Method: projects.locations.modelDeploymentMonitoringJobs.searchModelDeploymentMonitoringStatsAnomalies

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

string

Required. ModelDeploymentMonitoring Job resource name. Format: `projects/{project}/locations/{location}/modelDeploymentMonitoringJobs/{modelDeploymentMonitoringJob}

Request body

The request body contains data with the following structure:

JSON representation 
{
  "deployedModelId": string,
  "featureDisplayName": string,
  "objectives": [
    {
      object (StatsAnomaliesObjective)
    }
  ],
  "pageSize": integer,
  "pageToken": string,
  "startTime": string,
  "endTime": string
}
Fields
deployedModelId

string

Required. The DeployedModel ID of the [google.cloud.aiplatform.master.ModelDeploymentMonitoringObjectiveConfig.deployed_model_id].
featureDisplayName

string

The feature display name. If specified, only return the stats belonging to this feature. Format: ModelMonitoringStatsAnomalies.FeatureHistoricStatsAnomalies.feature_display_name, example: "user_destination".
objectives[]

object (StatsAnomaliesObjective)

Required. Objectives of the stats to retrieve.
pageSize

integer

The standard list page size.
pageToken

string

A page token received from a previous JobService.SearchModelDeploymentMonitoringStatsAnomalies call.
startTime

string (Timestamp format)

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: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".
endTime

string (Timestamp format)

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: "2014-10-02T15:01:23Z" and "2014-10-02T15:01:23.045123456Z".

Response body

If successful, the response body contains data with the following structure:

Response message for JobService.SearchModelDeploymentMonitoringStatsAnomalies.

JSON representation 
{
  "monitoringStats": [
    {
      object (ModelMonitoringStatsAnomalies)
    }
  ],
  "nextPageToken": string
}
Fields
monitoringStats[]

object (ModelMonitoringStatsAnomalies)

Stats retrieved for requested objectives. There are at most 1000 ModelMonitoringStatsAnomalies.FeatureHistoricStatsAnomalies.prediction_stats in the response.
nextPageToken

string

The page token that can be used by the next JobService.SearchModelDeploymentMonitoringStatsAnomalies call.

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 (ModelDeploymentMonitoringObjectiveType),
  "topFeatureCount": integer
}
Fields
type

enum (ModelDeploymentMonitoringObjectiveType)
topFeatureCount

integer

If set, all attribution scores between SearchModelDeploymentMonitoringStatsAnomaliesRequest.start_time and SearchModelDeploymentMonitoringStatsAnomaliesRequest.end_time are fetched, and page token doesn't take affect in this case. Only used to retrieve attribution score for the top Features which has the highest attribution score in the latest monitoring run.

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 (ModelDeploymentMonitoringObjectiveType),
  "deployedModelId": string,
  "anomalyCount": integer,
  "featureStats": [
    {
      object (FeatureHistoricStatsAnomalies)
    }
  ]
}
Fields
objective

enum (ModelDeploymentMonitoringObjectiveType)

Model Monitoring Objective those stats and anomalies belonging to.
deployedModelId

string

Deployed Model ID.
anomalyCount

integer

Number of anomalies within all stats.
featureStats[]

object (FeatureHistoricStatsAnomalies)

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 (ThresholdConfig)
  },
  "trainingStats": {
    object (FeatureStatsAnomaly)
  },
  "predictionStats": [
    {
      object (FeatureStatsAnomaly)
    }
  ]
}
Fields
featureDisplayName

string

Display Name of the Feature.
threshold

object (ThresholdConfig)

Threshold for anomaly detection.
trainingStats

object (FeatureStatsAnomaly)

Stats calculated for the Training Dataset.
predictionStats[]

object (FeatureStatsAnomaly)

A list of historical stats generated by different time window's Prediction Dataset.

FeatureStatsAnomaly

Stats and Anomaly generated at specific timestamp for specific Feature. The startTime and endTime are used to define the time range of the dataset that current stats belongs to, e.g. prediction traffic is bucketed into prediction datasets by time window. If the Dataset is not defined by time window, startTime = endTime. Timestamp of the stats and anomalies always refers to endTime. Raw stats and anomalies are stored in statsUri or anomalyUri in the tensorflow defined protos. Field dataStats contains almost identical information with the raw stats in Vertex AI defined proto, for UI to display.

JSON representation 
{
  "score": number,
  "statsUri": string,
  "anomalyUri": string,
  "distributionDeviation": number,
  "anomalyDetectionThreshold": number,
  "startTime": string,
  "endTime": string
}
Fields
score

number

Feature importance score, only populated when cross-feature monitoring is enabled. For now only used to represent feature attribution score within range [0, 1] for ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_SKEW and ModelDeploymentMonitoringObjectiveType.FEATURE_ATTRIBUTION_DRIFT.
statsUri

string

Path of the stats file for current feature values in Cloud Storage bucket. Format: gs:////stats. Example: gs://monitoring_bucket/feature_name/stats. Stats are stored as binary format with Protobuf message tensorflow.metadata.v0.FeatureNameStatistics.
anomalyUri

string

Path of the anomaly file for current feature values in Cloud Storage bucket. Format: gs:////anomalies. Example: gs://monitoring_bucket/feature_name/anomalies. Stats are stored as binary format with Protobuf message Anoamlies are stored as binary format with Protobuf message tensorflow.metadata.v0.AnomalyInfo.
distributionDeviation

number

Deviation from the current stats to baseline stats. 1. For categorical feature, the distribution distance is calculated by L-inifinity norm. 2. For numerical feature, the distribution distance is calculated by Jensen–Shannon divergence.
anomalyDetectionThreshold

number

This is the threshold used when detecting anomalies. The threshold can be changed by user, so this one might be different from ThresholdConfig.value.
startTime

string (Timestamp format)

The start timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), startTime is only used to indicate the monitoring intervals, so it always equals to (endTime - monitoringInterval).

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".
endTime

string (Timestamp format)

The end timestamp of window where stats were generated. For objectives where time window doesn't make sense (e.g. Featurestore Snapshot Monitoring), endTime indicates the timestamp of the data used to generate stats (e.g. timestamp we take snapshots for feature values).

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".