aws-sdk-sagemaker 1.191.0 → 1.192.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c5a11a92ae9b1f7dd4576c7bb6eae1b62aa9a1c0ed7ae60f9e9ed65530576e78
-  data.tar.gz: 20605cdbe5d1510b493fc76073591c26216eda6e4f87c492a119b07981bde826
+  metadata.gz: ea2b0bfd3b4390fa357475a5d054208271cd3aaf4e450e89531bf0f205b22a66
+  data.tar.gz: b84a2185dffd514d6f76fa68a05b2f546939b70177779278f88853e7e328be0a
 SHA512:
-  metadata.gz: ff5009d9104e86b816c8d1e5c888b5a62685dde25be5409dff164ecefb2f1e12bc3f45d48eb09871d0bd2913235b361230a8dfd13328def19821dc6e30953e4f
-  data.tar.gz: ae8df2ffe98ba597b35358eb42a32387d2371c05192aa72630445205b11fe68018b1d9f79f52ffa1052139abf3c452fb6dd5b4869da308e9ce294d6f06d0688e
+  metadata.gz: d8835cdf47bbb5c4e1b3bbc42cb782b0da023e3cb3790deeb32d6f006c901999aa620e04aea27f688410d70c0fed4efe8d970f592c0b1d9a36b6514f765c5d0c
+  data.tar.gz: abe87a3fa189453639cb875bdcd2750775c3f9716ea8fca2803879cfbc3252ed496954e2bd1f53452e4f0a0c9932331c05e80c36e1dfa138dc1a83d720c509e1

data/CHANGELOG.md

@@ -1,6 +1,11 @@
 Unreleased Changes
 ------------------
 
+1.192.0 (2023-06-29)
+------------------
+
+* Feature - Adding support for timeseries forecasting in the CreateAutoMLJobV2 API.
+
 1.191.0 (2023-06-28)
 ------------------
 

