如何使用SAS代码运行许多SVM模型？

时间：2017-03-21 19:28:58

标签： sas

我在Enterprise Miner工作，看到了this video from SAS，其中他简要地展示了一个运行一堆SVM模型的SAS代码节点。

他没有展示整件事，但足以让我对如何做到这一点感到好奇。这是我到目前为止所得到的：

%macro hpsvm (run=1,runLabel=,penalty=10,method=activeSet,kernel=TBF);

    proc hpsvm data=&em_import_data maxiter=25 metho = &method. tolerance=0.000001 c = &penalty.;
        input %em_internal_input / level = interval;
        target %em_target / level = binary ;
        lernel &kernel.;
        partition fraction (validate=.3 seed=12345);
        ods output fitStatistics=fitStats&run.;
    run;

    data firStats&run.;
        length method $ 10;
        length kernel $ 10;
        length runLabel $ 64;
        set fitStats&run.;
        run = &run;
        runLabel = "&runLabel";
        method="&method.";
        kernel="&kernel.";
        penalty=&penalty.;
    run;

    proc print data=fitStats&run.;
    run;

    proc append base=fitStats data=firStats&run.;

%mend hpsvm;

%hpsvm(run=1,runLabel=RBF c=1, method=activeSet, kernel=RBF,penalty=1);
%hpsvm(run=2,runLabel=RBF c=5, method=activeSet, kernel=RBF,penalty=5);
%hpsvm(run=3,runLabel=RBF c=10, method=activeSet, kernel=RBF,penalty=10);
%hpsvm(run=4,runLabel=RBF c=15, method=activeSet, kernel=RBF,penalty=15);
%hpsvm(run=5,runLabel=RBF c=20, method=activeSet, kernel=RBF,penalty=20);

%hpsvm(run=6,runLabel=Linear c=1, method=ipoint, kernel=linear,penalty=1);
%hpsvm(run=7,runLabel=Linear c=5, method=ipoint, kernel=linear,penalty=5);
%hpsvm(run=8,runLabel=Linear c=10, method=ipoint, kernel=linear,penalty=10);
%hpsvm(run=9,runLabel=Linear c=15, method=ipoint, kernel=linear,penalty=15);
%hpsvm(run=10,runLabel=Linear c=20, method=ipoint, kernel=linear,penalty=20);

%hpsvm(run=11,runLabel=Polynomial c=1, method=ipoint, kernel=POLYNOM,penalty=1);
%hpsvm(run=12,runLabel=Polynomial c=5, method=ipoint, kernel=POLYNOM,penalty=5);
%hpsvm(run=13,runLabel=Polynomial c=10, method=ipoint, kernel=POLYNOM,penalty=10);
%hpsvm(run=14,runLabel=Polynomial c=15, method=ipoint, kernel=POLYNOM,penalty=15);
%hpsvm(run=15,runLabel=Polynomial c=20, method=ipoint, kernel=POLYNOM,penalty=20);

%hpsvm(run=16,runLabel=Sigmoid c=1, method=activeSet, kernel=SIGMOID,penalty=1);
%hpsvm(run=17,runLabel=Sigmoid c=5, method=activeSet, kernel=SIGMOID,penalty=5);
%hpsvm(run=18,runLabel=Sigmoid c=10, method=activeSet, kernel=SIGMOID,penalty=10);
%hpsvm(run=19,runLabel=Sigmoid c=15, method=activeSet, kernel=SIGMOID,penalty=15);
%hpsvm(run=20,runLabel=Sigmoid c=20, method=activeSet, kernel=SIGMOID,penalty=20);

data fitStats;
    retain run runLabel method kernal penalty;
    set fitStats;
run;

%em_register(type=Data,key=fitStats);

data &em_user_fitStats;
    retain Penalty;
    set fitStats;
run;

%em_report(viewType=data,key=fitStats,autodisplay=y,description=Fit Statistics by Run);

%em_register(type=Data,key=Error);

有几点需要注意：

  • 我正在使用来自UCI 的MillionSongDataset（但是让我知道如何将数据输出到SO的良好格式，我会在这里添加一些）
  • 这应该使用前一节点（数据分区）
    • 的数据运行
  • 我能解决的唯一错误就是没有在正确的位置加上引号或分号，但一切看起来都不错（几乎没有SAS编码经验）。
  • 他没有显示剩余的1/5代码。

我希望运行许多SVM模型来尝试不同的选项组合以找到最佳模型。

1 个答案:

答案 0 :(得分：0)

