Struct LearningCurve 

pub struct LearningCurve {
    pub train_sizes: Vec<usize>,
    pub train_scores: Vec<Vec<f64>>,
    pub val_scores: Vec<Vec<f64>>,
}

Output of learning_curve.

Both train and validation scores are returned as [size][fold]: the gap between them at each size is the actual diagnostic (high bias vs. high variance), so neither can be dropped.

Fields

train_sizes: Vec<usize>

Absolute training-set sizes actually used, ascending.

train_scores: Vec<Vec<f64>>

Training scores as [size][fold].

val_scores: Vec<Vec<f64>>

Validation scores as [size][fold].

Implementations

impl LearningCurve

pub fn mean_train_scores(&self) -> Vec<f64>

Mean training score at each size (one value per size).

pub fn mean_val_scores(&self) -> Vec<f64>

Mean validation score at each size (one value per size).

Trait Implementations

impl Clone for LearningCurve

fn clone(&self) -> LearningCurve

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LearningCurve

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

Formats the value using the given formatter.