data/VERSION

@@ -1 +1 @@
-1.191.0
+1.192.0

data/lib/aws-sdk-sagemaker/client.rb

@@ -1307,7 +1307,7 @@ module Aws::SageMaker
     #     },
     #     problem_type: "BinaryClassification", # accepts BinaryClassification, MulticlassClassification, Regression
     #     auto_ml_job_objective: {
-    #       metric_name: "Accuracy", # required, accepts Accuracy, MSE, F1, F1macro, AUC, RMSE, MAE, R2, BalancedAccuracy, Precision, PrecisionMacro, Recall, RecallMacro
+    #       metric_name: "Accuracy", # required, accepts Accuracy, MSE, F1, F1macro, AUC, RMSE, MAE, R2, BalancedAccuracy, Precision, PrecisionMacro, Recall, RecallMacro, MAPE, MASE, WAPE, AverageWeightedQuantileLoss
     #     },
     #     auto_ml_job_config: {
     #       completion_criteria: {
@@ -1405,12 +1405,14 @@ module Aws::SageMaker
     #   [InputDataConfig][1] attribute in the `CreateAutoMLJob` input
     #   parameters. The supported formats depend on the problem type:
     #
-    #   * For Tabular problem types: `S3Prefix`, `ManifestFile`.
+    #   * For tabular problem types: `S3Prefix`, `ManifestFile`.
     #
-    #   * For ImageClassification: `S3Prefix`, `ManifestFile`,
+    #   * For image classification: `S3Prefix`, `ManifestFile`,
     #     `AugmentedManifestFile`.
     #
-    #   * For TextClassification: `S3Prefix`.
+    #   * For text classification: `S3Prefix`.
+    #
+    #   * For time-series forecasting: `S3Prefix`.
     #
     #
     #
@@ -1470,6 +1472,12 @@ module Aws::SageMaker
     #   For jobs created by calling `CreateAutoMLJob`, the validation dataset
     #   must be less than 2 GB in size.
     #
+    #   <note markdown="1"> This attribute must not be set for the time-series forecasting problem
+    #   type, as Autopilot automatically splits the input dataset into
+    #   training and validation sets.
+    #
+    #    </note>
+    #
     # @return [Types::CreateAutoMLJobV2Response] Returns a {Seahorse::Client::Response response} object which responds to the following methods:
     #
     #   * {Types::CreateAutoMLJobV2Response#auto_ml_job_arn #auto_ml_job_arn} => String
@@ -1532,6 +1540,33 @@ module Aws::SageMaker
     #         target_attribute_name: "TargetAttributeName", # required
     #         sample_weight_attribute_name: "SampleWeightAttributeName",
     #       },
+    #       time_series_forecasting_job_config: {
+    #         feature_specification_s3_uri: "S3Uri",
+    #         completion_criteria: {
+    #           max_candidates: 1,
+    #           max_runtime_per_training_job_in_seconds: 1,
+    #           max_auto_ml_job_runtime_in_seconds: 1,
+    #         },
+    #         forecast_frequency: "ForecastFrequency", # required
+    #         forecast_horizon: 1, # required
+    #         forecast_quantiles: ["ForecastQuantile"],
+    #         transformations: {
+    #           filling: {
+    #             "TransformationAttributeName" => {
+    #               "frontfill" => "FillingTransformationValue",
+    #             },
+    #           },
+    #           aggregation: {
+    #             "TransformationAttributeName" => "sum", # accepts sum, avg, first, min, max
+    #           },
+    #         },
+    #         time_series_config: { # required
+    #           target_attribute_name: "TargetAttributeName", # required
+    #           timestamp_attribute_name: "TimestampAttributeName", # required
+    #           item_identifier_attribute_name: "ItemIdentifierAttributeName", # required
+    #           grouping_attribute_names: ["GroupingAttributeName"],
+    #         },
+    #       },
     #     },
     #     role_arn: "RoleArn", # required
     #     tags: [
@@ -1549,7 +1584,7 @@ module Aws::SageMaker
     #       },
     #     },
     #     auto_ml_job_objective: {
-    #       metric_name: "Accuracy", # required, accepts Accuracy, MSE, F1, F1macro, AUC, RMSE, MAE, R2, BalancedAccuracy, Precision, PrecisionMacro, Recall, RecallMacro
+    #       metric_name: "Accuracy", # required, accepts Accuracy, MSE, F1, F1macro, AUC, RMSE, MAE, R2, BalancedAccuracy, Precision, PrecisionMacro, Recall, RecallMacro, MAPE, MASE, WAPE, AverageWeightedQuantileLoss
     #     },
     #     model_deploy_config: {
     #       auto_generate_endpoint_name: false,
@@ -10091,7 +10126,7 @@ module Aws::SageMaker
     #   resp.output_data_config.kms_key_id #=> String
     #   resp.output_data_config.s3_output_path #=> String
     #   resp.role_arn #=> String
-    #   resp.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.problem_type #=> String, one of "BinaryClassification", "MulticlassClassification", "Regression"
     #   resp.auto_ml_job_config.completion_criteria.max_candidates #=> Integer
     #   resp.auto_ml_job_config.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
@@ -10116,9 +10151,9 @@ module Aws::SageMaker
     #   resp.partial_failure_reasons[0].partial_failure_message #=> String
     #   resp.best_candidate.candidate_name #=> String
     #   resp.best_candidate.final_auto_ml_job_objective_metric.type #=> String, one of "Maximize", "Minimize"
-    #   resp.best_candidate.final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.best_candidate.final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.final_auto_ml_job_objective_metric.value #=> Float
-    #   resp.best_candidate.final_auto_ml_job_objective_metric.standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.best_candidate.final_auto_ml_job_objective_metric.standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.objective_status #=> String, one of "Succeeded", "Pending", "Failed"
     #   resp.best_candidate.candidate_steps #=> Array
     #   resp.best_candidate.candidate_steps[0].candidate_step_type #=> String, one of "AWS::SageMaker::TrainingJob", "AWS::SageMaker::TransformJob", "AWS::SageMaker::ProcessingJob"
@@ -10136,11 +10171,12 @@ module Aws::SageMaker
     #   resp.best_candidate.failure_reason #=> String
     #   resp.best_candidate.candidate_properties.candidate_artifact_locations.explainability #=> String
     #   resp.best_candidate.candidate_properties.candidate_artifact_locations.model_insights #=> String
+    #   resp.best_candidate.candidate_properties.candidate_artifact_locations.backtest_results #=> String
     #   resp.best_candidate.candidate_properties.candidate_metrics #=> Array
-    #   resp.best_candidate.candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.best_candidate.candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].value #=> Float
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].set #=> String, one of "Train", "Validation", "Test"
-    #   resp.best_candidate.candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency"
+    #   resp.best_candidate.candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.inference_container_definitions #=> Hash
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"] #=> Array
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"][0].image #=> String
@@ -10148,11 +10184,11 @@ module Aws::SageMaker
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"][0].environment #=> Hash
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"][0].environment["EnvironmentKey"] #=> String
     #   resp.auto_ml_job_status #=> String, one of "Completed", "InProgress", "Failed", "Stopped", "Stopping"
-    #   resp.auto_ml_job_secondary_status #=> String, one of "Starting", "AnalyzingData", "FeatureEngineering", "ModelTuning", "MaxCandidatesReached", "Failed", "Stopped", "MaxAutoMLJobRuntimeReached", "Stopping", "CandidateDefinitionsGenerated", "GeneratingExplainabilityReport", "Completed", "ExplainabilityError", "DeployingModel", "ModelDeploymentError", "GeneratingModelInsightsReport", "ModelInsightsError", "TrainingModels"
+    #   resp.auto_ml_job_secondary_status #=> String, one of "Starting", "AnalyzingData", "FeatureEngineering", "ModelTuning", "MaxCandidatesReached", "Failed", "Stopped", "MaxAutoMLJobRuntimeReached", "Stopping", "CandidateDefinitionsGenerated", "GeneratingExplainabilityReport", "Completed", "ExplainabilityError", "DeployingModel", "ModelDeploymentError", "GeneratingModelInsightsReport", "ModelInsightsError", "TrainingModels", "PreTraining"
     #   resp.generate_candidate_definitions_only #=> Boolean
     #   resp.auto_ml_job_artifacts.candidate_definition_notebook_location #=> String
     #   resp.auto_ml_job_artifacts.data_exploration_notebook_location #=> String
-    #   resp.resolved_attributes.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.resolved_attributes.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.resolved_attributes.problem_type #=> String, one of "BinaryClassification", "MulticlassClassification", "Regression"
     #   resp.resolved_attributes.completion_criteria.max_candidates #=> Integer
     #   resp.resolved_attributes.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
@@ -10225,7 +10261,7 @@ module Aws::SageMaker
     #   resp.output_data_config.kms_key_id #=> String
     #   resp.output_data_config.s3_output_path #=> String
     #   resp.role_arn #=> String
-    #   resp.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.auto_ml_problem_type_config.image_classification_job_config.completion_criteria.max_candidates #=> Integer
     #   resp.auto_ml_problem_type_config.image_classification_job_config.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
     #   resp.auto_ml_problem_type_config.image_classification_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds #=> Integer
@@ -10246,6 +10282,24 @@ module Aws::SageMaker
     #   resp.auto_ml_problem_type_config.tabular_job_config.problem_type #=> String, one of "BinaryClassification", "MulticlassClassification", "Regression"
     #   resp.auto_ml_problem_type_config.tabular_job_config.target_attribute_name #=> String
     #   resp.auto_ml_problem_type_config.tabular_job_config.sample_weight_attribute_name #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.feature_specification_s3_uri #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria.max_candidates #=> Integer
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.completion_criteria.max_auto_ml_job_runtime_in_seconds #=> Integer
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_frequency #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_horizon #=> Integer
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_quantiles #=> Array
