Google Cloud Ai Platform V1 Client - Class SampledShapleyAttribution (0.16.0)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class SampledShapleyAttribution.

An attribution method that approximates Shapley values for features that contribute to the label being predicted. A sampling strategy is used to approximate the value rather than considering all subsets of features.

Generated from protobuf message google.cloud.aiplatform.v1.SampledShapleyAttribution

Methods

__construct

Constructor.

Parameters
NameDescription
data array

Optional. Data for populating the Message object.

↳ path_count int

Required. The number of feature permutations to consider when approximating the Shapley values. Valid range of its value is [1, 50], inclusively.

getPathCount

Required. The number of feature permutations to consider when approximating the Shapley values.

Valid range of its value is [1, 50], inclusively.

Returns
TypeDescription
int

setPathCount

Required. The number of feature permutations to consider when approximating the Shapley values.

Valid range of its value is [1, 50], inclusively.

Parameter
NameDescription
var int
Returns
TypeDescription
$this