software.amazon.awssdk.services.sagemaker.model.TransformInput Maven / Gradle / Ivy
/*
* 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;
/**
*
* Describes the input source of a transform job and the way the transform job consumes it.
*
*/
@Generated("software.amazon.awssdk:codegen")
public final class TransformInput implements SdkPojo, Serializable, ToCopyableBuilder {
private static final SdkField DATA_SOURCE_FIELD = SdkField
. builder(MarshallingType.SDK_POJO).memberName("DataSource")
.getter(getter(TransformInput::dataSource)).setter(setter(Builder::dataSource))
.constructor(TransformDataSource::builder)
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("DataSource").build()).build();
private static final SdkField CONTENT_TYPE_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("ContentType").getter(getter(TransformInput::contentType)).setter(setter(Builder::contentType))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("ContentType").build()).build();
private static final SdkField COMPRESSION_TYPE_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("CompressionType").getter(getter(TransformInput::compressionTypeAsString))
.setter(setter(Builder::compressionType))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("CompressionType").build()).build();
private static final SdkField SPLIT_TYPE_FIELD = SdkField. builder(MarshallingType.STRING)
.memberName("SplitType").getter(getter(TransformInput::splitTypeAsString)).setter(setter(Builder::splitType))
.traits(LocationTrait.builder().location(MarshallLocation.PAYLOAD).locationName("SplitType").build()).build();
private static final List> SDK_FIELDS = Collections.unmodifiableList(Arrays.asList(DATA_SOURCE_FIELD,
CONTENT_TYPE_FIELD, COMPRESSION_TYPE_FIELD, SPLIT_TYPE_FIELD));
private static final long serialVersionUID = 1L;
private final TransformDataSource dataSource;
private final String contentType;
private final String compressionType;
private final String splitType;
private TransformInput(BuilderImpl builder) {
this.dataSource = builder.dataSource;
this.contentType = builder.contentType;
this.compressionType = builder.compressionType;
this.splitType = builder.splitType;
}
/**
*
* Describes the location of the channel data, which is, the S3 location of the input data that the model can
* consume.
*
*
* @return Describes the location of the channel data, which is, the S3 location of the input data that the model
* can consume.
*/
public final TransformDataSource dataSource() {
return dataSource;
}
/**
*
* The multipurpose internet mail extension (MIME) type of the data. Amazon SageMaker uses the MIME type with each
* http call to transfer data to the transform job.
*
*
* @return The multipurpose internet mail extension (MIME) type of the data. Amazon SageMaker uses the MIME type
* with each http call to transfer data to the transform job.
*/
public final String contentType() {
return contentType;
}
/**
*
* If your transform data is compressed, specify the compression type. Amazon SageMaker automatically decompresses
* the data for the transform job accordingly. The default value is None.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #compressionType}
* will return {@link CompressionType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available
* from {@link #compressionTypeAsString}.
*
*
* @return If your transform data is compressed, specify the compression type. Amazon SageMaker automatically
* decompresses the data for the transform job accordingly. The default value is None.
* @see CompressionType
*/
public final CompressionType compressionType() {
return CompressionType.fromValue(compressionType);
}
/**
*
* If your transform data is compressed, specify the compression type. Amazon SageMaker automatically decompresses
* the data for the transform job accordingly. The default value is None.
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #compressionType}
* will return {@link CompressionType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available
* from {@link #compressionTypeAsString}.
*
*
* @return If your transform data is compressed, specify the compression type. Amazon SageMaker automatically
* decompresses the data for the transform job accordingly. The default value is None.
* @see CompressionType
*/
public final String compressionTypeAsString() {
return compressionType;
}
/**
*
* The method to use to split the transform job's data files into smaller batches. Splitting is necessary when the
* total size of each object is too large to fit in a single request. You can also use data splitting to improve
* performance by processing multiple concurrent mini-batches. The default value for SplitType is
* None, which indicates that input data files are not split, and request payloads contain the entire
* contents of an input object. Set the value of this parameter to Line to split records on a newline
* character boundary. SplitType also supports a number of record-oriented binary data formats.
