Function learning_curve 

pub fn learning_curve<E, F, C>(
    estimator: E,
    x: &Array2<Float>,
    y: &Array1<Float>,
    cv: &C,
    train_sizes: Option<Vec<f64>>,
    scoring: Option<Scoring>,
    confidence_level: Option<f64>,
) -> Result<LearningCurveResult>
where
    E: Clone + Fit<Array2<Float>, Array1<Float>, Fitted = F>,
    F: Clone + Predict<Array2<Float>, Array1<Float>> + Score<Array2<Float>, Array1<Float>, Float = f64>,
    C: CrossValidator,

Compute learning curves for an estimator

Determines cross-validated training and test scores for different training set sizes. This is useful to find out if we suffer from bias vs variance when we add more data to the training set.

Arguments

• estimator - The estimator to evaluate
• x - Training data features
• y - Training data targets
• cv - Cross-validation splitter
• train_sizes - Relative or absolute numbers of training examples that will be used to generate the learning curve
• scoring - Scoring method to use
• confidence_level - Confidence level for confidence bands (default: 0.95 for 95% confidence interval)