software.amazon.awssdk.services.sagemaker.model.TabularJobConfig Maven / Gradle / Ivy
Show all versions of sagemaker Show documentation
/*
* Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Licensed under the Apache License, Version 2.0 (the "License"). You may not use this file except in compliance with
* the License. A copy of the License is located at
*
* http://aws.amazon.com/apache2.0
*
* or in the "license" file accompanying this file. This file is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
* CONDITIONS OF ANY KIND, either express or implied. See the License for the specific language governing permissions
* and limitations under the License.
*/
package software.amazon.awssdk.services.sagemaker.model;
import java.io.Serializable;
import java.util.Arrays;
import java.util.Collections;
import java.util.List;
import java.util.Objects;
import java.util.Optional;
import java.util.function.BiConsumer;
import java.util.function.Consumer;
import java.util.function.Function;
import software.amazon.awssdk.annotations.Generated;
import software.amazon.awssdk.core.SdkField;
import software.amazon.awssdk.core.SdkPojo;
import software.amazon.awssdk.core.protocol.MarshallLocation;
import software.amazon.awssdk.core.protocol.MarshallingType;
import software.amazon.awssdk.core.traits.LocationTrait;
import software.amazon.awssdk.utils.ToString;
import software.amazon.awssdk.utils.builder.CopyableBuilder;
import software.amazon.awssdk.utils.builder.ToCopyableBuilder;
/**
*
* The collection of settings used by an AutoML job V2 for the tabular problem type.
*
*/
@Generated("software.amazon.awssdk:codegen")
public final class TabularJobConfig implements SdkPojo, Serializable,
ToCopyableBuilder {
private static final SdkField CANDIDATE_GENERATION_CONFIG_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("CandidateGenerationConfig")
.getter(getter(TabularJobConfig::candidateGenerationConfig)).setter(setter(Builder::candidateGenerationConfig))
.constructor(CandidateGenerationConfig::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("CandidateGenerationConfig").build())
.build();
private static final SdkField COMPLETION_CRITERIA_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("CompletionCriteria")
.getter(getter(TabularJobConfig::completionCriteria)).setter(setter(Builder::completionCriteria))
.constructor(AutoMLJobCompletionCriteria::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("CompletionCriteria").build())
.build();
private static final SdkField FEATURE_SPECIFICATION_S3_URI_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("FeatureSpecificationS3Uri").getter(getter(TabularJobConfig::featureSpecificationS3Uri))
.setter(setter(Builder::featureSpecificationS3Uri))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("FeatureSpecificationS3Uri").build())
.build();
private static final SdkField MODE_FIELD = SdkField. builder(MarshallingType.STRING).memberName("Mode")
.getter(getter(TabularJobConfig::modeAsString)).setter(setter(Builder::mode))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("Mode").build()).build();
private static final SdkField GENERATE_CANDIDATE_DEFINITIONS_ONLY_FIELD = SdkField
. builder(MarshallingType.BOOLEAN)
.memberName("GenerateCandidateDefinitionsOnly")
.getter(getter(TabularJobConfig::generateCandidateDefinitionsOnly))
.setter(setter(Builder::generateCandidateDefinitionsOnly))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("GenerateCandidateDefinitionsOnly")
.build()).build();
private static final SdkField PROBLEM_TYPE_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("ProblemType").getter(getter(TabularJobConfig::problemTypeAsString)).setter(setter(Builder::problemType))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("ProblemType").build()).build();
private static final SdkField TARGET_ATTRIBUTE_NAME_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("TargetAttributeName").getter(getter(TabularJobConfig::targetAttributeName))
.setter(setter(Builder::targetAttributeName))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("TargetAttributeName").build())
.build();
private static final SdkField SAMPLE_WEIGHT_ATTRIBUTE_NAME_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("SampleWeightAttributeName").getter(getter(TabularJobConfig::sampleWeightAttributeName))
.setter(setter(Builder::sampleWeightAttributeName))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("SampleWeightAttributeName").build())
.build();
private static final List> SDK_FIELDS = Collections.unmodifiableList(Arrays.asList(
CANDIDATE_GENERATION_CONFIG_FIELD, COMPLETION_CRITERIA_FIELD, FEATURE_SPECIFICATION_S3_URI_FIELD, MODE_FIELD,
GENERATE_CANDIDATE_DEFINITIONS_ONLY_FIELD, PROBLEM_TYPE_FIELD, TARGET_ATTRIBUTE_NAME_FIELD,
SAMPLE_WEIGHT_ATTRIBUTE_NAME_FIELD));
private static final long serialVersionUID = 1L;
private final CandidateGenerationConfig candidateGenerationConfig;
private final AutoMLJobCompletionCriteria completionCriteria;
private final String featureSpecificationS3Uri;
private final String mode;
private final Boolean generateCandidateDefinitionsOnly;
private final String problemType;
private final String targetAttributeName;
private final String sampleWeightAttributeName;
private TabularJobConfig(BuilderImpl builder) {
this.candidateGenerationConfig = builder.candidateGenerationConfig;
this.completionCriteria = builder.completionCriteria;
this.featureSpecificationS3Uri = builder.featureSpecificationS3Uri;
this.mode = builder.mode;
this.generateCandidateDefinitionsOnly = builder.generateCandidateDefinitionsOnly;
this.problemType = builder.problemType;
this.targetAttributeName = builder.targetAttributeName;
this.sampleWeightAttributeName = builder.sampleWeightAttributeName;
}
/**
*
* The configuration information of how model candidates are generated.