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.forecast_quantiles[0] #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.filling #=> Hash
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.filling["TransformationAttributeName"] #=> Hash
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.filling["TransformationAttributeName"]["FillingType"] #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.aggregation #=> Hash
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.transformations.aggregation["TransformationAttributeName"] #=> String, one of "sum", "avg", "first", "min", "max"
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.target_attribute_name #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.timestamp_attribute_name #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.item_identifier_attribute_name #=> String
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.grouping_attribute_names #=> Array
+    #   resp.auto_ml_problem_type_config.time_series_forecasting_job_config.time_series_config.grouping_attribute_names[0] #=> String
     #   resp.creation_time #=> Time
     #   resp.end_time #=> Time
     #   resp.last_modified_time #=> Time
@@ -10254,9 +10308,9 @@ module Aws::SageMaker
     #   resp.partial_failure_reasons[0].partial_failure_message #=> String
     #   resp.best_candidate.candidate_name #=> String
     #   resp.best_candidate.final_auto_ml_job_objective_metric.type #=> String, one of "Maximize", "Minimize"
-    #   resp.best_candidate.final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.best_candidate.final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.final_auto_ml_job_objective_metric.value #=> Float
-    #   resp.best_candidate.final_auto_ml_job_objective_metric.standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.best_candidate.final_auto_ml_job_objective_metric.standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.objective_status #=> String, one of "Succeeded", "Pending", "Failed"
     #   resp.best_candidate.candidate_steps #=> Array
     #   resp.best_candidate.candidate_steps[0].candidate_step_type #=> String, one of "AWS::SageMaker::TrainingJob", "AWS::SageMaker::TransformJob", "AWS::SageMaker::ProcessingJob"
@@ -10274,11 +10328,12 @@ module Aws::SageMaker
     #   resp.best_candidate.failure_reason #=> String
     #   resp.best_candidate.candidate_properties.candidate_artifact_locations.explainability #=> String
     #   resp.best_candidate.candidate_properties.candidate_artifact_locations.model_insights #=> String
+    #   resp.best_candidate.candidate_properties.candidate_artifact_locations.backtest_results #=> String
     #   resp.best_candidate.candidate_properties.candidate_metrics #=> Array
-    #   resp.best_candidate.candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.best_candidate.candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].value #=> Float
     #   resp.best_candidate.candidate_properties.candidate_metrics[0].set #=> String, one of "Train", "Validation", "Test"
-    #   resp.best_candidate.candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency"
+    #   resp.best_candidate.candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.best_candidate.inference_container_definitions #=> Hash
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"] #=> Array
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"][0].image #=> String
@@ -10286,7 +10341,7 @@ module Aws::SageMaker
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"][0].environment #=> Hash
     #   resp.best_candidate.inference_container_definitions["AutoMLProcessingUnit"][0].environment["EnvironmentKey"] #=> String
     #   resp.auto_ml_job_status #=> String, one of "Completed", "InProgress", "Failed", "Stopped", "Stopping"
-    #   resp.auto_ml_job_secondary_status #=> String, one of "Starting", "AnalyzingData", "FeatureEngineering", "ModelTuning", "MaxCandidatesReached", "Failed", "Stopped", "MaxAutoMLJobRuntimeReached", "Stopping", "CandidateDefinitionsGenerated", "GeneratingExplainabilityReport", "Completed", "ExplainabilityError", "DeployingModel", "ModelDeploymentError", "GeneratingModelInsightsReport", "ModelInsightsError", "TrainingModels"
+    #   resp.auto_ml_job_secondary_status #=> String, one of "Starting", "AnalyzingData", "FeatureEngineering", "ModelTuning", "MaxCandidatesReached", "Failed", "Stopped", "MaxAutoMLJobRuntimeReached", "Stopping", "CandidateDefinitionsGenerated", "GeneratingExplainabilityReport", "Completed", "ExplainabilityError", "DeployingModel", "ModelDeploymentError", "GeneratingModelInsightsReport", "ModelInsightsError", "TrainingModels", "PreTraining"
     #   resp.model_deploy_config.auto_generate_endpoint_name #=> Boolean
     #   resp.model_deploy_config.endpoint_name #=> String
     #   resp.model_deploy_result.endpoint_name #=> String
@@ -10299,12 +10354,12 @@ module Aws::SageMaker
     #   resp.security_config.vpc_config.subnets[0] #=> String
     #   resp.auto_ml_job_artifacts.candidate_definition_notebook_location #=> String
     #   resp.auto_ml_job_artifacts.data_exploration_notebook_location #=> String
-    #   resp.resolved_attributes.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.resolved_attributes.auto_ml_job_objective.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.resolved_attributes.completion_criteria.max_candidates #=> Integer
     #   resp.resolved_attributes.completion_criteria.max_runtime_per_training_job_in_seconds #=> Integer
     #   resp.resolved_attributes.completion_criteria.max_auto_ml_job_runtime_in_seconds #=> Integer
     #   resp.resolved_attributes.auto_ml_problem_type_resolved_attributes.tabular_resolved_attributes.problem_type #=> String, one of "BinaryClassification", "MulticlassClassification", "Regression"
-    #   resp.auto_ml_problem_type_config_name #=> String, one of "ImageClassification", "TextClassification", "Tabular"
+    #   resp.auto_ml_problem_type_config_name #=> String, one of "ImageClassification", "TextClassification", "Tabular", "TimeSeriesForecasting"
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/DescribeAutoMLJobV2 AWS API Documentation
     #
@@ -15454,7 +15509,7 @@ module Aws::SageMaker
     #   resp.auto_ml_job_summaries[0].auto_ml_job_name #=> String
     #   resp.auto_ml_job_summaries[0].auto_ml_job_arn #=> String
     #   resp.auto_ml_job_summaries[0].auto_ml_job_status #=> String, one of "Completed", "InProgress", "Failed", "Stopped", "Stopping"
-    #   resp.auto_ml_job_summaries[0].auto_ml_job_secondary_status #=> String, one of "Starting", "AnalyzingData", "FeatureEngineering", "ModelTuning", "MaxCandidatesReached", "Failed", "Stopped", "MaxAutoMLJobRuntimeReached", "Stopping", "CandidateDefinitionsGenerated", "GeneratingExplainabilityReport", "Completed", "ExplainabilityError", "DeployingModel", "ModelDeploymentError", "GeneratingModelInsightsReport", "ModelInsightsError", "TrainingModels"
+    #   resp.auto_ml_job_summaries[0].auto_ml_job_secondary_status #=> String, one of "Starting", "AnalyzingData", "FeatureEngineering", "ModelTuning", "MaxCandidatesReached", "Failed", "Stopped", "MaxAutoMLJobRuntimeReached", "Stopping", "CandidateDefinitionsGenerated", "GeneratingExplainabilityReport", "Completed", "ExplainabilityError", "DeployingModel", "ModelDeploymentError", "GeneratingModelInsightsReport", "ModelInsightsError", "TrainingModels", "PreTraining"
     #   resp.auto_ml_job_summaries[0].creation_time #=> Time
     #   resp.auto_ml_job_summaries[0].end_time #=> Time
     #   resp.auto_ml_job_summaries[0].last_modified_time #=> Time
@@ -15521,9 +15576,9 @@ module Aws::SageMaker
     #   resp.candidates #=> Array
     #   resp.candidates[0].candidate_name #=> String
     #   resp.candidates[0].final_auto_ml_job_objective_metric.type #=> String, one of "Maximize", "Minimize"
-    #   resp.candidates[0].final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.candidates[0].final_auto_ml_job_objective_metric.metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.candidates[0].final_auto_ml_job_objective_metric.value #=> Float
-    #   resp.candidates[0].final_auto_ml_job_objective_metric.standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.candidates[0].final_auto_ml_job_objective_metric.standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.candidates[0].objective_status #=> String, one of "Succeeded", "Pending", "Failed"
     #   resp.candidates[0].candidate_steps #=> Array
     #   resp.candidates[0].candidate_steps[0].candidate_step_type #=> String, one of "AWS::SageMaker::TrainingJob", "AWS::SageMaker::TransformJob", "AWS::SageMaker::ProcessingJob"
@@ -15541,11 +15596,12 @@ module Aws::SageMaker
     #   resp.candidates[0].failure_reason #=> String
     #   resp.candidates[0].candidate_properties.candidate_artifact_locations.explainability #=> String
     #   resp.candidates[0].candidate_properties.candidate_artifact_locations.model_insights #=> String
+    #   resp.candidates[0].candidate_properties.candidate_artifact_locations.backtest_results #=> String
     #   resp.candidates[0].candidate_properties.candidate_metrics #=> Array
-    #   resp.candidates[0].candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro"
+    #   resp.candidates[0].candidate_properties.candidate_metrics[0].metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.candidates[0].candidate_properties.candidate_metrics[0].value #=> Float
     #   resp.candidates[0].candidate_properties.candidate_metrics[0].set #=> String, one of "Train", "Validation", "Test"
-    #   resp.candidates[0].candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency"
+    #   resp.candidates[0].candidate_properties.candidate_metrics[0].standard_metric_name #=> String, one of "Accuracy", "MSE", "F1", "F1macro", "AUC", "RMSE", "MAE", "R2", "BalancedAccuracy", "Precision", "PrecisionMacro", "Recall", "RecallMacro", "LogLoss", "InferenceLatency", "MAPE", "MASE", "WAPE", "AverageWeightedQuantileLoss"
     #   resp.candidates[0].inference_container_definitions #=> Hash
     #   resp.candidates[0].inference_container_definitions["AutoMLProcessingUnit"] #=> Array
     #   resp.candidates[0].inference_container_definitions["AutoMLProcessingUnit"][0].image #=> String
@@ -23762,7 +23818,7 @@ module Aws::SageMaker
         params: params,
         config: config)
       context[:gem_name] = 'aws-sdk-sagemaker'
-      context[:gem_version] = '1.191.0'
+      context[:gem_version] = '1.192.0'
       Seahorse::Client::Request.new(handlers, context)
     end
 

