software.amazon.awssdk.services.machinelearning.model.RedshiftDataSpec Maven / Gradle / Ivy
Show all versions of machinelearning 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.machinelearning.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;
/**
*
* Describes the data specification of an Amazon Redshift DataSource.
*
*/
@Generated("software.amazon.awssdk:codegen")
public final class RedshiftDataSpec implements SdkPojo, Serializable,
ToCopyableBuilder {
private static final SdkField DATABASE_INFORMATION_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("DatabaseInformation")
.getter(getter(RedshiftDataSpec::databaseInformation)).setter(setter(Builder::databaseInformation))
.constructor(RedshiftDatabase::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("DatabaseInformation").build())
.build();
private static final SdkField SELECT_SQL_QUERY_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("SelectSqlQuery").getter(getter(RedshiftDataSpec::selectSqlQuery))
.setter(setter(Builder::selectSqlQuery))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("SelectSqlQuery").build()).build();
private static final SdkField DATABASE_CREDENTIALS_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("DatabaseCredentials")
.getter(getter(RedshiftDataSpec::databaseCredentials)).setter(setter(Builder::databaseCredentials))
.constructor(RedshiftDatabaseCredentials::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("DatabaseCredentials").build())
.build();
private static final SdkField S3_STAGING_LOCATION_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("S3StagingLocation").getter(getter(RedshiftDataSpec::s3StagingLocation))
.setter(setter(Builder::s3StagingLocation))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("S3StagingLocation").build()).build();
private static final SdkField DATA_REARRANGEMENT_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("DataRearrangement").getter(getter(RedshiftDataSpec::dataRearrangement))
.setter(setter(Builder::dataRearrangement))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("DataRearrangement").build()).build();
private static final SdkField DATA_SCHEMA_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("DataSchema").getter(getter(RedshiftDataSpec::dataSchema)).setter(setter(Builder::dataSchema))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("DataSchema").build()).build();
private static final SdkField DATA_SCHEMA_URI_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("DataSchemaUri").getter(getter(RedshiftDataSpec::dataSchemaUri)).setter(setter(Builder::dataSchemaUri))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("DataSchemaUri").build()).build();
private static final List> SDK_FIELDS = Collections.unmodifiableList(Arrays.asList(DATABASE_INFORMATION_FIELD,
SELECT_SQL_QUERY_FIELD, DATABASE_CREDENTIALS_FIELD, S3_STAGING_LOCATION_FIELD, DATA_REARRANGEMENT_FIELD,
DATA_SCHEMA_FIELD, DATA_SCHEMA_URI_FIELD));
private static final long serialVersionUID = 1L;
private final RedshiftDatabase databaseInformation;
private final String selectSqlQuery;
private final RedshiftDatabaseCredentials databaseCredentials;
private final String s3StagingLocation;
private final String dataRearrangement;
private final String dataSchema;
private final String dataSchemaUri;
private RedshiftDataSpec(BuilderImpl builder) {
this.databaseInformation = builder.databaseInformation;
this.selectSqlQuery = builder.selectSqlQuery;
this.databaseCredentials = builder.databaseCredentials;
this.s3StagingLocation = builder.s3StagingLocation;
this.dataRearrangement = builder.dataRearrangement;
this.dataSchema = builder.dataSchema;
this.dataSchemaUri = builder.dataSchemaUri;
}
/**
*
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*
*
* @return Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*/
public final RedshiftDatabase databaseInformation() {
return databaseInformation;
}
/**
*
* Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift DataSource.
*
*
* @return Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift
* DataSource.
*/
public final String selectSqlQuery() {
return selectSqlQuery;
}
/**
*
* Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon Redshift
* database.
*
*
* @return Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon
* Redshift database.
*/
public final RedshiftDatabaseCredentials databaseCredentials() {
return databaseCredentials;
}
/**
*
* Describes an Amazon S3 location to store the result set of the SelectSqlQuery query.
*
*
* @return Describes an Amazon S3 location to store the result set of the SelectSqlQuery query.
