Question

当我运行topicmodel代码时，我发生了一个非常奇怪的错误。基本上我有一个带有用户评论的.csv文件。我想创建一个dtm，每个注释都是一个文档。我拿了8k评论样本并使用了以下代码：

> #LOAD LIBRARYS
> 
> library(tm)
> library(SnowballC)
> library(stringr)
> library(tictoc)
> tic()
> 
> #SET FILE LOCATION
> file_loc <- "C:/Users/Andreas/Desktop/first8k.csv"
> 
> #LOAD DOCUMENTS
> Database <- read.csv(file_loc, header = FALSE)
> require(tm)
> 
> #PROCEED
> Database <- Corpus(DataframeSource(Database))
> 
> Database <-tm_map(Database,content_transformer(tolower))
> 
> 
> Database <- tm_map(Database, removePunctuation)
> Database <- tm_map(Database, removeNumbers)
> Database <- tm_map(Database, removeWords, stopwords("english"))
> Database <- tm_map(Database, stripWhitespace)
> 
> 
> myStopwords <- c("some", "individual", "stop","words")
> Database <- tm_map(Database, removeWords, myStopwords)
> 
> Database <- tm_map(Database,stemDocument) 
> 
> 
> dtm <- DocumentTermMatrix(Database,          control=list(minDocFreq=2,minWordLength=2))
> 
> row_total = apply(dtm, 1, sum)
> dtm.new = dtm[row_total>0,]
> 
> removeSparseTerms( dtm, .99)
>
>>Outcome:DocumentTermMatrix (documents: 12753, terms: 194)
>Non-/sparse entries: 66261/2407821
>Sparsity           : 97%
>Maximal term length: 11
>Weighting          : term frequency (tf)
> 
> #TOPICMODELLING
> 
> library(topicmodels)
> 
>  
> 
> burnin <- 100
> iter <- 500
> thin <- 100
> seed <-list(200,5,500,3700,1666)
> nstart <- 5
> best <- TRUE
> 
>  
> k <- 12
> 
>
> ldaOut <-LDA(dtm.new,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))
>

所以这个工作得很好。如果我再采取8k注释，csv文件，相同格式等样本，则会发生以下错误：

> library(tm)
> library(SnowballC)
> library(stringr)
> library(tictoc)
> tic()
> 
> #SET FILE LOCATION
> file_loc <- "C:/Users/Andreas/Desktop/try8k.csv"
> 
> #LOAD DOCUMENTS
> Database <- read.csv(file_loc, header = FALSE)
> require(tm)
> 
> #PROCEED
> Database <- Corpus(DataframeSource(Database))
> 
> Database <-tm_map(Database,content_transformer(tolower))
> 
> 
> Database <- tm_map(Database, removePunctuation)
> Database <- tm_map(Database, removeNumbers)
> Database <- tm_map(Database, removeWords, stopwords("english"))
> Database <- tm_map(Database, stripWhitespace)
> 
> 
> myStopwords <- c("some", "individual", "stop","words")
> Database <- tm_map(Database, removeWords, myStopwords)
> 
> Database <- tm_map(Database,stemDocument) 
> 
> dtm <- DocumentTermMatrix(Database,control=list(minDocFreq=2,minWordLength=2))
> 
> row_total = apply(dtm, 1, sum)
> dtm.new = dtm[row_total>0,]
> 
> removeSparseTerms( dtm, .99)
>
>>Outcome:DocumentTermMatrix (documents: 9875, terms: 0)
Non-/sparse entries: 0/0
Sparsity           : 100%
Maximal term length: 0
Weighting          : term frequency (tf)
> 
> #TOPICMODELLING
> 
> library(topicmodels)
> 
>  
> 
> burnin <- 100
> iter <- 500
> thin <- 100
> seed <-list(200,5,500,3700,1666)
> nstart <- 5
> best <- TRUE
> 
>  
> k <- 12
> 
> 
> ldaOut <-LDA(dtm.new,k, method="Gibbs", control=list(nstart=nstart, seed = seed, best=best, burnin = burnin, iter = iter, thin=thin))

>Fehler in obj[[i]][[which.max(sapply(obj[[i]], logLik))]] :
>attempt to select less than one element in get1index

我猜dtm的东西不是因为它说有9875个文件而没有任何条款。但我完全不知道为什么代码适用于一个样本而不适用于另一个样本。如果我在代码上做错了或者你发现了其他任何错误，请告诉我。

提前致谢！

Answer 1

terms = 0这就是你有问题的原因

R：topicmodels，2个类似文档，代码与one一起工作，不与另一个一起工作

1 个答案: