Last active
June 2, 2016 22:12
-
-
Save s13731105/819f6387220892917e20 to your computer and use it in GitHub Desktop.
用 R 進行中文 text Mining
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
library(XML) | |
library(RCurl) | |
library(tm) | |
library(tmcn) | |
library(Rwordseg) | |
setwd("C:/test") | |
d.corpus <-Corpus(DirSource("/test/doc"), readerControl = list(language="UTF-8")) | |
#上兩行為抓取本機文字檔, 餘皆同網路上說明文字 | |
d.corpus <- tm_map(d.corpus, removePunctuation) | |
d.corpus <- tm_map(d.corpus, removeNumbers) | |
d.corpus <- tm_map(d.corpus, function(word) { | |
gsub("[A-Za-z0-9]", "", word) | |
}) | |
words <- readLines("http://wubi.sogou.com/dict/download_txt.php?id=9182") | |
words <- toTrad(words) | |
insertWords(words) | |
d.corpus <- tm_map(d.corpus[1:100], 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)) | |
myStopWords <- c(stopwordsCN(), "編輯", "時間", "標題", "發信", "實業", "作者") | |
d.corpus <- tm_map(d.corpus, removeWords, myStopWords) | |
head(myStopWords, 20) | |
tdm <- TermDocumentMatrix(d.corpus, control = list(wordLengths = c(2, Inf))) | |
inspect(tdm[1:10, 1:2]) | |
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)))) | |
d.dtm <- DocumentTermMatrix(d.corpus, control = list(wordLengths = c(2, Inf))) | |
inspect(d.dtm[1:10, 1:2]) | |
findFreqTerms(d.dtm, 30) | |
findAssocs(d.dtm, "同學", 0.5) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment