Class InputDataConfig (3.43.0)

public final class InputDataConfig extends GeneratedMessageV3 implements InputDataConfigOrBuilder

Specifies Vertex AI owned input data to be used for training, and possibly evaluating, the Model.

Protobuf type google.cloud.aiplatform.v1.InputDataConfig

Static Fields

ANNOTATIONS_FILTER_FIELD_NUMBER

public static final int ANNOTATIONS_FILTER_FIELD_NUMBER
Field Value
Type Description
int

ANNOTATION_SCHEMA_URI_FIELD_NUMBER

public static final int ANNOTATION_SCHEMA_URI_FIELD_NUMBER
Field Value
Type Description
int

BIGQUERY_DESTINATION_FIELD_NUMBER

public static final int BIGQUERY_DESTINATION_FIELD_NUMBER
Field Value
Type Description
int

DATASET_ID_FIELD_NUMBER

public static final int DATASET_ID_FIELD_NUMBER
Field Value
Type Description
int

FILTER_SPLIT_FIELD_NUMBER

public static final int FILTER_SPLIT_FIELD_NUMBER
Field Value
Type Description
int

FRACTION_SPLIT_FIELD_NUMBER

public static final int FRACTION_SPLIT_FIELD_NUMBER
Field Value
Type Description
int

GCS_DESTINATION_FIELD_NUMBER

public static final int GCS_DESTINATION_FIELD_NUMBER
Field Value
Type Description
int

PERSIST_ML_USE_ASSIGNMENT_FIELD_NUMBER

public static final int PERSIST_ML_USE_ASSIGNMENT_FIELD_NUMBER
Field Value
Type Description
int

PREDEFINED_SPLIT_FIELD_NUMBER

public static final int PREDEFINED_SPLIT_FIELD_NUMBER
Field Value
Type Description
int

SAVED_QUERY_ID_FIELD_NUMBER

public static final int SAVED_QUERY_ID_FIELD_NUMBER
Field Value
Type Description
int

STRATIFIED_SPLIT_FIELD_NUMBER

public static final int STRATIFIED_SPLIT_FIELD_NUMBER
Field Value
Type Description
int

TIMESTAMP_SPLIT_FIELD_NUMBER

public static final int TIMESTAMP_SPLIT_FIELD_NUMBER
Field Value
Type Description
int

Static Methods

getDefaultInstance()

public static InputDataConfig getDefaultInstance()
Returns
Type Description
InputDataConfig

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

newBuilder()

public static InputDataConfig.Builder newBuilder()
Returns
Type Description
InputDataConfig.Builder

newBuilder(InputDataConfig prototype)

public static InputDataConfig.Builder newBuilder(InputDataConfig prototype)
Parameter
Name Description
prototype InputDataConfig
Returns
Type Description
InputDataConfig.Builder

parseDelimitedFrom(InputStream input)

public static InputDataConfig parseDelimitedFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
InputDataConfig
Exceptions
Type Description
IOException

parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static InputDataConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
InputDataConfig
Exceptions
Type Description
IOException

parseFrom(byte[] data)

public static InputDataConfig parseFrom(byte[] data)
Parameter
Name Description
data byte[]
Returns
Type Description
InputDataConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)

public static InputDataConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data byte[]
extensionRegistry ExtensionRegistryLite
Returns
Type Description
InputDataConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data)

public static InputDataConfig parseFrom(ByteString data)
Parameter
Name Description
data ByteString
Returns
Type Description
InputDataConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)

public static InputDataConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteString
extensionRegistry ExtensionRegistryLite
Returns
Type Description
InputDataConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(CodedInputStream input)

public static InputDataConfig parseFrom(CodedInputStream input)
Parameter
Name Description
input CodedInputStream
Returns
Type Description
InputDataConfig
Exceptions
Type Description
IOException

parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public static InputDataConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
InputDataConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input)

public static InputDataConfig parseFrom(InputStream input)
Parameter
Name Description
input InputStream
Returns
Type Description
InputDataConfig
Exceptions
Type Description
IOException

parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)

public static InputDataConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input InputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
InputDataConfig
Exceptions
Type Description
IOException

parseFrom(ByteBuffer data)

public static InputDataConfig parseFrom(ByteBuffer data)
Parameter
Name Description
data ByteBuffer
Returns
Type Description
InputDataConfig
Exceptions
Type Description
InvalidProtocolBufferException

parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)

public static InputDataConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
data ByteBuffer
extensionRegistry ExtensionRegistryLite
Returns
Type Description
InputDataConfig
Exceptions
Type Description
InvalidProtocolBufferException

parser()

public static Parser<InputDataConfig> parser()
Returns
Type Description
Parser<InputDataConfig>

