Description Details Author(s) References See Also
ExactSampling contains functions that estimate the risk associated to a kNN prediction function (either in regression or binary classification) based on resampling method (leave-p-out cross-validation or bootstrap). It also contain a function knn.search
to obtain the list of k nearest neighbors for each point in the sample, and a function to compute the empirical risk of a kNN prediction function.
Package: | ExactSampling |
Type: | Package |
Version: | 1.0 |
Date: | 2013-01-22 |
License: | GPL(>=2) |
KAI LI Maintainer: Koskas Michel<Michel.Koskas@agroparistech.fr>
Celisse, A.and Mary-Huard, T. (2011) Exact Cross-Validation for kNN and applications to passive and active learning in classification. Journal de la SFdS, 152, 3.
knn.emp
for the empirical estimation of the risk, knn.boot
for an exact bootstrap estimation, knn.cv
for the cross-validated estimation for the kNN algorithm, and knn.search
to obtain the k nearest neighbors.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.