*
*
* @return The configuration information of how model candidates are generated.
*/
public final CandidateGenerationConfig candidateGenerationConfig() {
return candidateGenerationConfig;
}
/**
* Returns the value of the CompletionCriteria property for this object.
*
* @return The value of the CompletionCriteria property for this object.
*/
public final AutoMLJobCompletionCriteria completionCriteria() {
return completionCriteria;
}
/**
*
* 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.
*
*
* @return 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.
*/
public final String featureSpecificationS3Uri() {
return featureSpecificationS3Uri;
}
/**
*
* 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.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #mode} will return
* {@link AutoMLMode#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available from
* {@link #modeAsString}.
*
*
* @return 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.
* @see AutoMLMode
*/
public final AutoMLMode mode() {
return AutoMLMode.fromValue(mode);
}
/**
*
* 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.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #mode} will return
* {@link AutoMLMode#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available from
* {@link #modeAsString}.
*
*
* @return 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.
* @see AutoMLMode
*/
public final String modeAsString() {
return mode;
}
/**
*
* Generates possible candidates without training the models. A model candidate is a combination of data
* preprocessors, algorithms, and algorithm parameter settings.
*
*
* @return Generates possible candidates without training the models. A model candidate is a combination of data
* preprocessors, algorithms, and algorithm parameter settings.
*/
public final Boolean generateCandidateDefinitionsOnly() {
return generateCandidateDefinitionsOnly;
}
/**
*
* The type of supervised learning problem available for the model candidates of the AutoML job V2. For more
* information, see
* 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.
*
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #problemType} will
* return {@link ProblemType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available from
* {@link #problemTypeAsString}.
*
*
* @return The type of supervised learning problem available for the model candidates of the AutoML job V2. For more
* information, see 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.
*
* @see ProblemType
*/
public final ProblemType problemType() {
return ProblemType.fromValue(problemType);
}
/**
*
* The type of supervised learning problem available for the model candidates of the AutoML job V2. For more
* information, see
* 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.
*
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #problemType} will
* return {@link ProblemType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available from
* {@link #problemTypeAsString}.
*
*
* @return The type of supervised learning problem available for the model candidates of the AutoML job V2. For more
* information, see 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.
*
* @see ProblemType
*/
public final String problemTypeAsString() {
return problemType;
}
/**
*
* The name of the target variable in supervised learning, usually represented by 'y'.
*
*
* @return The name of the target variable in supervised learning, usually represented by 'y'.
*/
public final String targetAttributeName() {
return targetAttributeName;
}
/**
*
* 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.
*
*
* Sample weights should be numeric, non-negative, with larger values indicating which rows are more important than
* others. Data points that have invalid or no weight value are excluded.
*
*
* Support for sample weights is available in Ensembling
* mode only.
*
*
* @return 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.
*
* Sample weights should be numeric, non-negative, with larger values indicating which rows are more
* important than others. Data points that have invalid or no weight value are excluded.
*
*
* Support for sample weights is available in Ensembling mode only.
