mysnn: Stabilized Nearest Neighbor Classifier

In snn: Stabilized Nearest Neighbor Classifier

Description

Implement the stabilized nearest neighbor classification algorithm to predict the label of a new input using a training data set. The stabilized nearest neighbor classifier contains the K-nearest neighbor classifier and the optimal weighted nearest neighbor classifier as two special cases.

Usage

mysnn(train, test, lambda)

Arguments

train	Matrix of training data sets. An n by (d+1) matrix, where n is the sample size and d is the dimension. The last column is the class label.
test	Vector of a test point. It also admits a matrix input with each row representing a new test point.
lambda	Tuning parameter controlling the degree of stabilization of the nearest neighbor classification procedure. The larger lambda, the more stable the procedure is.

Details

The tuning parameter lambda can be tuned via cross-validation, see cv.tune for the tuning procedure.

Value

It returns the predicted class label of the new test point. If input is a matrix, it returns a vector which contains the predicted class labels of all the new test points.

Author(s)

Wei Sun, Xingye Qiao, and Guang Cheng

References

W. Sun, X. Qiao, and G. Cheng (2015) Stabilized Nearest Neighbor Classifier and Its Statistical Properties. Available at arxiv.org/abs/1405.6642.

Examples

	# Training data
	set.seed(1)
	n = 100
	d = 10
	DATA = mydata(n, d)

	# Testing data
	set.seed(2015)
	ntest = 100  
	TEST = mydata(ntest, d)
	TEST.x = TEST[,1:d]
	
	# stabilized nearest neighbor classifier
	mysnn(DATA, TEST.x, lambda = 10)

snn documentation built on May 1, 2019, 7:05 p.m.