*/
public final String s3StagingLocation() {
return s3StagingLocation;
}
/**
*
* A JSON string that represents the splitting and rearrangement processing to be applied to a
* DataSource. If the DataRearrangement parameter is not provided, all of the input data
* is used to create the Datasource.
*
*
* There are multiple parameters that control what data is used to create a datasource:
*
*
* -
*
* percentBegin
*
*
* Use percentBegin to indicate the beginning of the range of the data used to create the Datasource.
* If you do not include percentBegin and percentEnd, Amazon ML includes all of the data
* when creating the datasource.
*
*
* -
*
* percentEnd
*
*
* Use percentEnd to indicate the end of the range of the data used to create the Datasource. If you do
* not include percentBegin and percentEnd, Amazon ML includes all of the data when
* creating the datasource.
*
*
* -
*
* complement
*
*
* The complement parameter instructs Amazon ML to use the data that is not included in the range of
* percentBegin to percentEnd to create a datasource. The complement
* parameter is useful if you need to create complementary datasources for training and evaluation. To create a
* complementary datasource, use the same values for percentBegin and percentEnd, along
* with the complement parameter.
*
*
* For example, the following two datasources do not share any data, and can be used to train and evaluate a model.
* The first datasource has 25 percent of the data, and the second one has 75 percent of the data.
*
*
* Datasource for evaluation: {"splitting":{"percentBegin":0, "percentEnd":25}}
*
*
* Datasource for training: {"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
*
*
* -
*
* strategy
*
*
* To change how Amazon ML splits the data for a datasource, use the strategy parameter.
*
*
* The default value for the strategy parameter is sequential, meaning that Amazon ML
* takes all of the data records between the percentBegin and percentEnd parameters for
* the datasource, in the order that the records appear in the input data.
*
*
* The following two DataRearrangement lines are examples of sequentially ordered training and
* evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
*
*
* To randomly split the input data into the proportions indicated by the percentBegin and percentEnd parameters,
* set the strategy parameter to random and provide a string that is used as the seed
* value for the random data splitting (for example, you can use the S3 path to your data as the random seed
* string). If you choose the random split strategy, Amazon ML assigns each row of data a pseudo-random number
* between 0 and 100, and then selects the rows that have an assigned number between percentBegin and
* percentEnd. Pseudo-random numbers are assigned using both the input seed string value and the byte
* offset as a seed, so changing the data results in a different split. Any existing ordering is preserved. The
* random splitting strategy ensures that variables in the training and evaluation data are distributed similarly.
* It is useful in the cases where the input data may have an implicit sort order, which would otherwise result in
* training and evaluation datasources containing non-similar data records.
*
*
* The following two DataRearrangement lines are examples of non-sequentially ordered training and
* evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
*
*
*
*
* @return A JSON string that represents the splitting and rearrangement processing to be applied to a
* DataSource. If the DataRearrangement parameter is not provided, all of the
* input data is used to create the Datasource.
*
* There are multiple parameters that control what data is used to create a datasource:
*
*
* -
*
* percentBegin
*
*
* Use percentBegin to indicate the beginning of the range of the data used to create the
* Datasource. If you do not include percentBegin and percentEnd, Amazon ML
* includes all of the data when creating the datasource.
*
*
* -
*
* percentEnd
*
*
* Use percentEnd to indicate the end of the range of the data used to create the Datasource.
* If you do not include percentBegin and percentEnd, Amazon ML includes all of
* the data when creating the datasource.
*
*
* -
*
* complement
*
*
* The complement parameter instructs Amazon ML to use the data that is not included in the
* range of percentBegin to percentEnd to create a datasource. The
* complement parameter is useful if you need to create complementary datasources for training
* and evaluation. To create a complementary datasource, use the same values for percentBegin
* and percentEnd, along with the complement parameter.
*
*
* For example, the following two datasources do not share any data, and can be used to train and evaluate a
* model. The first datasource has 25 percent of the data, and the second one has 75 percent of the data.
*
*
* Datasource for evaluation: {"splitting":{"percentBegin":0, "percentEnd":25}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
*
*
* -
*
* strategy
*
*
* To change how Amazon ML splits the data for a datasource, use the strategy parameter.
