/** * Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved. * SPDX-License-Identifier: Apache-2.0. */ #pragma once #include #include #include #include #include #include #include namespace Aws { namespace Utils { namespace Json { class JsonValue; class JsonView; } // namespace Json } // namespace Utils namespace SageMaker { namespace Model { /** *

The collection of settings used by an AutoML job V2 for the * TABULAR problem type.

*/ class TabularJobConfig { public: AWS_SAGEMAKER_API TabularJobConfig(); AWS_SAGEMAKER_API TabularJobConfig(Aws::Utils::Json::JsonView jsonValue); AWS_SAGEMAKER_API TabularJobConfig& operator=(Aws::Utils::Json::JsonView jsonValue); AWS_SAGEMAKER_API Aws::Utils::Json::JsonValue Jsonize() const; /** *

The configuration information of how model candidates are generated.

*/ inline const CandidateGenerationConfig& GetCandidateGenerationConfig() const{ return m_candidateGenerationConfig; } /** *

The configuration information of how model candidates are generated.

*/ inline bool CandidateGenerationConfigHasBeenSet() const { return m_candidateGenerationConfigHasBeenSet; } /** *

The configuration information of how model candidates are generated.

*/ inline void SetCandidateGenerationConfig(const CandidateGenerationConfig& value) { m_candidateGenerationConfigHasBeenSet = true; m_candidateGenerationConfig = value; } /** *

The configuration information of how model candidates are generated.

*/ inline void SetCandidateGenerationConfig(CandidateGenerationConfig&& value) { m_candidateGenerationConfigHasBeenSet = true; m_candidateGenerationConfig = std::move(value); } /** *

The configuration information of how model candidates are generated.

*/ inline TabularJobConfig& WithCandidateGenerationConfig(const CandidateGenerationConfig& value) { SetCandidateGenerationConfig(value); return *this;} /** *

The configuration information of how model candidates are generated.

*/ inline TabularJobConfig& WithCandidateGenerationConfig(CandidateGenerationConfig&& value) { SetCandidateGenerationConfig(std::move(value)); return *this;} inline const AutoMLJobCompletionCriteria& GetCompletionCriteria() const{ return m_completionCriteria; } inline bool CompletionCriteriaHasBeenSet() const { return m_completionCriteriaHasBeenSet; } inline void SetCompletionCriteria(const AutoMLJobCompletionCriteria& value) { m_completionCriteriaHasBeenSet = true; m_completionCriteria = value; } inline void SetCompletionCriteria(AutoMLJobCompletionCriteria&& value) { m_completionCriteriaHasBeenSet = true; m_completionCriteria = std::move(value); } inline TabularJobConfig& WithCompletionCriteria(const AutoMLJobCompletionCriteria& value) { SetCompletionCriteria(value); return *this;} inline TabularJobConfig& WithCompletionCriteria(AutoMLJobCompletionCriteria&& value) { SetCompletionCriteria(std::move(value)); return *this;} /** *

A URL to the Amazon S3 data source containing selected features from the * input data source to run an Autopilot job V2. 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" ... } }

These column keys may not * include the target column.

In ensembling mode, Autopilot only * supports the following data types: numeric, * categorical, text, and datetime. In HPO * mode, Autopilot can support numeric, categorical, * text, datetime, and sequence.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

The key name FeatureAttributeNames is fixed. The values * listed in ["col1", "col2", ...] are case sensitive and should be a * list of strings containing unique values that are a subset of the column names * in the input data. The list of columns provided must not include the target * column.