data/lib/aws-sdk-sagemaker/client_api.rb

@@ -29,6 +29,8 @@ module Aws::SageMaker
     AdditionalInferenceSpecifications = Shapes::ListShape.new(name: 'AdditionalInferenceSpecifications')
     AgentVersion = Shapes::StructureShape.new(name: 'AgentVersion')
     AgentVersions = Shapes::ListShape.new(name: 'AgentVersions')
+    AggregationTransformationValue = Shapes::StringShape.new(name: 'AggregationTransformationValue')
+    AggregationTransformations = Shapes::MapShape.new(name: 'AggregationTransformations')
     Alarm = Shapes::StructureShape.new(name: 'Alarm')
     AlarmList = Shapes::ListShape.new(name: 'AlarmList')
     AlarmName = Shapes::StringShape.new(name: 'AlarmName')
@@ -152,6 +154,7 @@ module Aws::SageMaker
     Autotune = Shapes::StructureShape.new(name: 'Autotune')
     AutotuneMode = Shapes::StringShape.new(name: 'AutotuneMode')
     AwsManagedHumanLoopRequestSource = Shapes::StringShape.new(name: 'AwsManagedHumanLoopRequestSource')
+    BacktestResultsLocation = Shapes::StringShape.new(name: 'BacktestResultsLocation')
     BatchDataCaptureConfig = Shapes::StructureShape.new(name: 'BatchDataCaptureConfig')
     BatchDescribeModelPackageError = Shapes::StructureShape.new(name: 'BatchDescribeModelPackageError')
     BatchDescribeModelPackageErrorMap = Shapes::MapShape.new(name: 'BatchDescribeModelPackageErrorMap')
@@ -781,6 +784,10 @@ module Aws::SageMaker
     FileSystemDataSource = Shapes::StructureShape.new(name: 'FileSystemDataSource')
     FileSystemId = Shapes::StringShape.new(name: 'FileSystemId')
     FileSystemType = Shapes::StringShape.new(name: 'FileSystemType')
+    FillingTransformationMap = Shapes::MapShape.new(name: 'FillingTransformationMap')
+    FillingTransformationValue = Shapes::StringShape.new(name: 'FillingTransformationValue')
+    FillingTransformations = Shapes::MapShape.new(name: 'FillingTransformations')
+    FillingType = Shapes::StringShape.new(name: 'FillingType')
     Filter = Shapes::StructureShape.new(name: 'Filter')
     FilterList = Shapes::ListShape.new(name: 'FilterList')
     FilterValue = Shapes::StringShape.new(name: 'FilterValue')
@@ -801,6 +808,10 @@ module Aws::SageMaker
     FlowDefinitionTaskKeywords = Shapes::ListShape.new(name: 'FlowDefinitionTaskKeywords')
     FlowDefinitionTaskTimeLimitInSeconds = Shapes::IntegerShape.new(name: 'FlowDefinitionTaskTimeLimitInSeconds')
     FlowDefinitionTaskTitle = Shapes::StringShape.new(name: 'FlowDefinitionTaskTitle')
+    ForecastFrequency = Shapes::StringShape.new(name: 'ForecastFrequency')
+    ForecastHorizon = Shapes::IntegerShape.new(name: 'ForecastHorizon')
+    ForecastQuantile = Shapes::StringShape.new(name: 'ForecastQuantile')
+    ForecastQuantiles = Shapes::ListShape.new(name: 'ForecastQuantiles')
     Framework = Shapes::StringShape.new(name: 'Framework')
     FrameworkVersion = Shapes::StringShape.new(name: 'FrameworkVersion')
     GenerateCandidateDefinitionsOnly = Shapes::BooleanShape.new(name: 'GenerateCandidateDefinitionsOnly')
@@ -818,6 +829,8 @@ module Aws::SageMaker
     GitConfigForUpdate = Shapes::StructureShape.new(name: 'GitConfigForUpdate')
     GitConfigUrl = Shapes::StringShape.new(name: 'GitConfigUrl')
     Group = Shapes::StringShape.new(name: 'Group')
+    GroupingAttributeName = Shapes::StringShape.new(name: 'GroupingAttributeName')
+    GroupingAttributeNames = Shapes::ListShape.new(name: 'GroupingAttributeNames')
     Groups = Shapes::ListShape.new(name: 'Groups')
     HookParameters = Shapes::MapShape.new(name: 'HookParameters')
     Horovod = Shapes::BooleanShape.new(name: 'Horovod')
@@ -972,6 +985,7 @@ module Aws::SageMaker
     InvocationsMaxRetries = Shapes::IntegerShape.new(name: 'InvocationsMaxRetries')
     InvocationsTimeoutInSeconds = Shapes::IntegerShape.new(name: 'InvocationsTimeoutInSeconds')
     IotRoleAlias = Shapes::StringShape.new(name: 'IotRoleAlias')
+    ItemIdentifierAttributeName = Shapes::StringShape.new(name: 'ItemIdentifierAttributeName')
     JobDurationInSeconds = Shapes::IntegerShape.new(name: 'JobDurationInSeconds')
     JobReferenceCode = Shapes::StringShape.new(name: 'JobReferenceCode')
     JobReferenceCodeContains = Shapes::StringShape.new(name: 'JobReferenceCodeContains')
@@ -1829,8 +1843,12 @@ module Aws::SageMaker
     TerminationWaitInSeconds = Shapes::IntegerShape.new(name: 'TerminationWaitInSeconds')
     TextClassificationJobConfig = Shapes::StructureShape.new(name: 'TextClassificationJobConfig')
     ThingName = Shapes::StringShape.new(name: 'ThingName')
+    TimeSeriesConfig = Shapes::StructureShape.new(name: 'TimeSeriesConfig')
+    TimeSeriesForecastingJobConfig = Shapes::StructureShape.new(name: 'TimeSeriesForecastingJobConfig')
     TimeSeriesForecastingSettings = Shapes::StructureShape.new(name: 'TimeSeriesForecastingSettings')
+    TimeSeriesTransformations = Shapes::StructureShape.new(name: 'TimeSeriesTransformations')
     Timestamp = Shapes::TimestampShape.new(name: 'Timestamp')
+    TimestampAttributeName = Shapes::StringShape.new(name: 'TimestampAttributeName')
     TrafficDurationInSeconds = Shapes::IntegerShape.new(name: 'TrafficDurationInSeconds')
     TrafficPattern = Shapes::StructureShape.new(name: 'TrafficPattern')
     TrafficRoutingConfig = Shapes::StructureShape.new(name: 'TrafficRoutingConfig')
@@ -1884,6 +1902,7 @@ module Aws::SageMaker
     TransformOutput = Shapes::StructureShape.new(name: 'TransformOutput')
     TransformResources = Shapes::StructureShape.new(name: 'TransformResources')
     TransformS3DataSource = Shapes::StructureShape.new(name: 'TransformS3DataSource')
+    TransformationAttributeName = Shapes::StringShape.new(name: 'TransformationAttributeName')
     Trial = Shapes::StructureShape.new(name: 'Trial')
     TrialArn = Shapes::StringShape.new(name: 'TrialArn')
     TrialComponent = Shapes::StructureShape.new(name: 'TrialComponent')
@@ -2084,6 +2103,9 @@ module Aws::SageMaker
 
