Monitor features

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of theService Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see thelaunch stage descriptions.

Vertex AI Feature Store lets you schedule and run feature monitoring jobsto monitor feature data, retrieve feature statistics, anddetect feature drift. You can monitor feature data only ifyou've registered your feature data source in the Feature Registry.

To monitor feature data, you can create theFeatureMonitor resource under aFeatureGroup resource. While creating theFeatureMonitor resource, you canconfigure the monitoring schedule to periodically run monitoring jobs on the featuredata. Alternatively, you can run a feature monitoring job manually to monitor yourfeature data outside of the monitoring schedule.

For each monitoring job that's executed, Vertex AI Feature Storegenerates aFeatureMonitorJob resource, which you can retrieve to view thefeature statistics and information about drift detected in the feature data.

Before you begin

Before you monitor features using Vertex AI Feature Store, complete theprerequisites listed in this section.

Register feature data source

Register your feature data source from BigQuery in theFeature Registry by creatingfeature groups andandfeatures. TheFeatureMonitor resourcesused to retrieve and monitor feature statistics are associated with featuregroups.

Authenticate to Vertex AI

Authenticate toVertex AI, unless you've done so already.

Select the tab for how you plan to use the samples on this page:

Python

To use the Python samples on this page in a local development environment, install and initialize the gcloud CLI, and then set up Application Default Credentials with your user credentials.

    Install the Google Cloud CLI.

    If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

    If you're using a local shell, then create local authentication credentials for your user account:

    gcloudauthapplication-defaultlogin

    You don't need to do this if you're using Cloud Shell.

    If an authentication error is returned, and you are using an external identity provider (IdP), confirm that you have signed in to the gcloud CLI with your federated identity.

For more information, see Set up authentication for a local development environment.

REST

To use the REST API samples on this page in a local development environment, you use the credentials you provide to the gcloud CLI.

    Install the Google Cloud CLI.

    If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

For more information, seeAuthenticate for using REST in the Google Cloud authentication documentation.

Create a feature monitor with a monitoring schedule

To retrieve and monitor feature statistics, create aFeatureMonitor resourcespecifying the schedule to periodically execute feature monitoring jobs andretrieve feature statistics for the features registered in the feature group.

Use the following samples to create aFeatureMonitor resource. To set upmultiple schedules for the same feature group, you must create multipleFeatureMonitor resources.

REST

To create aFeatureMonitorresource and schedule feature monitoring jobs, send aPOST request by using thefeatureMonitors.createmethod.

Before using any of the request data, make the following replacements:

  • LOCATION_ID: Region where you want to create the feature monitor, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group where you set up feature monitoring.
  • FEATURE_MONITOR_NAME: A name for the new feature monitor that you want to create.
  • FEATURE_ID_1 andFEATURE_ID_2: The IDs of the features that you want to monitor.
  • DRIFT_THRESHOLD_1 andDRIFT_THRESHOLD_2: Drift thresholds for each feature included in the feature monitor. The drift threshold is used to detect anomalies, such as feature drift. Enter a value in the range[0, 1). If you don't enter a value, the threshold is set to0.3, by default.
    Vertex AI Feature Store compares the snapshots from consecutive feature monitor job executions and calculates drifts usingthe ML.TFDV_VALIDATE function in BigQuery. To classify anomalies,L-infinity distance is used for categorical features andJensen-Shannon divergence is used for numerical features.
  • CRON: Cron schedule expression representing the frquency for running the feature monitoring job. For more information, seecron.

