使用 R TM 包查找 2 和 3 词短语

Question

我正在尝试找到一个代码，该代码实际上可以在 R 文本挖掘包中找到最常用的两个和三个单词短语（也许还有另一个我不知道的包）。我一直在尝试使用标记器，但似乎没有运气。

如果您过去曾处理过类似情况，您能否发布一个经过测试且实际有效的代码？非常感谢！

Answer 1

corpus 库有一个名为 term_stats 的函数，可以满足您的需求：

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)

这里，count 是出现次数，support 是包含该词条的文档数。

Answer 2

试试 tidytext 包

library(dplyr)
library(tidytext)
library(janeaustenr)
library(tidyr

)

假设我有一个包含评论列的数据框 CommentData，我想同时查找两个单词的出现。那就试试吧

bigram_filtered <- CommentData %>%
  unnest_tokens(bigram, Comment, token= "ngrams", n=2) %>%
  separate(bigram, c("word1","word2"), sep=" ") %>%
  filter(!word1 %in% stop_words$word,
         !word2 %in% stop_words$word) %>%
  count(word1, word2, sort=TRUE)

上面的代码创建了标记，然后删除了对分析没有帮助的停用词（例如 the、an、to 等），然后计算这些词的出现次数。然后，您将使用联合函数来组合单个单词并记录它们的出现。

bigrams_united <- bigram_filtered %>%
  unite(bigram, word1, word2, sep=" ")
bigrams_united

Answer 3

试试这个代码。

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)

这是您可以使用的二元组或三元组部分

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"))

希望这会有所帮助。这是您可以使用的完整代码。

Answer 4

我通过使用tm 和ngram 包添加了类似的问题。 调试mclapply后，发现2个字以下的文档有问题，出现如下错误

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

所以我添加了一个过滤器来删除低字数的文档：

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

然后我的 tokenize 函数看起来像：

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 != '']
}

然后您可以使用以下方法测试该功能：

dtmTest <- lapply(myCorpus.3, bigramTokenizer)

最后：

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

Answer 5

这是我自己为不同目的而创作的作品，但我认为也可能适用于您的需求：

#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 6

这是tm 包的FAQ 的第5 部分：

5.我可以在术语文档矩阵中使用二元组而不是单个标记吗？

是的。 RWeka 为任意 n-gram 提供了一个分词器，它可以是 直接传递给术语文档矩阵构造函数。例如：

  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 7

您可以将自定义标记函数传递给tm 的DocumentTermMatrix 函数，因此如果您安装了包tau，它就相当简单了。

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))

tokenize_ngrams 函数中的n 是每个短语的单词数。这个特性也在包RTextTools中实现，进一步简化了事情。

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)

这将返回一个 DocumentTermMatrix 类，用于包 tm。