Class ModelEvaluation.BiasConfig.Builder (3.38.0)

public static final class ModelEvaluation.BiasConfig.Builder extends GeneratedMessageV3.Builder<ModelEvaluation.BiasConfig.Builder> implements ModelEvaluation.BiasConfigOrBuilder

Configuration for bias detection.

Protobuf type google.cloud.aiplatform.v1beta1.ModelEvaluation.BiasConfig

Static Methods

getDescriptor()

public static final Descriptors.Descriptor getDescriptor()
Returns
TypeDescription
Descriptor

Methods

addAllLabels(Iterable<String> values)

public ModelEvaluation.BiasConfig.Builder addAllLabels(Iterable<String> values)

Positive labels selection on the target field.

repeated string labels = 2;

Parameter
NameDescription
valuesIterable<String>

The labels to add.

Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

This builder for chaining.

addLabels(String value)

public ModelEvaluation.BiasConfig.Builder addLabels(String value)

Positive labels selection on the target field.

repeated string labels = 2;

Parameter
NameDescription
valueString

The labels to add.

Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

This builder for chaining.

addLabelsBytes(ByteString value)

public ModelEvaluation.BiasConfig.Builder addLabelsBytes(ByteString value)

Positive labels selection on the target field.

repeated string labels = 2;

Parameter
NameDescription
valueByteString

The bytes of the labels to add.

Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

This builder for chaining.

addRepeatedField(Descriptors.FieldDescriptor field, Object value)

public ModelEvaluation.BiasConfig.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

build()

public ModelEvaluation.BiasConfig build()
Returns
TypeDescription
ModelEvaluation.BiasConfig

buildPartial()

public ModelEvaluation.BiasConfig buildPartial()
Returns
TypeDescription
ModelEvaluation.BiasConfig

clear()

public ModelEvaluation.BiasConfig.Builder clear()
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

clearBiasSlices()

public ModelEvaluation.BiasConfig.Builder clearBiasSlices()

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

clearField(Descriptors.FieldDescriptor field)

public ModelEvaluation.BiasConfig.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
NameDescription
fieldFieldDescriptor
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

clearLabels()

public ModelEvaluation.BiasConfig.Builder clearLabels()

Positive labels selection on the target field.

repeated string labels = 2;

Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

This builder for chaining.

clearOneof(Descriptors.OneofDescriptor oneof)

public ModelEvaluation.BiasConfig.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
NameDescription
oneofOneofDescriptor
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

clone()

public ModelEvaluation.BiasConfig.Builder clone()
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

getBiasSlices()

public ModelEvaluationSlice.Slice.SliceSpec getBiasSlices()

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Returns
TypeDescription
ModelEvaluationSlice.Slice.SliceSpec

The biasSlices.

getBiasSlicesBuilder()

public ModelEvaluationSlice.Slice.SliceSpec.Builder getBiasSlicesBuilder()

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Returns
TypeDescription
ModelEvaluationSlice.Slice.SliceSpec.Builder

getBiasSlicesOrBuilder()

public ModelEvaluationSlice.Slice.SliceSpecOrBuilder getBiasSlicesOrBuilder()

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Returns
TypeDescription
ModelEvaluationSlice.Slice.SliceSpecOrBuilder

getDefaultInstanceForType()

public ModelEvaluation.BiasConfig getDefaultInstanceForType()
Returns
TypeDescription
ModelEvaluation.BiasConfig

getDescriptorForType()

public Descriptors.Descriptor getDescriptorForType()
Returns
TypeDescription
Descriptor
Overrides

getLabels(int index)

public String getLabels(int index)

Positive labels selection on the target field.

repeated string labels = 2;

Parameter
NameDescription
indexint

The index of the element to return.

Returns
TypeDescription
String

The labels at the given index.

getLabelsBytes(int index)

public ByteString getLabelsBytes(int index)

Positive labels selection on the target field.

repeated string labels = 2;

Parameter
NameDescription
indexint

The index of the value to return.

