Struct LinearPredictorBlock 

pub struct LinearPredictorBlock<X> {
    pub x: X,
}

Linear predictor block backed by a DesignMatrix.

This is the explicit adapter from matrix-based predictors to the more general PredictorBlock extension point.

Fields

x: X

Design matrix used by this predictor.

Implementations

impl<X> LinearPredictorBlock<X>

pub fn new(x: X) -> Self

Wraps a design matrix as a predictor block.

pub fn into_inner(self) -> X

Returns the wrapped design matrix.

Trait Implementations

impl<X: Clone> Clone for LinearPredictorBlock<X>

fn clone(&self) -> LinearPredictorBlock<X>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<X: Copy> Copy for LinearPredictorBlock<X>

impl<X: Debug> Debug for LinearPredictorBlock<X>

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

Formats the value using the given formatter.

impl<X: Default> Default for LinearPredictorBlock<X>

fn default() -> LinearPredictorBlock<X>

Returns the “default value” for a type.

impl<X: Eq> Eq for LinearPredictorBlock<X>

impl<X: PartialEq> PartialEq for LinearPredictorBlock<X>

fn eq(&self, other: &LinearPredictorBlock<X>) -> 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<X> PredictorBlock for LinearPredictorBlock<X>

where X: DesignMatrix,

fn nrows(&self) -> usize

Number of observations.

fn nparams(&self) -> usize

Number of local coefficients consumed by this block.

fn eta_row(&self, row: usize, beta: &[f64]) -> f64

Predictor contribution for one row.

fn add_gradient(&self, scores: &[f64], _: &[f64], grad: &mut [f64])

Adds the gradient contribution implied by scores into grad.

fn validate(&self) -> Result<(), ModelError>

Validates internal block consistency.

impl<X> StructuralPartialEq for LinearPredictorBlock<X>