1030文字雲.R

install.packages("rJava")
install.packages("Rwordseg", repos="http://R-Forge.R-project.org")
install.packages("tm")
install.packages("tmcn", repos="http://R-Forge.R-project.org", type="source")
install.packages("wordcloud")
install.packages("XML")
install.packages("RCurl")

library(tm)
setwd("C:/Users/yylee/Desktop/")
rm(d.corpus)
d.corpus <- Corpus(DirSource("b"), list(language = NA))


#清除標點符號#
d.corpus <- tm_map(d.corpus, removePunctuation)

#清除數字#
d.corpus <- tm_map(d.corpus, removeNumbers)

#清除大小寫英文與數字#
d.corpus <- tm_map(d.corpus, function(word) {
  gsub("[A-Za-z0-9]", "", word)
})

#載入資料庫，協助斷詞#
strwords <-  c("部落格", "獨立評論", "讀者投書")
insertWords(strwords, strtype=rep("n", length(strwords)), numfreq=rep(1000, length(strwords)))

#利用rJava去連結java分詞工具ansj來進行斷詞。 
#另外，斷詞後的詞彙有詞性，例如動詞、名詞、形容詞、介係詞等等，我們只挑出名詞來進行分析。
d.corpus <- tm_map(d.corpus[1:1002], segmentCN, nature = TRUE)
d.corpus <- tm_map(d.corpus, function(sentence) {
  noun <- lapply(sentence, function(w) {
    w[names(w) == "n"]
  })
  unlist(noun)
})
d.corpus <- Corpus(VectorSource(d.corpus))

#建立 text matrix#
d.corpus <- tm_map(d.corpus, PlainTextDocument)
tdm <- TermDocumentMatrix(d.corpus, control =list(wordLengths = c(2, Inf)))

#我們可以看看TermDocumentMatrix裡面，前兩篇文章的前10個關鍵字
inspect(tdm[1:10, 1:1002])

#文字雲，要用3.0.2以上版本的R#
library(RColorBrewer)
library(wordcloud)
m1 <- as.matrix(tdm)
v <- sort(rowSums(m1), decreasing = TRUE)
d <- data.frame(word = names(v), freq = v)
wordcloud(d$word, d$freq, min.freq =3, random.order = F, ordered.colors = F, 
          colors = rainbow(length(row.names(m1))))

#趴兔
#增加停用字符#
myStopWords <- c(stopwords(), "訂閱","電子","會員","雜誌","報","天下","通知","人","月","訂戶","信","名單","人員","人")
d.corpus <- tm_map(d.corpus, removeWords, myStopWords)

#檢查停用字符#
head(myStopWords, 20)
head(removeWords)

#建立 text matrix#
d.corpus <- tm_map(d.corpus, PlainTextDocument)
tdm <- TermDocumentMatrix(d.corpus, control =list(wordLengths = c(2, Inf)))

#我們可以看看TermDocumentMatrix裡面，前兩篇文章的前10個關鍵字
inspect(tdm[1:10, 1:1002])

#文字雲，要用3.0.2以上版本的R#
library(RColorBrewer)
library(wordcloud)
m1 <- as.matrix(tdm)
v <- sort(rowSums(m1), decreasing = TRUE)
d <- data.frame(word = names(v), freq = v)
wordcloud(d$word, d$freq, min.freq =10, random.order = F, ordered.colors = F, 
          colors = rainbow(length(row.names(m1))))


README.md

test