*
*
* The default value for the strategy parameter is sequential, meaning that Amazon
* ML takes all of the data records between the percentBegin and percentEnd
* parameters for the datasource, in the order that the records appear in the input data.
*
*
* The following two DataRearrangement lines are examples of sequentially ordered training and
* evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
*
*
* To randomly split the input data into the proportions indicated by the percentBegin and percentEnd
* parameters, set the strategy parameter to random and provide a string that is
* used as the seed value for the random data splitting (for example, you can use the S3 path to your data
* as the random seed string). If you choose the random split strategy, Amazon ML assigns each row of data a
* pseudo-random number between 0 and 100, and then selects the rows that have an assigned number between
* percentBegin and percentEnd. Pseudo-random numbers are assigned using both the
* input seed string value and the byte offset as a seed, so changing the data results in a different split.
* Any existing ordering is preserved. The random splitting strategy ensures that variables in the training
* and evaluation data are distributed similarly. It is useful in the cases where the input data may have an
* implicit sort order, which would otherwise result in training and evaluation datasources containing
* non-similar data records.
*
*
* The following two DataRearrangement lines are examples of non-sequentially ordered training
* and evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
*
*
*/
public final String dataRearrangement() {
return dataRearrangement;
}
/**
*
* A JSON string that represents the schema for an Amazon Redshift DataSource. The
* DataSchema defines the structure of the observation data in the data file(s) referenced in the
* DataSource.
*
*
* A DataSchema is not required if you specify a DataSchemaUri.
*
*
* Define your DataSchema as a series of key-value pairs. attributes and
* excludedVariableNames have an array of key-value pairs for their value. Use the following format to
* define your DataSchema.
*
*
* { "version": "1.0",
*
*
* "recordAnnotationFieldName": "F1",
*
*
* "recordWeightFieldName": "F2",
*
*
* "targetFieldName": "F3",
*
*
* "dataFormat": "CSV",
*
*
* "dataFileContainsHeader": true,
*
*
* "attributes": [
*
*
* { "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, { "fieldName": "F3",
* "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, { "fieldName": "F5", "fieldType":
* "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, { "fieldName": "F7", "fieldType":
* "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType": "WEIGHTED_STRING_SEQUENCE" } ],
*
*
* "excludedVariableNames": [ "F6" ] }
*
*
* @return A JSON string that represents the schema for an Amazon Redshift DataSource. The
* DataSchema defines the structure of the observation data in the data file(s) referenced in
* the DataSource.
*
* A DataSchema is not required if you specify a DataSchemaUri.
*
*
* Define your DataSchema as a series of key-value pairs. attributes and
* excludedVariableNames have an array of key-value pairs for their value. Use the following
* format to define your DataSchema.
*
*
* { "version": "1.0",
*
*
* "recordAnnotationFieldName": "F1",
*
*
* "recordWeightFieldName": "F2",
*
*
* "targetFieldName": "F3",
*
*
* "dataFormat": "CSV",
*
*
* "dataFileContainsHeader": true,
*
*
* "attributes": [
*
*
* { "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, { "fieldName":
* "F3", "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, { "fieldName": "F5",
* "fieldType": "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, { "fieldName": "F7",
* "fieldType": "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType": "WEIGHTED_STRING_SEQUENCE" } ],
*
*
* "excludedVariableNames": [ "F6" ] }
*/
public final String dataSchema() {
return dataSchema;
}
/**
*
* Describes the schema location for an Amazon Redshift DataSource.
*
*
* @return Describes the schema location for an Amazon Redshift DataSource.
