Struct ExplanationParameters 

#[non_exhaustive]
pub struct ExplanationParameters {
    pub top_k: i32,
    pub output_indices: Option<ListValue>,
    pub method: Option<Method>,
    /* private fields */
}

Available on crate features dataset-service or deployment-resource-pool-service or endpoint-service or job-service or model-service or pipeline-service or prediction-service only.

Parameters to configure explaining for Model’s predictions.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

top_k: i32

If populated, returns attributions for top K indices of outputs (defaults to 1). Only applies to Models that predicts more than one outputs (e,g, multi-class Models). When set to -1, returns explanations for all outputs.

output_indices: Option<ListValue>

If populated, only returns attributions that have output_index contained in output_indices. It must be an ndarray of integers, with the same shape of the output it’s explaining.

If not populated, returns attributions for top_k indices of outputs. If neither top_k nor output_indices is populated, returns the argmax index of the outputs.

Only applicable to Models that predict multiple outputs (e,g, multi-class Models that predict multiple classes).

method: Option<Method>

Implementations

impl ExplanationParameters

pub fn new() -> Self

pub fn set_top_k<T: Into<i32>>(self, v: T) -> Self

Sets the value of top_k.

Example

let x = ExplanationParameters::new().set_top_k(42);

pub fn set_output_indices<T>(self, v: T) -> Self

where T: Into<ListValue>,

Sets the value of output_indices.

Example

use wkt::ListValue;
let x = ExplanationParameters::new().set_output_indices(ListValue::default()/* use setters */);

pub fn set_or_clear_output_indices<T>(self, v: Option<T>) -> Self

where T: Into<ListValue>,

Sets or clears the value of output_indices.

Example

use wkt::ListValue;
let x = ExplanationParameters::new().set_or_clear_output_indices(Some(ListValue::default()/* use setters */));
let x = ExplanationParameters::new().set_or_clear_output_indices(None::<ListValue>);

pub fn set_method<T: Into<Option<Method>>>(self, v: T) -> Self

Sets the value of method.

Note that all the setters affecting method are mutually exclusive.

Example

use google_cloud_aiplatform_v1::model::SampledShapleyAttribution;
let x = ExplanationParameters::new().set_method(Some(
    google_cloud_aiplatform_v1::model::explanation_parameters::Method::SampledShapleyAttribution(SampledShapleyAttribution::default().into())));

pub fn sampled_shapley_attribution( &self, ) -> Option<&Box<SampledShapleyAttribution>>

The value of method if it holds a SampledShapleyAttribution, None if the field is not set or holds a different branch.

pub fn set_sampled_shapley_attribution<T: Into<Box<SampledShapleyAttribution>>>( self, v: T, ) -> Self

Sets the value of method to hold a SampledShapleyAttribution.

Note that all the setters affecting method are mutually exclusive.

Example

use google_cloud_aiplatform_v1::model::SampledShapleyAttribution;
let x = ExplanationParameters::new().set_sampled_shapley_attribution(SampledShapleyAttribution::default()/* use setters */);
assert!(x.sampled_shapley_attribution().is_some());
assert!(x.integrated_gradients_attribution().is_none());
assert!(x.xrai_attribution().is_none());
assert!(x.examples().is_none());

pub fn integrated_gradients_attribution( &self, ) -> Option<&Box<IntegratedGradientsAttribution>>

The value of method if it holds a IntegratedGradientsAttribution, None if the field is not set or holds a different branch.

pub fn set_integrated_gradients_attribution<T: Into<Box<IntegratedGradientsAttribution>>>( self, v: T, ) -> Self

Sets the value of method to hold a IntegratedGradientsAttribution.

Note that all the setters affecting method are mutually exclusive.

Example

use google_cloud_aiplatform_v1::model::IntegratedGradientsAttribution;
let x = ExplanationParameters::new().set_integrated_gradients_attribution(IntegratedGradientsAttribution::default()/* use setters */);
assert!(x.integrated_gradients_attribution().is_some());
assert!(x.sampled_shapley_attribution().is_none());
assert!(x.xrai_attribution().is_none());
assert!(x.examples().is_none());

pub fn xrai_attribution(&self) -> Option<&Box<XraiAttribution>>

The value of method if it holds a XraiAttribution, None if the field is not set or holds a different branch.

pub fn set_xrai_attribution<T: Into<Box<XraiAttribution>>>(self, v: T) -> Self

Sets the value of method to hold a XraiAttribution.

Note that all the setters affecting method are mutually exclusive.

Example

use google_cloud_aiplatform_v1::model::XraiAttribution;
let x = ExplanationParameters::new().set_xrai_attribution(XraiAttribution::default()/* use setters */);
assert!(x.xrai_attribution().is_some());
assert!(x.sampled_shapley_attribution().is_none());
assert!(x.integrated_gradients_attribution().is_none());
assert!(x.examples().is_none());

pub fn examples(&self) -> Option<&Box<Examples>>

The value of method if it holds a Examples, None if the field is not set or holds a different branch.

pub fn set_examples<T: Into<Box<Examples>>>(self, v: T) -> Self

Sets the value of method to hold a Examples.

Note that all the setters affecting method are mutually exclusive.

Example

use google_cloud_aiplatform_v1::model::Examples;
let x = ExplanationParameters::new().set_examples(Examples::default()/* use setters */);
assert!(x.examples().is_some());
assert!(x.sampled_shapley_attribution().is_none());
assert!(x.integrated_gradients_attribution().is_none());
assert!(x.xrai_attribution().is_none());

Trait Implementations

impl Clone for ExplanationParameters

fn clone(&self) -> ExplanationParameters

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ExplanationParameters

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ExplanationParameters

fn default() -> ExplanationParameters

Returns the “default value” for a type.

impl Message for ExplanationParameters

fn typename() -> &'static str

The typename of this message.

impl PartialEq for ExplanationParameters

fn eq(&self, other: &ExplanationParameters) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for ExplanationParameters