bindiego
9/15/2015 - 11:21 AM

tfidf in R by using package "tm" (text mining)

tfidf in R by using package "tm" (text mining)

tfidf.r
content_copyfile_download
#read 1000 txt articles from directory data/txt
corpus  <-Corpus(DirSource("data/txt"), readerControl = list(blank.lines.skip=TRUE));
#some preprocessing
corpus <- tm_map(corpus, removeWords, stopwords("english"))
corpus <- tm_map(corpus, stripWhitespace)
corpus <- tm_map(corpus, stemDocument, language="english")
#creating term matrix with TF-IDF weighting
terms <-DocumentTermMatrix(corpus,control = list(weighting = function(x) weightTfIdf(x, normalize = FALSE)))

#or compute cosine distance among documents
dissimilarity(tdm, method = "cosine")