components automl_many_models_inference - Azure/azureml-assets GitHub Wiki
Inference components for AutoML many model.
Version: 0.0.7
View in Studio: https://ml.azure.com/registries/azureml/components/automl_many_models_inference/version/0.0.7
| Name | Description | Type | Default | Optional | Enum |
|---|---|---|---|---|---|
| raw_data | Folder URI with inference data. | uri_folder | |||
| compute_name | Compute name for inference pipeline. | string | |||
| max_nodes | Number of nodes in a compute cluster we will run the inference step on. | integer | |||
| max_concurrency_per_node | 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 setting in seconds. | integer | 3600 | ||
| 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, possible values are forecast, predict and predict_proba. predict_proba`` should be used on the classification tasks, predictshould be used on the regression tasks andforecast` should be used on the forecasting tasks. |
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 rolling forecast. See more details here: https://learn.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-forecast?view=azureml-api-2#evaluating-model-accuracy-with-a-rolling-forecast | integer | 1 | True | |
| allow_multi_partitions | Allow multi paritions in one partitioned file | boolean | True | ||
| skip_concat_results | Flag on skip concat inferece results | boolean | True | ||
| early_validation_failure | Enable early failure validations | boolean | True | ||
| optional_train_metadata | Metadata from training run. | uri_folder | True | ||
| label_column_name | Label column name for the data. | string | True |
| Name | Description | Type |
|---|---|---|
| run_output | Folder URI representing the location of the output data | uri_folder |
| raw_predictions | The raw forecast results from each inferece run | uri_folder |
| evaluation_configs | The evaluation configs. | uri_file |
| evaluation_data | The evaluation data. | uri_file |