*/
public final String sampleWeightAttributeName() {
return sampleWeightAttributeName;
}
@Override
public Builder toBuilder() {
return new BuilderImpl(this);
}
public static Builder builder() {
return new BuilderImpl();
}
public static Class serializableBuilderClass() {
return BuilderImpl.class;
}
@Override
public final int hashCode() {
int hashCode = 1;
hashCode = 31 * hashCode + Objects.hashCode(candidateGenerationConfig());
hashCode = 31 * hashCode + Objects.hashCode(completionCriteria());
hashCode = 31 * hashCode + Objects.hashCode(featureSpecificationS3Uri());
hashCode = 31 * hashCode + Objects.hashCode(modeAsString());
hashCode = 31 * hashCode + Objects.hashCode(generateCandidateDefinitionsOnly());
hashCode = 31 * hashCode + Objects.hashCode(problemTypeAsString());
hashCode = 31 * hashCode + Objects.hashCode(targetAttributeName());
hashCode = 31 * hashCode + Objects.hashCode(sampleWeightAttributeName());
return hashCode;
}
@Override
public final boolean equals(Object obj) {
return equalsBySdkFields(obj);
}
@Override
public final boolean equalsBySdkFields(Object obj) {
if (this == obj) {
return true;
}
if (obj == null) {
return false;
}
if (!(obj instanceof TabularJobConfig)) {
return false;
}
TabularJobConfig other = (TabularJobConfig) obj;
return Objects.equals(candidateGenerationConfig(), other.candidateGenerationConfig())
&& Objects.equals(completionCriteria(), other.completionCriteria())
&& Objects.equals(featureSpecificationS3Uri(), other.featureSpecificationS3Uri())
&& Objects.equals(modeAsString(), other.modeAsString())
&& Objects.equals(generateCandidateDefinitionsOnly(), other.generateCandidateDefinitionsOnly())
&& Objects.equals(problemTypeAsString(), other.problemTypeAsString())
&& Objects.equals(targetAttributeName(), other.targetAttributeName())
&& Objects.equals(sampleWeightAttributeName(), other.sampleWeightAttributeName());
}
/**
* Returns a string representation of this object. This is useful for testing and debugging. Sensitive data will be
* redacted from this string using a placeholder value.
*/
@Override
public final String toString() {
return ToString.builder("TabularJobConfig").add("CandidateGenerationConfig", candidateGenerationConfig())
.add("CompletionCriteria", completionCriteria()).add("FeatureSpecificationS3Uri", featureSpecificationS3Uri())
.add("Mode", modeAsString()).add("GenerateCandidateDefinitionsOnly", generateCandidateDefinitionsOnly())
.add("ProblemType", problemTypeAsString()).add("TargetAttributeName", targetAttributeName())
.add("SampleWeightAttributeName", sampleWeightAttributeName()).build();
}
public final Optional getValueForField(String fieldName, Class clazz) {
switch (fieldName) {
case "CandidateGenerationConfig":
return Optional.ofNullable(clazz.cast(candidateGenerationConfig()));
case "CompletionCriteria":
return Optional.ofNullable(clazz.cast(completionCriteria()));
case "FeatureSpecificationS3Uri":
return Optional.ofNullable(clazz.cast(featureSpecificationS3Uri()));
case "Mode":
return Optional.ofNullable(clazz.cast(modeAsString()));
case "GenerateCandidateDefinitionsOnly":
return Optional.ofNullable(clazz.cast(generateCandidateDefinitionsOnly()));
case "ProblemType":
return Optional.ofNullable(clazz.cast(problemTypeAsString()));
case "TargetAttributeName":
return Optional.ofNullable(clazz.cast(targetAttributeName()));
case "SampleWeightAttributeName":
return Optional.ofNullable(clazz.cast(sampleWeightAttributeName()));
default:
return Optional.empty();
}
}
@Override
public final List> sdkFields() {
return SDK_FIELDS;
}
private static Function getter(Function g) {
return obj -> g.apply((TabularJobConfig) obj);
}
private static BiConsumer setter(BiConsumer s) {
return (obj, val) -> s.accept((Builder) obj, val);
}
public interface Builder extends SdkPojo, CopyableBuilder {
/**
*
* The configuration information of how model candidates are generated.
*
*
* @param candidateGenerationConfig
* The configuration information of how model candidates are generated.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder candidateGenerationConfig(CandidateGenerationConfig candidateGenerationConfig);
/**
*
* The configuration information of how model candidates are generated.
*
* This is a convenience method that creates an instance of the {@link CandidateGenerationConfig.Builder}
* avoiding the need to create one manually via {@link CandidateGenerationConfig#builder()}.
