决策树 香农熵

熵（entropy）是表示随机变量不确定性的度量.所以熵越小越好
之所以Po出来是因为里面好多小函数自己找了好久 R语言用的人太少了 好痛苦

#computing ShannonEnt
CalShannonEnt<-function(dataSet){
  #number of sample
  numEntries = nrow(dataSet)
  #labels you want to classify
  labels = levels(factor(dataSet[, "labels"]))
  labelCount = NULL
  #creat a new vector, recorder sample number in each label
  labelCount[labels] = rep(0, length(labels))
  for(i in 1:numEntries){
    #判断dataSet[i, "labels"]标签是否在labels中
    if(dataSet[i, "labels"] %in% labels){
      temp = dataSet[i, "labels"]
      labelCount[temp] = labelCount[temp] + 1
    }
  }
  t = NULL
  shannonEnt = 0
  for(i in  1:length(labelCount)){
    t[i]= labelCount[i] * 1.0 / numEntries
    shannonEnt = -t[i] * log2(t[i]) + shannonEnt
  }
#  labelCount = as.numeric(labelCount)
  return (shannonEnt)
}

dataSet = matrix(c(1, 1, "yes", 1, 1, "yes", 1, 0, "no", 1, 0, "no", 0, 1, "no"),
                 byrow = T, 
                 nrow =5)
colnames(dataSet)[3] = "labels"

s = calShannonEnt(dataSet)