WeLoveDoctor

Written by

byun1114

in

기본적으로 다음의 웹페이지에서 내용을 참고했다.

https://blog.pabii.co/wordcloud-r/

library(tm)
library(SnowballC)
library(wordcloud)
library(RColorBrewer)
A = read.csv("~/R/1.csv", stringsAsFactors = F)

A = Corpus(VectorSource(A))
B = tm_map(A, PlainTextDocument)

B = tm_map(B, content_transformer(tolower))
B = tm_map(B, removePunctuation)
B = tm_map(B, removeWords, stopwords('english'))
B = tm_map(B, removeNumbers)
excludes = c("with", "for", "were", "and", "was", "may", "performed", "high", "this", "the", "using", "cases", "can", "showed", "methods", "The", "results", "case", "similar", "revealed")
B = tm_map(B, removeWords, excludes)
# B = tm_map(B, stemDocument)
wordcloud(B, random.order = F, colors = brewer.pal(8, "Dark2"), rot.per = 0.1, max.words = 100)

Stemming 과정에서 단어가 짤리는게 꽤 나온다.

More posts