#Loading Packages
library(tm)
library(wordcloud)
library(RColorBrewer)
speech="/Users/GregDuncan/Desktop/bills.txt"
modi_txt = readLines(speech)
modi<-Corpus(VectorSource(modi_txt))
modi_data<-tm_map(modi,stripWhitespace)
modi_data<-tm_map(modi_data,tolower)
modi_data<-tm_map(modi_data,removeNumbers)
modi_data<-tm_map(modi_data,removePunctuation)
modi_data<-tm_map(modi_data,removeWords, stopwords(“english”))
tdm_modi<-TermDocumentMatrix (modi_data) #Creates a TDM
TDM1<-as.matrix(tdm_modi) #Convert this into a matrix format
v = sort(rowSums(TDM1), decreasing = TRUE) #Gives you the frequencies for every word
Summary(v)
wordcloud (modi_data, scale=c(5,0.5), max.words=1, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, “Dark2″))
所以我正试图从文档中创建一个词云。我试图用Rscript运行它,我遇到了一个问题,比如这个
enter Error: unexpected input in "modi_data<-tm_map(modi_data,removeWords, stopwords(?"
Execution haltedcode here
和
unexpected input in "wordcloud (modi_data, scale=c(5,0.5), max.words=1, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, �"
我对R很陌生,所以我想学习基础知识。我不知道有经验的人是否可以快速看到问题
答案 0 :(得分:0)
请注意以下更改,并且应该运行。我使用了tm包中的数据集crude
。
library(tm)
library(wordcloud)
library(RColorBrewer)
data(crude)
modi_txt <- crude
modi<-Corpus(VectorSource(modi_txt))
modi_data<-tm_map(modi,stripWhitespace)
modi_data<-tm_map(modi_data,tolower)
modi_data<-tm_map(modi_data,removeNumbers)
modi_data<-tm_map(modi_data,removePunctuation)
modi_data<-tm_map(modi_data, removeWords, stopwords("english")) # NB quote marks were wrong. This can happen if you copied from Word, for example
modi_data<-tm_map(modi_data, PlainTextDocument) # NB: added this call
tdm_modi<-TermDocumentMatrix (modi_data)
TDM1<-as.matrix(tdm_modi)
v = sort(rowSums(TDM1), decreasing = TRUE)
summary(v) # NB need lower case "s"
wordcloud (modi_data, scale=c(5,0.5), max.words=1, random.order=FALSE, rot.per=0.35,
use.r.layout=FALSE, colors=brewer.pal(8, "Dark2")) # NB had to fix quotes for "D...
这里的结果很奇怪,但您可能想要试验wordcloud
个参数。