     AgentVersions.member = Shapes::ShapeRef.new(shape: AgentVersion)
 
+    AggregationTransformations.key = Shapes::ShapeRef.new(shape: TransformationAttributeName)
+    AggregationTransformations.value = Shapes::ShapeRef.new(shape: AggregationTransformationValue)
+
     Alarm.add_member(:alarm_name, Shapes::ShapeRef.new(shape: AlarmName, location_name: "AlarmName"))
     Alarm.struct_class = Types::Alarm
 
@@ -2344,10 +2366,12 @@ module Aws::SageMaker
     AutoMLProblemTypeConfig.add_member(:image_classification_job_config, Shapes::ShapeRef.new(shape: ImageClassificationJobConfig, location_name: "ImageClassificationJobConfig"))
     AutoMLProblemTypeConfig.add_member(:text_classification_job_config, Shapes::ShapeRef.new(shape: TextClassificationJobConfig, location_name: "TextClassificationJobConfig"))
     AutoMLProblemTypeConfig.add_member(:tabular_job_config, Shapes::ShapeRef.new(shape: TabularJobConfig, location_name: "TabularJobConfig"))
+    AutoMLProblemTypeConfig.add_member(:time_series_forecasting_job_config, Shapes::ShapeRef.new(shape: TimeSeriesForecastingJobConfig, location_name: "TimeSeriesForecastingJobConfig"))
     AutoMLProblemTypeConfig.add_member(:unknown, Shapes::ShapeRef.new(shape: nil, location_name: 'unknown'))
     AutoMLProblemTypeConfig.add_member_subclass(:image_classification_job_config, Types::AutoMLProblemTypeConfig::ImageClassificationJobConfig)
     AutoMLProblemTypeConfig.add_member_subclass(:text_classification_job_config, Types::AutoMLProblemTypeConfig::TextClassificationJobConfig)
     AutoMLProblemTypeConfig.add_member_subclass(:tabular_job_config, Types::AutoMLProblemTypeConfig::TabularJobConfig)
+    AutoMLProblemTypeConfig.add_member_subclass(:time_series_forecasting_job_config, Types::AutoMLProblemTypeConfig::TimeSeriesForecastingJobConfig)
     AutoMLProblemTypeConfig.add_member_subclass(:unknown, Types::AutoMLProblemTypeConfig::Unknown)
     AutoMLProblemTypeConfig.struct_class = Types::AutoMLProblemTypeConfig
 
@@ -2448,6 +2472,7 @@ module Aws::SageMaker
 
     CandidateArtifactLocations.add_member(:explainability, Shapes::ShapeRef.new(shape: ExplainabilityLocation, required: true, location_name: "Explainability"))
     CandidateArtifactLocations.add_member(:model_insights, Shapes::ShapeRef.new(shape: ModelInsightsLocation, location_name: "ModelInsights"))
+    CandidateArtifactLocations.add_member(:backtest_results, Shapes::ShapeRef.new(shape: BacktestResultsLocation, location_name: "BacktestResults"))
     CandidateArtifactLocations.struct_class = Types::CandidateArtifactLocations
 
     CandidateGenerationConfig.add_member(:algorithms_config, Shapes::ShapeRef.new(shape: AutoMLAlgorithmsConfig, location_name: "AlgorithmsConfig"))
@@ -5102,6 +5127,12 @@ module Aws::SageMaker
     FileSystemDataSource.add_member(:directory_path, Shapes::ShapeRef.new(shape: DirectoryPath, required: true, location_name: "DirectoryPath"))
     FileSystemDataSource.struct_class = Types::FileSystemDataSource
 
