GENDATC

Generation of two spherical classes with different variances

    A = GENDATC(N,K,U,LABTYPE)

Input
N	Vector with class sizes (default: [50,50])
K	Dimensionality of the dataset (default: 2)
U	Mean of class 1 (default: 0)
LABTYPE	'crisp' or 'soft' labels (default: 'crisp')

Output
A	Dataset

Description

Generation of a K-dimensional 2-class dataset A of N objects.  Both classes are spherically Gaussian distributed.

Class 1 has the identity matrix as covariance matrix and  mean U. If U is a scalar then [U,0,0,..] is used as class mean.  Class 2 has also the identity matrix as covariance matrix, except  for a variance of 4 for the first two features. Its mean is 0.  Class priors are P(1) = P(2) = 0.5.

If N is a vector of sizes, exactly N(I) objects are generated  for class I, I = 1,2.

The default means result in a class overlap of 0.16.

LABTYPE defines the desired label type: 'crisp' or 'soft'. In the  latter case true posterior probabilities are set for the labels.

Defaults: N = [50,50], K = 2, U = 0, LABTYPE = 'crisp'.

See also

datasets, prdatasets,