Enum MultiClass 

pub enum MultiClass {
    Ovr,
    CrammerSinger,
}

Multiclass strategy for LinearSVC.

Mirrors sklearn.svm.LinearSVC’s multi_class parameter (sklearn/svm/_classes.py:239, constraint {"ovr", "crammer_singer"}, default "ovr"). Ovr trains one binary classifier per class (the default, using the penalty/loss/dual solver matrix); CrammerSinger runs the joint Crammer-Singer multiclass SVM solver (Solver_MCSVM_CS, liblinear/linear.cpp:493-787, solver type 4).

When CrammerSinger is selected, _get_liblinear_solver_type returns 4 regardless of penalty/loss/dual (_base.py:1017,1020-1021), so the penalty/loss/dual parameters are ignored and the joint solver runs.

Variants

Ovr

One-vs-rest: one binary sub-problem per class (the default).

CrammerSinger

Joint Crammer-Singer multiclass SVM (Solver_MCSVM_CS, solver type 4, linear.cpp:493-787). Ignores penalty/loss/dual (_base.py:1017).

Trait Implementations

impl Clone for MultiClass

fn clone(&self) -> MultiClass

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Copy for MultiClass

impl Debug for MultiClass

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

Formats the value using the given formatter.

impl Default for MultiClass

fn default() -> MultiClass

Returns the “default value” for a type.

impl Eq for MultiClass

impl PartialEq for MultiClass

fn eq(&self, other: &MultiClass) -> 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 StructuralPartialEq for MultiClass