0
我从公开的审阅数据创建相关的主题模型并获取相当奇怪的错误。R中的主题建模
当我在我的CTM上调用术语(ctm1,5)时,我找回了文档的名称,而不是每个主题的前5个术语。
更详细我跑,
library(topicmodels)
library(data.table)
library(tm)
a <-Corpus(DirSource("~/text", encoding="UTF-8"), readerControl =
list(language="lat"))
a <- tm_map(a, removeNumbers)
a <- tm_map(a, removePunctuation)
a <- tm_map(a , stripWhitespace)
a <- tm_map(a, tolower)
a <- tm_map(a, removeWords, stopwords("english"))
a <- tm_map(a, stemDocument, language = "english")
adtm <-TermDocumentMatrix(a)
adtm <- removeSparseTerms(adtm, 0.75)
ctm1 <- CTM(adtm, 30, method = "VEM", control = NULL, model = NULL)
terms(ctm1, 5)
其返回
terms(ctm1)
Topic 1 "cmnt656661.txt"
(等)