def test_run_with_experiments(
self,
mock_pipeline_service_create,
mock_dataset_time_series,
mock_model_service_get,
sync,
):
aiplatform.init(project=_TEST_PROJECT, staging_bucket=_TEST_BUCKET_NAME)
job = AutoMLForecastingTrainingJob(
display_name=_TEST_DISPLAY_NAME,
optimization_objective=_TEST_TRAINING_OPTIMIZATION_OBJECTIVE_NAME,
column_transformations=_TEST_TRAINING_COLUMN_TRANSFORMATIONS,
)
model_from_job = job._run_with_experiments(
dataset=mock_dataset_time_series,
target_column=_TEST_TRAINING_TARGET_COLUMN,
time_column=_TEST_TRAINING_TIME_COLUMN,
time_series_identifier_column=_TEST_TRAINING_TIME_SERIES_IDENTIFIER_COLUMN,
unavailable_at_forecast_columns=_TEST_TRAINING_UNAVAILABLE_AT_FORECAST_COLUMNS,
available_at_forecast_columns=_TEST_TRAINING_AVAILABLE_AT_FORECAST_COLUMNS,
forecast_horizon=_TEST_TRAINING_FORECAST_HORIZON,
data_granularity_unit=_TEST_TRAINING_DATA_GRANULARITY_UNIT,
data_granularity_count=_TEST_TRAINING_DATA_GRANULARITY_COUNT,
weight_column=_TEST_TRAINING_WEIGHT_COLUMN,
time_series_attribute_columns=_TEST_TRAINING_TIME_SERIES_ATTRIBUTE_COLUMNS,
context_window=_TEST_TRAINING_CONTEXT_WINDOW,
budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS,
export_evaluated_data_items=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS,
export_evaluated_data_items_bigquery_destination_uri=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
export_evaluated_data_items_override_destination=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
quantiles=_TEST_TRAINING_QUANTILES,
validation_options=_TEST_TRAINING_VALIDATION_OPTIONS,
sync=sync,
additional_experiments=_TEST_ADDITIONAL_EXPERIMENTS,
)
if not sync:
model_from_job.wait()
# Test that if defaults to the job display name
true_managed_model = gca_model.Model(display_name=_TEST_DISPLAY_NAME)
true_input_data_config = gca_training_pipeline.InputDataConfig(
dataset_id=mock_dataset_time_series.name,
)
true_training_pipeline = gca_training_pipeline.TrainingPipeline(
display_name=_TEST_DISPLAY_NAME,
training_task_definition=schema.training_job.definition.automl_forecasting,
training_task_inputs=_TEST_TRAINING_TASK_INPUTS_WITH_ADDITIONAL_EXPERIMENTS,
model_to_upload=true_managed_model,
input_data_config=true_input_data_config,
)
mock_pipeline_service_create.assert_called_once_with(
parent=initializer.global_config.common_location_path(),
training_pipeline=true_training_pipeline,
)
def test_run_called_twice_raises(
self, mock_dataset_time_series, sync,
):
aiplatform.init(project=_TEST_PROJECT, staging_bucket=_TEST_BUCKET_NAME)
job = AutoMLForecastingTrainingJob(
display_name=_TEST_DISPLAY_NAME,
optimization_objective=_TEST_TRAINING_OPTIMIZATION_OBJECTIVE_NAME,
column_transformations=_TEST_TRAINING_COLUMN_TRANSFORMATIONS,
)
job.run(
dataset=mock_dataset_time_series,
target_column=_TEST_TRAINING_TARGET_COLUMN,
time_column=_TEST_TRAINING_TIME_COLUMN,
time_series_identifier_column=_TEST_TRAINING_TIME_SERIES_IDENTIFIER_COLUMN,
unavailable_at_forecast_columns=_TEST_TRAINING_UNAVAILABLE_AT_FORECAST_COLUMNS,
available_at_forecast_columns=_TEST_TRAINING_AVAILABLE_AT_FORECAST_COLUMNS,
forecast_horizon=_TEST_TRAINING_FORECAST_HORIZON,
data_granularity_unit=_TEST_TRAINING_DATA_GRANULARITY_UNIT,
data_granularity_count=_TEST_TRAINING_DATA_GRANULARITY_COUNT,
model_display_name=_TEST_MODEL_DISPLAY_NAME,
weight_column=_TEST_TRAINING_WEIGHT_COLUMN,
time_series_attribute_columns=_TEST_TRAINING_TIME_SERIES_ATTRIBUTE_COLUMNS,
context_window=_TEST_TRAINING_CONTEXT_WINDOW,
budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS,
export_evaluated_data_items=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS,
export_evaluated_data_items_bigquery_destination_uri=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
export_evaluated_data_items_override_destination=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
quantiles=_TEST_TRAINING_QUANTILES,
validation_options=_TEST_TRAINING_VALIDATION_OPTIONS,
sync=sync,
)
with pytest.raises(RuntimeError):
job.run(
dataset=mock_dataset_time_series,
target_column=_TEST_TRAINING_TARGET_COLUMN,
