R语言计算IV值

CalcIV <- function(df_bin, key_var, y_var){
  N_0<-table(df_bin[, y_var])[1]
  N_1<-table(df_bin[, y_var])[2]
  iv_c<-NULL
  var_c<-NULL
  for (col in colnames(df_bin)){
    if (col != key_var && col != y_var) {
      frq<-as.data.frame(table(df_bin[, col], df_bin[, y_var]))
      len<-length(unique(frq$Var1))
      iv<-0
      for (i in 1:len){
        N_i_0<-frq$Freq[frq$Var1==i & frq$Var2==0]
        N_i_1<-frq$Freq[frq$Var1==i & frq$Var2==1]
        iv<-iv+(N_i_0/N_0- N_i_1/N_1)*log((N_i_0/N_0)/(N_i_1/N_1))
      }
      iv_c<-c(iv_c, iv)
      var_c<-c(var_c, col)
    }
  }
  iv_df<-data.frame(var=var_c, iv=iv_c, stringsAsFactors = FALSE)
  return(iv_df)
}