inpdfr (version 0.1.8)

doKmeansClust: Performs a k-means cluster analysis on the basis of the word-occurrence data.frame.

Description

Performs a k-means cluster analysis on the basis of the word-occurrence data.frame using kmeans function.

Usage

doKmeansClust(wordF, nbClust = 4, nbIter = 10,
  algo = "Hartigan-Wong", getPlot = TRUE, mwidth = 800,
  mheight = 800, formatType = "png", ...)

Arguments

wordF

The data.frame containing word occurrences.

nbClust

The number of clusters.

nbIter

The number of iterations allowed.

algo

The algoritm used (see kmeans).

getPlot

If TRUE, save the k-means cluster plot in the RESULTS directory.

mwidth

The width of the plot in pixels.

mheight

The height of the plot in pixels.

formatType

The format for the output file ("eps", "pdf", "png", "svg", "tiff", "jpeg", "bmp").

...

Additional arguments from the kmeans function.

Value

An object of class kmeans (see kmeans).

Examples

# NOT RUN {
data("loremIpsum")
loremIpsum01 <- loremIpsum[1:100]
loremIpsum02 <- loremIpsum[101:200]
loremIpsum03 <- loremIpsum[201:300]
loremIpsum04 <- loremIpsum[301:400]
loremIpsum05 <- loremIpsum[401:500]
subDir <- "RESULTS"
dir.create(file.path(getwd(), subDir), showWarnings = FALSE)
write(x = loremIpsum01, file = "RESULTS/loremIpsum01.txt")
write(x = loremIpsum02, file = "RESULTS/loremIpsum02.txt")
write(x = loremIpsum03, file = "RESULTS/loremIpsum03.txt")
write(x = loremIpsum04, file = "RESULTS/loremIpsum04.txt")
write(x = loremIpsum05, file = "RESULTS/loremIpsum05.txt")
wordOccuDF <- getwordOccuDF(mywd = paste0(getwd(), "/RESULTS"), excludeSW = FALSE)
file.remove(list.files(full.names = TRUE, 
  path = paste0(getwd(), "/RESULTS"), pattern = "loremIpsum"))
doKmeansClust(wordF = wordOccuDF, nbClust = 2)
# }