Struct VarianceThreshold 

pub struct VarianceThreshold<F> { /* private fields */ }

An unfitted variance-threshold feature selector.

During fitting the population variance of every column is computed (NaN values are treated as zero — use an imputer upstream if needed). Columns whose variance is less than or equal to the configured threshold are discarded during transformation.

The default threshold is 0.0, which removes features with exactly zero variance (i.e. constant columns).

Examples

use ferrolearn_preprocess::feature_selection::VarianceThreshold;
use ferrolearn_core::traits::{Fit, Transform};
use ndarray::array;

let sel = VarianceThreshold::<f64>::new(0.0);
// Column 1 is constant — will be removed
let x = array![[1.0, 7.0], [2.0, 7.0], [3.0, 7.0]];
let fitted = sel.fit(&x, &()).unwrap();
let out = fitted.transform(&x).unwrap();
assert_eq!(out.ncols(), 1);

Implementations

impl<F: Float + Send + Sync + 'static> VarianceThreshold<F>

pub fn new(threshold: F) -> Self

Create a new VarianceThreshold with the given threshold.

Pass F::zero() (the default) to remove only constant features.

Errors

Returns FerroError::InvalidParameter if threshold is negative.

pub fn threshold(&self) -> F

Return the variance threshold.

Trait Implementations

impl<F: Clone> Clone for VarianceThreshold<F>

fn clone(&self) -> VarianceThreshold<F>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for VarianceThreshold<F>

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

Formats the value using the given formatter.

impl<F: Float + Send + Sync + 'static> Default for VarianceThreshold<F>

fn default() -> Self

Returns the “default value” for a type.

impl<F: Float + Send + Sync + 'static> Fit<ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ()> for VarianceThreshold<F>

fn fit( &self, x: &Array2<F>, _y: &(), ) -> Result<FittedVarianceThreshold<F>, FerroError>

Fit by computing per-column population variances.

Errors

Returns FerroError::InsufficientSamples if the input has zero rows. Returns FerroError::InvalidParameter if the threshold is negative.

type Fitted = FittedVarianceThreshold<F>

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.

impl PipelineTransformer<f64> for VarianceThreshold<f64>

fn fit_pipeline( &self, x: &Array2<f64>, _y: &Array1<f64>, ) -> Result<Box<dyn FittedPipelineTransformer<f64>>, FerroError>

Fit using the pipeline interface; y is ignored.

Errors

Propagates errors from Fit::fit.