public sealed class ModelEvaluation.Types.BiasConfig : IMessage<ModelEvaluation.Types.BiasConfig>, IEquatable<ModelEvaluation.Types.BiasConfig>, IDeepCloneable<ModelEvaluation.Types.BiasConfig>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class ModelEvaluation.Types.BiasConfig.
public ModelEvaluationSlice.Types.Slice.Types.SliceSpec BiasSlices { get; set; }
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'.
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'.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-14 UTC."],[[["\u003cp\u003eThis documentation details the \u003ccode\u003eModelEvaluation.Types.BiasConfig\u003c/code\u003e class within the Vertex AI v1beta1 API, used for configuring bias detection in model evaluations.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eBiasConfig\u003c/code\u003e class implements interfaces such as \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, allowing it to be used with protobuf messages and deep cloning.\u003c/p\u003e\n"],["\u003cp\u003eThe class offers two constructors: a default constructor (\u003ccode\u003eBiasConfig()\u003c/code\u003e) and one that takes another \u003ccode\u003eBiasConfig\u003c/code\u003e object as an argument for creating a copy (\u003ccode\u003eBiasConfig(BiasConfig other)\u003c/code\u003e).\u003c/p\u003e\n"],["\u003cp\u003eIt includes properties like \u003ccode\u003eBiasSlices\u003c/code\u003e, which specifies how data is sliced for bias analysis, and \u003ccode\u003eLabels\u003c/code\u003e, for defining positive labels on the target field.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eBiasSlices\u003c/code\u003e property uses the \u003ccode\u003eModelEvaluationSlice.Types.Slice.Types.SliceSpec\u003c/code\u003e to define data slices, supporting up to two slices for comparison (slice_a vs. slice_b, or slice_a vs. not slice_a).\u003c/p\u003e\n"]]],[],null,[]]