HTTP method and URL:

POST https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors?feature_monitor_id=FEATURE_MONITOR_NAME

Request JSON body:

{  "feature_selection_config": {    "feature_configs": [      {"feature_id":"FEATURE_ID_1", "drift_threshold": "DRIFT_THRESHOLD_1" },      {"feature_id":"FEATURE_ID_2", "drift_threshold": "DRIFT_THRESHOLD_2" }    ],  },  "schedule_config": {    "cron": "CRON"  }}

To send your request, choose one of these options:

curl

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

Save the request body in a file namedrequest.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors?feature_monitor_id=FEATURE_MONITOR_NAME"

PowerShell

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

Save the request body in a file namedrequest.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors?feature_monitor_id=FEATURE_MONITOR_NAME" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/operations/OPERATION_ID",  "metadata": {    "@type": "type.googleapis.com/google.cloud.aiplatform.v1beta1.CreateFeatureMonitorOperationMetadata",    "genericMetadata": {      "createTime": "2024-12-15T19:35:03.975958Z",      "updateTime": "2024-12-15T19:35:03.975958Z"    }  }}

Python

Before trying this sample, follow thePython setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIPython API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storedefcreate_feature_monitor_sample(project:str,location:str,existing_feature_group_id:str,feature_monitor_id:str,feature_selection_configs:List[Tuple[str,float]]schedule_config:str# Cron string. For example, "0 * * * *" indicates hourly execution.):aiplatform.init(project="PROJECT_ID",location="LOCATION_ID")feature_group=feature_store.FeatureGroup("FEATUREGROUP_NAME")feature_monitor=feature_group.create_feature_monitor(name="FEATURE_MONITOR_NAME",feature_selection_configs=[("FEATURE_ID_1",DRIFT_THRESHOLD_1),("FEATURE_ID_2",DRIFT_THRESHOLD_2)],schedule_config="CRON")

Replace the following:

  • LOCATION_ID: Region where you want to create the feature monitor, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group where you set up feature monitoring.
  • FEATURE_MONITOR_NAME: A name for the new feature monitor that you want to create.
  • FEATURE_ID_1 andFEATURE_ID_2: The IDs of the features that you want to monitor.
  • DRIFT_THRESHOLD_1 andDRIFT_THRESHOLD_2: Drift thresholds for each Feature included in the feature monitor. The drift threshold is used to detect feature drift. Enter a value between0 and1. If you don't enter a value, the threshold is set to0.3, by default.
    Vertex AI Feature Store compares the data snapshot from the current feature monitor job with the data snapshot during the previous feature monitor job. Note that to calculate the distribution deviation, Vertex AI Feature Store usesthe ML.TFDV_VALIDATE function in BigQuery.
    For the metric used to compare statistics,L-infinity distance is used for categorical features andJensen-Shannon divergence is used for numerical features.
  • CRON: Cron schedule expression representing the frequency for running the feature monitoring job. For more information, seecron.

Run a feature monitoring job manually

You can skip the wait between consecutive scheduled feature monitoring jobs andmanually run a feature monitor job. This is useful if you want toretrieve monitoring information and detect anomalies in the feature dataimmediately instead of waiting for the next scheduled monitoring job to run.

REST

To run a feature monitoring job manually by creating aFeatureMonitorJobresource , send aPOST request by using thefeatureMonitorJobs.createmethod.

Before using any of the request data, make the following replacements:

  • LOCATION_ID: Region where you want to run the feature monitoring job, such asus-central1.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • PROJECT_ID: Your project ID.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which you want to run the feature monitoring job.

HTTP method and URL:

POST https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_ID/featureMonitorJobs

To send your request, choose one of these options:

curl

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

Execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d "" \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_ID/featureMonitorJobs"

PowerShell

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_ID/featureMonitorJobs" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID"}

Python

Before trying this sample, follow thePython setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIPython API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storeaiplatofrm.init(project="PROJECT_ID",location="LOCATION_ID")feature_group=FeatureGroup.get("FEATUREGROUP_NAME}")feature_monitor=feature_group.get_feature_monitor(FEATURE_MONITOR_NAME)feature_monitor_job=feature_monitor.create_feature_monitor_job()

Replace the following:

  • LOCATION_ID: Region where you want to run the feature monitoring job, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which you want to run the feature monitoring job.

Retrieve feature statistics from a monitoring job

You can retrieve feature statistics for all the features in a feature monitoringjob by retrieving theFeatureMonitorJob resource using the feature monitor jobID generated during the feature monitoring job execution. You can also retrievefeature statistics for a specific resource for the latest monitoring job.

