datasets

Creates, updates, deletes, gets or lists a datasets resource.

Overview

Name	datasets
Type	Resource
Id	google.datalabeling.datasets

Fields

Name	Datatype	Description
name	string	Output only. Dataset resource name, format is: projects/{project_id}/datasets/{dataset_id}
description	string	Optional. User-provided description of the annotation specification set. The description can be up to 10000 characters long.
blockingResources	array	Output only. The names of any related resources that are blocking changes to the dataset.
createTime	string	Output only. Time the dataset is created.
dataItemCount	string	Output only. The number of data items in the dataset.
displayName	string	Required. The display name of the dataset. Maximum of 64 characters.
inputConfigs	array	Output only. This is populated with the original input configs where ImportData is called. It is available only after the clients import data to this dataset.
lastMigrateTime	string	Last time that the Dataset is migrated to AI Platform V2. If any of the AnnotatedDataset is migrated, the last_migration_time in Dataset is also updated.

Methods

Name	Accessible by	Required Params	Description
projects_datasets_get	SELECT	datasetsId, projectsId	Gets dataset by resource name.
projects_datasets_list	SELECT	projectsId	Lists datasets under a project. Pagination is supported.
projects_datasets_create	INSERT	projectsId	Creates dataset. If success return a Dataset resource.
projects_datasets_delete	DELETE	datasetsId, projectsId	Deletes a dataset by resource name.
projects_datasets_export_data	EXEC	datasetsId, projectsId	Exports data and annotations from dataset.
projects_datasets_import_data	EXEC	datasetsId, projectsId	Imports data into dataset based on source locations defined in request. It can be called multiple times for the same dataset. Each dataset can only have one long running operation running on it. For example, no labeling task (also long running operation) can be started while importing is still ongoing. Vice versa.

SELECT examples

Lists datasets under a project. Pagination is supported.

SELECT
name,
description,
blockingResources,
createTime,
dataItemCount,
displayName,
inputConfigs,
lastMigrateTime
FROM google.datalabeling.datasets
WHERE projectsId = '{{ projectsId }}';

INSERT example

Use the following StackQL query and manifest file to create a new datasets resource.

All Properties

/*+ create */
INSERT INTO google.datalabeling.datasets (
projectsId,
dataset
)
SELECT 
'{{ projectsId }}',
'{{ dataset }}'
;

Manifest

- name: your_resource_model_name
  props:
    - name: dataset
      value:
        - name: name
          value: string
        - name: displayName
          value: string
        - name: description
          value: string
        - name: createTime
          value: string
        - name: inputConfigs
          value:
            - - name: textMetadata
                value:
                  - name: languageCode
                    value: string
              - name: gcsSource
                value:
                  - name: inputUri
                    value: string
                  - name: mimeType
                    value: string
              - name: bigquerySource
                value:
                  - name: inputUri
                    value: string
              - name: dataType
                value: string
              - name: annotationType
                value: string
              - name: classificationMetadata
                value:
                  - name: isMultiLabel
                    value: boolean
        - name: blockingResources
          value:
            - string
        - name: dataItemCount
          value: string
        - name: lastMigrateTime
          value: string

DELETE example

Deletes the specified datasets resource.

/*+ delete */
DELETE FROM google.datalabeling.datasets
WHERE datasetsId = '{{ datasetsId }}'
AND projectsId = '{{ projectsId }}';