R 评分卡模型 等宽分箱

R 等宽分箱

等宽分箱

近期做评分卡模型，对等宽分箱自定义了一个函数，可输出的结果包含分箱区间，分箱节点，每个分箱下的样本总计、坏样本总计、好样本总计、坏样本占比、woe值、iv值及总的IV值。

代码如下：

#参数说明：data为待分箱的特征变量，target为目标变量，bins为分箱个数（若数据集中包含空值，空值会单独自成一箱，不计算在bins之内）

width_dt=data.frame()
width_cut=function(data,target,bins){
  count_pos_sum = 0
  count_neg_sum = 0
  total_IV = 0
  for (n in target){
    if (n == 0)
      count_pos_sum = count_pos_sum + 1
    if (n == 1)
      count_neg_sum = count_neg_sum + 1
  }
  index_na = which(is.na(data))
  count_na = as.numeric(length(index_na))
  # 考虑样本有缺失值的情况
  if (count_na!=0){
    count_pos_na = 0
    count_neg_na = 0
    for (x in index_na){
      if (target[x]==0)
        count_pos_na = count_pos_na + 1
      if (target[x]==1)
        count_neg_na = count_neg_na +1
    }
    width_dt[1,1] = 'missing'
    width_dt[1,2] = 'missing'
    width_dt[1,3] = count_na
    width_dt[1,4] = count_pos_na
    width_dt[1,5] = count_neg_na
    width_dt[1,6] = count_neg_na / count_na
    Bad_distr_na = count_neg_na/count_neg_sum
    Good_distr_na = count_pos_na/count_pos_sum
    woe_na = log(Bad_distr_na / Good_distr_na)
    iv_na = (Bad_distr_na - Good_distr_na) * woe_na
    width_dt[1,7] = woe_na
    width_dt[1,8] = iv_na
    
    dt = data[-index_na]
    target = target[-index_na]
    inter = (max(dt)-min(dt)+1)/bins
    for (i in 1:bins){
      fx_min = min(dt)+(i-1)*inter
      fx_max = min(dt)+i*inter
      breaks = fx_max
      if (fx_min != max(dt)){
        if (fx_max != max(dt))
          fx = paste('[',round(fx_min,2),',',round(fx_max,2),')',sep = "")
        if (fx_max >= max(dt))
          fx = paste('[',round(fx_min,2),',',round(max(dt),2),']',sep = "")
      }
      if (fx_min == max(dt))
        fx = round(fx_min)
      index = c(which(dt>=fx_min & dt<fx_max))
      width_dt[i+1,1] = fx
      width_dt[i+1,2] = round(breaks,2)
      count_sum  = 0
      count_neg = 0
      count_pos = 0
      for (j in dt){
        if(j >= fx_min && j < fx_max)
          count_sum = count_sum + 1
      }
      width_dt[i+1,3] = count_sum
      for (k in index){
        if (target[k]==0)
          count_pos = count_pos + 1
        if (target[k]==1)
          count_neg = count_neg +1
      }
      width_dt[i+1,4] = count_pos
      width_dt[i+1,5] = count_neg
      width_dt[i+1,6] = count_neg / count_sum
      Bad_distr = count_neg/count_neg_sum
      Good_distr = count_pos/count_pos_sum
      woe = log(Bad_distr/Good_distr)
      IV = (Bad_distr - Good_distr) * log(Bad_distr/Good_distr)
      width_dt[i+1,7] = woe
      width_dt[i+1,8] = IV
      total_IV = total_IV + IV
    }
    width_dt[,9] = total_IV + iv_na
    colnames(width_dt)=c('fx','breaks','count','pos','neg','negprob','woe','IV','total_IV')
    print(width_dt) 
  }
  # 考虑样本无缺失值的情况
  if (count_na==0){
    dt = data
    target = target
    inter = (max(dt)-min(dt)+1)/bins
    for (i in 1:bins){
      fx_min = min(dt)+(i-1)*inter
      fx_max = min(dt)+i*inter
      breaks = fx_max
      if (fx_min != max(dt)){
        if (fx_max != max(dt))
          fx = paste('[',round(fx_min,2),',',round(fx_max,2),')',sep = "")
        if (fx_max >= max(dt))
          fx = paste('[',round(fx_min,2),',',round(max(dt),2),']',sep = "")
      }
      if (fx_min == max(dt))
        fx = round(fx_min)
      index = c(which(dt>=fx_min & dt<fx_max))
      width_dt[i,1] = fx
      width_dt[i,2] = round(breaks,2)
      count_sum  = 0
      count_neg = 0
      count_pos = 0
      for (j in dt){
        if(j >= fx_min && j < fx_max)
          count_sum = count_sum + 1
      }
      width_dt[i,3] = count_sum
      for (k in index){
        if (target[k]==0)
          count_pos = count_pos + 1
        if (target[k]==1)
          count_neg = count_neg +1
      }
      width_dt[i,4] = count_pos
      width_dt[i,5] = count_neg
      width_dt[i,6] = count_neg / count_sum
      Bad_distr = count_neg/count_neg_sum
      Good_distr = count_pos/count_pos_sum
      woe = log(Bad_distr/Good_distr)
      IV = (Bad_distr - Good_distr) * log(Bad_distr/Good_distr)
      width_dt[i,7] = woe
      width_dt[i,8] = IV
      total_IV = total_IV + IV
    }
    width_dt[,9] = total_IV
    colnames(width_dt)=c('fx','breaks','count','pos','neg','negprob','woe','IV','total_IV')
    print(width_dt)
  }
}