+    FillingTransformationMap.key = Shapes::ShapeRef.new(shape: FillingType)
+    FillingTransformationMap.value = Shapes::ShapeRef.new(shape: FillingTransformationValue)
+
+    FillingTransformations.key = Shapes::ShapeRef.new(shape: TransformationAttributeName)
+    FillingTransformations.value = Shapes::ShapeRef.new(shape: FillingTransformationMap)
+
     Filter.add_member(:name, Shapes::ShapeRef.new(shape: ResourcePropertyName, required: true, location_name: "Name"))
     Filter.add_member(:operator, Shapes::ShapeRef.new(shape: Operator, location_name: "Operator"))
     Filter.add_member(:value, Shapes::ShapeRef.new(shape: FilterValue, location_name: "Value"))
@@ -5137,6 +5168,8 @@ module Aws::SageMaker
 
     FlowDefinitionTaskKeywords.member = Shapes::ShapeRef.new(shape: FlowDefinitionTaskKeyword)
 
+    ForecastQuantiles.member = Shapes::ShapeRef.new(shape: ForecastQuantile)
+
     GetDeviceFleetReportRequest.add_member(:device_fleet_name, Shapes::ShapeRef.new(shape: EntityName, required: true, location_name: "DeviceFleetName"))
     GetDeviceFleetReportRequest.struct_class = Types::GetDeviceFleetReportRequest
 
@@ -5183,6 +5216,8 @@ module Aws::SageMaker
     GitConfigForUpdate.add_member(:secret_arn, Shapes::ShapeRef.new(shape: SecretArn, location_name: "SecretArn"))
     GitConfigForUpdate.struct_class = Types::GitConfigForUpdate
 
+    GroupingAttributeNames.member = Shapes::ShapeRef.new(shape: GroupingAttributeName)
+
     Groups.member = Shapes::ShapeRef.new(shape: Group)
 
     HookParameters.key = Shapes::ShapeRef.new(shape: ConfigKey)
@@ -8290,10 +8325,29 @@ module Aws::SageMaker
     TextClassificationJobConfig.add_member(:target_label_column, Shapes::ShapeRef.new(shape: TargetLabelColumn, location_name: "TargetLabelColumn"))
     TextClassificationJobConfig.struct_class = Types::TextClassificationJobConfig
 
+    TimeSeriesConfig.add_member(:target_attribute_name, Shapes::ShapeRef.new(shape: TargetAttributeName, required: true, location_name: "TargetAttributeName"))
+    TimeSeriesConfig.add_member(:timestamp_attribute_name, Shapes::ShapeRef.new(shape: TimestampAttributeName, required: true, location_name: "TimestampAttributeName"))
+    TimeSeriesConfig.add_member(:item_identifier_attribute_name, Shapes::ShapeRef.new(shape: ItemIdentifierAttributeName, required: true, location_name: "ItemIdentifierAttributeName"))
+    TimeSeriesConfig.add_member(:grouping_attribute_names, Shapes::ShapeRef.new(shape: GroupingAttributeNames, location_name: "GroupingAttributeNames"))
+    TimeSeriesConfig.struct_class = Types::TimeSeriesConfig
+
+    TimeSeriesForecastingJobConfig.add_member(:feature_specification_s3_uri, Shapes::ShapeRef.new(shape: S3Uri, location_name: "FeatureSpecificationS3Uri"))
+    TimeSeriesForecastingJobConfig.add_member(:completion_criteria, Shapes::ShapeRef.new(shape: AutoMLJobCompletionCriteria, location_name: "CompletionCriteria"))
+    TimeSeriesForecastingJobConfig.add_member(:forecast_frequency, Shapes::ShapeRef.new(shape: ForecastFrequency, required: true, location_name: "ForecastFrequency"))
+    TimeSeriesForecastingJobConfig.add_member(:forecast_horizon, Shapes::ShapeRef.new(shape: ForecastHorizon, required: true, location_name: "ForecastHorizon"))
+    TimeSeriesForecastingJobConfig.add_member(:forecast_quantiles, Shapes::ShapeRef.new(shape: ForecastQuantiles, location_name: "ForecastQuantiles"))
+    TimeSeriesForecastingJobConfig.add_member(:transformations, Shapes::ShapeRef.new(shape: TimeSeriesTransformations, location_name: "Transformations"))
+    TimeSeriesForecastingJobConfig.add_member(:time_series_config, Shapes::ShapeRef.new(shape: TimeSeriesConfig, required: true, location_name: "TimeSeriesConfig"))
+    TimeSeriesForecastingJobConfig.struct_class = Types::TimeSeriesForecastingJobConfig
+
     TimeSeriesForecastingSettings.add_member(:status, Shapes::ShapeRef.new(shape: FeatureStatus, location_name: "Status"))
     TimeSeriesForecastingSettings.add_member(:amazon_forecast_role_arn, Shapes::ShapeRef.new(shape: RoleArn, location_name: "AmazonForecastRoleArn"))
     TimeSeriesForecastingSettings.struct_class = Types::TimeSeriesForecastingSettings
 
+    TimeSeriesTransformations.add_member(:filling, Shapes::ShapeRef.new(shape: FillingTransformations, location_name: "Filling"))
+    TimeSeriesTransformations.add_member(:aggregation, Shapes::ShapeRef.new(shape: AggregationTransformations, location_name: "Aggregation"))
+    TimeSeriesTransformations.struct_class = Types::TimeSeriesTransformations
+
     TrafficPattern.add_member(:traffic_type, Shapes::ShapeRef.new(shape: TrafficType, location_name: "TrafficType"))
     TrafficPattern.add_member(:phases, Shapes::ShapeRef.new(shape: Phases, location_name: "Phases"))
     TrafficPattern.struct_class = Types::TrafficPattern

