Added create_training_pipeline_custom_training_managed_dataset_sample…

… and fixed unmanaged sample

samples/model-builder/create_training_pipeline_custom_job_sample.py

@@ -13,15 +13,16 @@
 # limitations under the License.
 
 from google.cloud import aiplatform
+from typing import List
 
 
 #  [START aiplatform_sdk_create_training_pipeline_custom_job_sample]
 def create_training_pipeline_custom_job_sample(
     project: str,
     display_name: str,
+    args: List[str],
     script_path: str,
     container_uri: str,
-    dataset_id: int,
     location: str = "us-central1",
     model_display_name: str = None,
     training_fraction_split: float = 0.8,
@@ -35,11 +36,9 @@ def create_training_pipeline_custom_job_sample(
         script_path=script_path,
         container_uri=container_uri)
 
-    my_image_ds = aiplatform.ImageDataset(dataset_id)
-
     model = job.run(
-        dataset=my_image_ds,
         model_display_name=model_display_name,
+        args=args,
         training_fraction_split=training_fraction_split,
         validation_fraction_split=validation_fraction_split,
         test_fraction_split=test_fraction_split,

samples/model-builder/create_training_pipeline_custom_job_test.py

@@ -19,26 +19,22 @@
 
 def test_create_training_pipeline_custom_job_sample(
     mock_sdk_init,
-    mock_image_dataset,
     mock_init_custom_training_job,
     mock_run_custom_training_job,
-    mock_get_image_dataset,
 ):
 
     create_training_pipeline_custom_job_sample.create_training_pipeline_custom_job_sample(
         project=constants.PROJECT,
         display_name=constants.DISPLAY_NAME,
+        args=constants.ARGS,
         script_path=constants.SCRIPT_PATH,
         container_uri=constants.CONTAINER_URI,
-        dataset_id=constants.RESOURCE_ID,
         model_display_name=constants.DISPLAY_NAME_2,
         training_fraction_split=constants.TRAINING_FRACTION_SPLIT,
         validation_fraction_split=constants.VALIDATION_FRACTION_SPLIT,
         test_fraction_split=constants.TEST_FRACTION_SPLIT,
     )
 
-    mock_get_image_dataset.assert_called_once_with(constants.RESOURCE_ID)
-
     mock_sdk_init.assert_called_once_with(
         project=constants.PROJECT, location=constants.LOCATION
     )
@@ -48,8 +44,8 @@ def test_create_training_pipeline_custom_job_sample(
         container_uri=constants.CONTAINER_URI,
     )
     mock_run_custom_training_job.assert_called_once_with(
-        dataset=mock_image_dataset,
         model_display_name=constants.DISPLAY_NAME_2,
+        args=constants.ARGS,
         training_fraction_split=constants.TRAINING_FRACTION_SPLIT,
         validation_fraction_split=constants.VALIDATION_FRACTION_SPLIT,
         test_fraction_split=constants.TEST_FRACTION_SPLIT,

samples/model-builder/create_training_pipeline_custom_training_managed_dataset_sample.py

@@ -0,0 +1,57 @@
+# Copyright 2021 Google LLC
+#
+# 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
+#
+#     https://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.
+
+from google.cloud import aiplatform
+
+
+#  [START aiplatform_sdk_create_training_pipeline_custom_job_sample]
+def create_training_pipeline_custom_training_managed_dataset_sample(
+    project: str,
+    display_name: str,
+    script_path: str,
+    container_uri: str,
+    dataset_id: int,
+    location: str = "us-central1",
+    model_display_name: str = None,
+    training_fraction_split: float = 0.8,
+    validation_fraction_split: float = 0.1,
+    test_fraction_split: float = 0.1,
+    sync: bool = True,
+):
+    aiplatform.init(project=project, location=location)
+
+    job = aiplatform.CustomTrainingJob(display_name=display_name, 
+        script_path=script_path,
+        container_uri=container_uri)
+
+    my_image_ds = aiplatform.ImageDataset(dataset_id)
+
+    model = job.run(
+        dataset=my_image_ds,
+        model_display_name=model_display_name,
+        training_fraction_split=training_fraction_split,
+        validation_fraction_split=validation_fraction_split,
+        test_fraction_split=test_fraction_split,
+        sync=sync,
+    )
+
+    model.wait()
+
+    print(model.display_name)
+    print(model.resource_name)
+    print(model.uri)
+    return model
+
+
+#  [END aiplatform_sdk_create_training_pipeline_custom_job_sample]

samples/model-builder/create_training_pipeline_custom_training_managed_dataset_test.py

@@ -0,0 +1,57 @@
+# Copyright 2021 Google LLC
+#
+# 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
+#
+#     https://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.
+
+
+import create_training_pipeline_custom_training_managed_dataset_sample
+import test_constants as constants
+
+
+def test_create_training_pipeline_custom_job_sample(
+    mock_sdk_init,
+    mock_image_dataset,
+    mock_init_custom_training_job,
+    mock_run_custom_training_job,
+    mock_get_image_dataset,
+):
+
+    create_training_pipeline_custom_training_managed_dataset_sample.create_training_pipeline_custom_training_managed_dataset_sample(
+        project=constants.PROJECT,
+        display_name=constants.DISPLAY_NAME,
+        script_path=constants.SCRIPT_PATH,
+        container_uri=constants.CONTAINER_URI,
+        dataset_id=constants.RESOURCE_ID,
+        model_display_name=constants.DISPLAY_NAME_2,
+        training_fraction_split=constants.TRAINING_FRACTION_SPLIT,
+        validation_fraction_split=constants.VALIDATION_FRACTION_SPLIT,
+        test_fraction_split=constants.TEST_FRACTION_SPLIT,
+    )
+
+    mock_get_image_dataset.assert_called_once_with(constants.RESOURCE_ID)
+
+    mock_sdk_init.assert_called_once_with(
+        project=constants.PROJECT, location=constants.LOCATION
+    )
+    mock_init_custom_training_job.assert_called_once_with(
+        display_name=constants.DISPLAY_NAME,
+        script_path=constants.SCRIPT_PATH,
+        container_uri=constants.CONTAINER_URI,
+    )
+    mock_run_custom_training_job.assert_called_once_with(
+        dataset=mock_image_dataset,
+        model_display_name=constants.DISPLAY_NAME_2,
+        training_fraction_split=constants.TRAINING_FRACTION_SPLIT,
+        validation_fraction_split=constants.VALIDATION_FRACTION_SPLIT,
+        test_fraction_split=constants.TEST_FRACTION_SPLIT,
+        sync=True,
+    )

samples/model-builder/test_constants.py

@@ -54,4 +54,5 @@
 PREDICTION_TEXT_INSTANCE = "This is some text for testing NLP prediction output"
 
 SCRIPT_PATH = "task.py"
-CONTAINER_URI = "gcr.io/my_project/my_image:latest"
+CONTAINER_URI = "gcr.io/my_project/my_image:latest"
+ARGS = ["--tfds", "tf_flowers:3.*.*"]