feat: Added AutoMLForecastingTrainingJob and tests

google/cloud/aiplatform/__init__.py

@@ -33,6 +33,7 @@
     CustomContainerTrainingJob,
     CustomPythonPackageTrainingJob,
     AutoMLTabularTrainingJob,
+    AutoMLForecastingTrainingJob,
     AutoMLImageTrainingJob,
     AutoMLTextTrainingJob,
     AutoMLVideoTrainingJob,
@@ -52,6 +53,7 @@
     "init",
     "AutoMLImageTrainingJob",
     "AutoMLTabularTrainingJob",
+    "AutoMLForecastingTrainingJob",
     "AutoMLTextTrainingJob",
     "AutoMLVideoTrainingJob",
     "BatchPredictionJob",
@@ -63,5 +65,6 @@
     "Model",
     "TabularDataset",
     "TextDataset",
+    "TimeSeriesDataset",
     "VideoDataset",
 )

google/cloud/aiplatform/datasets/__init__.py

@@ -17,6 +17,7 @@
 
 from google.cloud.aiplatform.datasets.dataset import _Dataset
 from google.cloud.aiplatform.datasets.tabular_dataset import TabularDataset
+from google.cloud.aiplatform.datasets.time_series_dataset import TimeSeriesDataset
 from google.cloud.aiplatform.datasets.image_dataset import ImageDataset
 from google.cloud.aiplatform.datasets.text_dataset import TextDataset
 from google.cloud.aiplatform.datasets.video_dataset import VideoDataset
@@ -25,6 +26,7 @@
 __all__ = (
     "_Dataset",
     "TabularDataset",
+    "TimeSeriesDataset",
     "ImageDataset",
     "TextDataset",
     "VideoDataset",

google/cloud/aiplatform/datasets/_datasources.py

@@ -224,6 +224,11 @@ def create_datasource(
             raise ValueError("tabular dataset does not support data import.")
         return TabularDatasource(gcs_source, bq_source)
 
+    if metadata_schema_uri == schema.dataset.metadata.time_series:
+        if import_schema_uri:
+            raise ValueError("time series dataset does not support data import.")
+        return TabularDatasource(gcs_source, bq_source)
+
     if not import_schema_uri and not gcs_source:
         return NonTabularDatasource()
     elif import_schema_uri and gcs_source:

