com.amazonaws.services.machinelearning.model.RedshiftDataSpec Maven / Gradle / Ivy
Show all versions of aws-java-sdk-machinelearning Show documentation
/*
* Copyright 2019-2024 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 com.amazonaws.services.machinelearning.model;
import java.io.Serializable;
import javax.annotation.Generated;
import com.amazonaws.protocol.StructuredPojo;
import com.amazonaws.protocol.ProtocolMarshaller;
/**
*
* Describes the data specification of an Amazon Redshift DataSource.
*
*/
@Generated("com.amazonaws:aws-java-sdk-code-generator")
public class RedshiftDataSpec implements Serializable, Cloneable, StructuredPojo {
/**
*
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*
*/
private RedshiftDatabase databaseInformation;
/**
*
* Describes the SQL Query to execute on an Amazon Redshift database for an Amazon Redshift DataSource.
*
*/
private String selectSqlQuery;
/**
*
* Describes AWS Identity and Access Management (IAM) credentials that are used connect to the Amazon Redshift
* database.
*
*/
private RedshiftDatabaseCredentials databaseCredentials;
/**
*
* Describes an Amazon S3 location to store the result set of the SelectSqlQuery query.
*
*/
private 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"}}
*
*
*
*/
private 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" ] }
*
*/
private String dataSchema;
/**
*
* Describes the schema location for an Amazon Redshift DataSource.
*
*/
private String dataSchemaUri;
/**
*
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*
*
* @param databaseInformation
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*/
public void setDatabaseInformation(RedshiftDatabase databaseInformation) {
this.databaseInformation = databaseInformation;
}
/**
*
* Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*
*
* @return Describes the DatabaseName and ClusterIdentifier for an Amazon Redshift
* DataSource.
*/
public RedshiftDatabase getDatabaseInformation() {
return this.databaseInformation;
}
/**
*
* 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.
*/
public RedshiftDataSpec withDatabaseInformation(RedshiftDatabase databaseInformation) {
setDatabaseInformation(databaseInformation);
return this;
}
/**
*
* 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.
*/
public void setSelectSqlQuery(String selectSqlQuery) {
this.selectSqlQuery = selectSqlQuery;
}
/**
*
* 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 String getSelectSqlQuery() {
return this.selectSqlQuery;
}
/**
*
* 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.
*/
public RedshiftDataSpec withSelectSqlQuery(String selectSqlQuery) {
setSelectSqlQuery(selectSqlQuery);
return this;
}
/**
*
* 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.
*/
public void setDatabaseCredentials(RedshiftDatabaseCredentials databaseCredentials) {
this.databaseCredentials = databaseCredentials;
}
/**
*
* 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 RedshiftDatabaseCredentials getDatabaseCredentials() {
return this.databaseCredentials;
}
/**
*
* 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.
*/
public RedshiftDataSpec withDatabaseCredentials(RedshiftDatabaseCredentials databaseCredentials) {
setDatabaseCredentials(databaseCredentials);
return this;
}
/**
*
* 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.
*/
public void setS3StagingLocation(String s3StagingLocation) {
this.s3StagingLocation = s3StagingLocation;
}
/**
*
* 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 String getS3StagingLocation() {
return this.s3StagingLocation;
}
/**
*
* 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.
*/
public RedshiftDataSpec withS3StagingLocation(String s3StagingLocation) {
setS3StagingLocation(s3StagingLocation);
return this;
}
/**
*
* 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"}}
*
*
*/
public void setDataRearrangement(String dataRearrangement) {
this.dataRearrangement = 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 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 String getDataRearrangement() {
return this.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"}}
*
*
*
*
* @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.
*/
public RedshiftDataSpec withDataRearrangement(String dataRearrangement) {
setDataRearrangement(dataRearrangement);
return this;
}
/**
*
* 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" ] }
*/
public void setDataSchema(String dataSchema) {
this.dataSchema = 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 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 String getDataSchema() {
return this.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" ] }
*
*
* @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.
*/
public RedshiftDataSpec withDataSchema(String dataSchema) {
setDataSchema(dataSchema);
return this;
}
/**
*
* Describes the schema location for an Amazon Redshift DataSource.
*
*
* @param dataSchemaUri
* Describes the schema location for an Amazon Redshift DataSource.
*/
public void setDataSchemaUri(String dataSchemaUri) {
this.dataSchemaUri = dataSchemaUri;
}
/**
*
* Describes the schema location for an Amazon Redshift DataSource.
*
*
* @return Describes the schema location for an Amazon Redshift DataSource.
*/
public String getDataSchemaUri() {
return this.dataSchemaUri;
}
/**
*
* 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.