List feature monitor jobs

The following samples show how to retrieve a list of all theFeatureMonitorJob resources created for a givenFeatureMonitor resource.

REST

To retrieve a list ofFeatureMonitorJobresources for a specifiedFeatureMonitor resource, send aGET request by using thefeatureMonitorJobs.listmethod.

Before using any of the request data, make the following replacements:

  • LOCATION_ID: Region where theFeature resource is located, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which you want to list the feature monitoring jobs.

HTTP method and URL:

GET https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs

To send your request, choose one of these options:

curl

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

Execute the following command:

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs"

PowerShell

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "featureMonitorJobs": [    {      "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID_1",      "createTime": "2024-12-18T19:18:18.077161Z",      "finalStatus": {},      "featureSelectionConfig": {        "featureConfigs": [          {            "featureId": "feature_name_1",            "driftThreshold": 0.2          },          {            "featureId": "feature_name_2",            "driftThreshold": 0.2          }        ]      }    },    {      "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID_2",      "createTime": "2024-12-19T19:18:30.859921Z",      "finalStatus": {},      "featureSelectionConfig": {        "featureConfigs": [          {            "featureId": "feature_name_1",            "driftThreshold": 0.2          },          {            "featureId": "feature_name_2",            "driftThreshold": 0.2          }        ]      }    }  ]}

Python

Before trying this sample, follow thePython setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIPython API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storeaiplatofrm.init(project="PROJECT_ID",location="LOCATION_ID")feature_group=FeatureGroup.get("FEATUREGROUP_NAME")feature_monitor=feature_group.get_feature_monitor(FEATURE_MONITOR_NAME)feature_monitor_jobs=feature_monitor.list_feature_monitor_jobs()

Replace the following:

  • LOCATION_ID: Region where theFeature resource is located, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which you want to list the feature monitoring jobs.

View feature statistics from a monitoring job

The following samples show how to view the feature statistics for all thefeatures in a feature monitoring job. For each feature, the statistics andanomalies are displayed in theFeatureNameStatistics format.

REST

To view the feature statistics from a monitoring job by retrieving aFeatureMonitorJobresource, send aGET request by using thefeatureMonitorJobs.getmethod.

Before using any of the request data, make the following replacements:

  • LOCATION_ID: Region where where the feature monitoring job was run, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which the feature monitoring job was run.
  • FEATURE_MONITOR_JOB_ID: The ID of theFeatureMonitorJob resource that you want to retrieve.

HTTP method and URL:

GET https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID

To send your request, choose one of these options:

curl

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

Execute the following command:

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID"

PowerShell

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID",  "createTime": "2024-12-19T19:18:18.077161Z",  "finalStatus": {},  "jobSummary": {    "featureStatsAndAnomalies": [      {        "featureId": "feature_id_1",        "featureStats": {          "name": "feature_name_1",          "type": "STRING",          "stringStats": {            "commonStats": {              "numNonMissing": "6",              "minNumValues": "1",              "maxNumValues": "1",              "avgNumValues": 1,              "numValuesHistogram": {                "buckets": [                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.6                  },                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.6                  }                ],                "type": "QUANTILES"              },              "totNumValues": "6"            },            "unique": "2",            "topValues": [              {                "value": "59",                "frequency": 2              },              {                "value": "19",                "frequency": 1              }            ],            "avgLength": 2,            "rankHistogram": {              "buckets": [                {                  "label": "59",                  "sampleCount": 2                },                {                  "lowRank": "1",                  "highRank": "1",                  "label": "19",                  "sampleCount": 1                }              ]            }          }        },        "statsTime": "2024-12-19T19:18:18.077161Z",        "featureMonitorJobId": "FEATURE_MONITOR_JOB_ID",        "featureMonitorId": "FEATURE_MONITOR_NAME"      },      {        "featureId": "feature_id_2",        "featureStats": {          "name": "feature_name_1",          "type": "STRING",          "stringStats": {            "commonStats": {              "numNonMissing": "6",              "minNumValues": "1",              "maxNumValues": "1",              "avgNumValues": 1,              "numValuesHistogram": {                "buckets": [                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.6                  },                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.6                  }                ],                "type": "QUANTILES"              },              "totNumValues": "6"            },            "unique": "2",            "topValues": [              {                "value": "59",                "frequency": 2              },              {                "value": "19",                "frequency": 1              }            ],            "avgLength": 2,            "rankHistogram": {              "buckets": [                {                  "label": "59",                  "sampleCount": 2                },                {                  "lowRank": "1",                  "highRank": "1",                  "label": "19",                  "sampleCount": 1                }              ]            }          }        },        "statsTime": "2024-12-19T19:18:18.077161Z",        "featureMonitorJobId": "FEATURE_MONITOR_JOB_ID",        "featureMonitorId": "FEATURE_MONITOR_NAME"      }    ]  },  "driftBaseFeatureMonitorJobId": "2250003330000300000",  "driftBaseSnapshotTime": "2024-12-12T16:00:01.211686Z",  "featureSelectionConfig": {    "featureConfigs": [      {        "featureId": "feature_id_1",        "driftThreshold": 0.2      },      {        "featureId": "feature_id_2",        "driftThreshold": 0.2      }    ]  },  "triggerType": "FEATURE_MONITOR_JOB_TRIGGER_ON_DEMAND"}

