Struct Fosr2dResult 

#[non_exhaustive]
pub struct Fosr2dResult {
    pub intercept: Vec<f64>,
    pub beta: FdMatrix,
    pub fitted: FdMatrix,
    pub residuals: FdMatrix,
    pub r_squared_pointwise: Vec<f64>,
    pub r_squared: f64,
    pub beta_se: Option<FdMatrix>,
    pub lambda_s: f64,
    pub lambda_t: f64,
    pub gcv: f64,
    pub grid: Grid2d,
}

Result of 2D function-on-scalar regression.

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.

intercept: Vec<f64>

Intercept surface beta_0(s,t), flattened column-major (length m1*m2).

beta: FdMatrix

Coefficient surfaces beta_j(s,t), p x (m1*m2) matrix (row j = flattened beta_j).

fitted: FdMatrix

Fitted surface values, n x (m1*m2) matrix.

residuals: FdMatrix

Residual surfaces, n x (m1*m2) matrix.

r_squared_pointwise: Vec<f64>

Pointwise R^2(s,t), flattened (length m1*m2).

r_squared: f64

Global R^2 (average of pointwise).

beta_se: Option<FdMatrix>

Standard error surfaces for each beta_j (p x (m1*m2)), or None if the system is underdetermined.

lambda_s: f64

Smoothing parameter in the s-direction.

lambda_t: f64

Smoothing parameter in the t-direction.

gcv: f64

Generalised cross-validation score.

grid: Grid2d

Grid specification.

Implementations

impl Fosr2dResult

pub fn beta_surface(&self, j: usize) -> FdMatrix

Reshape the j-th coefficient surface into an m1 x m2 matrix.

Panics

Panics if j >= p (number of predictors).

pub fn r_squared_surface(&self) -> FdMatrix

Reshape pointwise R^2(s,t) into an m1 x m2 matrix.

pub fn residual_surface(&self, i: usize) -> FdMatrix

Reshape the residual for observation i into an m1 x m2 matrix.

Panics

Panics if i >= n (number of observations).

pub fn predict(&self, new_predictors: &FdMatrix) -> Result<FdMatrix, FdarError>

Predict functional surfaces for new predictors. Delegates to predict_fosr_2d.

Trait Implementations

impl Clone for Fosr2dResult

fn clone(&self) -> Fosr2dResult

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Fosr2dResult

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

Formats the value using the given formatter.

impl PartialEq for Fosr2dResult

fn eq(&self, other: &Fosr2dResult) -> bool

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for Fosr2dResult