*/
public final String dataSchemaUri() {
return dataSchemaUri;
}
@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(databaseInformation());
hashCode = 31 * hashCode + Objects.hashCode(selectSqlQuery());
hashCode = 31 * hashCode + Objects.hashCode(databaseCredentials());
hashCode = 31 * hashCode + Objects.hashCode(s3StagingLocation());
hashCode = 31 * hashCode + Objects.hashCode(dataRearrangement());
hashCode = 31 * hashCode + Objects.hashCode(dataSchema());
hashCode = 31 * hashCode + Objects.hashCode(dataSchemaUri());
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 RedshiftDataSpec)) {
return false;
}
RedshiftDataSpec other = (RedshiftDataSpec) obj;
return Objects.equals(databaseInformation(), other.databaseInformation())
&& Objects.equals(selectSqlQuery(), other.selectSqlQuery())
&& Objects.equals(databaseCredentials(), other.databaseCredentials())
&& Objects.equals(s3StagingLocation(), other.s3StagingLocation())
&& Objects.equals(dataRearrangement(), other.dataRearrangement())
&& Objects.equals(dataSchema(), other.dataSchema()) && Objects.equals(dataSchemaUri(), other.dataSchemaUri());
}
/**
* 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("RedshiftDataSpec").add("DatabaseInformation", databaseInformation())
.add("SelectSqlQuery", selectSqlQuery()).add("DatabaseCredentials", databaseCredentials())
.add("S3StagingLocation", s3StagingLocation()).add("DataRearrangement", dataRearrangement())
.add("DataSchema", dataSchema()).add("DataSchemaUri", dataSchemaUri()).build();
}
public final Optional getValueForField(String fieldName, Class clazz) {
switch (fieldName) {
case "DatabaseInformation":
return Optional.ofNullable(clazz.cast(databaseInformation()));
case "SelectSqlQuery":
return Optional.ofNullable(clazz.cast(selectSqlQuery()));
case "DatabaseCredentials":
return Optional.ofNullable(clazz.cast(databaseCredentials()));
case "S3StagingLocation":
return Optional.ofNullable(clazz.cast(s3StagingLocation()));
case "DataRearrangement":
return Optional.ofNullable(clazz.cast(dataRearrangement()));
case "DataSchema":
return Optional.ofNullable(clazz.cast(dataSchema()));
case "DataSchemaUri":
return Optional.ofNullable(clazz.cast(dataSchemaUri()));
default:
return Optional.empty();
}
}
@Override
public final List> sdkFields() {
return SDK_FIELDS;
}
private static Function getter(Function g) {
return obj -> g.apply((RedshiftDataSpec) obj);
}
private static BiConsumer setter(BiConsumer s) {
return (obj, val) -> s.accept((Builder) obj, val);
}
public interface Builder extends SdkPojo, CopyableBuilder {
/**
*
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*
*
* @param databaseInformation
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder databaseInformation(RedshiftDatabase databaseInformation);
/**
*
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*
* This is a convenience method that creates an instance of the {@link RedshiftDatabase.Builder} avoiding the
* need to create one manually via {@link RedshiftDatabase#builder()}.
*
*
* When the {@link Consumer} completes, {@link RedshiftDatabase.Builder#build()} is called immediately and its
* result is passed to {@link #databaseInformation(RedshiftDatabase)}.
*
* @param databaseInformation
* a consumer that will call methods on {@link RedshiftDatabase.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #databaseInformation(RedshiftDatabase)
*/
default Builder databaseInformation(Consumer databaseInformation) {
return databaseInformation(RedshiftDatabase.builder().applyMutation(databaseInformation).build());
}
/**
*
* Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift
* DataSource.
*
*
* @param selectSqlQuery
* Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift
* DataSource.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder selectSqlQuery(String selectSqlQuery);
/**
*
* Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon Redshift
* database.
*
*
* @param databaseCredentials
* Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon
* Redshift database.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder databaseCredentials(RedshiftDatabaseCredentials databaseCredentials);
/**
*
* Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon Redshift
* database.
*
* This is a convenience method that creates an instance of the {@link RedshiftDatabaseCredentials.Builder}
* avoiding the need to create one manually via {@link RedshiftDatabaseCredentials#builder()}.
*
*
* When the {@link Consumer} completes, {@link RedshiftDatabaseCredentials.Builder#build()} is called
* immediately and its result is passed to {@link #databaseCredentials(RedshiftDatabaseCredentials)}.
*
* @param databaseCredentials
* a consumer that will call methods on {@link RedshiftDatabaseCredentials.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #databaseCredentials(RedshiftDatabaseCredentials)
*/
default Builder databaseCredentials(Consumer databaseCredentials) {
return databaseCredentials(RedshiftDatabaseCredentials.builder().applyMutation(databaseCredentials).build());
}
/**
*
* Describes an Amazon S3 location to store the result set of the SelectSqlQuery query.