Python

Before trying this sample, follow thePython setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIPython API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storeaiplatofrm.init(project="PROJECT_ID",location="LOCATION_ID")feature_group=FeatureGroup.get("FEATUREGROUP_NAME"})feature_monitor=feature_group.get_feature_monitor("FEATURE_MONITOR_NAME")feature_monitor_job=feature_monitor.get_feature_monitor_job("FEATURE_MONITOR_JOB_ID)")# Retrieve feature stats and anomaliesfeature_stats_and_anomalies=feature_monitor_job.feature_stats_and_anomaliesprint(feature_stats_and_anomalies)

Replace the following:

  • LOCATION_ID: Region where where the feature monitoring job was run, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which the feature monitoring job was run.
  • FEATURE_MONITOR_JOB_ID: The ID of theFeatureMonitorJob resource that you want to retrieve.

View feature statistics for a feature

You can retrieve the feature statistics for a specific feature from the mostrecent feature monitoring jobs executed, by retrieving the feature detailsand specifying the number of monitoring jobs that you want to retrieve thestatistics from. The statistics and anomalies are displayed in theFeatureNameStatistics format.

The following samples show how to view the feature statistics for a specificfeature from a specified number of recent feature monitoring jobs.

REST

To view the feature statistics for a specific feature in aFeatureresource, send aGET request using thefeatures.getmethod and specifying the number of monitoring jobs to retrieve the statistics from.

Before using any of the request data, make the following replacements:

  • LOCATION_ID: Region where where the feature monitoring job was run, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing the feature.
  • FEATURE_NAME: The name of theFeature resource for which you want to retrieve the feature statistics.
  • LATEST_STATS_COUNT: The number of the latest monitoring jobs to retrieve the feature statistics from.

HTTP method and URL:

GET https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/features/FEATURE_NAME?feature_stats_and_anomaly_spec.latest_stats_count=LATEST_STATS_COUNT

To send your request, choose one of these options:

curl

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

Execute the following command:

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/features/FEATURE_NAME?feature_stats_and_anomaly_spec.latest_stats_count=LATEST_STATS_COUNT"

