chiMerge {dprep} | R Documentation |
This function performs supervised discretization using the Chi Merge method
chiMerge(data, varcon, alpha = 0.1)
data |
The name of the dataset to be discretize |
varcon |
Vector of continuous variables |
alpha |
The significance level |
In case of datasets containing negative values apply first a range normalization to change the range of the attributes values to an interval containing positive values. The discretization process slows down when the number of variables increases (say for more than 100 variables).
discdata |
A new data matrix containing the discretized features |
Edgar Acuna, Jaime Porras, and Carlos Lopez
Kantardzic M. (2003). Data Mining: Concepts, Models, methods, and Algorithms. John Wiley. New York.
disc.ef
, disc.ew
,disc.1r
,disc.mentr
#-----Discretization using the ChiMerge method data(my.iris) a=chiMerge(my.iris,1:4,alpha=0.05) #-----Applying chiMerge a dataset containing negative values #data(ionosphere) #normionos=rangenorm(ionosphere,"mmnorm") #b=chiMerge(normionos,1:32)