*
*
* @param s3StagingLocation
* Describes an Amazon S3 location to store the result set of the SelectSqlQuery query.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder s3StagingLocation(String s3StagingLocation);
/**
*
* A JSON string that represents the splitting and rearrangement processing to be applied to a
* DataSource. If the DataRearrangement parameter is not provided, all of the input
* data is used to create the Datasource.
*
*
* There are multiple parameters that control what data is used to create a datasource:
*
*
* -
*
* percentBegin
*
*
* Use percentBegin to indicate the beginning of the range of the data used to create the
* Datasource. If you do not include percentBegin and percentEnd, Amazon ML includes
* all of the data when creating the datasource.
*
*
* -
*
* percentEnd
*
*
* Use percentEnd to indicate the end of the range of the data used to create the Datasource. If
* you do not include percentBegin and percentEnd, Amazon ML includes all of the data
* when creating the datasource.
*
*
* -
*
* complement
*
*
* The complement parameter instructs Amazon ML to use the data that is not included in the range
* of percentBegin to percentEnd to create a datasource. The complement
* parameter is useful if you need to create complementary datasources for training and evaluation. To create a
* complementary datasource, use the same values for percentBegin and percentEnd,
* along with the complement parameter.
*
*
* For example, the following two datasources do not share any data, and can be used to train and evaluate a
* model. The first datasource has 25 percent of the data, and the second one has 75 percent of the data.
*
*
* Datasource for evaluation: {"splitting":{"percentBegin":0, "percentEnd":25}}
*
*
* Datasource for training: {"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
*
*
* -
*
* strategy
*
*
* To change how Amazon ML splits the data for a datasource, use the strategy parameter.
*
*
* The default value for the strategy parameter is sequential, meaning that Amazon ML
* takes all of the data records between the percentBegin and percentEnd parameters
* for the datasource, in the order that the records appear in the input data.
*
*
* The following two DataRearrangement lines are examples of sequentially ordered training and
* evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
*
*
* To randomly split the input data into the proportions indicated by the percentBegin and percentEnd
* parameters, set the strategy parameter to random and provide a string that is used
* as the seed value for the random data splitting (for example, you can use the S3 path to your data as the
* random seed string). If you choose the random split strategy, Amazon ML assigns each row of data a
* pseudo-random number between 0 and 100, and then selects the rows that have an assigned number between
* percentBegin and percentEnd. Pseudo-random numbers are assigned using both the
* input seed string value and the byte offset as a seed, so changing the data results in a different split. Any
* existing ordering is preserved. The random splitting strategy ensures that variables in the training and
* evaluation data are distributed similarly. It is useful in the cases where the input data may have an
* implicit sort order, which would otherwise result in training and evaluation datasources containing
* non-similar data records.
*
*
* The following two DataRearrangement lines are examples of non-sequentially ordered training and
* evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
*
*
*
*
* @param dataRearrangement
* A JSON string that represents the splitting and rearrangement processing to be applied to a
* DataSource. If the DataRearrangement parameter is not provided, all of the
* input data is used to create the Datasource.
*
* There are multiple parameters that control what data is used to create a datasource:
*
*
* -
*
* percentBegin
*
*
* Use percentBegin to indicate the beginning of the range of the data used to create the
* Datasource. If you do not include percentBegin and percentEnd, Amazon ML
* includes all of the data when creating the datasource.
*
*
* -
*
* percentEnd
*
*
* Use percentEnd to indicate the end of the range of the data used to create the
* Datasource. If you do not include percentBegin and percentEnd, Amazon ML
* includes all of the data when creating the datasource.
*
*
* -
*
* complement
*
*
* The complement parameter instructs Amazon ML to use the data that is not included in the
* range of percentBegin to percentEnd to create a datasource. The
* complement parameter is useful if you need to create complementary datasources for
* training and evaluation. To create a complementary datasource, use the same values for
* percentBegin and percentEnd, along with the complement
* parameter.
