TEXT MINING

gistfile1.txt

Revised <- read.csv(file="D:/Data/Revised/revised data2013.csv", na.string = "NA", header = T, sep = ",", quote = "\"", dec = ".", fill = T, encoding="ANSI", stringsAsFactors = FALSE )
##載入檔案
library(tm)
library(tmcn)
library(rJava)
library(Rwordseg)
##一些TEXT MINING必用的套件


#將每個分詞切開統計次數，沒有切到"字"
Detail = Revised[c(16)]
R_corpus <- Corpus(DataframeSource(Detail,encoding="ANSI"))
##TEXT MINING的特殊物件格式，需要用這個來讀取要分析的文字檔案

#R_corpus <- tm_map(R_corpus, segmentCN)
#R_Corpus1 <- Corpus(VectorSource(R_corpus))
##上述兩個套件會把中文依字詞拆開來，但是今天我們的分析只是想整理一下文字檔的內容，不用切到詞彙

tdm <- TermDocumentMatrix(R_corpus)
##到這裡就整理出將鋸子拆開來的矩陣檔

#inspect(tdm[1:10,1:2])

library(wordcloud)
#載入文字雲套件

m1 <- as.matrix(tdm)
v <- sort(rowSums(m1),decreasing = TRUE)
#計算每個字詞的FREQ
d <- data.frame(word = names(v), freq = v)
#轉乘DATA FRAME的格式給文字雲套件吃

wordcloud(d$word, d$freq, min.freq = 10, random.order = F, ordered.colors = F, 
          colors = rainbow(length(row.names(m1))))

write.csv(d, "d.csv", row.names=F)