* Currently, the supported record formats are:
*
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the BatchStrategy and
* MaxPayloadInMB parameters. When the value of BatchStrategy is MultiRecord,
* Amazon SageMaker sends the maximum number of records in each request, up to the MaxPayloadInMB
* limit. If the value of BatchStrategy is SingleRecord, Amazon SageMaker sends individual
* records in each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When splitting is
* applied to a binary data format, padding is removed if the value of BatchStrategy is set to
* SingleRecord. Padding is not removed if the value of BatchStrategy is set to
* MultiRecord.
*
*
* For more information about RecordIO, see Create
* a Dataset Using RecordIO in the MXNet documentation. For more information about TFRecord, see Consuming TFRecord data in the
* TensorFlow documentation.
*
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #splitType} will
* return {@link SplitType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available from
* {@link #splitTypeAsString}.
*
*
* @return The method to use to split the transform job's data files into smaller batches. Splitting is necessary
* when the total size of each object is too large to fit in a single request. You can also use data
* splitting to improve performance by processing multiple concurrent mini-batches. The default value for
* SplitType is None, which indicates that input data files are not split, and
* request payloads contain the entire contents of an input object. Set the value of this parameter to
* Line to split records on a newline character boundary. SplitType also supports
* a number of record-oriented binary data formats. Currently, the supported record formats are:
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the
* BatchStrategy and MaxPayloadInMB parameters. When the value of
* BatchStrategy is MultiRecord, Amazon SageMaker sends the maximum number of
* records in each request, up to the MaxPayloadInMB limit. If the value of
* BatchStrategy is SingleRecord, Amazon SageMaker sends individual records in
* each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When splitting
* is applied to a binary data format, padding is removed if the value of BatchStrategy is set
* to SingleRecord. Padding is not removed if the value of BatchStrategy is set to
* MultiRecord.
*
*
* For more information about RecordIO, see Create a Dataset Using RecordIO in the MXNet
* documentation. For more information about TFRecord, see Consuming TFRecord data in the
* TensorFlow documentation.
*
* @see SplitType
*/
public final SplitType splitType() {
return SplitType.fromValue(splitType);
}
/**
*
* The method to use to split the transform job's data files into smaller batches. Splitting is necessary when the
* total size of each object is too large to fit in a single request. You can also use data splitting to improve
* performance by processing multiple concurrent mini-batches. The default value for SplitType is
* None, which indicates that input data files are not split, and request payloads contain the entire
* contents of an input object. Set the value of this parameter to Line to split records on a newline
* character boundary. SplitType also supports a number of record-oriented binary data formats.
* Currently, the supported record formats are:
*
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the BatchStrategy and
* MaxPayloadInMB parameters. When the value of BatchStrategy is MultiRecord,
* Amazon SageMaker sends the maximum number of records in each request, up to the MaxPayloadInMB
* limit. If the value of BatchStrategy is SingleRecord, Amazon SageMaker sends individual
* records in each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When splitting is
* applied to a binary data format, padding is removed if the value of BatchStrategy is set to
* SingleRecord. Padding is not removed if the value of BatchStrategy is set to
* MultiRecord.
*
*
* For more information about RecordIO, see Create
* a Dataset Using RecordIO in the MXNet documentation. For more information about TFRecord, see Consuming TFRecord data in the
* TensorFlow documentation.
*
*
*
* If the service returns an enum value that is not available in the current SDK version, {@link #splitType} will
* return {@link SplitType#UNKNOWN_TO_SDK_VERSION}. The raw value returned by the service is available from
* {@link #splitTypeAsString}.
