Components - Added AutoML Tables components and tests (#2174)

* Components - Added AutoML Tables components

* Added the sample - AutoML Tables - Retail product stockout prediction

* Replaced the project ID with dummy placeholder

* Fixed the description parameter passing

* Replaced pip with pip3 and changed quotes

* Added licenses

* Updated the component links

* Revert "Replaced pip with pip3"

This reverts commit 65ed0a7. (part of it)

Here, `pip` is not the name of executable. It's the module name which is
just `pip`, not `pip3`.

* Changed quotes to single quotes

* Moved the components to the gcp folder

* Switched container images to python:3.7

* Updated component versions in sample

components/gcp/automl/create_dataset_for_tables/component.py

@@ -0,0 +1,58 @@
+# 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.
+# 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.
+
+from typing import NamedTuple
+
+
+def automl_create_dataset_for_tables(
+    gcp_project_id: str,
+    gcp_region: str,
+    display_name: str,
+    description: str = None,
+    tables_dataset_metadata: dict = {},
+    retry=None, #=google.api_core.gapic_v1.method.DEFAULT,
+    timeout: float = None, #=google.api_core.gapic_v1.method.DEFAULT,
+    metadata: dict = None,
+) -> NamedTuple('Outputs', [('dataset_path', str), ('create_time', str), ('dataset_id', str)]):
+    '''automl_create_dataset_for_tables creates an empty Dataset for AutoML tables
+    '''
+    import sys
+    import subprocess
+    subprocess.run([sys.executable, '-m', 'pip', 'install', 'google-cloud-automl==0.4.0', '--quiet', '--no-warn-script-location'], env={'PIP_DISABLE_PIP_VERSION_CHECK': '1'}, check=True)
+
+    import google
+    from google.cloud import automl
+    client = automl.AutoMlClient()
+
+    location_path = client.location_path(gcp_project_id, gcp_region)
+    dataset_dict = {
+        'display_name': display_name,
+        'description': description,
+        'tables_dataset_metadata': tables_dataset_metadata,
+    }
+    dataset = client.create_dataset(
+        location_path,
+        dataset_dict,
+        retry or google.api_core.gapic_v1.method.DEFAULT,
+        timeout or google.api_core.gapic_v1.method.DEFAULT,
+        metadata,
+    )
+    print(dataset)
+    dataset_id = dataset.name.rsplit('/', 1)[-1]
+    return (dataset.name, dataset.create_time, dataset_id)
+
+
+if __name__ == '__main__':
+    import kfp
+    kfp.components.func_to_container_op(automl_create_dataset_for_tables, output_component_file='component.yaml', base_image='python:3.7')