*
*
* When the {@link Consumer} completes, {@link CandidateGenerationConfig.Builder#build()} is called immediately
* and its result is passed to {@link #candidateGenerationConfig(CandidateGenerationConfig)}.
*
* @param candidateGenerationConfig
* a consumer that will call methods on {@link CandidateGenerationConfig.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #candidateGenerationConfig(CandidateGenerationConfig)
*/
default Builder candidateGenerationConfig(Consumer candidateGenerationConfig) {
return candidateGenerationConfig(CandidateGenerationConfig.builder().applyMutation(candidateGenerationConfig).build());
}
/**
* Sets the value of the CompletionCriteria property for this object.
*
* @param completionCriteria
* The new value for the CompletionCriteria property for this object.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder completionCriteria(AutoMLJobCompletionCriteria completionCriteria);
/**
* Sets the value of the CompletionCriteria property for this object.
*
* This is a convenience method that creates an instance of the {@link AutoMLJobCompletionCriteria.Builder}
* avoiding the need to create one manually via {@link AutoMLJobCompletionCriteria#builder()}.
*
*
* When the {@link Consumer} completes, {@link AutoMLJobCompletionCriteria.Builder#build()} is called
* immediately and its result is passed to {@link #completionCriteria(AutoMLJobCompletionCriteria)}.
*
* @param completionCriteria
* a consumer that will call methods on {@link AutoMLJobCompletionCriteria.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #completionCriteria(AutoMLJobCompletionCriteria)
*/
default Builder completionCriteria(Consumer completionCriteria) {
return completionCriteria(AutoMLJobCompletionCriteria.builder().applyMutation(completionCriteria).build());
}
/**
*
* 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.
*
*
* @param featureSpecificationS3Uri
* 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.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder featureSpecificationS3Uri(String featureSpecificationS3Uri);
/**
*
* 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.
*
*
* @param mode
* 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.
* @see AutoMLMode
* @return Returns a reference to this object so that method calls can be chained together.
* @see AutoMLMode
*/
Builder mode(String mode);
/**
*
* 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.
*
*
* @param mode
* 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.
* @see AutoMLMode
* @return Returns a reference to this object so that method calls can be chained together.
* @see AutoMLMode
*/
Builder mode(AutoMLMode mode);
/**
*
* Generates possible candidates without training the models. A model candidate is a combination of data
* preprocessors, algorithms, and algorithm parameter settings.
*
*
* @param generateCandidateDefinitionsOnly
* Generates possible candidates without training the models. A model candidate is a combination of data
* preprocessors, algorithms, and algorithm parameter settings.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder generateCandidateDefinitionsOnly(Boolean generateCandidateDefinitionsOnly);
/**
*
* The type of supervised learning problem available for the model candidates of the AutoML job V2. For more
* information, see 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.
*
*
*
* @param problemType
* The type of supervised learning problem available for the model candidates of the AutoML job V2. For
* more information, see 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.
*
* @see ProblemType
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProblemType
*/
Builder problemType(String problemType);
/**
*
* The type of supervised learning problem available for the model candidates of the AutoML job V2. For more
* information, see 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.
*
*
*
* @param problemType
* The type of supervised learning problem available for the model candidates of the AutoML job V2. For
* more information, see 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.
*
* @see ProblemType
* @return Returns a reference to this object so that method calls can be chained together.
* @see ProblemType
*/
Builder problemType(ProblemType problemType);
/**
*
* The name of the target variable in supervised learning, usually represented by 'y'.
*
*
* @param targetAttributeName
* The name of the target variable in supervised learning, usually represented by 'y'.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder targetAttributeName(String targetAttributeName);
/**
*
* 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.
*
*
* Sample weights should be numeric, non-negative, with larger values indicating which rows are more important
* than others. Data points that have invalid or no weight value are excluded.
*
*
* Support for sample weights is available in Ensembling mode only.
*
*
* @param sampleWeightAttributeName
* 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.
*
* Sample weights should be numeric, non-negative, with larger values indicating which rows are more
* important than others. Data points that have invalid or no weight value are excluded.