*/
public RedshiftDataSpec withDataSchemaUri(String dataSchemaUri) {
setDataSchemaUri(dataSchemaUri);
return this;
}
/**
* 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.
*
* @return A string representation of this object.
*
* @see java.lang.Object#toString()
*/
@Override
public String toString() {
StringBuilder sb = new StringBuilder();
sb.append("{");
if (getDatabaseInformation() != null)
sb.append("DatabaseInformation: ").append(getDatabaseInformation()).append(",");
if (getSelectSqlQuery() != null)
sb.append("SelectSqlQuery: ").append(getSelectSqlQuery()).append(",");
if (getDatabaseCredentials() != null)
sb.append("DatabaseCredentials: ").append(getDatabaseCredentials()).append(",");
if (getS3StagingLocation() != null)
sb.append("S3StagingLocation: ").append(getS3StagingLocation()).append(",");
if (getDataRearrangement() != null)
sb.append("DataRearrangement: ").append(getDataRearrangement()).append(",");
if (getDataSchema() != null)
sb.append("DataSchema: ").append(getDataSchema()).append(",");
if (getDataSchemaUri() != null)
sb.append("DataSchemaUri: ").append(getDataSchemaUri());
sb.append("}");
return sb.toString();
}
@Override
public boolean equals(Object obj) {
if (this == obj)
return true;
if (obj == null)
return false;
if (obj instanceof RedshiftDataSpec == false)
return false;
RedshiftDataSpec other = (RedshiftDataSpec) obj;
if (other.getDatabaseInformation() == null ^ this.getDatabaseInformation() == null)
return false;
if (other.getDatabaseInformation() != null && other.getDatabaseInformation().equals(this.getDatabaseInformation()) == false)
return false;
if (other.getSelectSqlQuery() == null ^ this.getSelectSqlQuery() == null)
return false;
if (other.getSelectSqlQuery() != null && other.getSelectSqlQuery().equals(this.getSelectSqlQuery()) == false)
return false;
if (other.getDatabaseCredentials() == null ^ this.getDatabaseCredentials() == null)
return false;
if (other.getDatabaseCredentials() != null && other.getDatabaseCredentials().equals(this.getDatabaseCredentials()) == false)
return false;
if (other.getS3StagingLocation() == null ^ this.getS3StagingLocation() == null)
return false;
if (other.getS3StagingLocation() != null && other.getS3StagingLocation().equals(this.getS3StagingLocation()) == false)
return false;
if (other.getDataRearrangement() == null ^ this.getDataRearrangement() == null)
return false;
if (other.getDataRearrangement() != null && other.getDataRearrangement().equals(this.getDataRearrangement()) == false)
return false;
if (other.getDataSchema() == null ^ this.getDataSchema() == null)
return false;
if (other.getDataSchema() != null && other.getDataSchema().equals(this.getDataSchema()) == false)
return false;
if (other.getDataSchemaUri() == null ^ this.getDataSchemaUri() == null)
return false;
if (other.getDataSchemaUri() != null && other.getDataSchemaUri().equals(this.getDataSchemaUri()) == false)
return false;
return true;
}
@Override
public int hashCode() {
final int prime = 31;
int hashCode = 1;
hashCode = prime * hashCode + ((getDatabaseInformation() == null) ? 0 : getDatabaseInformation().hashCode());
hashCode = prime * hashCode + ((getSelectSqlQuery() == null) ? 0 : getSelectSqlQuery().hashCode());
hashCode = prime * hashCode + ((getDatabaseCredentials() == null) ? 0 : getDatabaseCredentials().hashCode());
hashCode = prime * hashCode + ((getS3StagingLocation() == null) ? 0 : getS3StagingLocation().hashCode());
hashCode = prime * hashCode + ((getDataRearrangement() == null) ? 0 : getDataRearrangement().hashCode());
hashCode = prime * hashCode + ((getDataSchema() == null) ? 0 : getDataSchema().hashCode());
hashCode = prime * hashCode + ((getDataSchemaUri() == null) ? 0 : getDataSchemaUri().hashCode());
return hashCode;
}
@Override
public RedshiftDataSpec clone() {
try {
return (RedshiftDataSpec) super.clone();
} catch (CloneNotSupportedException e) {
throw new IllegalStateException("Got a CloneNotSupportedException from Object.clone() " + "even though we're Cloneable!", e);
}
}
@com.amazonaws.annotation.SdkInternalApi
@Override
public void marshall(ProtocolMarshaller protocolMarshaller) {
com.amazonaws.services.machinelearning.model.transform.RedshiftDataSpecMarshaller.getInstance().marshall(this, protocolMarshaller);
}
}