Class ModelMonitoringSchema.Builder (3.43.0)

public static final class ModelMonitoringSchema.Builder extends GeneratedMessageV3.Builder<ModelMonitoringSchema.Builder> implements ModelMonitoringSchemaOrBuilder

The Model Monitoring Schema definition.

Protobuf type google.cloud.aiplatform.v1beta1.ModelMonitoringSchema

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
Type Description
Descriptor

Methods

addAllFeatureFields(Iterable<? extends ModelMonitoringSchema.FieldSchema> values)

public ModelMonitoringSchema.Builder addAllFeatureFields(Iterable<? extends ModelMonitoringSchema.FieldSchema> values)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
values Iterable<? extends com.google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema>
Returns
Type Description
ModelMonitoringSchema.Builder

addAllGroundTruthFields(Iterable<? extends ModelMonitoringSchema.FieldSchema> values)

public ModelMonitoringSchema.Builder addAllGroundTruthFields(Iterable<? extends ModelMonitoringSchema.FieldSchema> values)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
values Iterable<? extends com.google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema>
Returns
Type Description
ModelMonitoringSchema.Builder

addAllPredictionFields(Iterable<? extends ModelMonitoringSchema.FieldSchema> values)

public ModelMonitoringSchema.Builder addAllPredictionFields(Iterable<? extends ModelMonitoringSchema.FieldSchema> values)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
values Iterable<? extends com.google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema>
Returns
Type Description
ModelMonitoringSchema.Builder

addFeatureFields(ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder addFeatureFields(ModelMonitoringSchema.FieldSchema value)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

addFeatureFields(ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder addFeatureFields(ModelMonitoringSchema.FieldSchema.Builder builderForValue)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

addFeatureFields(int index, ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder addFeatureFields(int index, ModelMonitoringSchema.FieldSchema value)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameters
Name Description
index int
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

addFeatureFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder addFeatureFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameters
Name Description
index int
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

addFeatureFieldsBuilder()

public ModelMonitoringSchema.FieldSchema.Builder addFeatureFieldsBuilder()

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

addFeatureFieldsBuilder(int index)

public ModelMonitoringSchema.FieldSchema.Builder addFeatureFieldsBuilder(int index)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

addGroundTruthFields(ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder addGroundTruthFields(ModelMonitoringSchema.FieldSchema value)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

addGroundTruthFields(ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder addGroundTruthFields(ModelMonitoringSchema.FieldSchema.Builder builderForValue)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

addGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder addGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema value)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameters
Name Description
index int
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

addGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder addGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameters
Name Description
index int
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

addGroundTruthFieldsBuilder()

public ModelMonitoringSchema.FieldSchema.Builder addGroundTruthFieldsBuilder()

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

addGroundTruthFieldsBuilder(int index)

public ModelMonitoringSchema.FieldSchema.Builder addGroundTruthFieldsBuilder(int index)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

addPredictionFields(ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder addPredictionFields(ModelMonitoringSchema.FieldSchema value)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

addPredictionFields(ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder addPredictionFields(ModelMonitoringSchema.FieldSchema.Builder builderForValue)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

addPredictionFields(int index, ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder addPredictionFields(int index, ModelMonitoringSchema.FieldSchema value)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameters
Name Description
index int
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

addPredictionFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder addPredictionFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameters
Name Description
index int
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

addPredictionFieldsBuilder()

public ModelMonitoringSchema.FieldSchema.Builder addPredictionFieldsBuilder()

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

addPredictionFieldsBuilder(int index)

public ModelMonitoringSchema.FieldSchema.Builder addPredictionFieldsBuilder(int index)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public ModelMonitoringSchema.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

build()

public ModelMonitoringSchema build()
Returns
Type Description
ModelMonitoringSchema

buildPartial()

public ModelMonitoringSchema buildPartial()
Returns
Type Description
ModelMonitoringSchema

clear()

public ModelMonitoringSchema.Builder clear()
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

clearFeatureFields()

public ModelMonitoringSchema.Builder clearFeatureFields()

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Returns
Type Description
ModelMonitoringSchema.Builder

clearField(Descriptors.FieldDescriptor field)

public ModelMonitoringSchema.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
Name Description
field FieldDescriptor
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

clearGroundTruthFields()

public ModelMonitoringSchema.Builder clearGroundTruthFields()

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Returns
Type Description
ModelMonitoringSchema.Builder

clearOneof(Descriptors.OneofDescriptor oneof)

public ModelMonitoringSchema.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
Name Description
oneof OneofDescriptor
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

clearPredictionFields()

public ModelMonitoringSchema.Builder clearPredictionFields()

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Returns
Type Description
ModelMonitoringSchema.Builder

clone()

public ModelMonitoringSchema.Builder clone()
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

getDefaultInstanceForType()

public ModelMonitoringSchema getDefaultInstanceForType()
Returns
Type Description
ModelMonitoringSchema

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
Type Description
Descriptor
Overrides

getFeatureFields(int index)

public ModelMonitoringSchema.FieldSchema getFeatureFields(int index)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema

getFeatureFieldsBuilder(int index)

public ModelMonitoringSchema.FieldSchema.Builder getFeatureFieldsBuilder(int index)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

getFeatureFieldsBuilderList()

public List<ModelMonitoringSchema.FieldSchema.Builder> getFeatureFieldsBuilderList()

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Returns
Type Description
List<Builder>

getFeatureFieldsCount()

public int getFeatureFieldsCount()

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Returns
Type Description
int

getFeatureFieldsList()

public List<ModelMonitoringSchema.FieldSchema> getFeatureFieldsList()