data/lib/aws-sdk-sagemaker/types.rb

@@ -2086,20 +2086,29 @@ module Aws::SageMaker
     #   The type of channel. Defines whether the data are used for training
     #   or validation. The default value is `training`. Channels for
     #   `training` and `validation` must share the same `ContentType`
+    #
+    #   <note markdown="1"> The type of channel defaults to `training` for the time-series
+    #   forecasting problem type.
+    #
+    #    </note>
     #   @return [String]
     #
     # @!attribute [rw] content_type
     #   The content type of the data from the input source. The following
     #   are the allowed content types for different problems:
     #
-    #   * For Tabular problem types: `text/csv;header=present` or
+    #   * For tabular problem types: `text/csv;header=present` or
     #     `x-application/vnd.amazon+parquet`. The default value is
     #     `text/csv;header=present`.
     #
-    #   * For ImageClassification: `image/png`, `image/jpeg`, or `image/*`.
+    #   * For image classification: `image/png`, `image/jpeg`, or `image/*`.
     #     The default value is `image/*`.
     #
-    #   * For TextClassification: `text/csv;header=present` or
+    #   * For text classification: `text/csv;header=present` or
+    #     `x-application/vnd.amazon+parquet`. The default value is
+    #     `text/csv;header=present`.
+    #
+    #   * For time-series forecasting: `text/csv;header=present` or
     #     `x-application/vnd.amazon+parquet`. The default value is
     #     `text/csv;header=present`.
     #   @return [String]
@@ -2132,8 +2141,9 @@ module Aws::SageMaker
     # @!attribute [rw] max_candidates
     #   The maximum number of times a training job is allowed to run.
     #
-    #   For job V2s (jobs created by calling `CreateAutoMLJobV2`), the
-    #   supported value is 1.
+    #   For text and image classification, as well as time-series
+    #   forecasting problem types, the supported value is 1. For tabular
+    #   problem types, the maximum value is 750.
     #   @return [Integer]
     #
     # @!attribute [rw] max_runtime_per_training_job_in_seconds
@@ -2261,6 +2271,9 @@ module Aws::SageMaker
     #
     #   * For image or text classification problem types: `Accuracy`
     #
+    #   * For time-series forecasting problem types:
+    #     `AverageWeightedQuantileLoss`
+    #
     #
     #
     #   [1]: https://docs.aws.amazon.com/sagemaker/latest/dg/autopilot-metrics-validation.html#autopilot-metrics
@@ -2399,12 +2412,18 @@ module Aws::SageMaker
     #   type (regression, classification).
     #   @return [Types::TabularJobConfig]
     #
+    # @!attribute [rw] time_series_forecasting_job_config
+    #   Settings used to configure an AutoML job V2 for a time-series
+    #   forecasting problem type.
+    #   @return [Types::TimeSeriesForecastingJobConfig]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/AutoMLProblemTypeConfig AWS API Documentation
     #
     class AutoMLProblemTypeConfig < Struct.new(
       :image_classification_job_config,
       :text_classification_job_config,
       :tabular_job_config,
+      :time_series_forecasting_job_config,
       :unknown)
       SENSITIVE = []
       include Aws::Structure
@@ -2413,6 +2432,7 @@ module Aws::SageMaker
       class ImageClassificationJobConfig < AutoMLProblemTypeConfig; end
       class TextClassificationJobConfig < AutoMLProblemTypeConfig; end
       class TabularJobConfig < AutoMLProblemTypeConfig; end
+      class TimeSeriesForecastingJobConfig < AutoMLProblemTypeConfig; end
       class Unknown < AutoMLProblemTypeConfig; end
     end
 
@@ -2987,11 +3007,18 @@ module Aws::SageMaker
     #   the AutoML candidate.
     #   @return [String]
     #
+    # @!attribute [rw] backtest_results
+    #   The Amazon S3 prefix to the accuracy metrics and the inference
+    #   results observed over the testing window. Available only for the
+    #   time-series forecasting problem type.
+    #   @return [String]
+    #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/CandidateArtifactLocations AWS API Documentation
     #
     class CandidateArtifactLocations < Struct.new(
       :explainability,
-      :model_insights)
+      :model_insights,
+      :backtest_results)
       SENSITIVE = []
       include Aws::Structure
     end
@@ -4717,12 +4744,14 @@ module Aws::SageMaker
     #   [InputDataConfig][1] attribute in the `CreateAutoMLJob` input
     #   parameters. The supported formats depend on the problem type:
     #
-    #   * For Tabular problem types: `S3Prefix`, `ManifestFile`.
+    #   * For tabular problem types: `S3Prefix`, `ManifestFile`.
     #
-    #   * For ImageClassification: `S3Prefix`, `ManifestFile`,
+    #   * For image classification: `S3Prefix`, `ManifestFile`,
     #     `AugmentedManifestFile`.
     #
-    #   * For TextClassification: `S3Prefix`.
+    #   * For text classification: `S3Prefix`.
+    #
+    #   * For time-series forecasting: `S3Prefix`.
     #
     #
     #
@@ -4789,6 +4818,12 @@ module Aws::SageMaker
     #   The validation and training datasets must contain the same headers.
     #   For jobs created by calling `CreateAutoMLJob`, the validation
     #   dataset must be less than 2 GB in size.
+    #
+    #   <note markdown="1"> This attribute must not be set for the time-series forecasting
+    #   problem type, as Autopilot automatically splits the input dataset
+    #   into training and validation sets.
+    #
+    #    </note>
     #   @return [Types::AutoMLDataSplitConfig]
     #
     # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/CreateAutoMLJobV2Request AWS API Documentation
@@ -36920,6 +36955,157 @@ module Aws::SageMaker
       include Aws::Structure
     end
 