Methods

equals(Object obj)

public boolean equals(Object obj)
Parameter
Name Description
obj Object
Returns
Type Description
boolean
Overrides

getAnnotationSchemaUri()

public String getAnnotationSchemaUri()

Applicable only to custom training with Datasets that have DataItems and Annotations.

Cloud Storage URI that points to a YAML file describing the annotation schema. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/annotation/ , note that the chosen schema must be consistent with metadata of the Dataset specified by dataset_id.

Only Annotations that both match this schema and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on.

When used in conjunction with annotations_filter, the Annotations used for training are filtered by both annotations_filter and annotation_schema_uri.

string annotation_schema_uri = 9;

Returns
Type Description
String

The annotationSchemaUri.

getAnnotationSchemaUriBytes()

public ByteString getAnnotationSchemaUriBytes()

Applicable only to custom training with Datasets that have DataItems and Annotations.

Cloud Storage URI that points to a YAML file describing the annotation schema. The schema is defined as an OpenAPI 3.0.2 Schema Object. The schema files that can be used here are found in gs://google-cloud-aiplatform/schema/dataset/annotation/ , note that the chosen schema must be consistent with metadata of the Dataset specified by dataset_id.

Only Annotations that both match this schema and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on.

When used in conjunction with annotations_filter, the Annotations used for training are filtered by both annotations_filter and annotation_schema_uri.

string annotation_schema_uri = 9;

Returns
Type Description
ByteString

The bytes for annotationSchemaUri.

getAnnotationsFilter()

public String getAnnotationsFilter()

Applicable only to Datasets that have DataItems and Annotations.

A filter on Annotations of the Dataset. Only Annotations that both match this filter and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on (for the auto-assigned that role is decided by Vertex AI). A filter with same syntax as the one used in ListAnnotations may be used, but note here it filters across all Annotations of the Dataset, and not just within a single DataItem.

string annotations_filter = 6;

Returns
Type Description
String

The annotationsFilter.

getAnnotationsFilterBytes()

public ByteString getAnnotationsFilterBytes()

Applicable only to Datasets that have DataItems and Annotations.

A filter on Annotations of the Dataset. Only Annotations that both match this filter and belong to DataItems not ignored by the split method are used in respectively training, validation or test role, depending on the role of the DataItem they are on (for the auto-assigned that role is decided by Vertex AI). A filter with same syntax as the one used in ListAnnotations may be used, but note here it filters across all Annotations of the Dataset, and not just within a single DataItem.

string annotations_filter = 6;

Returns
Type Description
ByteString

The bytes for annotationsFilter.

getBigqueryDestination()

public BigQueryDestination getBigqueryDestination()

Only applicable to custom training with tabular Dataset with BigQuery source.

The BigQuery project location where the training data is to be written to. In the given project a new dataset is created with name dataset_<dataset-id><annotation-type><timestamp-of-training-call> where timestamp is in YYYY_MM_DDThh_mm_ss_sssZ format. All training input data is written into that dataset. In the dataset three tables are created, training, validation and test.

  • AIP_DATA_FORMAT = "bigquery".
  • AIP_TRAINING_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.training"

  • AIP_VALIDATION_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.validation"

  • AIP_TEST_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.test"

.google.cloud.aiplatform.v1.BigQueryDestination bigquery_destination = 10;

Returns
Type Description
BigQueryDestination

The bigqueryDestination.

getBigqueryDestinationOrBuilder()

public BigQueryDestinationOrBuilder getBigqueryDestinationOrBuilder()

Only applicable to custom training with tabular Dataset with BigQuery source.

The BigQuery project location where the training data is to be written to. In the given project a new dataset is created with name dataset_<dataset-id><annotation-type><timestamp-of-training-call> where timestamp is in YYYY_MM_DDThh_mm_ss_sssZ format. All training input data is written into that dataset. In the dataset three tables are created, training, validation and test.

  • AIP_DATA_FORMAT = "bigquery".
  • AIP_TRAINING_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.training"

  • AIP_VALIDATION_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.validation"

  • AIP_TEST_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.test"

.google.cloud.aiplatform.v1.BigQueryDestination bigquery_destination = 10;

Returns
Type Description
BigQueryDestinationOrBuilder

getDatasetId()

public String getDatasetId()

Required. The ID of the Dataset in the same Project and Location which data will be used to train the Model. The Dataset must use schema compatible with Model being trained, and what is compatible should be described in the used TrainingPipeline's [training_task_definition] [google.cloud.aiplatform.v1.TrainingPipeline.training_task_definition]. For tabular Datasets, all their data is exported to training, to pick and choose from.

string dataset_id = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
String

The datasetId.

getDatasetIdBytes()

public ByteString getDatasetIdBytes()

Required. The ID of the Dataset in the same Project and Location which data will be used to train the Model. The Dataset must use schema compatible with Model being trained, and what is compatible should be described in the used TrainingPipeline's [training_task_definition] [google.cloud.aiplatform.v1.TrainingPipeline.training_task_definition]. For tabular Datasets, all their data is exported to training, to pick and choose from.

string dataset_id = 1 [(.google.api.field_behavior) = REQUIRED];

Returns
Type Description
ByteString

The bytes for datasetId.

getDefaultInstanceForType()

public InputDataConfig getDefaultInstanceForType()
Returns
Type Description
InputDataConfig

getDestinationCase()

public InputDataConfig.DestinationCase getDestinationCase()
Returns
Type Description
InputDataConfig.DestinationCase

getFilterSplit()

public FilterSplit getFilterSplit()

Split based on the provided filters for each set.

.google.cloud.aiplatform.v1.FilterSplit filter_split = 3;

Returns
Type Description
FilterSplit

The filterSplit.

getFilterSplitOrBuilder()

public FilterSplitOrBuilder getFilterSplitOrBuilder()

Split based on the provided filters for each set.

.google.cloud.aiplatform.v1.FilterSplit filter_split = 3;

Returns
Type Description
FilterSplitOrBuilder

getFractionSplit()

public FractionSplit getFractionSplit()

Split based on fractions defining the size of each set.

.google.cloud.aiplatform.v1.FractionSplit fraction_split = 2;

Returns
Type Description
FractionSplit

The fractionSplit.

getFractionSplitOrBuilder()

public FractionSplitOrBuilder getFractionSplitOrBuilder()

Split based on fractions defining the size of each set.

.google.cloud.aiplatform.v1.FractionSplit fraction_split = 2;

Returns
Type Description
FractionSplitOrBuilder

getGcsDestination()

public GcsDestination getGcsDestination()

The Cloud Storage location where the training data is to be written to. In the given directory a new directory is created with name: dataset-<dataset-id>-<annotation-type>-<timestamp-of-training-call> where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. All training input data is written into that directory.

The Vertex AI environment variables representing Cloud Storage data URIs are represented in the Cloud Storage wildcard format to support sharded data. e.g.: "gs://.../training-*.jsonl"

  • AIP_DATA_FORMAT = "jsonl" for non-tabular data, "csv" for tabular data
  • AIP_TRAINING_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/training-*.${AIP_DATA_FORMAT}"

  • AIP_VALIDATION_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/validation-*.${AIP_DATA_FORMAT}"

  • AIP_TEST_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/test-*.${AIP_DATA_FORMAT}"

.google.cloud.aiplatform.v1.GcsDestination gcs_destination = 8;

Returns
Type Description
GcsDestination

The gcsDestination.

getGcsDestinationOrBuilder()

public GcsDestinationOrBuilder getGcsDestinationOrBuilder()

The Cloud Storage location where the training data is to be written to. In the given directory a new directory is created with name: dataset-<dataset-id>-<annotation-type>-<timestamp-of-training-call> where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. All training input data is written into that directory.