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Returns
Type Description
List<FieldSchema>

getFeatureFieldsOrBuilder(int index)

public ModelMonitoringSchema.FieldSchemaOrBuilder getFeatureFieldsOrBuilder(int index)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchemaOrBuilder

getFeatureFieldsOrBuilderList()

public List<? extends ModelMonitoringSchema.FieldSchemaOrBuilder> getFeatureFieldsOrBuilderList()

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Returns
Type Description
List<? extends com.google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchemaOrBuilder>

getGroundTruthFields(int index)

public ModelMonitoringSchema.FieldSchema getGroundTruthFields(int index)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema

getGroundTruthFieldsBuilder(int index)

public ModelMonitoringSchema.FieldSchema.Builder getGroundTruthFieldsBuilder(int index)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

getGroundTruthFieldsBuilderList()

public List<ModelMonitoringSchema.FieldSchema.Builder> getGroundTruthFieldsBuilderList()

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Returns
Type Description
List<Builder>

getGroundTruthFieldsCount()

public int getGroundTruthFieldsCount()

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Returns
Type Description
int

getGroundTruthFieldsList()

public List<ModelMonitoringSchema.FieldSchema> getGroundTruthFieldsList()

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Returns
Type Description
List<FieldSchema>

getGroundTruthFieldsOrBuilder(int index)

public ModelMonitoringSchema.FieldSchemaOrBuilder getGroundTruthFieldsOrBuilder(int index)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchemaOrBuilder

getGroundTruthFieldsOrBuilderList()

public List<? extends ModelMonitoringSchema.FieldSchemaOrBuilder> getGroundTruthFieldsOrBuilderList()

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Returns
Type Description
List<? extends com.google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchemaOrBuilder>

getPredictionFields(int index)

public ModelMonitoringSchema.FieldSchema getPredictionFields(int index)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema

getPredictionFieldsBuilder(int index)

public ModelMonitoringSchema.FieldSchema.Builder getPredictionFieldsBuilder(int index)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchema.Builder

getPredictionFieldsBuilderList()

public List<ModelMonitoringSchema.FieldSchema.Builder> getPredictionFieldsBuilderList()

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Returns
Type Description
List<Builder>

getPredictionFieldsCount()

public int getPredictionFieldsCount()

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Returns
Type Description
int

getPredictionFieldsList()

public List<ModelMonitoringSchema.FieldSchema> getPredictionFieldsList()

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Returns
Type Description
List<FieldSchema>

getPredictionFieldsOrBuilder(int index)

public ModelMonitoringSchema.FieldSchemaOrBuilder getPredictionFieldsOrBuilder(int index)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.FieldSchemaOrBuilder

getPredictionFieldsOrBuilderList()

public List<? extends ModelMonitoringSchema.FieldSchemaOrBuilder> getPredictionFieldsOrBuilderList()

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Returns
Type Description
List<? extends com.google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchemaOrBuilder>

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Type Description
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
Type Description
boolean
Overrides

mergeFrom(ModelMonitoringSchema other)

public ModelMonitoringSchema.Builder mergeFrom(ModelMonitoringSchema other)
Parameter
Name Description
other ModelMonitoringSchema
Returns
Type Description
ModelMonitoringSchema.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public ModelMonitoringSchema.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Name Description
input CodedInputStream
extensionRegistry ExtensionRegistryLite
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides
Exceptions
Type Description
IOException

mergeFrom(Message other)

public ModelMonitoringSchema.Builder mergeFrom(Message other)
Parameter
Name Description
other Message
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

mergeUnknownFields(UnknownFieldSet unknownFields)

public final ModelMonitoringSchema.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

removeFeatureFields(int index)

public ModelMonitoringSchema.Builder removeFeatureFields(int index)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.Builder

removeGroundTruthFields(int index)

public ModelMonitoringSchema.Builder removeGroundTruthFields(int index)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.Builder

removePredictionFields(int index)

public ModelMonitoringSchema.Builder removePredictionFields(int index)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameter
Name Description
index int
Returns
Type Description
ModelMonitoringSchema.Builder

setFeatureFields(int index, ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder setFeatureFields(int index, ModelMonitoringSchema.FieldSchema value)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameters
Name Description
index int
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

setFeatureFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder setFeatureFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

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 is an array, ensure that the sequence in 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].

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema feature_fields = 1;

Parameters
Name Description
index int
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public ModelMonitoringSchema.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
Name Description
field FieldDescriptor
value Object
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

setGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder setGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema value)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameters
Name Description
index int
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

setGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder setGroundTruthFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

Target /ground truth names of the model.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;

Parameters
Name Description
index int
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

setPredictionFields(int index, ModelMonitoringSchema.FieldSchema value)

public ModelMonitoringSchema.Builder setPredictionFields(int index, ModelMonitoringSchema.FieldSchema value)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameters
Name Description
index int
value ModelMonitoringSchema.FieldSchema
Returns
Type Description
ModelMonitoringSchema.Builder

setPredictionFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

public ModelMonitoringSchema.Builder setPredictionFields(int index, ModelMonitoringSchema.FieldSchema.Builder builderForValue)

Prediction output names of the model. The requirements are the same as the 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.

repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema prediction_fields = 2;

Parameters
Name Description
index int
builderForValue ModelMonitoringSchema.FieldSchema.Builder
Returns
Type Description
ModelMonitoringSchema.Builder

setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)

public ModelMonitoringSchema.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
Name Description
field FieldDescriptor
index int
value Object
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides

setUnknownFields(UnknownFieldSet unknownFields)

public final ModelMonitoringSchema.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
Name Description
unknownFields UnknownFieldSet
Returns
Type Description
ModelMonitoringSchema.Builder
Overrides