Struct CounterfactualKernel 

pub struct CounterfactualKernel<State = Untrained> { /* private fields */ }

Counterfactual Kernel Approximation

Implements kernel methods for counterfactual reasoning: “What would have happened if the treatment had been different?”

Mathematical Background

Counterfactual: Y(t) | X=x, T=t’, Y=y Uses nearest-neighbor matching in kernel feature space with propensity score adjustment.

Examples

use sklears_kernel_approximation::causal_kernels::{CounterfactualKernel, CausalKernelConfig};
use scirs2_core::ndarray::array;
use sklears_core::traits::{Fit, Transform};

let config = CausalKernelConfig::default();
let cf = CounterfactualKernel::new(config);

let data = array![[1.0, 0.0, 2.0], [2.0, 1.0, 5.0]];
let fitted = cf.fit(&data, &()).unwrap();

Implementations

impl CounterfactualKernel<Untrained>

pub fn new(config: CausalKernelConfig) -> Self

Create a new counterfactual kernel

pub fn with_components(n_components: usize) -> Self

Create with default configuration

impl CounterfactualKernel<Trained>

pub fn propensity_scores(&self) -> &Array1<Float>

Get propensity scores from training data

pub fn estimate_ite(&self, sample: &Array2<Float>) -> Result<Float>

Estimate individual treatment effect for a sample

Trait Implementations

impl<State: Clone> Clone for CounterfactualKernel<State>

fn clone(&self) -> CounterfactualKernel<State>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<State: Debug> Debug for CounterfactualKernel<State>

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

Formats the value using the given formatter.

impl Estimator for CounterfactualKernel<Untrained>

type Config = CausalKernelConfig

Configuration type for the estimator

type Error = SklearsError

Error type for the estimator

type Float = f64

The numeric type used by this estimator

fn config(&self) -> &Self::Config

Get estimator configuration

fn validate_config(&self) -> Result<(), SklearsError>

Validate estimator configuration with detailed error context

fn check_compatibility( &self, n_samples: usize, n_features: usize, ) -> Result<(), SklearsError>

Check if estimator is compatible with given data dimensions

fn metadata(&self) -> EstimatorMetadata

Get estimator metadata

impl Fit<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>, ()> for CounterfactualKernel<Untrained>

type Fitted = CounterfactualKernel<Trained>

The fitted model type

fn fit(self, x: &Array2<Float>, _y: &()) -> Result<Self::Fitted>

Fit the model to the provided data with validation

fn fit_with_validation( self, x: &X, y: &Y, _x_val: Option<&X>, _y_val: Option<&Y>, ) -> Result<(Self::Fitted, FitMetrics), SklearsError>

where Self: Sized,

Fit with custom validation and early stopping

impl Transform<ArrayBase<OwnedRepr<f64>, Dim<[usize; 2]>>> for CounterfactualKernel<Trained>

fn transform(&self, x: &Array2<Float>) -> Result<Array2<Float>>

Transform the input data