Struct forester::split::BestSplitRandomFeature [−][src]
pub struct BestSplitRandomFeature { /* fields omitted */ }
Find best split, in a number of randomly selected features.
Normally, exactly n_features
are tested. However, there are two notable exceptions:
- if a "perfect split" is encountered (split criterion is exactly zero) the search stops early.
- if after no split has been found after
n_features
the search continues until it finds one or runs out of features.
Methods
impl BestSplitRandomFeature
[src]
impl BestSplitRandomFeature
Trait Implementations
impl SplitFinder for BestSplitRandomFeature
[src]
impl SplitFinder for BestSplitRandomFeature
fn find_split<Sample, Training: ?Sized>(
&self,
data: &mut Training
) -> Option<Split<Sample::ThetaSplit, Sample::Feature>> where
Sample: SampleDescription,
Training: TrainingData<Sample>,
[src]
fn find_split<Sample, Training: ?Sized>(
&self,
data: &mut Training
) -> Option<Split<Sample::ThetaSplit, Sample::Feature>> where
Sample: SampleDescription,
Training: TrainingData<Sample>,
Attempt to find a split for the given data set.
Auto Trait Implementations
impl Send for BestSplitRandomFeature
impl Send for BestSplitRandomFeature
impl Sync for BestSplitRandomFeature
impl Sync for BestSplitRandomFeature