SAS实际上通过电子邮件向我发送了密码！

%macro hpsvm (run=1,runLabel=,penalty=10,method=activeSet,kernel=RBF);


   proc hpsvm data=&em_import_data maxiter=25 method = &method. tolerance=0.000001 c = &Penalty.;
     input  %em_interval_input / level = interval;
     target %em_target / level = binary ;
     kernel &kernel.;
     partition fraction (validate=.3 seed=12345);
     ods output fitStatistics=fitStats&run.;
   run;

   data fitStats&run.;
     length method $ 10;
     length kernel $ 10;
     length runLabel $ 64;
     set fitStats&run.;
     run = &run;
     runLabel = "&runLabel";
     method="&method.";
     kernel="&kernel.";
     penalty=&penalty.;
   run;

   proc print data=fitStats&run.;
   run;

   proc append base=fitStats data=fitStats&run.;
   run;

%mend hpsvm;

%hpsvm(run=1,runLabel=RBF c=1,method=activeSet,kernel=RBF,penalty=1);
%hpsvm(run=2,runLabel=RBF c=5,method=activeSet,kernel=RBF,penalty=5);
%hpsvm(run=3,runLabel=RBF c=10,method=activeSet,kernel=RBF,penalty=10);
%hpsvm(run=4,runLabel=RBF c=15,method=activeSet,kernel=RBF,penalty=15);
%hpsvm(run=5,runLabel=RBF c=20,method=activeSet,kernel=RBF,penalty=20);

%hpsvm(run=6,runLabel=Linear c=1,method=ipoint,kernel=linear,penalty=1);
%hpsvm(run=7,runLabel=Linear c=5,method=ipoint,kernel=linear,penalty=5);
%hpsvm(run=8,runLabel=Linear c=10,method=ipoint,kernel=linear,penalty=10);
%hpsvm(run=9,runLabel=Linear c=15,method=ipoint,kernel=linear,penalty=15);
%hpsvm(run=10,runLabel=Linear c=20,method=ipoint,kernel=linear,penalty=20);

%hpsvm(run=11,runLabel=RBF c=1,method=ipoint,kernel=POLYNOM,penalty=1);
%hpsvm(run=12,runLabel=RBF c=5,method=ipoint,kernel=POLYNOM,penalty=5);
%hpsvm(run=13,runLabel=RBF c=10,method=ipoint,kernel=POLYNOM,penalty=10);
%hpsvm(run=14,runLabel=RBF c=15,method=ipoint,kernel=POLYNOM,penalty=15);
%hpsvm(run=15,runLabel=RBF c=20,method=ipoint,kernel=POLYNOM,penalty=20);

%hpsvm(run=16,runLabel=Linear c=1,method=activeSet,kernel=SIGMOID,penalty=1);
%hpsvm(run=17,runLabel=Linear c=5,method=activeSet,kernel=SIGMOID,penalty=5);
%hpsvm(run=18,runLabel=Linear c=10,method=activeSet,kernel=SIGMOID,penalty=10);
%hpsvm(run=19,runLabel=Linear c=15,method=activeSet,kernel=SIGMOID,penalty=15);
%hpsvm(run=20,runLabel=Linear c=20,method=activeSet,kernel=SIGMOID,penalty=20);


data fitStats;
  retain run runLabel method kernel penalty;
  set fitStats;
run;


proc print data=fitStats;
run;


%em_register(type=Data,key=fitStats);

data &em_user_fitStats;
   retain Penalty;
   set fitStats;
run;

%em_report(viewType=data,key=fitStats,autodisplay=y,description=Fit Statistics by Run);

%em_register(type=Data,key=Error);

data &em_user_Error;
   set fitStats;
   if statistic = 'Error';
run;

%em_report(viewType=lineplot,key=Error,x=penalty,y=validation,group=kernel,description=Classification Error by penalty,autodisplay=y);


%em_register(type=Data,key=Sensitivity);

data &em_user_Sensitivity;
   set fitStats;
   if statistic = 'Sensitivity';
run;

%em_report(viewType=lineplot,key=Sensitivity,x=penalty,y=validation,group=kernel,description=Sensitivity by penalty,autodisplay=y);


%em_register(type=Data,key=Specificity);

data &em_user_Specificity;
   set fitStats;
   if statistic = 'Specificity';
run;

%em_report(viewType=lineplot,key=Specificity,x=penalty,y=validation,group=kernel,description=Specificity by penalty,autodisplay=y);
相关问题
最新问题