',
+  description='Download two messages in parallel and prints the concatenated result.'
 )
 def download_and_join(
-  url1='gs://ml-pipeline-playground/shakespeare1.txt',
-  url2='gs://ml-pipeline-playground/shakespeare2.txt'):
-  """A three-step pipeline with first two running in parallel."""
-
-  download1 = dsl.ContainerOp(
-     name='download1',
-     image='google/cloud-sdk:216.0.0',
-     command=['sh', '-c'],
-     arguments=['gsutil cat %s | tee /tmp/results.txt' % url1],
-     file_outputs={'downloaded': '/tmp/results.txt'})
-
-  download2 = dsl.ContainerOp(
-     name='download2',
-     image='google/cloud-sdk:216.0.0',
-     command=['sh', '-c'],
-     arguments=['gsutil cat %s | tee /tmp/results.txt' % url2],
-     file_outputs={'downloaded': '/tmp/results.txt'})
-
-  echo = dsl.ContainerOp(
-     name='echo',
-     image='library/bash:4.4.23',
-     command=['sh', '-c'],
-     arguments=['echo %s %s' % (download1.output, download2.output)])
+    url1='gs://ml-pipeline-playground/shakespeare1.txt',
+    url2='gs://ml-pipeline-playground/shakespeare2.txt'
+):
+    """A three-step pipeline with first two running in parallel."""
+
+    download1_task = gcs_download_op(url1)
+    download2_task = gcs_download_op(url2)
+
+    echo_task = echo2_op(download1_task.output, download2_task.output)
 
 if __name__ == '__main__':
-  import kfp.compiler as compiler
-  compiler.Compiler().compile(download_and_join, __file__ + '.zip')
+    kfp.compiler.Compiler().compile(download_and_join, __file__ + '.zip')