Question

我正在使用支持向量机进行文档分类任务！它将我在训练集中的所有文章分类，但未能对我的测试集中的文章进行分类！ trainDTM是我的训练集的文档术语矩阵。 testDTM是测试集的一个。这是我的（不那么漂亮）代码：

# create data.frame with labelled sentences

labeled <- as.data.frame(read.xlsx("C:\\Users\\LABELED.xlsx", 1, header=T))

# create training set and test set
traindata <- as.data.frame(labeled[1:700,c("ARTICLE","CLASS")])
testdata <- as.data.frame(labeled[701:1000, c("ARTICLE","CLASS")])

# Vector, Source Transformation
trainvector <- as.vector(traindata$"ARTICLE")
testvector <- as.vector(testdata$"ARTICLE")
trainsource <- VectorSource(trainvector)
testsource <- VectorSource(testvector)

# CREATE CORPUS FOR DATA
traincorpus <- Corpus(trainsource)
testcorpus <- Corpus(testsource)

# my own stopwords
sw <- c("i", "me", "my")

## CLEAN TEXT

# FUNCTION FOR CLEANING
cleanCorpus <- function(corpus){
  corpus.tmp <- tm_map(corpus, removePunctuation)
  corpus.tmp <- tm_map(corpus.tmp,stripWhitespace)
  corpus.tmp <- tm_map(corpus.tmp,tolower)
  corpus.tmp <- tm_map(corpus.tmp, removeWords, sw)
  corpus.tmp <- tm_map(corpus.tmp, removeNumbers)
  corpus.tmp <- tm_map(corpus.tmp, stemDocument, language="en")
  return(corpus.tmp)}

# CLEAN CORP WITH ABOVE FUNCTION
traincorpus.cln <- cleanCorpus(traincorpus)
testcorpus.cln <- cleanCorpus(testcorpus)

## CREATE N-GRAM DOCUMENT TERM MATRIX 
# CREATE N-GRAM TOKENIZER

BigramTokenizer <- function(x) NGramTokenizer(x, Weka_control(min = 1, max = 1))

# CREATE DTM
trainmatrix.cln.bi <- DocumentTermMatrix(traincorpus.cln, control = list(tokenize = BigramTokenizer))
testmatrix.cln.bi <- DocumentTermMatrix(testcorpus.cln, control = list(tokenize = BigramTokenizer))

# REMOVE SPARSE TERMS
trainDTM <- removeSparseTerms(trainmatrix.cln.bi, 0.98)
testDTM <- removeSparseTerms(testmatrix.cln.bi, 0.98)

# train the model
SVM <- svm(as.matrix(trainDTM), as.factor(traindata$CLASS))

# get classifications for training-set
results.train <- predict(SVM, as.matrix(trainDTM)) # works fine!

# get classifications for test-set
results <- predict(SVM,as.matrix(testDTM))

Error in scale.default(newdata[, object$scaled, drop = FALSE], center = object$x.scale$"scaled:center",  : 
  length of 'center' must equal the number of columns of 'x'

我不明白这个错误。什么是“中心”？

谢谢!!

Answer 1

训练和测试数据必须位于相同的特征空间内;构建两个以这种方式分离DTM是行不通的。

使用RTextTools的解决方案：

DocTermMatrix <- create_matrix(labeled, language="english", removeNumbers=TRUE, stemWords=TRUE, ...)
container <- create_container(DocTermMatrix, labels, trainSize=1:700, testSize=701:1000, virgin=FALSE)
models <- train_models(container, "SVM")
results <- classify_models(container, models)

或者，要回答您的问题（使用e1071），您可以在投影中指定词汇表（'features'）（DocumentTermMatrix）：

DocTermMatrixTrain <- DocumentTermMatrix(Corpus(VectorSource(trainDoc)));
Features <- DocTermMatrixTrain$dimnames$Terms;

DocTermMatrixTest <- DocumentTermMatrix(Corpus(VectorSource(testDoc)),control=list(dictionary=Features));

支持向量机适用于训练集但不适用于R中的测试集（使用e1071）

1 个答案: