evaluation_jobs
Creates, updates, deletes, gets or lists a evaluation_jobs
resource.
Overview
Name | evaluation_jobs |
Type | Resource |
Id | google.datalabeling.evaluation_jobs |
Fields
Name | Datatype | Description |
---|---|---|
name | string | Output only. After you create a job, Data Labeling Service assigns a name to the job with the following format: "projects/{project_id}/evaluationJobs/ {evaluation_job_id}" |
description | string | Required. Description of the job. The description can be up to 25,000 characters long. |
annotationSpecSet | string | Required. Name of the AnnotationSpecSet describing all the labels that your machine learning model outputs. You must create this resource before you create an evaluation job and provide its name in the following format: "projects/{project_id}/annotationSpecSets/{annotation_spec_set_id}" |
attempts | array | Output only. Every time the evaluation job runs and an error occurs, the failed attempt is appended to this array. |
createTime | string | Output only. Timestamp of when this evaluation job was created. |
evaluationJobConfig | object | Configures specific details of how a continuous evaluation job works. Provide this configuration when you create an EvaluationJob. |
labelMissingGroundTruth | boolean | Required. Whether you want Data Labeling Service to provide ground truth labels for prediction input. If you want the service to assign human labelers to annotate your data, set this to true . If you want to provide your own ground truth labels in the evaluation job's BigQuery table, set this to false . |
modelVersion | string | Required. The AI Platform Prediction model version to be evaluated. Prediction input and output is sampled from this model version. When creating an evaluation job, specify the model version in the following format: "projects/{project_id}/models/{model_name}/versions/{version_name}" There can only be one evaluation job per model version. |
schedule | string | Required. Describes the interval at which the job runs. This interval must be at least 1 day, and it is rounded to the nearest day. For example, if you specify a 50-hour interval, the job runs every 2 days. You can provide the schedule in crontab format or in an English-like format. Regardless of what you specify, the job will run at 10:00 AM UTC. Only the interval from this schedule is used, not the specific time of day. |
state | string | Output only. Describes the current state of the job. |
Methods
Name | Accessible by | Required Params | Description |
---|---|---|---|
projects_evaluation_jobs_get | SELECT | evaluationJobsId, projectsId | Gets an evaluation job by resource name. |
projects_evaluation_jobs_list | SELECT | projectsId | Lists all evaluation jobs within a project with possible filters. Pagination is supported. |
projects_evaluation_jobs_create | INSERT | projectsId | Creates an evaluation job. |
projects_evaluation_jobs_delete | DELETE | evaluationJobsId, projectsId | Stops and deletes an evaluation job. |
projects_evaluation_jobs_patch | UPDATE | evaluationJobsId, projectsId | Updates an evaluation job. You can only update certain fields of the job's EvaluationJobConfig: humanAnnotationConfig.instruction , exampleCount , and exampleSamplePercentage . If you want to change any other aspect of the evaluation job, you must delete the job and create a new one. |
projects_evaluation_jobs_pause | EXEC | evaluationJobsId, projectsId | Pauses an evaluation job. Pausing an evaluation job that is already in a PAUSED state is a no-op. |
projects_evaluation_jobs_resume | EXEC | evaluationJobsId, projectsId | Resumes a paused evaluation job. A deleted evaluation job can't be resumed. Resuming a running or scheduled evaluation job is a no-op. |
SELECT
examples
Lists all evaluation jobs within a project with possible filters. Pagination is supported.
SELECT
name,
description,
annotationSpecSet,
attempts,
createTime,
evaluationJobConfig,
labelMissingGroundTruth,
modelVersion,
schedule,
state
FROM google.datalabeling.evaluation_jobs
WHERE projectsId = '{{ projectsId }}';
INSERT
example
Use the following StackQL query and manifest file to create a new evaluation_jobs
resource.
- All Properties
- Manifest
/*+ create */
INSERT INTO google.datalabeling.evaluation_jobs (
projectsId,
job
)
SELECT
'{{ projectsId }}',
'{{ job }}'
;
- name: your_resource_model_name
props:
- name: job
value:
- name: name
value: string
- name: description
value: string
- name: state
value: string
- name: schedule
value: string
- name: modelVersion
value: string
- name: evaluationJobConfig
value:
- name: imageClassificationConfig
value:
- name: annotationSpecSet
value: string
- name: allowMultiLabel
value: boolean
- name: answerAggregationType
value: string
- name: boundingPolyConfig
value:
- name: annotationSpecSet
value: string
- name: instructionMessage
value: string
- name: textClassificationConfig
value:
- name: allowMultiLabel
value: boolean
- name: annotationSpecSet
value: string
- name: sentimentConfig
value:
- name: enableLabelSentimentSelection
value: boolean
- name: inputConfig
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: evaluationConfig
value:
- name: boundingBoxEvaluationOptions
value:
- name: iouThreshold
value: number
- name: humanAnnotationConfig
value:
- name: instruction
value: string
- name: annotatedDatasetDisplayName
value: string
- name: annotatedDatasetDescription
value: string
- name: labelGroup
value: string
- name: languageCode
value: string
- name: replicaCount
value: integer
- name: questionDuration
value: string
- name: contributorEmails
value:
- string
- name: userEmailAddress
value: string
- name: bigqueryImportKeys
value: object
- name: exampleCount
value: integer
- name: exampleSamplePercentage
value: number
- name: evaluationJobAlertConfig
value:
- name: email
value: string
- name: minAcceptableMeanAveragePrecision
value: number
- name: annotationSpecSet
value: string
- name: labelMissingGroundTruth
value: boolean
- name: attempts
value:
- - name: attemptTime
value: string
- name: partialFailures
value:
- - name: code
value: integer
- name: message
value: string
- name: details
value:
- object
- name: createTime
value: string
UPDATE
example
Updates a evaluation_jobs
resource.
/*+ update */
UPDATE google.datalabeling.evaluation_jobs
SET
name = '{{ name }}',
description = '{{ description }}',
state = '{{ state }}',
schedule = '{{ schedule }}',
modelVersion = '{{ modelVersion }}',
evaluationJobConfig = '{{ evaluationJobConfig }}',
annotationSpecSet = '{{ annotationSpecSet }}',
labelMissingGroundTruth = true|false,
attempts = '{{ attempts }}'
WHERE
evaluationJobsId = '{{ evaluationJobsId }}'
AND projectsId = '{{ projectsId }}';
DELETE
example
Deletes the specified evaluation_jobs
resource.
/*+ delete */
DELETE FROM google.datalabeling.evaluation_jobs
WHERE evaluationJobsId = '{{ evaluationJobsId }}'
AND projectsId = '{{ projectsId }}';