Package smile.validation

Interface LOOCV

public interface LOOCV
Leave-one-out cross validation. LOOCV uses a single observation from the original sample as the validation data, and the remaining observations as the training data. This is repeated such that each observation in the sample is used once as the validation data. This is the same as a K-fold cross-validation with K being equal to the number of observations in the original sample. Leave-one-out cross-validation is usually very expensive from a computational point of view because of the large number of times the training process is repeated.

  • Method Details

    • of

      static int[][] of(int n)
      Returns the training sample index for each round.
      Parameters:
      n - the number of samples.
      Returns:
      The index of training instances for each round. The left one of i-th round is i-th sample.

    • classification

      static <T, M extends Classifier<T>> ClassificationMetrics classification(T[] x, int[] y, BiFunction<T[],int[],M> trainer)
      Runs leave-one-out cross validation tests.
      Type Parameters:
      T - the data type of samples.
      M - the model type.
      Parameters:
      x - the training data.
      y - the class labels of training data.
      trainer - the lambda to train the model.
      Returns:
      the validation results.

    • classification

      static ClassificationMetrics classification(Formula formula, DataFrame data, BiFunction<Formula,DataFrame,DataFrameClassifier> trainer)
      Runs leave-one-out cross validation tests.
      Parameters:
      formula - the model formula.
      data - the training data.
      trainer - the lambda to train the model.
      Returns:
      the validation results.

    • regression

      static <T, M extends Regression<T>> RegressionMetrics regression(T[] x, double[] y, BiFunction<T[],double[],M> trainer)
      Runs leave-one-out cross validation tests.
      Type Parameters:
      T - the data type of samples.
      M - the model type.
      Parameters:
      x - the training data.
      y - the responsible variable of training data.
      trainer - the lambda to train the model.
      Returns:
      the validation results.

    • regression

      static RegressionMetrics regression(Formula formula, DataFrame data, BiFunction<Formula,DataFrame,DataFrameRegression> trainer)
      Runs leave-one-out cross validation tests.
      Parameters:
      formula - the model formula.
      data - the training data.
      trainer - the lambda to train the model.
      Returns:
      the validation results.