*/ inline const Aws::String& GetFeatureSpecificationS3Uri() const{ return m_featureSpecificationS3Uri; } /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline bool FeatureSpecificationS3UriHasBeenSet() const { return m_featureSpecificationS3UriHasBeenSet; } /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline void SetFeatureSpecificationS3Uri(const Aws::String& value) { m_featureSpecificationS3UriHasBeenSet = true; m_featureSpecificationS3Uri = value; } /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline void SetFeatureSpecificationS3Uri(Aws::String&& value) { m_featureSpecificationS3UriHasBeenSet = true; m_featureSpecificationS3Uri = std::move(value); } /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline void SetFeatureSpecificationS3Uri(const char* value) { m_featureSpecificationS3UriHasBeenSet = true; m_featureSpecificationS3Uri.assign(value); } /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline TabularJobConfig& WithFeatureSpecificationS3Uri(const Aws::String& value) { SetFeatureSpecificationS3Uri(value); return *this;} /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline TabularJobConfig& WithFeatureSpecificationS3Uri(Aws::String&& value) { SetFeatureSpecificationS3Uri(std::move(value)); return *this;} /** *

{ "FeatureAttributeNames":["col1", "col2", ...] }.

You can also specify the data type of the feature (optional) in the format * shown below:

{ "FeatureDataTypes":{"col1":"numeric", * "col2":"categorical" ... } }

These column keys may not * include the target column.

If * only FeatureDataTypes is provided, the column keys * (col1, col2,..) should be a subset of the column names * in the input data.

If both FeatureDataTypes and * FeatureAttributeNames are provided, then the column keys should be * a subset of the column names provided in FeatureAttributeNames. *

*/ inline TabularJobConfig& WithFeatureSpecificationS3Uri(const char* value) { SetFeatureSpecificationS3Uri(value); return *this;} /** *

The method that Autopilot uses to train the data. You can either specify the * mode manually or let Autopilot choose for you based on the dataset size by * selecting AUTO. In AUTO mode, Autopilot chooses * ENSEMBLING for datasets smaller than 100 MB, and * HYPERPARAMETER_TUNING for larger ones.

The * ENSEMBLING mode uses a multi-stack ensemble model to predict * classification and regression tasks directly from your dataset. This machine * learning mode combines several base models to produce an optimal predictive * model. It then uses a stacking ensemble method to combine predictions from * contributing members. A multi-stack ensemble model can provide better * performance over a single model by combining the predictive capabilities of * multiple models. See Autopilot * algorithm support for a list of algorithms supported by * ENSEMBLING mode.

The HYPERPARAMETER_TUNING * (HPO) mode uses the best hyperparameters to train the best version of a model. * HPO automatically selects an algorithm for the type of problem you want to * solve. Then HPO finds the best hyperparameters according to your objective * metric. See Autopilot * algorithm support for a list of algorithms supported by * HYPERPARAMETER_TUNING mode.

*/ inline const AutoMLMode& GetMode() const{ return m_mode; } /** *

*/ inline bool ModeHasBeenSet() const { return m_modeHasBeenSet; } /** *

*/ inline void SetMode(const AutoMLMode& value) { m_modeHasBeenSet = true; m_mode = value; } /** *

*/ inline void SetMode(AutoMLMode&& value) { m_modeHasBeenSet = true; m_mode = std::move(value); } /** *

*/ inline TabularJobConfig& WithMode(const AutoMLMode& value) { SetMode(value); return *this;} /** *

*/ inline TabularJobConfig& WithMode(AutoMLMode&& value) { SetMode(std::move(value)); return *this;} /** *

Generates possible candidates without training the models. A model candidate * is a combination of data preprocessors, algorithms, and algorithm parameter * settings.

*/ inline bool GetGenerateCandidateDefinitionsOnly() const{ return m_generateCandidateDefinitionsOnly; } /** *

Generates possible candidates without training the models. A model candidate * is a combination of data preprocessors, algorithms, and algorithm parameter * settings.

*/ inline bool GenerateCandidateDefinitionsOnlyHasBeenSet() const { return m_generateCandidateDefinitionsOnlyHasBeenSet; } /** *

Generates possible candidates without training the models. A model candidate * is a combination of data preprocessors, algorithms, and algorithm parameter * settings.