Returns
TypeDescription
ByteString

The bytes of the labels at the given index.

getLabelsCount()

public int getLabelsCount()

Positive labels selection on the target field.

repeated string labels = 2;

Returns
TypeDescription
int

The count of labels.

getLabelsList()

public ProtocolStringList getLabelsList()

Positive labels selection on the target field.

repeated string labels = 2;

Returns
TypeDescription
ProtocolStringList

A list containing the labels.

hasBiasSlices()

public boolean hasBiasSlices()

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Returns
TypeDescription
boolean

Whether the biasSlices field is set.

internalGetFieldAccessorTable()

protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
TypeDescription
FieldAccessorTable
Overrides

isInitialized()

public final boolean isInitialized()
Returns
TypeDescription
boolean
Overrides

mergeBiasSlices(ModelEvaluationSlice.Slice.SliceSpec value)

public ModelEvaluation.BiasConfig.Builder mergeBiasSlices(ModelEvaluationSlice.Slice.SliceSpec value)

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Parameter
NameDescription
valueModelEvaluationSlice.Slice.SliceSpec
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

mergeFrom(ModelEvaluation.BiasConfig other)

public ModelEvaluation.BiasConfig.Builder mergeFrom(ModelEvaluation.BiasConfig other)
Parameter
NameDescription
otherModelEvaluation.BiasConfig
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)

public ModelEvaluation.BiasConfig.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
NameDescription
inputCodedInputStream
extensionRegistryExtensionRegistryLite
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides
Exceptions
TypeDescription
IOException

mergeFrom(Message other)

public ModelEvaluation.BiasConfig.Builder mergeFrom(Message other)
Parameter
NameDescription
otherMessage
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

mergeUnknownFields(UnknownFieldSet unknownFields)

public final ModelEvaluation.BiasConfig.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

setBiasSlices(ModelEvaluationSlice.Slice.SliceSpec value)

public ModelEvaluation.BiasConfig.Builder setBiasSlices(ModelEvaluationSlice.Slice.SliceSpec value)

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Parameter
NameDescription
valueModelEvaluationSlice.Slice.SliceSpec
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

setBiasSlices(ModelEvaluationSlice.Slice.SliceSpec.Builder builderForValue)

public ModelEvaluation.BiasConfig.Builder setBiasSlices(ModelEvaluationSlice.Slice.SliceSpec.Builder builderForValue)

Specification for how the data should be sliced for bias. It contains a list of slices, with limitation of two slices. The first slice of data will be the slice_a. The second slice in the list (slice_b) will be compared against the first slice. If only a single slice is provided, then slice_a will be compared against "not slice_a". Below are examples with feature "education" with value "low", "medium", "high" in the dataset:

Example 1:

 bias_slices = [{'education': 'low'}]

A single slice provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'medium' or 'high'.

Example 2:

 bias_slices = [{'education': 'low'},
                {'education': 'high'}]

Two slices provided. In this case, slice_a is the collection of data with 'education' equals 'low', and slice_b is the collection of data with 'education' equals 'high'.

.google.cloud.aiplatform.v1beta1.ModelEvaluationSlice.Slice.SliceSpec bias_slices = 1;

Parameter
NameDescription
builderForValueModelEvaluationSlice.Slice.SliceSpec.Builder
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

setField(Descriptors.FieldDescriptor field, Object value)

public ModelEvaluation.BiasConfig.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
NameDescription
fieldFieldDescriptor
valueObject
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

setLabels(int index, String value)

public ModelEvaluation.BiasConfig.Builder setLabels(int index, String value)

Positive labels selection on the target field.

repeated string labels = 2;

Parameters
NameDescription
indexint

The index to set the value at.

valueString

The labels to set.

Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder

This builder for chaining.

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

public ModelEvaluation.BiasConfig.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
NameDescription
fieldFieldDescriptor
indexint
valueObject
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides

setUnknownFields(UnknownFieldSet unknownFields)

public final ModelEvaluation.BiasConfig.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
NameDescription
unknownFieldsUnknownFieldSet
Returns
TypeDescription
ModelEvaluation.BiasConfig.Builder
Overrides