Searches Model Monitoring Statistics generated within a given time window.
HTTP request
POST https://{service-endpoint}/v1/{modelDeploymentMonitoringJob}:searchModelDeploymentMonitoringStatsAnomalies
Where {service-endpoint}
is one of the supported service endpoints.
Path parameters
Parameters | |
---|---|
modelDeploymentMonitoringJob |
Required. ModelDeploymentMonitoring Job resource name. Format: |
Request body
The request body contains data with the following structure:
JSON representation |
---|
{
"deployedModelId": string,
"featureDisplayName": string,
"objectives": [
{
object ( |
Fields | |
---|---|
deployedModelId |
Required. The DeployedModel id of the [ModelDeploymentMonitoringObjectiveConfig.deployed_model_id]. |
featureDisplayName |
The feature display name. If specified, only return the stats belonging to this feature. Format: |
objectives[] |
Required. Objectives of the stats to retrieve. |
pageSize |
The standard list page size. |
pageToken |
A page token received from a previous |
startTime |
The earliest timestamp of stats being generated. If not set, indicates fetching stats till the earliest possible one. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
endTime |
The latest timestamp of stats being generated. If not set, indicates feching stats till the latest possible one. A timestamp in RFC3339 UTC "Zulu" format, with nanosecond resolution and up to nine fractional digits. Examples: |
Response body
Response message for JobService.SearchModelDeploymentMonitoringStatsAnomalies
.
If successful, the response body contains data with the following structure:
JSON representation |
---|
{
"monitoringStats": [
{
object ( |
Fields | |
---|---|
monitoringStats[] |
Stats retrieved for requested objectives. There are at most 1000 |
nextPageToken |
The page token that can be used by the next |
Authorization scopes
Requires the following OAuth scope:
https://www.googleapis.com/auth/cloud-platform
For more information, see the Authentication Overview.
IAM Permissions
Requires the following IAM permission on the modelDeploymentMonitoringJob
resource:
aiplatform.modelDeploymentMonitoringJobs.searchStatsAnomalies
For more information, see the IAM documentation.
StatsAnomaliesObjective
Stats requested for specific objective.
JSON representation |
---|
{
"type": enum ( |
Fields | |
---|---|
type |
|
topFeatureCount |
If set, all attribution scores between |
ModelDeploymentMonitoringObjectiveType
The Model Monitoring Objective types.
Enums | |
---|---|
MODEL_DEPLOYMENT_MONITORING_OBJECTIVE_TYPE_UNSPECIFIED |
Default value, should not be set. |
RAW_FEATURE_SKEW |
Raw feature values' stats to detect skew between Training-Prediction datasets. |
RAW_FEATURE_DRIFT |
Raw feature values' stats to detect drift between Serving-Prediction datasets. |
FEATURE_ATTRIBUTION_SKEW |
feature attribution scores to detect skew between Training-Prediction datasets. |
FEATURE_ATTRIBUTION_DRIFT |
feature attribution scores to detect skew between Prediction datasets collected within different time windows. |
ModelMonitoringStatsAnomalies
Statistics and anomalies generated by Model Monitoring.
JSON representation |
---|
{ "objective": enum ( |
Fields | |
---|---|
objective |
Model Monitoring Objective those stats and anomalies belonging to. |
deployedModelId |
Deployed Model id. |
anomalyCount |
Number of anomalies within all stats. |
featureStats[] |
A list of historical Stats and Anomalies generated for all Features. |
FeatureHistoricStatsAnomalies
Historical Stats (and Anomalies) for a specific feature.
JSON representation |
---|
{ "featureDisplayName": string, "threshold": { object ( |
Fields | |
---|---|
featureDisplayName |
Display name of the feature. |
threshold |
Threshold for anomaly detection. |
trainingStats |
Stats calculated for the Training Dataset. |
predictionStats[] |
A list of historical stats generated by different time window's Prediction Dataset. |