Package com.google.cloud.aiplatform.v1beta1

Interface ModelEvaluation.BiasConfigOrBuilder

All Superinterfaces:
com.google.protobuf.MessageLiteOrBuilder, com.google.protobuf.MessageOrBuilder
All Known Implementing Classes:
ModelEvaluation.BiasConfig, ModelEvaluation.BiasConfig.Builder
Enclosing class:
ModelEvaluation
public static interface ModelEvaluation.BiasConfigOrBuilder extends com.google.protobuf.MessageOrBuilder

  • Method Summary

    Modifier and Type
    Method
    Description
    ModelEvaluationSlice.Slice.SliceSpec
    getBiasSlices()
    Specification for how the data should be sliced for bias.
    ModelEvaluationSlice.Slice.SliceSpecOrBuilder
    getBiasSlicesOrBuilder()
    Specification for how the data should be sliced for bias.
    String
    getLabels(int index)
    Positive labels selection on the target field.
    com.google.protobuf.ByteString
    getLabelsBytes(int index)
    Positive labels selection on the target field.
    int
    getLabelsCount()
    Positive labels selection on the target field.
    List<String>
    getLabelsList()
    Positive labels selection on the target field.
    boolean
    hasBiasSlices()
    Specification for how the data should be sliced for bias.

    Methods inherited from interface com.google.protobuf.MessageLiteOrBuilder

    isInitialized

    Methods inherited from interface com.google.protobuf.MessageOrBuilder

    findInitializationErrors, getAllFields, getDefaultInstanceForType, getDescriptorForType, getField, getInitializationErrorString, getOneofFieldDescriptor, getRepeatedField, getRepeatedFieldCount, getUnknownFields, hasField, hasOneof

  • Method Details

    • hasBiasSlices

      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:
      Whether the biasSlices field is set.

    • getBiasSlices

      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:
      The biasSlices.

    • getBiasSlicesOrBuilder

      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;

    • getLabelsList

      List<String> getLabelsList()
       Positive labels selection on the target field.
      repeated string labels = 2;
      Returns:
      A list containing the labels.

    • getLabelsCount

      int getLabelsCount()
       Positive labels selection on the target field.
      repeated string labels = 2;
      Returns:
      The count of labels.

    • getLabels

      String getLabels(int index)
       Positive labels selection on the target field.
      repeated string labels = 2;
      Parameters:
      index - The index of the element to return.
      Returns:
      The labels at the given index.

    • getLabelsBytes

      com.google.protobuf.ByteString getLabelsBytes(int index)
       Positive labels selection on the target field.
      repeated string labels = 2;
      Parameters:
      index - The index of the value to return.
      Returns:
      The bytes of the labels at the given index.