The Vertex AI environment variables representing Cloud Storage data URIs are represented in the Cloud Storage wildcard format to support sharded data. e.g.: "gs://.../training-*.jsonl"

  • AIP_DATA_FORMAT = "jsonl" for non-tabular data, "csv" for tabular data
  • AIP_TRAINING_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/training-*.${AIP_DATA_FORMAT}"

  • AIP_VALIDATION_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/validation-*.${AIP_DATA_FORMAT}"

  • AIP_TEST_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/test-*.${AIP_DATA_FORMAT}"

.google.cloud.aiplatform.v1.GcsDestination gcs_destination = 8;

Returns
Type Description
GcsDestinationOrBuilder

getParserForType()

public Parser<InputDataConfig> getParserForType()
Returns
Type Description
Parser<InputDataConfig>
Overrides

getPersistMlUseAssignment()

public boolean getPersistMlUseAssignment()

Whether to persist the ML use assignment to data item system labels.

bool persist_ml_use_assignment = 11;

Returns
Type Description
boolean

The persistMlUseAssignment.

getPredefinedSplit()

public PredefinedSplit getPredefinedSplit()

Supported only for tabular Datasets.

Split based on a predefined key.

.google.cloud.aiplatform.v1.PredefinedSplit predefined_split = 4;

Returns
Type Description
PredefinedSplit

The predefinedSplit.

getPredefinedSplitOrBuilder()

public PredefinedSplitOrBuilder getPredefinedSplitOrBuilder()

Supported only for tabular Datasets.

Split based on a predefined key.

.google.cloud.aiplatform.v1.PredefinedSplit predefined_split = 4;

Returns
Type Description
PredefinedSplitOrBuilder

getSavedQueryId()

public String getSavedQueryId()

Only applicable to Datasets that have SavedQueries.

The ID of a SavedQuery (annotation set) under the Dataset specified by dataset_id used for filtering Annotations for training.

Only Annotations that are associated with this SavedQuery are used in respectively training. When used in conjunction with annotations_filter, the Annotations used for training are filtered by both saved_query_id and annotations_filter.

Only one of saved_query_id and annotation_schema_uri should be specified as both of them represent the same thing: problem type.

string saved_query_id = 7;

Returns
Type Description
String

The savedQueryId.

getSavedQueryIdBytes()

public ByteString getSavedQueryIdBytes()

Only applicable to Datasets that have SavedQueries.

The ID of a SavedQuery (annotation set) under the Dataset specified by dataset_id used for filtering Annotations for training.

Only Annotations that are associated with this SavedQuery are used in respectively training. When used in conjunction with annotations_filter, the Annotations used for training are filtered by both saved_query_id and annotations_filter.

Only one of saved_query_id and annotation_schema_uri should be specified as both of them represent the same thing: problem type.

string saved_query_id = 7;

Returns
Type Description
ByteString

The bytes for savedQueryId.

getSerializedSize()

public int getSerializedSize()
Returns
Type Description
int
Overrides

getSplitCase()

public InputDataConfig.SplitCase getSplitCase()
Returns
Type Description
InputDataConfig.SplitCase

getStratifiedSplit()

public StratifiedSplit getStratifiedSplit()

Supported only for tabular Datasets.

Split based on the distribution of the specified column.

.google.cloud.aiplatform.v1.StratifiedSplit stratified_split = 12;

Returns
Type Description
StratifiedSplit

The stratifiedSplit.

getStratifiedSplitOrBuilder()

public StratifiedSplitOrBuilder getStratifiedSplitOrBuilder()

Supported only for tabular Datasets.

Split based on the distribution of the specified column.

.google.cloud.aiplatform.v1.StratifiedSplit stratified_split = 12;

Returns
Type Description
StratifiedSplitOrBuilder

getTimestampSplit()

public TimestampSplit getTimestampSplit()

Supported only for tabular Datasets.

Split based on the timestamp of the input data pieces.

.google.cloud.aiplatform.v1.TimestampSplit timestamp_split = 5;

Returns
Type Description
TimestampSplit

The timestampSplit.

getTimestampSplitOrBuilder()

public TimestampSplitOrBuilder getTimestampSplitOrBuilder()

Supported only for tabular Datasets.

Split based on the timestamp of the input data pieces.