*
*
* @return The method to use to split the transform job's data files into smaller batches. Splitting is necessary
* when the total size of each object is too large to fit in a single request. You can also use data
* splitting to improve performance by processing multiple concurrent mini-batches. The default value for
* SplitType is None, which indicates that input data files are not split, and
* request payloads contain the entire contents of an input object. Set the value of this parameter to
* Line to split records on a newline character boundary. SplitType also supports
* a number of record-oriented binary data formats. Currently, the supported record formats are:
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the
* BatchStrategy and MaxPayloadInMB parameters. When the value of
* BatchStrategy is MultiRecord, Amazon SageMaker sends the maximum number of
* records in each request, up to the MaxPayloadInMB limit. If the value of
* BatchStrategy is SingleRecord, Amazon SageMaker sends individual records in
* each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When splitting
* is applied to a binary data format, padding is removed if the value of BatchStrategy is set
* to SingleRecord. Padding is not removed if the value of BatchStrategy is set to
* MultiRecord.
*
*
* For more information about RecordIO, see Create a Dataset Using RecordIO in the MXNet
* documentation. For more information about TFRecord, see Consuming TFRecord data in the
* TensorFlow documentation.
*
* @see SplitType
*/
public final String splitTypeAsString() {
return splitType;
}
@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(dataSource());
hashCode = 31 * hashCode + Objects.hashCode(contentType());
hashCode = 31 * hashCode + Objects.hashCode(compressionTypeAsString());
hashCode = 31 * hashCode + Objects.hashCode(splitTypeAsString());
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 TransformInput)) {
return false;
}
TransformInput other = (TransformInput) obj;
return Objects.equals(dataSource(), other.dataSource()) && Objects.equals(contentType(), other.contentType())
&& Objects.equals(compressionTypeAsString(), other.compressionTypeAsString())
&& Objects.equals(splitTypeAsString(), other.splitTypeAsString());
}
/**
* 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("TransformInput").add("DataSource", dataSource()).add("ContentType", contentType())
.add("CompressionType", compressionTypeAsString()).add("SplitType", splitTypeAsString()).build();
}
public final Optional getValueForField(String fieldName, Class clazz) {
switch (fieldName) {
case "DataSource":
return Optional.ofNullable(clazz.cast(dataSource()));
case "ContentType":
return Optional.ofNullable(clazz.cast(contentType()));
case "CompressionType":
return Optional.ofNullable(clazz.cast(compressionTypeAsString()));
case "SplitType":
return Optional.ofNullable(clazz.cast(splitTypeAsString()));
default:
return Optional.empty();
}
}
@Override
public final List> sdkFields() {
return SDK_FIELDS;
}
private static Function getter(Function g) {
return obj -> g.apply((TransformInput) obj);
}
private static BiConsumer setter(BiConsumer s) {
return (obj, val) -> s.accept((Builder) obj, val);
}
public interface Builder extends SdkPojo, CopyableBuilder {
/**
*
* Describes the location of the channel data, which is, the S3 location of the input data that the model can
* consume.
*
*
* @param dataSource
* Describes the location of the channel data, which is, the S3 location of the input data that the model
* can consume.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder dataSource(TransformDataSource dataSource);
/**
*
* Describes the location of the channel data, which is, the S3 location of the input data that the model can
* consume.
*
* This is a convenience method that creates an instance of the {@link TransformDataSource.Builder} avoiding the
* need to create one manually via {@link TransformDataSource#builder()}.
*
*
* When the {@link Consumer} completes, {@link TransformDataSource.Builder#build()} is called immediately and
* its result is passed to {@link #dataSource(TransformDataSource)}.
*
* @param dataSource
* a consumer that will call methods on {@link TransformDataSource.Builder}
* @return Returns a reference to this object so that method calls can be chained together.
* @see #dataSource(TransformDataSource)
*/
default Builder dataSource(Consumer dataSource) {
return dataSource(TransformDataSource.builder().applyMutation(dataSource).build());
}
/**
*
* The multipurpose internet mail extension (MIME) type of the data. Amazon SageMaker uses the MIME type with
* each http call to transfer data to the transform job.
*
*
* @param contentType
* The multipurpose internet mail extension (MIME) type of the data. Amazon SageMaker uses the MIME type
* with each http call to transfer data to the transform job.
* @return Returns a reference to this object so that method calls can be chained together.