*
*
* For example, the following two datasources do not share any data, and can be used to train and
* evaluate a model. The first datasource has 25 percent of the data, and the second one has 75 percent
* of the data.
*
*
* Datasource for evaluation: {"splitting":{"percentBegin":0, "percentEnd":25}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":0, "percentEnd":25, "complement":"true"}}
*
*
* -
*
* strategy
*
*
* To change how Amazon ML splits the data for a datasource, use the strategy parameter.
*
*
* The default value for the strategy parameter is sequential, meaning that
* Amazon ML takes all of the data records between the percentBegin and
* percentEnd parameters for the datasource, in the order that the records appear in the
* input data.
*
*
* The following two DataRearrangement lines are examples of sequentially ordered training
* and evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"sequential", "complement":"true"}}
*
*
* To randomly split the input data into the proportions indicated by the percentBegin and percentEnd
* parameters, set the strategy parameter to random and provide a string that
* is used as the seed value for the random data splitting (for example, you can use the S3 path to your
* data as the random seed string). If you choose the random split strategy, Amazon ML assigns each row
* of data a pseudo-random number between 0 and 100, and then selects the rows that have an assigned
* number between percentBegin and percentEnd. Pseudo-random numbers are
* assigned using both the input seed string value and the byte offset as a seed, so changing the data
* results in a different split. Any existing ordering is preserved. The random splitting strategy
* ensures that variables in the training and evaluation data are distributed similarly. It is useful in
* the cases where the input data may have an implicit sort order, which would otherwise result in
* training and evaluation datasources containing non-similar data records.
*
*
* The following two DataRearrangement lines are examples of non-sequentially ordered
* training and evaluation datasources:
*
*
* Datasource for evaluation:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv"}}
*
*
* Datasource for training:
* {"splitting":{"percentBegin":70, "percentEnd":100, "strategy":"random", "randomSeed"="s3://my_s3_path/bucket/file.csv", "complement":"true"}}
*
*
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder dataRearrangement(String dataRearrangement);
/**
*
* A JSON string that represents the schema for an Amazon Redshift DataSource. The
* DataSchema defines the structure of the observation data in the data file(s) referenced in the
* DataSource.
*
*
* A DataSchema is not required if you specify a DataSchemaUri.
*
*
* Define your DataSchema as a series of key-value pairs. attributes and
* excludedVariableNames have an array of key-value pairs for their value. Use the following format
* to define your DataSchema.
*
*
* { "version": "1.0",
*
*
* "recordAnnotationFieldName": "F1",
*
*
* "recordWeightFieldName": "F2",
*
*
* "targetFieldName": "F3",
*
*
* "dataFormat": "CSV",
*
*
* "dataFileContainsHeader": true,
*
*
* "attributes": [
*
*
* { "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, { "fieldName":
* "F3", "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, { "fieldName": "F5",
* "fieldType": "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, { "fieldName": "F7", "fieldType":
* "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType": "WEIGHTED_STRING_SEQUENCE" } ],
*
*
* "excludedVariableNames": [ "F6" ] }
*
*
* @param dataSchema
* A JSON string that represents the schema for an Amazon Redshift DataSource. The
* DataSchema defines the structure of the observation data in the data file(s) referenced
* in the DataSource.
*
* A DataSchema is not required if you specify a DataSchemaUri.
*
*
* Define your DataSchema as a series of key-value pairs. attributes and
* excludedVariableNames have an array of key-value pairs for their value. Use the following
* format to define your DataSchema.
*
*
* { "version": "1.0",
*
*
* "recordAnnotationFieldName": "F1",
*
*
* "recordWeightFieldName": "F2",
*
*
* "targetFieldName": "F3",
*
*
* "dataFormat": "CSV",
*
*
* "dataFileContainsHeader": true,
*
*
* "attributes": [
*
*
* { "fieldName": "F1", "fieldType": "TEXT" }, { "fieldName": "F2", "fieldType": "NUMERIC" }, {
* "fieldName": "F3", "fieldType": "CATEGORICAL" }, { "fieldName": "F4", "fieldType": "NUMERIC" }, {
* "fieldName": "F5", "fieldType": "CATEGORICAL" }, { "fieldName": "F6", "fieldType": "TEXT" }, {
* "fieldName": "F7", "fieldType": "WEIGHTED_INT_SEQUENCE" }, { "fieldName": "F8", "fieldType":
* "WEIGHTED_STRING_SEQUENCE" } ],
*
*
* "excludedVariableNames": [ "F6" ] }
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder dataSchema(String dataSchema);
/**
*
* Describes the schema location for an Amazon Redshift DataSource.
