机器学习- SVM-RFE算法的实现

Question

我使用R代码从这个源http://www.uccor.edu.ar/paginas/seminarios/Software/SVM_RFE_R_implementation.pdf实现SVM-RFE算法，但我做了一个小的修改，使R代码使用gnum库。代码如下:

svmrfeFeatureRanking = function(x,y){
  n = ncol(x)
  survivingFeaturesIndexes = seq(1:n)
  featureRankedList = vector(length=n)
  rankedFeatureIndex = n
  while(length(survivingFeaturesIndexes)>0){
    #train the support vector machine
    svmModel = SVM(x[, survivingFeaturesIndexes], y, C = 10, cache_size=500,kernel="linear" )

    #compute ranking criteria
    rankingCriteria = svmModel$w * svmModel$w
    #rank the features
    ranking = sort(rankingCriteria, index.return = TRUE)$ix
    #update feature ranked list
    featureRankedList[rankedFeatureIndex] = survivingFeaturesIndexes[ranking[1]]
    rankedFeatureIndex = rankedFeatureIndex - 1
    #eliminate the feature with smallest ranking criterion
    (survivingFeaturesIndexes = survivingFeaturesIndexes[-ranking[1]])
  }
  return (featureRankedList)
} 

该函数接收x的matrix作为input, y的factor作为input。我对一些数据使用该函数，并且在最后的迭代中收到以下错误消息:

 Error in if (nrow(x) != length(y)) { : argument is of length zero 

调试代码，我得到了这个:

3 SVM.default(x[, survivingFeaturesIndexes], y, C = 10, cache_size = 500, 
    kernel = "linear") 
2 SVM(x[, survivingFeaturesIndexes], y, C = 10, cache_size = 500, 
    kernel = "linear") 
1 svmrfeFeatureRanking(sdatx, ym) 

那么，函数的误差是多少?

Answer 1

看起来你的矩阵被转换成一个列表时，只剩下一个特征。试试这个:

svmModel = SVM(as.matrix(x[, survivingFeaturesIndexes]), y, C = 10, cache_size=500,kernel="linear" )