time_column=_TEST_TRAINING_TIME_COLUMN,
time_series_identifier_column=_TEST_TRAINING_TIME_SERIES_IDENTIFIER_COLUMN,
unavailable_at_forecast_columns=_TEST_TRAINING_UNAVAILABLE_AT_FORECAST_COLUMNS,
available_at_forecast_columns=_TEST_TRAINING_AVAILABLE_AT_FORECAST_COLUMNS,
forecast_horizon=_TEST_TRAINING_FORECAST_HORIZON,
data_granularity_unit=_TEST_TRAINING_DATA_GRANULARITY_UNIT,
data_granularity_count=_TEST_TRAINING_DATA_GRANULARITY_COUNT,
model_display_name=_TEST_MODEL_DISPLAY_NAME,
weight_column=_TEST_TRAINING_WEIGHT_COLUMN,
time_series_attribute_columns=_TEST_TRAINING_TIME_SERIES_ATTRIBUTE_COLUMNS,
context_window=_TEST_TRAINING_CONTEXT_WINDOW,
budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS,
export_evaluated_data_items=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS,
export_evaluated_data_items_bigquery_destination_uri=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
export_evaluated_data_items_override_destination=_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
quantiles=_TEST_TRAINING_QUANTILES,
validation_options=_TEST_TRAINING_VALIDATION_OPTIONS,
sync=sync,
)
def test_raises_before_run_is_called(self, mock_pipeline_service_create):
aiplatform.init(project=_TEST_PROJECT, staging_bucket=_TEST_BUCKET_NAME)
job = AutoMLForecastingTrainingJob(
display_name=_TEST_DISPLAY_NAME,
optimization_objective=_TEST_TRAINING_OPTIMIZATION_OBJECTIVE_NAME,
column_transformations=_TEST_TRAINING_COLUMN_TRANSFORMATIONS,
)
with pytest.raises(RuntimeError):
job.get_model()
with pytest.raises(RuntimeError):
job.has_failed
with pytest.raises(RuntimeError):
job.state
def test_run_call_pipeline_service_create(
self,
mock_pipeline_service_create,
mock_pipeline_service_get,
mock_dataset_time_series,
mock_model_service_get,
sync,
):
aiplatform.init(project=_TEST_PROJECT,
staging_bucket=_TEST_BUCKET_NAME)
job = AutoMLForecastingTrainingJob(
display_name=_TEST_DISPLAY_NAME,
optimization_objective=_TEST_TRAINING_OPTIMIZATION_OBJECTIVE_NAME,
column_transformations=_TEST_TRAINING_COLUMN_TRANSFORMATIONS,
)
model_from_job = job.run(
dataset=mock_dataset_time_series,
target_column=_TEST_TRAINING_TARGET_COLUMN,
time_column=_TEST_TRAINING_TIME_COLUMN,
time_series_identifier_column=
_TEST_TRAINING_TIME_SERIES_IDENTIFIER_COLUMN,
unavailable_at_forecast_columns=
_TEST_TRAINING_UNAVAILABLE_AT_FORECAST_COLUMNS,
available_at_forecast_columns=
_TEST_TRAINING_AVAILABLE_AT_FORECAST_COLUMNS,
forecast_horizon=_TEST_TRAINING_FORECAST_HORIZON,
data_granularity_unit=_TEST_TRAINING_DATA_GRANULARITY_UNIT,
data_granularity_count=_TEST_TRAINING_DATA_GRANULARITY_COUNT,
model_display_name=_TEST_MODEL_DISPLAY_NAME,
predefined_split_column_name=_TEST_PREDEFINED_SPLIT_COLUMN_NAME,
weight_column=_TEST_TRAINING_WEIGHT_COLUMN,
time_series_attribute_columns=
_TEST_TRAINING_TIME_SERIES_ATTRIBUTE_COLUMNS,
context_window=_TEST_TRAINING_CONTEXT_WINDOW,
budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS,
export_evaluated_data_items=
_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS,
export_evaluated_data_items_bigquery_destination_uri=
_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
export_evaluated_data_items_override_destination=
_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
quantiles=_TEST_TRAINING_QUANTILES,
validation_options=_TEST_TRAINING_VALIDATION_OPTIONS,
sync=sync,
)
if not sync:
model_from_job.wait()
true_fraction_split = gca_training_pipeline.FractionSplit(
training_fraction=_TEST_TRAINING_FRACTION_SPLIT,
validation_fraction=_TEST_VALIDATION_FRACTION_SPLIT,
test_fraction=_TEST_TEST_FRACTION_SPLIT,
)
true_managed_model = gca_model.Model(
display_name=_TEST_MODEL_DISPLAY_NAME)
true_input_data_config = gca_training_pipeline.InputDataConfig(
fraction_split=true_fraction_split,
predefined_split=gca_training_pipeline.PredefinedSplit(
key=_TEST_PREDEFINED_SPLIT_COLUMN_NAME),
dataset_id=mock_dataset_time_series.name,
)
true_training_pipeline = gca_training_pipeline.TrainingPipeline(
display_name=_TEST_DISPLAY_NAME,
training_task_definition=schema.training_job.definition.