PowerShell

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/features/FEATURE_NAME?feature_stats_and_anomaly_spec.latest_stats_count=LATEST_STATS_COUNT" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/features/FEATURE_NAME",  "createTime": "2024-12-19T21:17:23.373559Z",  "updateTime": "2024-12-19T21:17:23.373559Z",  "etag": "sample_etag",  "featureStatsAndAnomaly": [    {      "featureStats": {        "name": "FEATURE_NAME",        "type": "STRING",        "stringStats": {          "commonStats": {            "numNonMissing": "4",            "minNumValues": "1",            "maxNumValues": "1",            "avgNumValues": 1,            "numValuesHistogram": {              "buckets": [                {                  "lowValue": 1,                  "highValue": 1,                  "sampleCount": 0.4                },                {                  "lowValue": 1,                  "highValue": 1,                  "sampleCount": 0.4                },                {                  "lowValue": 1,                  "highValue": 1,                  "sampleCount": 0.4                },                {                  "lowValue": 1,                  "highValue": 1,                  "sampleCount": 0.4                }              ],              "type": "QUANTILES"            },            "totNumValues": "4"          },          "unique": "4",          "topValues": [            {              "value": "feature_value_1",              "frequency": 1            },            {              "value": "feature_value_2",              "frequency": 1            },            {              "value": "feature_value_3",              "frequency": 1            },            {              "value": "feature_value_4",              "frequency": 1            }          ],          "avgLength": 4,          "rankHistogram": {            "buckets": [              {                "label": "label_1",                "sampleCount": 1              },              {                "lowRank": "1",                "highRank": "1",                "label": "label_2",                "sampleCount": 1              },              {                "lowRank": "2",                "highRank": "2",                "label": "label_3",                "sampleCount": 1              },              {                "lowRank": "3",                "highRank": "3",                "label": "label_4",                "sampleCount": 1              }            ]          }        }      },      "driftDetectionThreshold": 0.1,      "statsTime": "2024-12-19T22:00:02.734796Z",      "featureMonitorJobId": "feature_monitor_job_id_1",      "featureMonitorId": "feature_monitor_name_1"    }  ],  "versionColumnName": "version_column_name"}

Python

Before trying this sample, follow thePython setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIPython API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storeaiplatofrm.init(project="PROJECT_ID",location="LOCATION_ID")feature_group=FeatureGroup.get("FEATUREGROUP_NAME"})feature_stats_and_anomalies=feature_group.get_feature("FEATURE_NAME",latest_stats_count=LATEST_STATS_COUNT)print(feature_stats_and_anomalies)

Replace the following:

  • LOCATION_ID: Region where where the feature monitoring job was run, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_NAME: The name of the feature for which you want to retrieve the feature statistics.
  • LATEST_STATS_COUNT: The number of latest monitoring jobs to retrieve the feature statistics from.

Example use case: Use feature monitoring to detect feature drift

You can use feature monitoring to detect an anomaly in feature data calledfeature drift. A drift is a significant and unforeseen change to feature data inBigQuery over time. Vertex AI Feature Store helps youidentify feature drift by comparing the snapshot at the time when the monitoringjob is run, with the data snapshot during the previous monitoring job execution.

For any feature included in the feature monitor, if the difference between thetwo snapshots exceeds the threshold specified in thedrift_thresholdparameter, Vertex AI Feature Store identifies afeature drift and returns the following information in theFeatureMonitorJob resource:

  • ThedriftDetected parameter is set totrue.

  • The distribution deviation between the two snapshots.For numerical features, Vertex AI Feature Store calculates thisvalue usingJensen-Shannon divergence.For categorical features, Vertex AI Feature Store calculates thisvalue usingL-infinity distance.

  • The threshold that was exceeded by the distribution deviation.

The following samples show how to retrieve aFeatureMonitorJob resourceand verify whether a drift was detected.

REST

To retrieve aFeatureMonitorJobresource , send aGET request by using thefeatureMonitorJobs.getmethod.

Before using any of the request data, make the following replacements:

  • LOCATION_ID: Region where where the feature monitoring job was run, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which the feature monitoring job was run.
  • FEATURE_MONITOR_JOB_ID: The ID of theFeatureMonitorJob resource that you want to retrieve.

HTTP method and URL:

GET https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID

To send your request, choose one of these options:

curl

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login , or by usingCloud Shell, which automatically logs you into thegcloud CLI . You can check the currently active account by runninggcloud auth list.

Execute the following command:

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID"

PowerShell

Note: The following command assumes that you have logged in to thegcloud CLI with your user account by runninggcloud init orgcloud auth login . You can check the currently active account by runninggcloud auth list.

Execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://LOCATION_ID-aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{  "name": "projects/PROJECT_NUMBER/locations/LOCATION_ID/featureGroups/FEATUREGROUP_NAME/featureMonitors/FEATURE_MONITOR_NAME/featureMonitorJobs/FEATURE_MONITOR_JOB_ID",  "createTime": "2024-12-14T19:45:30.026522Z",  "finalStatus": {},  "jobSummary": {    "featureStatsAndAnomalies": [      {        "featureId": "feature_id_1",        "featureStats": {          "name": "feature_name_1",          "type": "STRING",          "stringStats": {            "commonStats": {              "numNonMissing": "3",              "minNumValues": "1",              "maxNumValues": "1",              "avgNumValues": 1,              "numValuesHistogram": {                "buckets": [                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.9                  },                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.9                  },                  {                    "lowValue": 1,                    "highValue": 1,                    "sampleCount": 0.9                  }                ],                "type": "QUANTILES"              },              "totNumValues": "3"            },            "unique": "3",            "topValues": [              {                "value": "sample_value_1",                "frequency": 1              },              {                "value": "sample_value_2",                "frequency": 1              },              {                "value": "sample_value_3",                "frequency": 1              }            ],            "avgLength": 3,            "rankHistogram": {              "buckets": [                {                  "label": "sample_label_1",                  "sampleCount": 1                },                {                  "lowRank": "1",                  "highRank": "1",                  "label": "sample_label_2",                  "sampleCount": 1                },                {                  "lowRank": "2",                  "highRank": "3",                  "label": "sample_label_3",                  "sampleCount": 1                }              ]            }          }        },"distributionDeviation": 0.1388880008888000,"driftDetectionThreshold": 0.1,"driftDetected": true,        "statsTime": "2024-12-15T19:45:37.026522Z",        "featureMonitorJobId": "FEATURE_MONITOR_JOB_ID",        "featureMonitorId": "FEATURE_MONITOR_NAME"      }    ]  },  "driftBaseFeatureMonitorJobId": "2250003330000300000",  "driftBaseSnapshotTime": "2024-12-12T18:18:18.077161Z",  "description": "sample_feature_monitor_job_description",  "featureSelectionConfig": {    "featureConfigs": [      {        "featureId": "feature_name",        "driftThreshold": 0.1      }    ]  },  "triggerType": "FEATURE_MONITOR_JOB_TRIGGER_ON_DEMAND"}

Python

Before trying this sample, follow thePython setup instructions in theVertex AI quickstart using client libraries. For more information, see theVertex AIPython API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, seeSet up authentication for a local development environment.

fromgoogle.cloudimportaiplatformfromvertexai.resources.previewimportfeature_storeaiplatofrm.init(project="PROJECT_ID",location="LOCATION_ID")feature_group=FeatureGroup.get("FEATUREGROUP_NAME"})feature_monitor=feature_group.get_feature_monitor("FEATURE_MONITOR_NAME")feature_monitor_job=feature_monitor.get_feature_monitor_job("FEATURE_MONITOR_JOB_ID)")# Retrieve feature stats and anomaliesfeature_stats_and_anomalies=feature_monitor_job.feature_stats_and_anomaliesprint(feature_stats_and_anomalies)# Check whether drifts are detectedforfeature_stats_and_anomaliesinfeature_monitor_job.feature_stats_and_anomalies:print("feature: ",feature_stats_and_anomalies.feature_id)print("distribution deviation: ",feature_stats_and_anomalies.distribution_deviation)print("drift detected: ",feature_stats_and_anomalies.drift_detected)

Replace the following:

  • LOCATION_ID: Region where where the feature monitoring job was run, such asus-central1.
  • PROJECT_ID: Your project ID.
  • FEATUREGROUP_NAME: The name of the feature group containing theFeatureMonitor resource.
  • FEATURE_MONITOR_NAME: The name of theFeatureMonitor resource for which the feature monitoring job was run.
  • FEATURE_MONITOR_JOB_ID: The ID of theFeatureMonitorJob resource that you want to retrieve.

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-12-15 UTC.