smile.validation

Class LOOCV

java.lang.Object

smile.validation.LOOCV

public class LOOCV
extends java.lang.Object

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.

Field Summary

Fields

Modifier and Type	Field and Description
int[]	test The index of testing instances.
int[][]	train The index of training instances.

Constructor Summary

Constructors

Constructor and Description
LOOCV(int n) Constructor.

Method Summary

Modifier and Type	Method and Description
static int[]	classification(smile.data.formula.Formula formula, smile.data.DataFrame data, java.util.function.BiFunction<smile.data.formula.Formula,smile.data.DataFrame,DataFrameClassifier> trainer) Runs leave-one-out cross validation tests.
static <T> int[]	classification(T[] x, int[] y, java.util.function.BiFunction<T[],int[],Classifier<T>> trainer) Runs leave-one-out cross validation tests.
static double[]	regression(smile.data.formula.Formula formula, smile.data.DataFrame data, java.util.function.BiFunction<smile.data.formula.Formula,smile.data.DataFrame,DataFrameRegression> trainer) Runs leave-one-out cross validation tests.
static <T> double[]	regression(T[] x, double[] y, java.util.function.BiFunction<T[],double[],Regression<T>> trainer) Runs leave-one-out cross validation tests.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

train

public final int[][] train

The index of training instances.

test

public final int[] test

The index of testing instances.

Constructor Detail

LOOCV

public LOOCV(int n)

Constructor.

Parameters:

n - the number of samples.

Method Detail

classification

public static <T> int[] classification(T[] x,
                                       int[] y,
                                       java.util.function.BiFunction<T[],int[],Classifier<T>> trainer)

Runs leave-one-out cross validation tests.

Returns:

the predictions.

classification

public static int[] classification(smile.data.formula.Formula formula,
                                   smile.data.DataFrame data,
                                   java.util.function.BiFunction<smile.data.formula.Formula,smile.data.DataFrame,DataFrameClassifier> trainer)

Runs leave-one-out cross validation tests.

Returns:

the predictions.

regression

public static <T> double[] regression(T[] x,
                                      double[] y,
                                      java.util.function.BiFunction<T[],double[],Regression<T>> trainer)

Runs leave-one-out cross validation tests.

Returns:

the predictions.

regression

public static double[] regression(smile.data.formula.Formula formula,
                                  smile.data.DataFrame data,
                                  java.util.function.BiFunction<smile.data.formula.Formula,smile.data.DataFrame,DataFrameRegression> trainer)

Runs leave-one-out cross validation tests.

Returns:

the predictions.