*/ inline void SetGenerateCandidateDefinitionsOnly(bool value) { m_generateCandidateDefinitionsOnlyHasBeenSet = true; m_generateCandidateDefinitionsOnly = value; } /** *

Generates possible candidates without training the models. A model candidate * is a combination of data preprocessors, algorithms, and algorithm parameter * settings.

*/ inline TabularJobConfig& WithGenerateCandidateDefinitionsOnly(bool value) { SetGenerateCandidateDefinitionsOnly(value); return *this;} /** *

The type of supervised learning problem available for the model candidates of * the AutoML job V2. For more information, see * Amazon SageMaker Autopilot problem types.

You must either * specify the type of supervised learning problem in ProblemType and * provide the AutoMLJobObjective * metric, or none at all.

*/ inline const ProblemType& GetProblemType() const{ return m_problemType; } /** *

The type of supervised learning problem available for the model candidates of * the AutoML job V2. For more information, see * Amazon SageMaker Autopilot problem types.

You must either * specify the type of supervised learning problem in ProblemType and * provide the AutoMLJobObjective * metric, or none at all.

*/ inline bool ProblemTypeHasBeenSet() const { return m_problemTypeHasBeenSet; } /** *

The type of supervised learning problem available for the model candidates of * the AutoML job V2. For more information, see * Amazon SageMaker Autopilot problem types.

You must either * specify the type of supervised learning problem in ProblemType and * provide the AutoMLJobObjective * metric, or none at all.

*/ inline void SetProblemType(const ProblemType& value) { m_problemTypeHasBeenSet = true; m_problemType = value; } /** *

The type of supervised learning problem available for the model candidates of * the AutoML job V2. For more information, see * Amazon SageMaker Autopilot problem types.

You must either * specify the type of supervised learning problem in ProblemType and * provide the AutoMLJobObjective * metric, or none at all.

*/ inline void SetProblemType(ProblemType&& value) { m_problemTypeHasBeenSet = true; m_problemType = std::move(value); } /** *

The type of supervised learning problem available for the model candidates of * the AutoML job V2. For more information, see * Amazon SageMaker Autopilot problem types.

You must either * specify the type of supervised learning problem in ProblemType and * provide the AutoMLJobObjective * metric, or none at all.

*/ inline TabularJobConfig& WithProblemType(const ProblemType& value) { SetProblemType(value); return *this;} /** *

The type of supervised learning problem available for the model candidates of * the AutoML job V2. For more information, see * Amazon SageMaker Autopilot problem types.

You must either * specify the type of supervised learning problem in ProblemType and * provide the AutoMLJobObjective * metric, or none at all.

*/ inline TabularJobConfig& WithProblemType(ProblemType&& value) { SetProblemType(std::move(value)); return *this;} /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline const Aws::String& GetTargetAttributeName() const{ return m_targetAttributeName; } /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline bool TargetAttributeNameHasBeenSet() const { return m_targetAttributeNameHasBeenSet; } /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline void SetTargetAttributeName(const Aws::String& value) { m_targetAttributeNameHasBeenSet = true; m_targetAttributeName = value; } /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline void SetTargetAttributeName(Aws::String&& value) { m_targetAttributeNameHasBeenSet = true; m_targetAttributeName = std::move(value); } /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline void SetTargetAttributeName(const char* value) { m_targetAttributeNameHasBeenSet = true; m_targetAttributeName.assign(value); } /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline TabularJobConfig& WithTargetAttributeName(const Aws::String& value) { SetTargetAttributeName(value); return *this;} /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline TabularJobConfig& WithTargetAttributeName(Aws::String&& value) { SetTargetAttributeName(std::move(value)); return *this;} /** *

The name of the target variable in supervised learning, usually represented * by 'y'.

*/ inline TabularJobConfig& WithTargetAttributeName(const char* value) { SetTargetAttributeName(value); return *this;} /** *

If specified, this column name indicates which column of the dataset should * be treated as sample weights for use by the objective metric during the * training, evaluation, and the selection of the best model. This column is not * considered as a predictive feature. For more information on Autopilot metrics, * see Metrics * and validation.