stm包中的fitNewDocuments之后的新docnum列

如何解决stm包中的fitNewDocuments之后的新docnum列

我有5354条新闻文章的语料库，里面有很多重复的文章。使用stm包，我为906篇独特的文章运行了stm模型，并使用alignCorpus和fitNewDocuments将模型应用到语料库的其余部分。然后，我使用make.dt制作数据表，以生成整个语料库的theta值。此过程创建了一个新列，称为“ docnum”。我希望这是分配给每个文档的一列单独的数字，但是，它包括数字1-906，并且每个数字出现5-6次并且对应于相同的theta值集（请参见屏幕截图）。我认为它不应该这样做，但是我不明白为什么会这样。对于alignCorpus和fitNewDocuments函数（stm包的一部分），我在Internet上找不到很多帮助，因此，我很感谢您对这里可能发生的事情的任何想法或建议。很难为这种情况提供一个可重现的示例，因此下面提供了我的整个过程代码和所得excel文档的屏幕截图。

temp <- textProcessor(documents = NCA4_Data_3$text[1:906],Metadata = NCA4_Data_3[1:906,],lowercase = FALSE,removestopwords = TRUE,removenumbers = TRUE,removepunctuation = TRUE,ucp = TRUE,stem = FALSE,wordLengths = c(3,Inf),sparselevel = 1,language = "en",verbose = TRUE,onlycharacter = FALSE,striphtml = TRUE,customstopwords = 
                             c("https","ads","info","privacy","com","gov","via","email","print","embedded","said","will","says","can","like","also","photo","photograph","video","credit","sen","rep","dr","mr","ms","mrs","professor","prof"),v1 = FALSE)

out <- prepDocuments(temp$documents,temp$vocab,temp$Meta,lower.thresh = 1,upper.thresh = 815,subsample = NULL,verbose = TRUE)

STM.17 <- stm(documents = out$documents,vocab = out$vocab,K = 17,data = out$Meta,prevalence = ~media_type,max.em.its = 1000,init.type = "Spectral",verbose = TRUE)

#Now we process the remaining documents
temp <- textProcessor(documents = NCA4_Data_3$text[907:nrow(NCA4_Data_3)],Metadata = NCA4_Data_3[907:nrow(NCA4_Data_3),])

#note we don't run prepCorpus here because we don't want to drop any words- we want 
#every word that showed up in the old documents.
newdocs <- alignCorpus(new = temp,old.vocab = STM.17$vocab)

#we get some helpful Feedback on what has been retained and lost in the print out.
#and Now we can fit our new held-out documents
fitNewDocuments(model = STM.17,documents = newdocs$documents,newData = newdocs$Meta,origData = out$Meta,prevalencePrior="Covariate")

# #Export excel with theta values
stm.17.datatable <- make.dt(STM.17,Meta = NCA4_Data_3)
view(stm.17.datatable)
write.xlsx(stm.17.datatable,"~/Desktop/Oct.23.2020/stm.17.datatable.xlsx")

enter image description here