Struct linfa::composing::platt_scaling::PlattValidParams
source · pub struct PlattValidParams<F, O> { /* private fields */ }
Expand description
Parameters for Platt’s Newton method
Trait Implementations§
source§impl<F: Clone, O: Clone> Clone for PlattValidParams<F, O>
impl<F: Clone, O: Clone> Clone for PlattValidParams<F, O>
source§fn clone(&self) -> PlattValidParams<F, O>
fn clone(&self) -> PlattValidParams<F, O>
Returns a copy of the value. Read more
1.0.0 · source§fn clone_from(&mut self, source: &Self)
fn clone_from(&mut self, source: &Self)
Performs copy-assignment from
source
. Read moresource§impl<'a, F: Float, O: 'a> FitWith<'a, ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<bool>, Dim<[usize; 1]>>, PlattError> for PlattValidParams<F, O>where
O: PredictInplace<Array2<F>, Array1<F>>,
impl<'a, F: Float, O: 'a> FitWith<'a, ArrayBase<OwnedRepr<F>, Dim<[usize; 2]>>, ArrayBase<OwnedRepr<bool>, Dim<[usize; 1]>>, PlattError> for PlattValidParams<F, O>where
O: PredictInplace<Array2<F>, Array1<F>>,
source§fn fit_with(
&self,
obj: O,
ds: &DatasetBase<Array2<F>, Array1<bool>>
) -> Result<Self::ObjectOut, PlattError>
fn fit_with(
&self,
obj: O,
ds: &DatasetBase<Array2<F>, Array1<bool>>
) -> Result<Self::ObjectOut, PlattError>
Calibrate another model with Platt scaling
This function takes another model and binary decision dataset and calibrates it to produce probability values. The returned model therefore implements the prediction trait for probability targets.