错误：protect（）：运行文本分析时保护堆栈溢出

Question

我正在尝试对RStudio（在MacBook Pro上）R版本3.4.1中的大型文本语音进行线性判别分析。基于其他问题，我设置了最大ppsize。

options(expressions = 5e5)

下面是一个可重现的示例，它会抛出相同的错误。有什么建议吗？

library(tm)
library(MASS)

shakespeare.v<-scan("https://archive.org/stream/in.ernet.dli.2015.182303/2015.182303.Shakespeare-Complete-Works_djvu.txt",what="character",sep="\n",)


docs<-Corpus(VectorSource(shakespeare.v))

toSpace <- content_transformer(function(x, pattern) {return 
(gsub(pattern, " ", x))})

docs<-tm_map(docs,content_transformer(tolower))

docs<-tm_map(docs, removePunctuation)
docs<-tm_map(docs, removeNumbers)
docs<-tm_map(docs, toSpace, "page")
docs<-tm_map(docs, stripWhitespace)
docs<-tm_map(docs, toSpace, "filename")

full.words.l<-gsub("[^[:alnum:][:space:]']", " ", docs)
full.words.l<-strsplit(full.words.l, "\\s+")

full.words.v<-unlist(full.words.l)

full.l.3000 <- split(full.words.v, 
ceiling(seq_along(full.words.v)/3000))


chunks.v.3000<-unlist(full.l.3000)


chunks.c.3000<-Corpus(VectorSource(full.l.3000))

matrix.3000<-matrix(chunks.c.3000)

dtm.3000<-DocumentTermMatrix(chunks.c.3000)
m.3000<-as.matrix(dtm.3000)
df.3000<-as.data.frame(m.3000)

lda.3000<-lda(full.l.3000~.,
      df.3000, na.action = "na.omit", CV=TRUE)