components/gcp/automl/create_dataset_for_tables/component.yaml

@@ -0,0 +1,149 @@
+description: |
+  automl_create_dataset_for_tables creates an empty Dataset for AutoML tables
+implementation:
+  container:
+    args:
+    - --gcp-project-id
+    - inputValue: gcp_project_id
+    - --gcp-region
+    - inputValue: gcp_region
+    - --display-name
+    - inputValue: display_name
+    - if:
+        cond:
+          isPresent: description
+        then:
+        - --description
+        - inputValue: description
+    - if:
+        cond:
+          isPresent: tables_dataset_metadata
+        then:
+        - --tables-dataset-metadata
+        - inputValue: tables_dataset_metadata
+    - if:
+        cond:
+          isPresent: retry
+        then:
+        - --retry
+        - inputValue: retry
+    - if:
+        cond:
+          isPresent: timeout
+        then:
+        - --timeout
+        - inputValue: timeout
+    - if:
+        cond:
+          isPresent: metadata
+        then:
+        - --metadata
+        - inputValue: metadata
+    - '----output-paths'
+    - outputPath: dataset_path
+    - outputPath: create_time
+    - outputPath: dataset_id
+    command:
+    - python3
+    - -u
+    - -c
+    - |
+      from typing import NamedTuple
+
+      def automl_create_dataset_for_tables(
+          gcp_project_id: str,
+          gcp_region: str,
+          display_name: str,
+          description: str = None,
+          tables_dataset_metadata: dict = {},
+          retry=None, #=google.api_core.gapic_v1.method.DEFAULT,
+          timeout: float = None, #=google.api_core.gapic_v1.method.DEFAULT,
+          metadata: dict = None,
+      ) -> NamedTuple('Outputs', [('dataset_path', str), ('create_time', str), ('dataset_id', str)]):
+          '''automl_create_dataset_for_tables creates an empty Dataset for AutoML tables
+          '''
+          import sys
+          import subprocess
+          subprocess.run([sys.executable, '-m', 'pip', 'install', 'google-cloud-automl==0.4.0', '--quiet', '--no-warn-script-location'], env={'PIP_DISABLE_PIP_VERSION_CHECK': '1'}, check=True)
+
+          import google
+          from google.cloud import automl
+          client = automl.AutoMlClient()
+
+          location_path = client.location_path(gcp_project_id, gcp_region)
+          dataset_dict = {
+              'display_name': display_name,
+              'description': description,
+              'tables_dataset_metadata': tables_dataset_metadata,
+          }
+          dataset = client.create_dataset(
+              location_path,
+              dataset_dict,
+              retry or google.api_core.gapic_v1.method.DEFAULT,
+              timeout or google.api_core.gapic_v1.method.DEFAULT,
+              metadata,
+          )
+          print(dataset)
+          dataset_id = dataset.name.rsplit('/', 1)[-1]
+          return (dataset.name, dataset.create_time, dataset_id)
+
+      import json
+      import argparse
+      _missing_arg = object()
+      _parser = argparse.ArgumentParser(prog='Automl create dataset for tables', description='automl_create_dataset_for_tables creates an empty Dataset for AutoML tables\n')
+      _parser.add_argument("--gcp-project-id", dest="gcp_project_id", type=str, required=True, default=_missing_arg)
+      _parser.add_argument("--gcp-region", dest="gcp_region", type=str, required=True, default=_missing_arg)
+      _parser.add_argument("--display-name", dest="display_name", type=str, required=True, default=_missing_arg)
+      _parser.add_argument("--description", dest="description", type=str, required=False, default=_missing_arg)
+      _parser.add_argument("--tables-dataset-metadata", dest="tables_dataset_metadata", type=json.loads, required=False, default=_missing_arg)
+      _parser.add_argument("--retry", dest="retry", type=str, required=False, default=_missing_arg)
+      _parser.add_argument("--timeout", dest="timeout", type=float, required=False, default=_missing_arg)
+      _parser.add_argument("--metadata", dest="metadata", type=json.loads, required=False, default=_missing_arg)
+      _parser.add_argument("----output-paths", dest="_output_paths", type=str, nargs=3)
+      _parsed_args = {k: v for k, v in vars(_parser.parse_args()).items() if v is not _missing_arg}
+      _output_files = _parsed_args.pop("_output_paths", [])
+
+      _outputs = automl_create_dataset_for_tables(**_parsed_args)
+
+      if not hasattr(_outputs, '__getitem__') or isinstance(_outputs, str):
+          _outputs = [_outputs]
+
+      import os
+      for idx, output_file in enumerate(_output_files):
+          try:
+              os.makedirs(os.path.dirname(output_file))
+          except OSError:
+              pass
+          with open(output_file, 'w') as f:
+              f.write(str(_outputs[idx]))
+    image: python:3.7
+inputs:
+- name: gcp_project_id
+  type: String
+- name: gcp_region
+  type: String
+- name: display_name
+  type: String
+- name: description
+  optional: true
+  type: String
+- default: '{}'
+  name: tables_dataset_metadata
+  optional: true
+  type: JsonObject
+- name: retry
+  optional: true
+- name: timeout
+  optional: true
+  type: Float
+- name: metadata
+  optional: true
+  type: JsonObject
+name: Automl create dataset for tables
+outputs:
+- name: dataset_path
+  type: String
+- name: create_time
+  type: String
+- name: dataset_id
+  type: String

components/gcp/automl/create_model_for_tables/component.py

@@ -0,0 +1,58 @@
+# 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.
+# 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.
+
+from typing import NamedTuple
+
+
+def automl_create_model_for_tables(
+    gcp_project_id: str,
+    gcp_region: str,
+    display_name: str,
+    dataset_id: str,
+    target_column_path: str = None,
+    input_feature_column_paths: list = None,
+    optimization_objective: str = 'MAXIMIZE_AU_PRC',
+    train_budget_milli_node_hours: int = 1000,
+) -> NamedTuple('Outputs', [('model_path', str), ('model_id', str)]):
+    import sys
+    import subprocess
+    subprocess.run([sys.executable, '-m', 'pip', 'install', 'google-cloud-automl==0.4.0', '--quiet', '--no-warn-script-location'], env={'PIP_DISABLE_PIP_VERSION_CHECK': '1'}, check=True)
+
+    from google.cloud import automl
+    client = automl.AutoMlClient()
+
+    location_path = client.location_path(gcp_project_id, gcp_region)
+    model_dict = {
+        'display_name': display_name,
+        'dataset_id': dataset_id, 
+        'tables_model_metadata': {
+            'target_column_spec': automl.types.ColumnSpec(name=target_column_path),
+            'input_feature_column_specs': [automl.types.ColumnSpec(name=path) for path in input_feature_column_paths] if input_feature_column_paths else None,
+            'optimization_objective': optimization_objective,
+            'train_budget_milli_node_hours': train_budget_milli_node_hours,
+        },  
+    }
+
+    create_model_response = client.create_model(location_path, model_dict)
+    print('Create model operation: {}'.format(create_model_response.operation))
+    result = create_model_response.result()
+    print(result)
+    model_name = result.name
+    model_id = model_name.rsplit('/', 1)[-1]
+    return (model_name, model_id)
+
+
+if __name__ == '__main__':
+    import kfp
+    kfp.components.func_to_container_op(automl_create_model_for_tables, output_component_file='component.yaml', base_image='python:3.7')