Cloud AI Platform v1beta1 API - Class ModelMonitoringSchema (1.0.0-beta01) 

public sealed class ModelMonitoringSchema : IMessage<ModelMonitoringSchema>, IEquatable<ModelMonitoringSchema>, IDeepCloneable<ModelMonitoringSchema>, IBufferMessage, IMessage

Reference documentation and code samples for the Cloud AI Platform v1beta1 API class ModelMonitoringSchema.

The Model Monitoring Schema definition.

Inheritance

object > ModelMonitoringSchema

Namespace

Google.Cloud.AIPlatform.V1Beta1

Assembly

Google.Cloud.AIPlatform.V1Beta1.dll

Constructors

ModelMonitoringSchema()

public ModelMonitoringSchema()

ModelMonitoringSchema(ModelMonitoringSchema)

public ModelMonitoringSchema(ModelMonitoringSchema other)
Parameter
Name Description
other ModelMonitoringSchema

Properties

FeatureFields

public RepeatedField<ModelMonitoringSchema.Types.FieldSchema> FeatureFields { get; }

Feature names of the model. Vertex AI will try to match the features from your dataset as follows:

  • For 'csv' files, the header names are required, and we will extract the corresponding feature values when the header names align with the feature names.
  • For 'jsonl' files, we will extract the corresponding feature values if the key names match the feature names. Note: Nested features are not supported, so please ensure your features are flattened. Ensure the feature values are scalar or an array of scalars.
  • For 'bigquery' dataset, we will extract the corresponding feature values if the column names match the feature names. Note: The column type can be a scalar or an array of scalars. STRUCT or JSON types are not supported. You may use SQL queries to select or aggregate the relevant features from your original table. However, ensure that the 'schema' of the query results meets our requirements.
  • For the Vertex AI Endpoint Request Response Logging table or Vertex AI Batch Prediction Job results. If the [instance_type][google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.instance_type] is an array, ensure that the sequence in [feature_fields][google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.feature_fields] matches the order of features in the prediction instance. We will match the feature with the array in the order specified in [feature_fields].
Property Value
Type Description
RepeatedFieldModelMonitoringSchemaTypesFieldSchema

GroundTruthFields

public RepeatedField<ModelMonitoringSchema.Types.FieldSchema> GroundTruthFields { get; }

Target /ground truth names of the model.

Property Value
Type Description
RepeatedFieldModelMonitoringSchemaTypesFieldSchema

PredictionFields

public RepeatedField<ModelMonitoringSchema.Types.FieldSchema> PredictionFields { get; }

Prediction output names of the model. The requirements are the same as the [feature_fields][google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.feature_fields]. For AutoML Tables, the prediction output name presented in schema will be: predicted_{target_column}, the target_column is the one you specified when you train the model. For Prediction output drift analysis:

  • AutoML Classification, the distribution of the argmax label will be analyzed.
  • AutoML Regression, the distribution of the value will be analyzed.
Property Value
Type Description
RepeatedFieldModelMonitoringSchemaTypesFieldSchema