Struct ndarray_glm::logistic_link::Logit
source · [−]pub struct Logit {}
Expand description
The canonical link function for logistic regression is the logit function g(p) = log(p/(1-p)).
Trait Implementations
sourceimpl Link<Logistic<Logit>> for Logit
impl Link<Logistic<Logit>> for Logit
impl Canonical for Logit
Auto Trait Implementations
impl RefUnwindSafe for Logit
impl Send for Logit
impl Sync for Logit
impl Unpin for Logit
impl UnwindSafe for Logit
Blanket Implementations
sourceimpl<T> BorrowMut<T> for T where
T: ?Sized,
impl<T> BorrowMut<T> for T where
T: ?Sized,
const: unstable · sourcefn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
sourceimpl<T> Transform for T where
T: Canonical,
impl<T> Transform for T where
T: Canonical,
sourcefn nat_param<F>(
lin_pred: ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>
) -> ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>> where
F: Float,
fn nat_param<F>(
lin_pred: ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>
) -> ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>> where
F: Float,
By defintion this function is the identity function for canonical links.
sourcefn adjust_errors_variance<F>(
errors: ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>,
variance: ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>,
_lin_pred: &ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>
) -> (ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>, ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>) where
F: Float,
fn adjust_errors_variance<F>(
errors: ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>,
variance: ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>,
_lin_pred: &ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>
) -> (ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>, ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>) where
F: Float,
The canonical link function requires no transformation of the error and variance terms.
sourcefn d_nat_param<F>(
lin_pred: &ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>
) -> ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>> where
F: Float,
fn d_nat_param<F>(
lin_pred: &ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>>
) -> ArrayBase<OwnedRepr<F>, Dim<[usize; 1]>> where
F: Float,
The derivative of the transformation to the natural parameter. If it is zero in a region that the IRLS is in the algorithm may have difficulty converging. Read more