disc.mentr: Discretization using the minimum entropy criterion
Description
This function discretizes the continuous attributes of a data frame
using the minumum entropy criterion along with the minimum description length
as stopping rule.
Usage
disc.mentr(data, varcon,out=c("symb","num"))
Arguments
data
The name of the dataset to be discretized
varcon
A vector containing the indices of the columms
to be discretized
out
To get the data discretized in numerical form enter "num".
To get the data discretized in interval form enter "symb"
Value
Returns a matrix containing only discretized features.
References
Dougherty, J., Kohavi, R., and Sahami, M. (1995). Supervised and unsupervised discretization
of continuous features. ML-95.
## Not run: # #----Discretization using the entropy with Minimum Description Length.# data(bupa)# bupa.disc=disc.mentr(bupa,1:6,out="num")# ## End(Not run)