*/
Builder contentType(String contentType);
/**
*
* If your transform data is compressed, specify the compression type. Amazon SageMaker automatically
* decompresses the data for the transform job accordingly. The default value is None.
*
*
* @param compressionType
* If your transform data is compressed, specify the compression type. Amazon SageMaker automatically
* decompresses the data for the transform job accordingly. The default value is None.
* @see CompressionType
* @return Returns a reference to this object so that method calls can be chained together.
* @see CompressionType
*/
Builder compressionType(String compressionType);
/**
*
* If your transform data is compressed, specify the compression type. Amazon SageMaker automatically
* decompresses the data for the transform job accordingly. The default value is None.
*
*
* @param compressionType
* If your transform data is compressed, specify the compression type. Amazon SageMaker automatically
* decompresses the data for the transform job accordingly. The default value is None.
* @see CompressionType
* @return Returns a reference to this object so that method calls can be chained together.
* @see CompressionType
*/
Builder compressionType(CompressionType compressionType);
/**
*
* The method to use to split the transform job's data files into smaller batches. Splitting is necessary when
* the total size of each object is too large to fit in a single request. You can also use data splitting to
* improve performance by processing multiple concurrent mini-batches. The default value for
* SplitType is None, which indicates that input data files are not split, and request
* payloads contain the entire contents of an input object. Set the value of this parameter to Line
* to split records on a newline character boundary. SplitType also supports a number of
* record-oriented binary data formats. Currently, the supported record formats are:
*
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the BatchStrategy
* and MaxPayloadInMB parameters. When the value of BatchStrategy is
* MultiRecord, Amazon SageMaker sends the maximum number of records in each request, up to the
* MaxPayloadInMB limit. If the value of BatchStrategy is SingleRecord,
* Amazon SageMaker sends individual records in each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When splitting is
* applied to a binary data format, padding is removed if the value of BatchStrategy is set to
* SingleRecord. Padding is not removed if the value of BatchStrategy is set to
* MultiRecord.
*
*
* For more information about RecordIO, see Create a Dataset Using RecordIO in the MXNet
* documentation. For more information about TFRecord, see Consuming TFRecord data in the
* TensorFlow documentation.
*
*
*
* @param splitType
* The method to use to split the transform job's data files into smaller batches. Splitting is necessary
* when the total size of each object is too large to fit in a single request. You can also use data
* splitting to improve performance by processing multiple concurrent mini-batches. The default value for
* SplitType is None, which indicates that input data files are not split, and
* request payloads contain the entire contents of an input object. Set the value of this parameter to
* Line to split records on a newline character boundary. SplitType also
* supports a number of record-oriented binary data formats. Currently, the supported record formats
* are:
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the
* BatchStrategy and MaxPayloadInMB parameters. When the value of
* BatchStrategy is MultiRecord, Amazon SageMaker sends the maximum number of
* records in each request, up to the MaxPayloadInMB limit. If the value of
* BatchStrategy is SingleRecord, Amazon SageMaker sends individual records in
* each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When
* splitting is applied to a binary data format, padding is removed if the value of
* BatchStrategy is set to SingleRecord. Padding is not removed if the value of
* BatchStrategy is set to MultiRecord.
*
*
* For more information about RecordIO, see Create a Dataset Using RecordIO in the MXNet
* documentation. For more information about TFRecord, see Consuming TFRecord data in
* the TensorFlow documentation.
*
* @see SplitType
* @return Returns a reference to this object so that method calls can be chained together.
* @see SplitType
*/
Builder splitType(String splitType);
/**
*
* The method to use to split the transform job's data files into smaller batches. Splitting is necessary when
* the total size of each object is too large to fit in a single request. You can also use data splitting to
* improve performance by processing multiple concurrent mini-batches. The default value for
* SplitType is None, which indicates that input data files are not split, and request
* payloads contain the entire contents of an input object. Set the value of this parameter to Line
* to split records on a newline character boundary. SplitType also supports a number of
* record-oriented binary data formats. Currently, the supported record formats are:
*
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the BatchStrategy
* and MaxPayloadInMB parameters. When the value of BatchStrategy is
* MultiRecord, Amazon SageMaker sends the maximum number of records in each request, up to the
* MaxPayloadInMB limit. If the value of BatchStrategy is SingleRecord,
* Amazon SageMaker sends individual records in each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When splitting is
* applied to a binary data format, padding is removed if the value of BatchStrategy is set to
* SingleRecord. Padding is not removed if the value of BatchStrategy is set to
* MultiRecord.