+    # The collection of components that defines the time-series.
+    #
+    # @!attribute [rw] target_attribute_name
+    #   The name of the column representing the target variable that you
+    #   want to predict for each item in your dataset. The data type of the
+    #   target variable must be numerical.
+    #   @return [String]
+    #
+    # @!attribute [rw] timestamp_attribute_name
+    #   The name of the column indicating a point in time at which the
+    #   target value of a given item is recorded.
+    #   @return [String]
+    #
+    # @!attribute [rw] item_identifier_attribute_name
+    #   The name of the column that represents the set of item identifiers
+    #   for which you want to predict the target value.
+    #   @return [String]
+    #
+    # @!attribute [rw] grouping_attribute_names
+    #   A set of columns names that can be grouped with the item identifier
+    #   column to create a composite key for which a target value is
+    #   predicted.
+    #   @return [Array<String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/TimeSeriesConfig AWS API Documentation
+    #
+    class TimeSeriesConfig < Struct.new(
+      :target_attribute_name,
+      :timestamp_attribute_name,
+      :item_identifier_attribute_name,
+      :grouping_attribute_names)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
+    # The collection of settings used by an AutoML job V2 for the
+    # time-series forecasting problem type.
+    #
+    # <note markdown="1"> The `TimeSeriesForecastingJobConfig` problem type is only available in
+    # private beta. Contact Amazon Web Services Support or your account
+    # manager to learn more about access privileges.
+    #
+    #  </note>
+    #
+    # @!attribute [rw] feature_specification_s3_uri
+    #   A URL to the Amazon S3 data source containing additional selected
+    #   features that complement the target, itemID, timestamp, and grouped
+    #   columns set in `TimeSeriesConfig`. When not provided, the AutoML job
+    #   V2 includes all the columns from the original dataset that are not
+    #   already declared in `TimeSeriesConfig`. If provided, the AutoML job
+    #   V2 only considers these additional columns as a complement to the
+    #   ones declared in `TimeSeriesConfig`.
+    #
+    #   You can input `FeatureAttributeNames` (optional) in JSON format as
+    #   shown below:
+    #
+    #   `\{ "FeatureAttributeNames":["col1", "col2", ...] \}`.
+    #
+    #   You can also specify the data type of the feature (optional) in the
+    #   format shown below:
+    #
+    #   `\{ "FeatureDataTypes":\{"col1":"numeric", "col2":"categorical" ...
+    #   \} \}`
+    #
+    #   Autopilot supports the following data types: `numeric`,
+    #   `categorical`, `text`, and `datetime`.
+    #
+    #   <note markdown="1"> These column keys must not include any column set in
+    #   `TimeSeriesConfig`.
+    #
+    #    </note>
+    #
+    #   When not provided, the AutoML job V2 includes all the columns from
+    #   the original dataset that are not already declared in
+    #   `TimeSeriesConfig`. If provided, the AutoML job V2 only considers
+    #   these additional columns as a complement to the ones declared in
+    #   `TimeSeriesConfig`.
+    #
+    #   Autopilot supports the following data types: `numeric`,
+    #   `categorical`, `text`, and `datetime`.
+    #   @return [String]
+    #
+    # @!attribute [rw] completion_criteria
+    #   How long a job is allowed to run, or how many candidates a job is
+    #   allowed to generate.
+    #   @return [Types::AutoMLJobCompletionCriteria]
+    #
+    # @!attribute [rw] forecast_frequency
+    #   The frequency of predictions in a forecast.
+    #
+    #   Valid intervals are an integer followed by Y (Year), M (Month), W
+    #   (Week), D (Day), H (Hour), and min (Minute). For example, `1D`
+    #   indicates every day and `15min` indicates every 15 minutes. The
+    #   value of a frequency must not overlap with the next larger
+    #   frequency. For example, you must use a frequency of `1H` instead of
+    #   `60min`.
+    #
+    #   The valid values for each frequency are the following:
+    #
+    #   * Minute - 1-59
+    #
+    #   * Hour - 1-23
+    #
+    #   * Day - 1-6
+    #
+    #   * Week - 1-4
+    #
+    #   * Month - 1-11
+    #
+    #   * Year - 1
+    #   @return [String]
+    #
+    # @!attribute [rw] forecast_horizon
+    #   The number of time-steps that the model predicts. The forecast
+    #   horizon is also called the prediction length. The maximum forecast
+    #   horizon is the lesser of 500 time-steps or 1/4 of the time-steps in
+    #   the dataset.
+    #   @return [Integer]
+    #
+    # @!attribute [rw] forecast_quantiles
+    #   The quantiles used to train the model for forecasts at a specified
+    #   quantile. You can specify quantiles from `0.01` (p1) to `0.99`
+    #   (p99), by increments of 0.01 or higher. Up to five forecast
+    #   quantiles can be specified. When `ForecastQuantiles` is not
+    #   provided, the AutoML job uses the quantiles p10, p50, and p90 as
+    #   default.
+    #   @return [Array<String>]
+    #
+    # @!attribute [rw] transformations
+    #   The transformations modifying specific attributes of the
+    #   time-series, such as filling strategies for missing values.
+    #   @return [Types::TimeSeriesTransformations]
+    #
+    # @!attribute [rw] time_series_config
+    #   The collection of components that defines the time-series.
+    #   @return [Types::TimeSeriesConfig]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/TimeSeriesForecastingJobConfig AWS API Documentation
+    #
+    class TimeSeriesForecastingJobConfig < Struct.new(
+      :feature_specification_s3_uri,
+      :completion_criteria,
+      :forecast_frequency,
+      :forecast_horizon,
+      :forecast_quantiles,
+      :transformations,
+      :time_series_config)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # Time series forecast settings for the SageMaker Canvas application.
     #
     # @!attribute [rw] status
@@ -36952,6 +37138,56 @@ module Aws::SageMaker
       include Aws::Structure
     end
 
+    # Transformations allowed on the dataset. Supported transformations are
+    # `Filling` and `Aggregation`. `Filling` specifies how to add values to
+    # missing values in the dataset. `Aggregation` defines how to aggregate
+    # data that does not align with forecast frequency.
+    #
+    # @!attribute [rw] filling
+    #   A key value pair defining the filling method for a column, where the
+    #   key is the column name and the value is an object which defines the
+    #   filling logic. You can specify multiple filling methods for a single
+    #   column.
+    #
+    #   The supported filling methods and their corresponding options are:
+    #
+    #   * `frontfill`: `none` (Supported only for target column)
+    #
+    #   * `middlefill`: `zero`, `value`, `median`, `mean`, `min`, `max`
+    #
+    #   * `backfill`: `zero`, `value`, `median`, `mean`, `min`, `max`
+    #
+    #   * `futurefill`: `zero`, `value`, `median`, `mean`, `min`, `max`
+    #
+    #   To set a filling method to a specific value, set the fill parameter
+    #   to the chosen filling method value (for example `"backfill" :
+    #   "value"`), and define the filling value in an additional parameter
+    #   prefixed with "\_value". For example, to set `backfill` to a value
+    #   of `2`, you must include two parameters: `"backfill": "value"` and
+    #   `"backfill_value":"2"`.
+    #   @return [Hash<String,Hash<String,String>>]
+    #
+    # @!attribute [rw] aggregation
+    #   A key value pair defining the aggregation method for a column, where
+    #   the key is the column name and the value is the aggregation method.
+    #
+    #   The supported aggregation methods are `sum` (default), `avg`,
+    #   `first`, `min`, `max`.
+    #
+    #   <note markdown="1"> Aggregation is only supported for the target column.
+    #
+    #    </note>
+    #   @return [Hash<String,String>]
+    #
+    # @see http://docs.aws.amazon.com/goto/WebAPI/sagemaker-2017-07-24/TimeSeriesTransformations AWS API Documentation
+    #
+    class TimeSeriesTransformations < Struct.new(
+      :filling,
+      :aggregation)
+      SENSITIVE = []
+      include Aws::Structure
+    end
+
     # Defines the traffic pattern of the load test.
     #
     # @!attribute [rw] traffic_type

data/lib/aws-sdk-sagemaker.rb

@@ -53,6 +53,6 @@ require_relative 'aws-sdk-sagemaker/customizations'
 # @!group service
 module Aws::SageMaker
 
-  GEM_VERSION = '1.191.0'
+  GEM_VERSION = '1.192.0'
 
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: aws-sdk-sagemaker
 version: !ruby/object:Gem::Version
-  version: 1.191.0
+  version: 1.192.0
 platform: ruby
 authors:
 - Amazon Web Services
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2023-06-28 00:00:00.000000000 Z
+date: 2023-06-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: aws-sdk-core