.google.cloud.aiplatform.v1.TimestampSplit timestamp_split = 5;

Returns
Type Description
TimestampSplitOrBuilder

hasBigqueryDestination()

public boolean hasBigqueryDestination()

Only applicable to custom training with tabular Dataset with BigQuery source.

The BigQuery project location where the training data is to be written to. In the given project a new dataset is created with name dataset_<dataset-id><annotation-type><timestamp-of-training-call> where timestamp is in YYYY_MM_DDThh_mm_ss_sssZ format. All training input data is written into that dataset. In the dataset three tables are created, training, validation and test.

  • AIP_DATA_FORMAT = "bigquery".
  • AIP_TRAINING_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.training"

  • AIP_VALIDATION_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.validation"

  • AIP_TEST_DATA_URI = "bigquery_destination.dataset_<dataset-id><annotation-type><time>.test"

.google.cloud.aiplatform.v1.BigQueryDestination bigquery_destination = 10;

Returns
Type Description
boolean

Whether the bigqueryDestination field is set.

hasFilterSplit()

public boolean hasFilterSplit()

Split based on the provided filters for each set.

.google.cloud.aiplatform.v1.FilterSplit filter_split = 3;

Returns
Type Description
boolean

Whether the filterSplit field is set.

hasFractionSplit()

public boolean hasFractionSplit()

Split based on fractions defining the size of each set.

.google.cloud.aiplatform.v1.FractionSplit fraction_split = 2;

Returns
Type Description
boolean

Whether the fractionSplit field is set.

hasGcsDestination()

public boolean hasGcsDestination()

The Cloud Storage location where the training data is to be written to. In the given directory a new directory is created with name: dataset-<dataset-id>-<annotation-type>-<timestamp-of-training-call> where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format. All training input data is written into that directory.

The Vertex AI environment variables representing Cloud Storage data URIs are represented in the Cloud Storage wildcard format to support sharded data. e.g.: "gs://.../training-*.jsonl"

  • AIP_DATA_FORMAT = "jsonl" for non-tabular data, "csv" for tabular data
  • AIP_TRAINING_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/training-*.${AIP_DATA_FORMAT}"

  • AIP_VALIDATION_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/validation-*.${AIP_DATA_FORMAT}"

  • AIP_TEST_DATA_URI = "gcs_destination/dataset-<dataset-id>-<annotation-type>-<time>/test-*.${AIP_DATA_FORMAT}"

.google.cloud.aiplatform.v1.GcsDestination gcs_destination = 8;

Returns
Type Description
boolean

Whether the gcsDestination field is set.

hasPredefinedSplit()

public boolean hasPredefinedSplit()

Supported only for tabular Datasets.

Split based on a predefined key.

.google.cloud.aiplatform.v1.PredefinedSplit predefined_split = 4;

Returns
Type Description
boolean

Whether the predefinedSplit field is set.

hasStratifiedSplit()

public boolean hasStratifiedSplit()

Supported only for tabular Datasets.

Split based on the distribution of the specified column.

.google.cloud.aiplatform.v1.StratifiedSplit stratified_split = 12;

Returns
Type Description
boolean

Whether the stratifiedSplit field is set.

hasTimestampSplit()

public boolean hasTimestampSplit()

Supported only for tabular Datasets.

Split based on the timestamp of the input data pieces.

.google.cloud.aiplatform.v1.TimestampSplit timestamp_split = 5;

Returns
Type Description
boolean

Whether the timestampSplit field is set.

hashCode()

public int hashCode()
Returns
Type Description
int
Overrides

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

newBuilderForType()

public InputDataConfig.Builder newBuilderForType()
Returns
Type Description
InputDataConfig.Builder

newBuilderForType(GeneratedMessageV3.BuilderParent parent)

protected InputDataConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Name Description
parent BuilderParent
Returns
Type Description
InputDataConfig.Builder
Overrides

newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)

protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Name Description
unused UnusedPrivateParameter
Returns
Type Description
Object
Overrides

toBuilder()

public InputDataConfig.Builder toBuilder()
Returns
Type Description
InputDataConfig.Builder

writeTo(CodedOutputStream output)

public void writeTo(CodedOutputStream output)
Parameter
Name Description
output CodedOutputStream
Overrides
Exceptions
Type Description
IOException