最近在学习关于LDA模型的知识，做一些细粒度观点挖掘。在学习过程中发现原来R中还有一个专门的LDA包。

我用LDA为两个文本文档建立了一个主题模型，分别是a和B。文档a与计算机科学高度相关，文档B与地球科学高度相关。然后我用这个命令训练lda。

text<- c(A,B) # introduced above
     r <- Corpus(VectorSource(text)) # create corpus object
     r <- tm_map(r, tolower) # convert all text to lower case
     r <- tm_map(r, removePunctuation) 
     r <- tm_map(r, removeNumbers)
     r <- tm_map(r, removeWords, stopwords("english"))
     r.dtm <- TermDocumentMatrix(r, control = list(minWordLength = 3))    
     my_lda <- LDA(r.dtm,2)

现在我想用my_lda来预测一个新文档的上下文，比如C，我想看看它是否与计算机科学或地球科学相关。我知道如果我用这个代码来预测。

 x<-C# a new document (a long string) introduced above for prediction
     rp <- Corpus(VectorSource(x)) # create corpus object
     rp <- tm_map(rp, tolower) # convert all text to lower case
     rp <- tm_map(rp, removePunctuation) 
     rp <- tm_map(rp, removeNumbers)
     rp <- tm_map(rp, removeWords, stopwords("english"))
     rp.dtm <- TermDocumentMatrix(rp, control = list(minWordLength = 3))    
     test.topics <- posterior(my_lda,rp.dtm)

可以从我的LDA topicmodel中提取最有可能的术语，并将这些黑箱数字名称替换为您想要的任意数量的名称。

> library(topicmodels)
> data(AssociatedPress)
> 
> train <- AssociatedPress[1:100]
> test <- AssociatedPress[101:150]
> 
> train.lda <- LDA(train,2)
> 
> #returns those black box names
> test.topics <- posterior(train.lda,test)$topics
> head(test.topics)
              1           2
[1,] 0.57245696 0.427543038
[2,] 0.56281568 0.437184320
[3,] 0.99486888 0.005131122
[4,] 0.45298547 0.547014530
[5,] 0.72006712 0.279932882
[6,] 0.03164725 0.968352746
> #extract top 5 terms for each topic and assign as variable names
> colnames(test.topics) <- apply(terms(train.lda,5),2,paste,collapse=",")
> head(test.topics)
     percent,year,i,new,last new,people,i,soviet,states
[1,]              0.57245696                0.427543038
[2,]              0.56281568                0.437184320
[3,]              0.99486888                0.005131122
[4,]              0.45298547                0.547014530
[5,]              0.72006712                0.279932882
[6,]              0.03164725                0.968352746
> #round to one topic if you'd prefer
> test.topics <- apply(test.topics,1,function(x) colnames(test.topics)[which.max(x)])
> head(test.topics)
[1] "percent,year,i,new,last"    "percent,year,i,new,last"    "percent,year,i,new,last"   
[4] "new,people,i,soviet,states" "percent,year,i,new,last"    "new,people,i,soviet,states"