REST Resource: projects.locations.modelMonitors.modelMonitoringJobs

Resource: ModelMonitoringJob

Represents a model monitoring job that analyze dataset using different monitoring algorithm.

JSON representation 
{
  "name": string,
  "displayName": string,
  "modelMonitoringSpec": {
    object (ModelMonitoringSpec)
  },
  "createTime": string,
  "updateTime": string,
  "state": enum (JobState),
  "schedule": string,
  "jobExecutionDetail": {
    object (ModelMonitoringJobExecutionDetail)
  },
  "scheduleTime": string
}
Fields
name

string

Output only. Resource name of a ModelMonitoringJob. Format: projects/{projectId}/locations/{locationId}/modelMonitors/{modelMonitorId}/modelMonitoringJobs/{modelMonitoringJobId}
displayName

string

The display name of the ModelMonitoringJob. The name can be up to 128 characters long and can consist of any UTF-8.
modelMonitoringSpec

object (ModelMonitoringSpec)

Monitoring monitoring job spec. It outlines the specifications for monitoring objectives, notifications, and result exports. If left blank, the default monitoring specifications from the top-level resource 'ModelMonitor' will be applied. If provided, we will use the specification defined here rather than the default one.
createTime

string (Timestamp format)

Output only. timestamp when this ModelMonitoringJob was created.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".
updateTime

string (Timestamp format)

Output only. timestamp when this ModelMonitoringJob was updated most recently.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".
state

enum (JobState)

Output only. The state of the monitoring job. * When the job is still creating, the state will be 'JOB_STATE_PENDING'. * Once the job is successfully created, the state will be 'JOB_STATE_RUNNING'. * Once the job is finished, the state will be one of 'JOB_STATE_FAILED', 'JOB_STATE_SUCCEEDED', 'JOB_STATE_PARTIALLY_SUCCEEDED'.
schedule

string

Output only. Schedule resource name. It will only appear when this job is triggered by a schedule.
jobExecutionDetail

object (ModelMonitoringJobExecutionDetail)

Output only. Execution results for all the monitoring objectives.
scheduleTime

string (Timestamp format)

Output only. timestamp when this ModelMonitoringJob was scheduled. It will only appear when this job is triggered by a schedule.

A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

ModelMonitoringSpec

Monitoring monitoring job spec. It outlines the specifications for monitoring objectives, notifications, and result exports.

JSON representation 
{
  "objectiveSpec": {
    object (ModelMonitoringObjectiveSpec)
  },
  "notificationSpec": {
    object (ModelMonitoringNotificationSpec)
  },
  "outputSpec": {
    object (ModelMonitoringOutputSpec)
  }
}
Fields
objectiveSpec

object (ModelMonitoringObjectiveSpec)

The monitoring objective spec.
notificationSpec

object (ModelMonitoringNotificationSpec)

The model monitoring notification spec.
outputSpec

object (ModelMonitoringOutputSpec)

The Output destination spec for metrics, error logs, etc.

ModelMonitoringObjectiveSpec

Monitoring objectives spec.

JSON representation 
{
  "explanationSpec": {
    object (ExplanationSpec)
  },
  "baselineDataset": {
    object (ModelMonitoringInput)
  },
  "targetDataset": {
    object (ModelMonitoringInput)
  },

  // Union field objective can be only one of the following:
  "tabularObjective": {
    object (TabularObjective)
  }
  // End of list of possible types for union field objective.
}
Fields
explanationSpec

object (ExplanationSpec)

The explanation spec. This spec is required when the objectives spec includes feature attribution objectives.
baselineDataset

object (ModelMonitoringInput)

baseline dataset. It could be the training dataset or production serving dataset from a previous period.
targetDataset

object (ModelMonitoringInput)

Target dataset.
Union field objective. The monitoring objective. objective can be only one of the following:
tabularObjective

object (TabularObjective)

Tabular monitoring objective.

ModelMonitoringJobExecutionDetail

Represent the execution details of the job.

JSON representation 
{
  "baselineDatasets": [
    {
      object (ProcessedDataset)
    }
  ],
  "targetDatasets": [
    {
      object (ProcessedDataset)
    }
  ],
  "objectiveStatus": {
    string: {
      object (Status)
    },
    ...
  },
  "error": {
    object (Status)
  }
}
Fields
baselineDatasets[]

object (ProcessedDataset)

Processed baseline datasets.
targetDatasets[]

object (ProcessedDataset)

Processed target datasets.
objectiveStatus

map (key: string, value: object (Status))

Status of data processing for each monitoring objective. Key is the objective.
error

object (Status)

Additional job error status.

ProcessedDataset

Processed dataset information.

JSON representation 
{
  "location": string,
  "timeRange": {
    object (Interval)
  }
}
Fields
location

string

Actual data location of the processed dataset.
timeRange

object (Interval)

Dataset time range information if any.

Methods

create

 Creates a ModelMonitoringJob.

delete

 Deletes a ModelMonitoringJob.

get

 Gets a ModelMonitoringJob.

list

 Lists ModelMonitoringJobs.