sas构建评分卡模型过程详解（三）：变量分箱及特征筛选补充

在sas构建评分卡系列一已经对变量分箱在保证woe的单调作了补充sas构建评分卡模型过程详解（一）：特征处理及变量分箱
我们希望的好的分箱是这样子的：

但是如果加单调限制的iv相比不加单调限制的iv差别不小，或者有的变量在有跳点的情况下也符合业务需求，这时处于中间的风险低于或者高于两侧的风险。
如：

但我们通常也不希望跳点多于1个，像下面这样子：

因此，可以实现挑选出最多只有一个跳点的分箱，

/*计算woe值的跳点*/

%macro cal_woe_jump;
%do ci=3 %to 6;
data mp;
   set dt.New_lx_mapiv_0_&ci.;
   where GRP_VAR^=0;
run;
proc sort data=mp;by varname GRP_VAR;run;
data mp1;
   set mp;
   by varname GRP_VAR;
   retain woe_fg 0;
   if first.varname then woe_fg=woe;
    else do; 
       if woe_fg>woe then fg=-1;
         else fg=1;
       woe_fg=woe;
      end;
 run;

  proc sql;
    create table mp2 as
     select varname,max(iv) as iv,
             max(case when fg=1 then GRP_VAR else 0 end) as a_rank,
             min(case when fg=1 then GRP_VAR else 999 end) as a_rank_min,
              sum(case when fg=1 then fg else 0 end) as a_sum,
              max(case when fg=-1 then GRP_VAR else 0 end) as d_rank,
              min(case when fg=-1 then GRP_VAR else 999 end) as d_rank_min,
              sum(case when fg=-1 then -fg else 0 end) as d_sum,
              max(GRP_VAR) as GRP_VAR
       from mp1
       group by 1;
  quit;

data mp3;
   set mp2;
   num=&ci.;
   where iv>=0.02;
   if (d_rank_min-a_rank=1 or a_rank_min-d_rank=1)  or a_sum=0 or d_sum=0;
   keep varname iv GRP_VAR;
   rename iv=iv_&ci. GRP_VAR=GRP_VAR_&ci.;
run;

    %if &ci=3 %then %do;
       data out_woe;
          set mp3;
        run;
     %end;

     %else %do;
     proc sql;
        create table out_woe as 
          select a.*,b.*
          from out_woe a
          left join mp3 b on a.varname=b.varname;
      quit;
    %end;

%end;


%mend;

%cal_woe_jump;

并与不加单调限制的分箱对比，

proc sql;
   create table out_woe1 as
    select a.*,b.iv as iv0,b.GRP_VAR as GRP_VAR0
    from out_woe a
    left join iv3 b on a.varname=b.varname;
quit;

data out_woe2;
   set out_woe1;
   array ar{*} iv_:;
   do i=1 to dim(ar);
      if ar(i)>temp then do;temp=ar(i);s_name=vname(ar(i));end;
    end;
  keep varname iv: s_name;
run;

以此来挑选出好的分箱。