2

这是我用来创建带有频率列表的二元组的代码：

library(tm)
library(RWeka)
#data <- myData[,2]


tdm.generate <- function(string, ng){

  # tutorial on rweka - http://tm.r-forge.r-project.org/faq.html

  corpus <- Corpus(VectorSource(string)) # create corpus for TM processing
  corpus <- tm_map(corpus, content_transformer(tolower))
  corpus <- tm_map(corpus, removeNumbers) 
  corpus <- tm_map(corpus, removePunctuation)
  corpus <- tm_map(corpus, stripWhitespace)
  # corpus <- tm_map(corpus, removeWords, stopwords("english")) 
  options(mc.cores=1) # http://stackoverflow.com/questions/17703553/bigrams-instead-of-single-words-in-termdocument-matrix-using-r-and-rweka/20251039#20251039
  BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = ng, max = ng)) # create n-grams
  tdm <- TermDocumentMatrix(corpus, control = list(tokenize = BigramTokenizer)) # create tdm from n-grams
  tdm
}



source("GenerateTDM.R") # generatetdm function in appendix
tdm <- tdm.generate("The book The book The greatest The book",2)

tdm.matrix <- as.matrix(tdm)
topwords <- rowSums(tdm.matrix)
topwords <- as.numeric(topwords)
hist(topwords, breaks = 10)


tdm.matrix <- as.matrix(tdm)
topwords <- rowSums(tdm.matrix)
head(sort(topwords, decreasing = TRUE))

上述代码的结果是：

the     book greatest 
4        3        1

相反，我正在寻找显示二元组的结果，如下所示：

"the book" "book the"
  3          2

上面的代码需要改变什么才能得到上面的输出？

4

1 回答 1

1

您需要使用 VCorpus 而不是 Corpus，我遇到了同样的问题，您可以在此处查看更多详细信息

于 2017-09-05T20:14:21.493 回答