From 46e92657def3652239174fa56e866e076e3aab07 Mon Sep 17 00:00:00 2001 From: AWS <> Date: Wed, 21 Feb 2024 19:08:08 +0000 Subject: [PATCH] Amazon Lookout for Equipment Update: This release adds a field exposing model quality to read APIs for models. It also adds a model quality field to the API response when creating an inference scheduler. --- ...ure-AmazonLookoutforEquipment-9831e1a.json | 6 ++++ .../codegen-resources/service-2.json | 30 ++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-) create mode 100644 .changes/next-release/feature-AmazonLookoutforEquipment-9831e1a.json diff --git a/.changes/next-release/feature-AmazonLookoutforEquipment-9831e1a.json b/.changes/next-release/feature-AmazonLookoutforEquipment-9831e1a.json new file mode 100644 index 000000000000..7c34d68b7624 --- /dev/null +++ b/.changes/next-release/feature-AmazonLookoutforEquipment-9831e1a.json @@ -0,0 +1,6 @@ +{ + "type": "feature", + "category": "Amazon Lookout for Equipment", + "contributor": "", + "description": "This release adds a field exposing model quality to read APIs for models. It also adds a model quality field to the API response when creating an inference scheduler." +} diff --git a/services/lookoutequipment/src/main/resources/codegen-resources/service-2.json b/services/lookoutequipment/src/main/resources/codegen-resources/service-2.json index cb0f9dce1bff..396daf6fc2fe 100644 --- a/services/lookoutequipment/src/main/resources/codegen-resources/service-2.json +++ b/services/lookoutequipment/src/main/resources/codegen-resources/service-2.json @@ -1076,6 +1076,10 @@ "Status":{ "shape":"InferenceSchedulerStatus", "documentation":"

Indicates the status of the CreateInferenceScheduler operation.

" + }, + "ModelQuality":{ + "shape":"ModelQuality", + "documentation":"

Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value is QUALITY_THRESHOLD_MET.

If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels to the input dataset and retraining the model.

For information about using labels with your models, see Understanding labeling.

For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.

" } } }, @@ -2029,6 +2033,10 @@ "ModelDiagnosticsOutputConfiguration":{ "shape":"ModelDiagnosticsOutputConfiguration", "documentation":"

Configuration information for the model's pointwise model diagnostics.

" + }, + "ModelQuality":{ + "shape":"ModelQuality", + "documentation":"

Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value is QUALITY_THRESHOLD_MET.

If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels to the input dataset and retraining the model.

For information about using labels with your models, see Understanding labeling.

For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.

" } } }, @@ -2181,6 +2189,10 @@ "ModelDiagnosticsResultsObject":{ "shape":"S3Object", "documentation":"

The Amazon S3 output prefix for where Lookout for Equipment saves the pointwise model diagnostics for the model version.

" + }, + "ModelQuality":{ + "shape":"ModelQuality", + "documentation":"

Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value is QUALITY_THRESHOLD_MET.

If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels to the input dataset and retraining the model.

For information about using labels with your models, see Understanding labeling.

For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.

" } } }, @@ -3522,6 +3534,14 @@ "MANUAL" ] }, + "ModelQuality":{ + "type":"string", + "enum":[ + "QUALITY_THRESHOLD_MET", + "CANNOT_DETERMINE_QUALITY", + "POOR_QUALITY_DETECTED" + ] + }, "ModelStatus":{ "type":"string", "enum":[ @@ -3590,7 +3610,11 @@ "shape":"RetrainingSchedulerStatus", "documentation":"

Indicates the status of the retraining scheduler.

" }, - "ModelDiagnosticsOutputConfiguration":{"shape":"ModelDiagnosticsOutputConfiguration"} + "ModelDiagnosticsOutputConfiguration":{"shape":"ModelDiagnosticsOutputConfiguration"}, + "ModelQuality":{ + "shape":"ModelQuality", + "documentation":"

Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value is QUALITY_THRESHOLD_MET.

If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels to the input dataset and retraining the model.

For information about using labels with your models, see Understanding labeling.

For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.

" + } }, "documentation":"

Provides information about the specified machine learning model, including dataset and model names and ARNs, as well as status.

" }, @@ -3656,6 +3680,10 @@ "SourceType":{ "shape":"ModelVersionSourceType", "documentation":"

Indicates how this model version was generated.

" + }, + "ModelQuality":{ + "shape":"ModelQuality", + "documentation":"

Provides a quality assessment for a model that uses labels. If Lookout for Equipment determines that the model quality is poor based on training metrics, the value is POOR_QUALITY_DETECTED. Otherwise, the value is QUALITY_THRESHOLD_MET.

If the model is unlabeled, the model quality can't be assessed and the value of ModelQuality is CANNOT_DETERMINE_QUALITY. In this situation, you can get a model quality assessment by adding labels to the input dataset and retraining the model.

For information about improving the quality of a model, see Best practices with Amazon Lookout for Equipment.

" } }, "documentation":"

Contains information about the specific model version.

"