Finding 2 & 3 word Phrases Using R TM Package

Question

I am trying to find a code that actually works to find the most frequently used two and three word phrases in R text mining package (maybe there is another package for it th

Answer 1

This is part 5 of the FAQ of the tm package:

5. Can I use bigrams instead of single tokens in a term-document matrix?

Yes. RWeka provides a tokenizer for arbitrary n-grams which can be directly passed on to the term-document matrix constructor. E.g.:

  library("RWeka")
  library("tm")

  data("crude")

  BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 2, max = 2))
  tdm <- TermDocumentMatrix(crude, control = list(tokenize = BigramTokenizer))

  inspect(tdm[340:345,1:10])

Answer 2

Try this code.

library(tm)
library(SnowballC)
library(class)
library(wordcloud)

keywords <- read.csv(file.choose(), header = TRUE, na.strings=c("NA","-","?"))
keywords_doc <- Corpus(VectorSource(keywords$"use your column that you need"))
keywords_doc <- tm_map(keywords_doc, removeNumbers)
keywords_doc <- tm_map(keywords_doc, tolower)
keywords_doc <- tm_map(keywords_doc, stripWhitespace)
keywords_doc <- tm_map(keywords_doc, removePunctuation)
keywords_doc <- tm_map(keywords_doc, PlainTextDocument)
keywords_doc <- tm_map(keywords_doc, stemDocument)

This is the bigrams or tri grams section that you could use

BigramTokenizer <-  function(x)
unlist(lapply(ngrams(words(x), 2), paste, collapse = " "), use.names = FALSE)
# creating of document matrix
keywords_matrix <- TermDocumentMatrix(keywords_doc, control = list(tokenize = BigramTokenizer))

# remove sparse terms 
keywords_naremoval <- removeSparseTerms(keywords_matrix, 0.95)

# Frequency of the words appearing
keyword.freq <- rowSums(as.matrix(keywords_naremoval))
subsetkeyword.freq <-subset(keyword.freq, keyword.freq >=20)
frequentKeywordSubsetDF <- data.frame(term = names(subsetkeyword.freq), freq = subsetkeyword.freq) 

# Sorting of the words
frequentKeywordDF <- data.frame(term = names(keyword.freq), freq = keyword.freq)
frequentKeywordSubsetDF <- frequentKeywordSubsetDF[with(frequentKeywordSubsetDF, order(-frequentKeywordSubsetDF$freq)), ]
frequentKeywordDF <- frequentKeywordDF[with(frequentKeywordDF, order(-frequentKeywordDF$freq)), ]

# Printing of the words
wordcloud(frequentKeywordDF$term, freq=frequentKeywordDF$freq, random.order = FALSE, rot.per=0.35, scale=c(5,0.5), min.freq = 30, colors = brewer.pal(8,"Dark2"))

Hope this helps. This is an entire code that you could use.

Answer 3

This is my own made up creation for different purposes but I think may applicable to your needs too:

#User Defined Functions
Trim <- function (x) gsub("^\\s+|\\s+$", "", x)

breaker <- function(x) unlist(strsplit(x, "[[:space:]]|(?=[.!?*-])", perl=TRUE))

strip <- function(x, digit.remove = TRUE, apostrophe.remove = FALSE){
    strp <- function(x, digit.remove, apostrophe.remove){
        x2 <- Trim(tolower(gsub(".*?($|'|[^[:punct:]]).*?", "\\1", as.character(x))))
        x2 <- if(apostrophe.remove) gsub("'", "", x2) else x2
        ifelse(digit.remove==TRUE, gsub("[[:digit:]]", "", x2), x2)
    }
unlist(lapply(x, function(x) Trim(strp(x =x, digit.remove = digit.remove, 
    apostrophe.remove = apostrophe.remove)) ))
}

unblanker <- function(x)subset(x, nchar(x)>0)

#Fake Text Data
x <- "I like green eggs and ham.  They are delicious.  They taste so yummy.  I'm talking about ham and eggs of course"

#The code using Base R to Do what you want
breaker(x)
strip(x)
words <- unblanker(breaker(strip(x)))
textDF <- as.data.frame(table(words))
textDF$characters <- sapply(as.character(textDF$words), nchar)
textDF2 <- textDF[order(-textDF$characters, textDF$Freq), ]
rownames(textDF2) <- 1:nrow(textDF2)
textDF2
subset(textDF2, characters%in%2:3)

Answer 4

You can pass in a custom tokenizing function to tm's DocumentTermMatrix function, so if you have package tau installed it's fairly straightforward.

library(tm); library(tau);

tokenize_ngrams <- function(x, n=3) return(rownames(as.data.frame(unclass(textcnt(x,method="string",n=n)))))

texts <- c("This is the first document.", "This is the second file.", "This is the third text.")
corpus <- Corpus(VectorSource(texts))
matrix <- DocumentTermMatrix(corpus,control=list(tokenize=tokenize_ngrams))

Where n in the tokenize_ngrams function is the number of words per phrase. This feature is also implemented in package RTextTools, which further simplifies things.

library(RTextTools)
texts <- c("This is the first document.", "This is the second file.", "This is the third text.")
matrix <- create_matrix(texts,ngramLength=3)

This returns a class of DocumentTermMatrix for use with package tm.

Answer 5

The corpus library has a function called term_stats that does what you want:

library(corpus)
corpus <- gutenberg_corpus(55) # Project Gutenberg #55, _The Wizard of Oz_
text_filter(corpus)$drop_punct <- TRUE # ignore punctuation
term_stats(corpus, ngrams = 2:3)
##    term             count support
## 1  of the             336       1
## 2  the scarecrow      208       1
## 3  to the             185       1
## 4  and the            166       1
## 5  said the           152       1
## 6  in the             147       1
## 7  the lion           141       1
## 8  the tin            123       1
## 9  the tin woodman    114       1
## 10 tin woodman        114       1
## 11 i am                84       1
## 12 it was              69       1
## 13 in a                64       1
## 14 the great           63       1
## 15 the wicked          61       1
## 16 wicked witch        60       1
## 17 at the              59       1
## 18 the little          59       1
## 19 the wicked witch    58       1
## 20 back to             57       1
## ⋮  (52511 rows total)

Here, count is the number of appearances, and support is the number of documents containing the term.

Answer 6

I add a similar problem by using tm and ngram packages. After debugging mclapply, I saw there where problems on documents with less than 2 words with the following error

   input 'x' has nwords=1 and n=2; must have nwords >= n

So I've added a filter to remove document with low word count number:

    myCorpus.3 <- tm_filter(myCorpus.2, function (x) {
      length(unlist(strsplit(stringr::str_trim(x$content), '[[:blank:]]+'))) > 1
    })

Then my tokenize function looks like:

bigramTokenizer <- function(x) {
  x <- as.character(x)

  # Find words
  one.list <- c()
  tryCatch({
    one.gram <- ngram::ngram(x, n = 1)
    one.list <- ngram::get.ngrams(one.gram)
  }, 
  error = function(cond) { warning(cond) })

  # Find 2-grams
  two.list <- c()
  tryCatch({
    two.gram <- ngram::ngram(x, n = 2)
    two.list <- ngram::get.ngrams(two.gram)
  },
  error = function(cond) { warning(cond) })

  res <- unlist(c(one.list, two.list))
  res[res != '']
}

Then you can test the function with:

dtmTest <- lapply(myCorpus.3, bigramTokenizer)

And finally:

dtm <- DocumentTermMatrix(myCorpus.3, control = list(tokenize = bigramTokenizer))