google/cloud/aiplatform/datasets/time_series_dataset.py

@@ -0,0 +1,134 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2020 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 Optional, Sequence, Tuple, Union
+
+from google.auth import credentials as auth_credentials
+
+from google.cloud.aiplatform import datasets
+from google.cloud.aiplatform.datasets import _datasources
+from google.cloud.aiplatform import initializer
+from google.cloud.aiplatform import schema
+from google.cloud.aiplatform import utils
+
+
+class TimeSeriesDataset(datasets._Dataset):
+    """Managed time series dataset resource for AI Platform"""
+
+    _supported_metadata_schema_uris: Optional[Tuple[str]] = (
+        schema.dataset.metadata.time_series,
+    )
+
+    @classmethod
+    def create(
+        cls,
+        display_name: str,
+        gcs_source: Optional[Union[str, Sequence[str]]] = None,
+        bq_source: Optional[str] = None,
+        project: Optional[str] = None,
+        location: Optional[str] = None,
+        credentials: Optional[auth_credentials.Credentials] = None,
+        request_metadata: Optional[Sequence[Tuple[str, str]]] = (),
+        encryption_spec_key_name: Optional[str] = None,
+        sync: bool = True,
+    ) -> "TimeSeriesDataset":
+        """Creates a new tabular dataset.
+
+        Args:
+            display_name (str):
+                Required. The user-defined name of the Dataset.
+                The name can be up to 128 characters long and can be consist
+                of any UTF-8 characters.
+            gcs_source (Union[str, Sequence[str]]):
+                Google Cloud Storage URI(-s) to the
+                input file(s). May contain wildcards. For more
+                information on wildcards, see
+                https://cloud.google.com/storage/docs/gsutil/addlhelp/WildcardNames.
+                examples:
+                    str: "gs://bucket/file.csv"
+                    Sequence[str]: ["gs://bucket/file1.csv", "gs://bucket/file2.csv"]
+            bq_source (str):
+                BigQuery URI to the input table.
+                example:
+                    "bq://project.dataset.table_name"
+            project (str):
+                Project to upload this model to. Overrides project set in
+                aiplatform.init.
+            location (str):
+                Location to upload this model to. Overrides location set in
+                aiplatform.init.
+            credentials (auth_credentials.Credentials):
+                Custom credentials to use to upload this model. Overrides
+                credentials set in aiplatform.init.
+            request_metadata (Sequence[Tuple[str, str]]):
+                Strings which should be sent along with the request as metadata.
+            encryption_spec_key_name (Optional[str]):
+                Optional. The Cloud KMS resource identifier of the customer
+                managed encryption key used to protect the dataset. Has the
+                form:
+                ``projects/my-project/locations/my-region/keyRings/my-kr/cryptoKeys/my-key``.
+                The key needs to be in the same region as where the compute
+                resource is created.
+
+                If set, this Dataset and all sub-resources of this Dataset will be secured by this key.
+
+                Overrides encryption_spec_key_name set in aiplatform.init.
+            sync (bool):
+                Whether to execute this method synchronously. If False, this method
+                will be executed in concurrent Future and any downstream object will
+                be immediately returned and synced when the Future has completed.
+
+        Returns:
+            time_series_dataset (TimeSeriesDataset):
+                Instantiated representation of the managed time series dataset resource.
+
+        """
+
+        utils.validate_display_name(display_name)
+
+        api_client = cls._instantiate_client(location=location, credentials=credentials)
+
+        metadata_schema_uri = schema.dataset.metadata.time_series
+
+        datasource = _datasources.create_datasource(
+            metadata_schema_uri=metadata_schema_uri,
+            gcs_source=gcs_source,
+            bq_source=bq_source,
+        )
+
+        return cls._create_and_import(
+            api_client=api_client,
+            parent=initializer.global_config.common_location_path(
+                project=project, location=location
+            ),
+            display_name=display_name,
+            metadata_schema_uri=metadata_schema_uri,
+            datasource=datasource,
+            project=project or initializer.global_config.project,
+            location=location or initializer.global_config.location,
+            credentials=credentials or initializer.global_config.credentials,
+            request_metadata=request_metadata,
+            encryption_spec=initializer.global_config.get_encryption_spec(
+                encryption_spec_key_name=encryption_spec_key_name
+            ),
+            sync=sync,
+        )
+
+    def import_data(self):
+        raise NotImplementedError(
+            f"{self.__class__.__name__} class does not support 'import_data'"
+        )

google/cloud/aiplatform/schema.py

@@ -22,6 +22,7 @@ class training_job:
     class definition:
         custom_task = "gs://google-cloud-aiplatform/schema/trainingjob/definition/custom_task_1.0.0.yaml"
         automl_tabular = "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_tabular_1.0.0.yaml"
+        automl_forecasting = "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_time_series_forecasting_1.0.0.yaml"
         automl_image_classification = "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_image_classification_1.0.0.yaml"
         automl_image_object_detection = "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_image_object_detection_1.0.0.yaml"
         automl_text_classification = "gs://google-cloud-aiplatform/schema/trainingjob/definition/automl_text_classification_1.0.0.yaml"
@@ -37,6 +38,7 @@ class metadata:
         tabular = (
             "gs://google-cloud-aiplatform/schema/dataset/metadata/tabular_1.0.0.yaml"
         )
+        time_series = "gs://google-cloud-aiplatform/schema/dataset/metadata/time_series_1.0.0.yaml"
         image = "gs://google-cloud-aiplatform/schema/dataset/metadata/image_1.0.0.yaml"
         text = "gs://google-cloud-aiplatform/schema/dataset/metadata/text_1.0.0.yaml"
         video = "gs://google-cloud-aiplatform/schema/dataset/metadata/video_1.0.0.yaml"