automl_forecasting,
training_task_inputs=_TEST_TRAINING_TASK_INPUTS,
model_to_upload=true_managed_model,
input_data_config=true_input_data_config,
)
mock_pipeline_service_create.assert_called_once_with(
parent=initializer.global_config.common_location_path(),
training_pipeline=true_training_pipeline,
)
assert job._gca_resource is mock_pipeline_service_get.return_value
mock_model_service_get.assert_called_once_with(name=_TEST_MODEL_NAME)
assert model_from_job._gca_resource is mock_model_service_get.return_value
assert job.get_model(
)._gca_resource is mock_model_service_get.return_value
assert not job.has_failed
assert job.state == gca_pipeline_state.PipelineState.PIPELINE_STATE_SUCCEEDED
def test_splits_default(
self,
mock_pipeline_service_create,
mock_pipeline_service_get,
mock_dataset_time_series,
mock_model_service_get,
sync,
):
"""
Initiate aiplatform with encryption key name.
Create and run an AutoML Video Classification training job, verify calls and return value
"""
aiplatform.init(
project=_TEST_PROJECT,
encryption_spec_key_name=_TEST_DEFAULT_ENCRYPTION_KEY_NAME,
)
job = AutoMLForecastingTrainingJob(
display_name=_TEST_DISPLAY_NAME,
optimization_objective=_TEST_TRAINING_OPTIMIZATION_OBJECTIVE_NAME,
column_transformations=_TEST_TRAINING_COLUMN_TRANSFORMATIONS,
)
model_from_job = job.run(
dataset=mock_dataset_time_series,
target_column=_TEST_TRAINING_TARGET_COLUMN,
time_column=_TEST_TRAINING_TIME_COLUMN,
time_series_identifier_column=
_TEST_TRAINING_TIME_SERIES_IDENTIFIER_COLUMN,
unavailable_at_forecast_columns=
_TEST_TRAINING_UNAVAILABLE_AT_FORECAST_COLUMNS,
available_at_forecast_columns=
_TEST_TRAINING_AVAILABLE_AT_FORECAST_COLUMNS,
forecast_horizon=_TEST_TRAINING_FORECAST_HORIZON,
data_granularity_unit=_TEST_TRAINING_DATA_GRANULARITY_UNIT,
data_granularity_count=_TEST_TRAINING_DATA_GRANULARITY_COUNT,
model_display_name=_TEST_MODEL_DISPLAY_NAME,
weight_column=_TEST_TRAINING_WEIGHT_COLUMN,
time_series_attribute_columns=
_TEST_TRAINING_TIME_SERIES_ATTRIBUTE_COLUMNS,
context_window=_TEST_TRAINING_CONTEXT_WINDOW,
budget_milli_node_hours=_TEST_TRAINING_BUDGET_MILLI_NODE_HOURS,
export_evaluated_data_items=
_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS,
export_evaluated_data_items_bigquery_destination_uri=
_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_BIGQUERY_DESTINATION_URI,
export_evaluated_data_items_override_destination=
_TEST_TRAINING_EXPORT_EVALUATED_DATA_ITEMS_OVERRIDE_DESTINATION,
quantiles=_TEST_TRAINING_QUANTILES,
validation_options=_TEST_TRAINING_VALIDATION_OPTIONS,
sync=sync,
create_request_timeout=None,
)
if not sync:
model_from_job.wait()
true_managed_model = gca_model.Model(
display_name=_TEST_MODEL_DISPLAY_NAME,
encryption_spec=_TEST_DEFAULT_ENCRYPTION_SPEC,
)
true_input_data_config = gca_training_pipeline.InputDataConfig(
dataset_id=mock_dataset_time_series.name, )
true_training_pipeline = gca_training_pipeline.TrainingPipeline(
display_name=_TEST_DISPLAY_NAME,
training_task_definition=schema.training_job.definition.
automl_forecasting,
training_task_inputs=_TEST_TRAINING_TASK_INPUTS,
model_to_upload=true_managed_model,
input_data_config=true_input_data_config,
encryption_spec=_TEST_DEFAULT_ENCRYPTION_SPEC,
)
mock_pipeline_service_create.assert_called_once_with(
parent=initializer.global_config.common_location_path(),
training_pipeline=true_training_pipeline,
timeout=None,
)