*
*
* For more information about RecordIO, see Create a Dataset Using RecordIO in the MXNet
* documentation. For more information about TFRecord, see Consuming TFRecord data in the
* TensorFlow documentation.
*
*
*
* @param splitType
* The method to use to split the transform job's data files into smaller batches. Splitting is necessary
* when the total size of each object is too large to fit in a single request. You can also use data
* splitting to improve performance by processing multiple concurrent mini-batches. The default value for
* SplitType is None, which indicates that input data files are not split, and
* request payloads contain the entire contents of an input object. Set the value of this parameter to
* Line to split records on a newline character boundary. SplitType also
* supports a number of record-oriented binary data formats. Currently, the supported record formats
* are:
*
* -
*
* RecordIO
*
*
* -
*
* TFRecord
*
*
*
*
* When splitting is enabled, the size of a mini-batch depends on the values of the
* BatchStrategy and MaxPayloadInMB parameters. When the value of
* BatchStrategy is MultiRecord, Amazon SageMaker sends the maximum number of
* records in each request, up to the MaxPayloadInMB limit. If the value of
* BatchStrategy is SingleRecord, Amazon SageMaker sends individual records in
* each request.
*
*
*
* Some data formats represent a record as a binary payload wrapped with extra padding bytes. When
* splitting is applied to a binary data format, padding is removed if the value of
* BatchStrategy is set to SingleRecord. Padding is not removed if the value of
* BatchStrategy is set to MultiRecord.
*
*
* For more information about RecordIO, see Create a Dataset Using RecordIO in the MXNet
* documentation. For more information about TFRecord, see Consuming TFRecord data in
* the TensorFlow documentation.
*
* @see SplitType
* @return Returns a reference to this object so that method calls can be chained together.
* @see SplitType
*/
Builder splitType(SplitType splitType);
}
static final class BuilderImpl implements Builder {
private TransformDataSource dataSource;
private String contentType;
private String compressionType;
private String splitType;
private BuilderImpl() {
}
private BuilderImpl(TransformInput model) {
dataSource(model.dataSource);
contentType(model.contentType);
compressionType(model.compressionType);
splitType(model.splitType);
}
public final TransformDataSource.Builder getDataSource() {
return dataSource != null ? dataSource.toBuilder() : null;
}
public final void setDataSource(TransformDataSource.BuilderImpl dataSource) {
this.dataSource = dataSource != null ? dataSource.build() : null;
}
@Override
public final Builder dataSource(TransformDataSource dataSource) {
this.dataSource = dataSource;
return this;
}
public final String getContentType() {
return contentType;
}
public final void setContentType(String contentType) {
this.contentType = contentType;
}
@Override
public final Builder contentType(String contentType) {
this.contentType = contentType;
return this;
}
public final String getCompressionType() {
return compressionType;
}
public final void setCompressionType(String compressionType) {
this.compressionType = compressionType;
}
@Override
public final Builder compressionType(String compressionType) {
this.compressionType = compressionType;
return this;
}
@Override
public final Builder compressionType(CompressionType compressionType) {
this.compressionType(compressionType == null ? null : compressionType.toString());
return this;
}
public final String getSplitType() {
return splitType;
}
public final void setSplitType(String splitType) {
this.splitType = splitType;
}
@Override
public final Builder splitType(String splitType) {
this.splitType = splitType;
return this;
}
@Override
public final Builder splitType(SplitType splitType) {
this.splitType(splitType == null ? null : splitType.toString());
return this;
}
@Override
public TransformInput build() {
return new TransformInput(this);
}
@Override
public List> sdkFields() {
return SDK_FIELDS;
}
}
}