*
*
* Support for sample weights is available in Ensembling mode only.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder sampleWeightAttributeName(String sampleWeightAttributeName);
}
static final class BuilderImpl implements Builder {
private CandidateGenerationConfig candidateGenerationConfig;
private AutoMLJobCompletionCriteria completionCriteria;
private String featureSpecificationS3Uri;
private String mode;
private Boolean generateCandidateDefinitionsOnly;
private String problemType;
private String targetAttributeName;
private String sampleWeightAttributeName;
private BuilderImpl() {
}
private BuilderImpl(TabularJobConfig model) {
candidateGenerationConfig(model.candidateGenerationConfig);
completionCriteria(model.completionCriteria);
featureSpecificationS3Uri(model.featureSpecificationS3Uri);
mode(model.mode);
generateCandidateDefinitionsOnly(model.generateCandidateDefinitionsOnly);
problemType(model.problemType);
targetAttributeName(model.targetAttributeName);
sampleWeightAttributeName(model.sampleWeightAttributeName);
}
public final CandidateGenerationConfig.Builder getCandidateGenerationConfig() {
return candidateGenerationConfig != null ? candidateGenerationConfig.toBuilder() : null;
}
public final void setCandidateGenerationConfig(CandidateGenerationConfig.BuilderImpl candidateGenerationConfig) {
this.candidateGenerationConfig = candidateGenerationConfig != null ? candidateGenerationConfig.build() : null;
}
@Override
public final Builder candidateGenerationConfig(CandidateGenerationConfig candidateGenerationConfig) {
this.candidateGenerationConfig = candidateGenerationConfig;
return this;
}
public final AutoMLJobCompletionCriteria.Builder getCompletionCriteria() {
return completionCriteria != null ? completionCriteria.toBuilder() : null;
}
public final void setCompletionCriteria(AutoMLJobCompletionCriteria.BuilderImpl completionCriteria) {
this.completionCriteria = completionCriteria != null ? completionCriteria.build() : null;
}
@Override
public final Builder completionCriteria(AutoMLJobCompletionCriteria completionCriteria) {
this.completionCriteria = completionCriteria;
return this;
}
public final String getFeatureSpecificationS3Uri() {
return featureSpecificationS3Uri;
}
public final void setFeatureSpecificationS3Uri(String featureSpecificationS3Uri) {
this.featureSpecificationS3Uri = featureSpecificationS3Uri;
}
@Override
public final Builder featureSpecificationS3Uri(String featureSpecificationS3Uri) {
this.featureSpecificationS3Uri = featureSpecificationS3Uri;
return this;
}
public final String getMode() {
return mode;
}
public final void setMode(String mode) {
this.mode = mode;
}
@Override
public final Builder mode(String mode) {
this.mode = mode;
return this;
}
@Override
public final Builder mode(AutoMLMode mode) {
this.mode(mode == null ? null : mode.toString());
return this;
}
public final Boolean getGenerateCandidateDefinitionsOnly() {
return generateCandidateDefinitionsOnly;
}
public final void setGenerateCandidateDefinitionsOnly(Boolean generateCandidateDefinitionsOnly) {
this.generateCandidateDefinitionsOnly = generateCandidateDefinitionsOnly;
}
@Override
public final Builder generateCandidateDefinitionsOnly(Boolean generateCandidateDefinitionsOnly) {
this.generateCandidateDefinitionsOnly = generateCandidateDefinitionsOnly;
return this;
}
public final String getProblemType() {
return problemType;
}
public final void setProblemType(String problemType) {
this.problemType = problemType;
}
@Override
public final Builder problemType(String problemType) {
this.problemType = problemType;
return this;
}
@Override
public final Builder problemType(ProblemType problemType) {
this.problemType(problemType == null ? null : problemType.toString());
return this;
}
public final String getTargetAttributeName() {
return targetAttributeName;
}
public final void setTargetAttributeName(String targetAttributeName) {
this.targetAttributeName = targetAttributeName;
}
@Override
public final Builder targetAttributeName(String targetAttributeName) {
this.targetAttributeName = targetAttributeName;
return this;
}
public final String getSampleWeightAttributeName() {
return sampleWeightAttributeName;
}
public final void setSampleWeightAttributeName(String sampleWeightAttributeName) {
this.sampleWeightAttributeName = sampleWeightAttributeName;
}
@Override
public final Builder sampleWeightAttributeName(String sampleWeightAttributeName) {
this.sampleWeightAttributeName = sampleWeightAttributeName;
return this;
}
@Override
public TabularJobConfig build() {
return new TabularJobConfig(this);
}
@Override
public List> sdkFields() {
return SDK_FIELDS;
}
}
}