components automl_many_models_inference_setup_step

AutoML Many Models - Inference Setup Step

automl_many_models_inference_setup_step

Overview

Version: 0.0.6

View in Studio: https://ml.azure.com/registries/azureml/components/automl_many_models_inference_setup_step/version/0.0.6

Inputs

Name	Description	Type	Default	Optional	Enum
raw_data	Folder URI with inferencing test data to be partitioned.	uri_folder
instance_count	Number of nodes in a compute cluster we will run the inference step on.	integer
max_concurrency_per_instance	Number of processes that will be run concurrently on any given node. This number should not be larger than 1/2 of the number of cores in an individual node in the specified cluster	integer
parallel_step_timeout_in_seconds	The PRS step time out settings.	integer
train_run_id	The train run id used for training models that will be used to generate forecasts.	string		True
training_experiment_name	The training experiment that used for inference	string		True
partition_column_names	The partition column names for inference.	string		True
forecast_quantiles	Space separated list of quantiles for forecasting jobs. It is applicable only when the forecast_mode is recursive.	string		True
inference_type	The inference type of the inference. The default value will be forecast.	string		True	['forecast', 'predict', 'predict_proba']
forecast_mode	The forecast mode used for inference. The possible values are recursive and rolling.	string		True	['recursive', 'rolling']
forecast_step	The forecast step used for inference.	integer		True
allow_multi_partitions	Allow multi paritions in one partitioned file.	boolean		True
skip_concat_results	Flag on skip concat inference results.	boolean		True
early_validation_failure	Enable early validation Failure.	boolean		True
optional_train_metadata	Metadata from training run.	uri_folder		True
label_column_name	Label column name for the data.	string		True
internal_skip_data_access	Early failure when disabling data access in setup phase.	boolean	False	True
enable_event_logger	Enable event logger.	boolean		True

Outputs

Name	Description	Type
metadata	The metadata from the setup outputs.	uri_folder
processed_data	The processed data after setup step.	uri_folder

Environment

azureml://registries/azureml/environments/automl-gpu/labels/latest