SAS--chapter11data子集（if 、select、 delete）

libname clinic 'D:\sas';
filename test 'D:\sas\test.txt';   *纯文本;
data clinic.yb;
infile test;
input sex $1-2 weight 3-6 height 7-9;  *和顺序有关，查看test.txt;
retain hh 2;            *hh 从2开始加，默认是0;
hh+height;            *创建新变量hh，且不需要关键词开头，遇到缺失值直接跳过;
if weight>80 then description ='heave';     *if weight<=80,description will be missing;
RUN;

data clinic.data2;
    infile test;
    input sex $1 weight 3;
    retain w 4;
    w+weight;
run;


if test<85 and time<=20
    then Status='RETEST';

if region in ('NE','NW','SW')
    then Rate=fee-25;

if target gt 300 or sales ge 50000
    then Bonus=salary*.05;

if status='OK' and type=3
    then Count+1;

if (age^=agecheck | time^=3)
    & error=1 then Test=1;

if (age^=agecheck | time^=3)
& error=1 then Test=1;

if status='S' or cond='E'
    then Control='Stop';

if not(loghours<7500)
    then Schedule='Quarterly';

if region not in ('NE','SE')
    then Bonus=200;

if status='OK' and type=3
    then Count+1;

if status='S' or cond='E'
    then Control='Stop';

if not(loghours<7500)
    then Schedule='Quarterly';

if region not in ('NE','SE')
    then Bonus=200;

*数字0 和 missing 为false，其他数字为true;
if x=1 or 2;   *always true;
if x=1 or x=2;  *right;

if totaltime>800 then TestLength='Long';
else if 750<=totaltime<=800 then TestLength='Normal';   *esle if 比 多个if then  连用节省系统资源;
else if totaltime<750 then TestLength='Short';

filename test 'D:\sas\test.txt';   *纯文本;
data clinic.yb;
infile test;
input sex $1 weight 3-5 height 7-8;  
if weight<170 then description='short';  *出现的这一列内容width以该变量赋的第一个值为准;
else if 170<=weight<=180 then description='Normal';
else if weight>180 then   description='longgg';
RUN;

length Type $ 8;
length Address1 Address2 Address3 $ 200;
length FirstName $ 12 LastName $ 16;

data clinic.yb;
infile test;
input sex $1 weight 3-5 height 7-8;  
length description $ 10;              *给新变量赋上长度,length出现在变量初始化之前;
if weight<170 then description='short'; 
else if 170<=weight<=180 then description='Normal';
else if weight>180 then   description='longgg';
RUN;

data clinic.yb;
infile test;
input sex $1 weight 3-5 height 7-8;  
if weight<170 then delete;  *删除满足if的observations;
RUN;


data clinic.yb (drop=height);  *去掉某些列 data\print均可用;
infile test;
input sex $1 weight 3-5 height 7-8;  
RUN;

data clinic.yb ;
infile test;
input sex $1 weight 3-5 height 7-8;  
drop  height;                 *方式2  !!drop keep只能用在data步，proc不可用;
RUN;

data clinic.yb ;
infile test;
input sex $1 weight 3-5 height 7-8;  
label height='H';      * 该变量名 ，data步为永久的，print步为临时的;
format weight comm1.2  *;
RUN;


*当变量为数值型且 互斥时，select 比if then 高效;
filename test 'D:\sas\test1.txt';   *纯文本;

data clinic.data1 ;
infile test;
input sex $1 weight 3;  
select (weight);
when (1) x='一';
when (2) x='二';
when (3) x='三';
when (4) x='四';
when (5) x='五';
when (6) x='六';
otherwise;
end;
RUN;
*or;
data clinic.data1 ;
infile test;
input sex $1 weight 3;  
select (weight);
when (1) x='一';
when (2) x='二';
when (3) x='三';
when (4) x='四';
when (5) x='五';
otherwise (6) x='六';
end;
RUN;

data clinic.data1 ;
infile test;
input sex $1 weight 3;  
select;
when (weight=1) x='一';
when (weight=2) x='二';
otherwise ;
end;
RUN;

*do end 组合，对满足某一条件的数据执行多个操作;
data clinic.data1 ;
    infile test;
    input sex $1 weight 3;  
        select (weight);
        when (1) x='一';
        when (2) x='二';
        when (3) 
            do;
                x='三';
                y='middle';
            end;
        when (4) x='四';
        when (5) x='五';
        otherwise put 'problem';   *不能（6)='六', 什么都不写 or put;
        end;
RUN;

data clinic.data2;
    infile test;
    input sex $1 weight 3;
        if weight=1 then x='一';
        else if weight=2 then 
        do; 
            x='二';
            y='middle';
        end;
run;

 

libname clinic "E:\sas";
filename saledata "e:\sas\test.txt";
data clinic.sales(drop=sex);
   infile saledata;
   input name $ 1-10 sex $ 12-13 age 15 height 17-19 weight 21-23;
   Total=height+weight;
   retain CumTotal 1254657;
   cumtotal+total;
   if sex="女" then delete;
   if cumtotal>1255500 then 
    do;
    testlength="short";
    y=1;
    end;
   else if 1254900<=cumtotal<1265000 then testlength="long";
   else testlength="1234567";  *只有12345，因为testlength录入的第一个值为short，只有五个字符;
run;
proc print data=clinic.sales;
run;