public final class ModelMonitoringSchema extends GeneratedMessageV3 implements ModelMonitoringSchemaOrBuilder
The Model Monitoring Schema definition.
Protobuf type google.cloud.aiplatform.v1beta1.ModelMonitoringSchema
Inherited Members
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT)
com.google.protobuf.GeneratedMessageV3.<ListT>makeMutableCopy(ListT,int)
com.google.protobuf.GeneratedMessageV3.<T>emptyList(java.lang.Class<T>)
com.google.protobuf.GeneratedMessageV3.internalGetMapFieldReflection(int)
Static Fields
public static final int FEATURE_FIELDS_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int GROUND_TRUTH_FIELDS_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
public static final int PREDICTION_FIELDS_FIELD_NUMBER
| Field Value |
| Type |
Description |
int |
|
Static Methods
public static ModelMonitoringSchema getDefaultInstance()
public static final Descriptors.Descriptor getDescriptor()
public static ModelMonitoringSchema.Builder newBuilder()
public static ModelMonitoringSchema.Builder newBuilder(ModelMonitoringSchema prototype)
public static ModelMonitoringSchema parseDelimitedFrom(InputStream input)
public static ModelMonitoringSchema parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static ModelMonitoringSchema parseFrom(byte[] data)
| Parameter |
| Name |
Description |
data |
byte[]
|
public static ModelMonitoringSchema parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
public static ModelMonitoringSchema parseFrom(ByteString data)
public static ModelMonitoringSchema parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
public static ModelMonitoringSchema parseFrom(CodedInputStream input)
public static ModelMonitoringSchema parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
public static ModelMonitoringSchema parseFrom(InputStream input)
public static ModelMonitoringSchema parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
public static ModelMonitoringSchema parseFrom(ByteBuffer data)
public static ModelMonitoringSchema parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
public static Parser<ModelMonitoringSchema> parser()
Methods
public boolean equals(Object obj)
| Parameter |
| Name |
Description |
obj |
Object
|
Overrides
public ModelMonitoringSchema getDefaultInstanceForType()
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
|
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 |
|
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;
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
|
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> |
|
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
|
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 |
|
public List<ModelMonitoringSchema.FieldSchema> getGroundTruthFieldsList()
Target /ground truth names of the model.
repeated .google.cloud.aiplatform.v1beta1.ModelMonitoringSchema.FieldSchema ground_truth_fields = 3;
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
|
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> |
|
public Parser<ModelMonitoringSchema> getParserForType()
Overrides
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
|
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 |
|
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;
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
|
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> |
|
public int getSerializedSize()
| Returns |
| Type |
Description |
int |
|
Overrides
| Returns |
| Type |
Description |
int |
|
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Overrides
public final boolean isInitialized()
Overrides
public ModelMonitoringSchema.Builder newBuilderForType()
protected ModelMonitoringSchema.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
| Returns |
| Type |
Description |
Object |
|
Overrides
public ModelMonitoringSchema.Builder toBuilder()
public void writeTo(CodedOutputStream output)
Overrides