*
*
* @param dataSchemaUri
* Describes the schema location for an Amazon Redshift DataSource.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder dataSchemaUri(String dataSchemaUri);
}
static final class BuilderImpl implements Builder {
private RedshiftDatabase databaseInformation;
private String selectSqlQuery;
private RedshiftDatabaseCredentials databaseCredentials;
private String s3StagingLocation;
private String dataRearrangement;
private String dataSchema;
private String dataSchemaUri;
private BuilderImpl() {
}
private BuilderImpl(RedshiftDataSpec model) {
databaseInformation(model.databaseInformation);
selectSqlQuery(model.selectSqlQuery);
databaseCredentials(model.databaseCredentials);
s3StagingLocation(model.s3StagingLocation);
dataRearrangement(model.dataRearrangement);
dataSchema(model.dataSchema);
dataSchemaUri(model.dataSchemaUri);
}
public final RedshiftDatabase.Builder getDatabaseInformation() {
return databaseInformation != null ? databaseInformation.toBuilder() : null;
}
public final void setDatabaseInformation(RedshiftDatabase.BuilderImpl databaseInformation) {
this.databaseInformation = databaseInformation != null ? databaseInformation.build() : null;
}
@Override
public final Builder databaseInformation(RedshiftDatabase databaseInformation) {
this.databaseInformation = databaseInformation;
return this;
}
public final String getSelectSqlQuery() {
return selectSqlQuery;
}
public final void setSelectSqlQuery(String selectSqlQuery) {
this.selectSqlQuery = selectSqlQuery;
}
@Override
public final Builder selectSqlQuery(String selectSqlQuery) {
this.selectSqlQuery = selectSqlQuery;
return this;
}
public final RedshiftDatabaseCredentials.Builder getDatabaseCredentials() {
return databaseCredentials != null ? databaseCredentials.toBuilder() : null;
}
public final void setDatabaseCredentials(RedshiftDatabaseCredentials.BuilderImpl databaseCredentials) {
this.databaseCredentials = databaseCredentials != null ? databaseCredentials.build() : null;
}
@Override
public final Builder databaseCredentials(RedshiftDatabaseCredentials databaseCredentials) {
this.databaseCredentials = databaseCredentials;
return this;
}
public final String getS3StagingLocation() {
return s3StagingLocation;
}
public final void setS3StagingLocation(String s3StagingLocation) {
this.s3StagingLocation = s3StagingLocation;
}
@Override
public final Builder s3StagingLocation(String s3StagingLocation) {
this.s3StagingLocation = s3StagingLocation;
return this;
}
public final String getDataRearrangement() {
return dataRearrangement;
}
public final void setDataRearrangement(String dataRearrangement) {
this.dataRearrangement = dataRearrangement;
}
@Override
public final Builder dataRearrangement(String dataRearrangement) {
this.dataRearrangement = dataRearrangement;
return this;
}
public final String getDataSchema() {
return dataSchema;
}
public final void setDataSchema(String dataSchema) {
this.dataSchema = dataSchema;
}
@Override
public final Builder dataSchema(String dataSchema) {
this.dataSchema = dataSchema;
return this;
}
public final String getDataSchemaUri() {
return dataSchemaUri;
}
public final void setDataSchemaUri(String dataSchemaUri) {
this.dataSchemaUri = dataSchemaUri;
}
@Override
public final Builder dataSchemaUri(String dataSchemaUri) {
this.dataSchemaUri = dataSchemaUri;
return this;
}
@Override
public RedshiftDataSpec build() {
return new RedshiftDataSpec(this);
}
@Override
public List> sdkFields() {
return SDK_FIELDS;
}
}
}