0

你可以帮帮我吗？我想分析一些句子以将它们分配给主题这不是一个困难的过程，但是当我调用 terms(x) 时，我只看到数字，例如

terms(x) 主题 1 主题 2 主题 3 主题 4 主题 5 “121880” “173807” “38655” “190018” “67905” 我的代码有什么问题？

 library("RODBC")
library("tm")
library("wordcloud")
library("SnowballC")
library("pvclust")
library("textcat")

dbHandle <- odbcDriverConnect("driver={SQL Server};server=BIDBRU01;database=ClinCheckCommentsClust;trusted_connection=true")

sql <- 
  "select --top (10000)
              rx_form_id
       ,  doctor_comment
       , comment_date
from dbo.tblPuFormBinInternal cc
where comment_date >= '20140101'
and comment_date < '20140601'"

cccomments <- sqlQuery(dbHandle, sql)

cccomments.lang_category <- textcat(cccomments$doctor_comment);
comments.eng <- cccomments[cccomments.lang_category == 'english',]
cc.corpus <- Corpus(VectorSource(comments.eng$doctor_comment))
tdm <- TermDocumentMatrix(cc.corpus,
                          control = list(removePunctuation = TRUE,
                                         stopwords =TRUE,

                                         weighting =
                                           function(x)
                                             weightTf(x)

  ))
tdm <- removeSparseTerms(tdm, sparse=0.8)

library(RTextTools)
library(topicmodels)
k <- length(unique(cc.corpus$Topic.Code))
x <- LDA(tdm, 5)
str(x)
terms(x)
topics(x)
m = as.matrix(tdm);
v = sort(colSums(m), decreasing=TRUE);
myNames = names(v);
k = which(names(v)=="miners");
myNames[k] = "mining";
d = data.frame(word=myNames, freq=v);
wordcloud(d$word, colors=c(3,4), random.color=FALSE, d$freq, min.freq=20);     

> str(x)
Formal class 'LDA_VEM' [package "topicmodels"] with 14 slots
  ..@ alpha          : num 5160
  ..@ call           : language LDA(x = tdm, k = 5)
  ..@ Dim            : int [1:2] 3 284848
  ..@ control        :Formal class 'LDA_VEMcontrol' [package "topicmodels"] with 13 slots
  .. .. ..@ estimate.alpha: logi TRUE
  .. .. ..@ alpha         : num 10
  .. .. ..@ seed          : int 1423217142
  .. .. ..@ verbose       : int 0
  .. .. ..@ prefix        : chr "C:\\Users\\Admin\\AppData\\Local\\Temp\\RtmpIvmDWl\\file136030c2577d"
  .. .. ..@ save          : int 0
  .. .. ..@ nstart        : int 1
  .. .. ..@ best          : logi TRUE
  .. .. ..@ keep          : int 0
  .. .. ..@ estimate.beta : logi TRUE
  .. .. ..@ var           :Formal class 'OPTcontrol' [package "topicmodels"] with 2 slots
  .. .. .. .. ..@ iter.max: int 500
  .. .. .. .. ..@ tol     : num 1e-06
  .. .. ..@ em            :Formal class 'OPTcontrol' [package "topicmodels"] with 2 slots
  .. .. .. .. ..@ iter.max: int 1000
  .. .. .. .. ..@ tol     : num 1e-04
  .. .. ..@ initialize    : chr "random"
  ..@ k              : int 5
  ..@ terms          : chr [1:284848] "1" "2" "3" "4" ...
  ..@ documents      : chr [1:3] "ipr" "lower" "upper"
  ..@ beta           : num [1:5, 1:284848] -100 -100 -100 -100 -100 -100 -100 -100 -100 -100 ...
  ..@ gamma          : num [1:3, 1:5] 0.208 0.196 0.197 0.195 0.203 ...
  ..@ wordassignments:List of 5
  .. ..$ i   : int [1:244179] 1 1 1 1 1 1 1 1 1 1 ...
  .. ..$ j   : int [1:244179] 6 15 34 50 54 63 69 77 88 91 ...
  .. ..$ v   : num [1:244179] 1 1 3 3 1 3 3 3 3 3 ...
  .. ..$ nrow: int 3
  .. ..$ ncol: int 284848
  .. ..- attr(*, "class")= chr "simple_triplet_matrix"
  ..@ loglikelihood  : num [1:3] -1210792 -1400929 -1405806
  ..@ iter           : int 3
  ..@ logLiks        : num(0) 
  ..@ n              : int 343192
> terms(x)
 Topic 1  Topic 2  Topic 3  Topic 4  Topic 5 
"121880" "173807"  "38655" "190018"  "67905" 
> topics(x)
  ipr lower upper 
    3     2     4
4

0 回答 0