docs(samples): Added seq2seq sample

samples/model-builder/conftest.py

@@ -249,6 +249,19 @@ def mock_run_automl_forecasting_training_job(mock_forecasting_training_job):
         yield mock
 
 
+@pytest.fixture
+def mock_get_automl_forecasting_seq2seq_training_job(mock_forecasting_training_job):
+    with patch.object(aiplatform, "SequenceToSequencePlusForecastingTrainingJob") as mock:
+        mock.return_value = mock_forecasting_training_job
+        yield mock
+
+
+@pytest.fixture
+def mock_run_automl_forecasting_seq2seq_training_job(mock_forecasting_training_job):
+    with patch.object(mock_forecasting_training_job, "run") as mock:
+        yield mock
+
+
 @pytest.fixture
 def mock_get_automl_image_training_job(mock_image_training_job):
     with patch.object(aiplatform, "AutoMLImageTrainingJob") as mock:

samples/model-builder/create_training_pipeline_forecasting_sample.py

@@ -23,7 +23,7 @@ def create_training_pipeline_forecasting_sample(
     display_name: str,
     dataset_id: str,
     location: str = "us-central1",
-    model_display_name: str = None,
+    model_display_name: str = "my_model",
     target_column: str = "target_column",
     time_column: str = "date",
     time_series_identifier_column: str = "time_series_id",

samples/model-builder/create_training_pipeline_forecasting_seq2seq_sample.py

@@ -0,0 +1,98 @@
+# Copyright 2022 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 typing import List, Optional
+
+from google.cloud import aiplatform
+
+
+#  [START aiplatform_sdk_create_training_pipeline_forecasting_seq2seq_sample]
+def create_training_pipeline_forecasting_seq2seq_sample(
+    project: str,
+    display_name: str,
+    dataset_id: str,
+    location: str = "us-central1",
+    model_display_name: str = "my_model",
+    target_column: str = "target_column",
+    time_column: str = "date",
+    time_series_identifier_column: str = "time_series_id",
+    unavailable_at_forecast_columns: List[str] = [],
+    available_at_forecast_columns: List[str] = [],
+    forecast_horizon: int = 1,
+    data_granularity_unit: str = "week",
+    data_granularity_count: int = 1,
+    training_fraction_split: float = 0.8,
+    validation_fraction_split: float = 0.1,
+    test_fraction_split: float = 0.1,
+    budget_milli_node_hours: int = 8000,
+    timestamp_split_column_name: str = "timestamp_split",
+    weight_column: str = "weight",
+    time_series_attribute_columns: List[str] = [],
+    context_window: int = 0,
+    export_evaluated_data_items: bool = False,
+    export_evaluated_data_items_bigquery_destination_uri: Optional[str] = None,
+    export_evaluated_data_items_override_destination: bool = False,
+    quantiles: Optional[List[float]] = None,
+    validation_options: Optional[str] = None,
+    predefined_split_column_name: Optional[str] = None,
+    sync: bool = True,
+):
+    aiplatform.init(project=project, location=location)
+
+    # Create training job
+    forecasting_seq2seq_job = aiplatform.SequenceToSequencePlusForecastingTrainingJob(
+        display_name=display_name, optimization_objective="minimize-rmse"
+    )
+
+    # Retrieve existing dataset
+    dataset = aiplatform.TimeSeriesDataset(dataset_id)
+
+    # Run training job
+    model = forecasting_seq2seq_job.run(
+        dataset=dataset,
+        target_column=target_column,
+        time_column=time_column,
+        time_series_identifier_column=time_series_identifier_column,
+        unavailable_at_forecast_columns=unavailable_at_forecast_columns,
+        available_at_forecast_columns=available_at_forecast_columns,
+        forecast_horizon=forecast_horizon,
+        data_granularity_unit=data_granularity_unit,
+        data_granularity_count=data_granularity_count,
+        training_fraction_split=training_fraction_split,
+        validation_fraction_split=validation_fraction_split,
+        test_fraction_split=test_fraction_split,
+        predefined_split_column_name=predefined_split_column_name,
+        timestamp_split_column_name=timestamp_split_column_name,
+        weight_column=weight_column,
+        time_series_attribute_columns=time_series_attribute_columns,
+        context_window=context_window,
+        export_evaluated_data_items=export_evaluated_data_items,
+        export_evaluated_data_items_bigquery_destination_uri=export_evaluated_data_items_bigquery_destination_uri,
+        export_evaluated_data_items_override_destination=export_evaluated_data_items_override_destination,
+        quantiles=quantiles,
+        validation_options=validation_options,
+        budget_milli_node_hours=budget_milli_node_hours,
+        model_display_name=model_display_name,
+        sync=sync,
+    )
+
+    model.wait()
+
+    print(model.display_name)
+    print(model.resource_name)
+    print(model.uri)
+    return model
+
+
+#  [END aiplatform_sdk_create_training_pipeline_forecasting_seq2seq_sample]

samples/model-builder/create_training_pipeline_forecasting_seq2seq_sample_test.py

@@ -0,0 +1,85 @@
+# Copyright 2022 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_forecasting_seq2seq_sample
+import test_constants as constants
+
+
+def test_create_training_pipeline_forecasting_seq2seq_sample(
+    mock_sdk_init,
+    mock_time_series_dataset,
+    mock_get_automl_forecasting_seq2seq_training_job,
+    mock_run_automl_forecasting_seq2seq_training_job,
+    mock_get_time_series_dataset,
+):
+
+    create_training_pipeline_forecasting_seq2seq_sample.create_training_pipeline_forecasting_seq2seq_sample(
+        project=constants.PROJECT,
+        display_name=constants.DISPLAY_NAME,
+        dataset_id=constants.RESOURCE_ID,
+        model_display_name=constants.DISPLAY_NAME_2,
+        target_column=constants.TABULAR_TARGET_COLUMN,
+        training_fraction_split=constants.TRAINING_FRACTION_SPLIT,
+        validation_fraction_split=constants.VALIDATION_FRACTION_SPLIT,
+        test_fraction_split=constants.TEST_FRACTION_SPLIT,
+        budget_milli_node_hours=constants.BUDGET_MILLI_NODE_HOURS_8000,
+        timestamp_split_column_name=constants.TIMESTAMP_SPLIT_COLUMN_NAME,
+        weight_column=constants.WEIGHT_COLUMN,
+        time_series_attribute_columns=constants.TIME_SERIES_ATTRIBUTE_COLUMNS,
+        context_window=constants.CONTEXT_WINDOW,
+        export_evaluated_data_items=constants.EXPORT_EVALUATED_DATA_ITEMS,
+        export_evaluated_data_items_bigquery_destination_uri=constants.EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
+        export_evaluated_data_items_override_destination=constants.EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
+        quantiles=constants.QUANTILES,
+        validation_options=constants.VALIDATION_OPTIONS,
+        predefined_split_column_name=constants.PREDEFINED_SPLIT_COLUMN_NAME,
+    )
+
+    mock_get_time_series_dataset.assert_called_once_with(constants.RESOURCE_ID)
+
+    mock_sdk_init.assert_called_once_with(
+        project=constants.PROJECT, location=constants.LOCATION
+    )
+    mock_get_automl_forecasting_seq2seq_training_job.assert_called_once_with(
+        display_name=constants.DISPLAY_NAME,
+        optimization_objective="minimize-rmse",
+    )
+    mock_run_automl_forecasting_seq2seq_training_job.assert_called_once_with(
+        dataset=mock_time_series_dataset,
+        target_column=constants.TABULAR_TARGET_COLUMN,
+        time_column=constants.FORECASTNG_TIME_COLUMN,
+        time_series_identifier_column=constants.FORECASTNG_TIME_SERIES_IDENTIFIER_COLUMN,
+        unavailable_at_forecast_columns=constants.FORECASTNG_UNAVAILABLE_AT_FORECAST_COLUMNS,
+        available_at_forecast_columns=constants.FORECASTNG_AVAILABLE_AT_FORECAST_COLUMNS,
+        forecast_horizon=constants.FORECASTNG_FORECAST_HORIZON,
+        data_granularity_unit=constants.DATA_GRANULARITY_UNIT,
+        data_granularity_count=constants.DATA_GRANULARITY_COUNT,
+        training_fraction_split=constants.TRAINING_FRACTION_SPLIT,
+        validation_fraction_split=constants.VALIDATION_FRACTION_SPLIT,
+        test_fraction_split=constants.TEST_FRACTION_SPLIT,
+        budget_milli_node_hours=constants.BUDGET_MILLI_NODE_HOURS_8000,
+        model_display_name=constants.DISPLAY_NAME_2,
+        timestamp_split_column_name=constants.TIMESTAMP_SPLIT_COLUMN_NAME,
+        weight_column=constants.WEIGHT_COLUMN,
+        time_series_attribute_columns=constants.TIME_SERIES_ATTRIBUTE_COLUMNS,
+        context_window=constants.CONTEXT_WINDOW,
+        export_evaluated_data_items=constants.EXPORT_EVALUATED_DATA_ITEMS,
+        export_evaluated_data_items_bigquery_destination_uri=constants.EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
+        export_evaluated_data_items_override_destination=constants.EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
+        quantiles=constants.QUANTILES,
+        validation_options=constants.VALIDATION_OPTIONS,
+        predefined_split_column_name=constants.PREDEFINED_SPLIT_COLUMN_NAME,
+        sync=True,
+    )

samples/model-builder/create_training_pipeline_tabular_regression_sample.py

@@ -21,7 +21,7 @@ def create_training_pipeline_tabular_regression_sample(
     display_name: str,
     dataset_id: str,
     location: str = "us-central1",
-    model_display_name: str = None,
+    model_display_name: str = "my_model",
     target_column: str = "target_column",
     training_fraction_split: float = 0.8,
     validation_fraction_split: float = 0.1,