SAS数据集中的累积频率

我的数据集如下所示：

 Customer Sales
        1    15
        2    14
        3    13
        4    11
        5    12
        6    18
        7    21

我需要按销售额百分比对客户进行分类，然后将他们分为高、中、低三类

 Customer Sales  %Sales
        7    21     20%
        6    18     17%
        1    15     14%
        2    14     13%
        3    13     13%
        5    12     12%
        4    11     11%

铲斗需要基于累积频率：

 Customer Sales %Sales CumFreq Bucket
        7    21    20%     20%   High
        6    18    17%     38% Medium
        1    15    14%     52% Medium
        2    14    13%     65% Medium
        3    13    13%     78%    Low
        5    12    12%     89%    Low
        4    11    11%    100%    Low

---

因此，正如你所看到的，在前33%的销售额中，任何人都将处于高位，中间33%的销售额将处于中位，而底部33%的销售额将处于低位，因此你需要对列进行求和，对数据集进行排序，然后计算累计百分比。使用自定义格式创建Bucket列

/*untested: don't have access to SAS right now*/

PROC SQL noprint;
/*1st get the total no. of sales and stick it into a macro variable*/
select sum(sales) into: TotalSales
from someCustomertable;

create table topCustomers as 
select 
a.Customer
, a.sales
, a.sales/&TotalSales as salesPerc format=percent11.2
, case
    when calculated salesPerc <=1/3 then "High"
    when calculated salesPerc <=2/3 then "Medium"
    else "Low"
  end as Bucket
from someCustomertable as a
order by 3
QUIT;

data sales;
input  Customer Sales;
datalines;
        1    15
        2    14
        3    13
        4    11
        5    12
        6    18
        7    21
;
run;

proc sort data=sales;
by descending sales ;
run;

proc sql noprint;
select sum(sales) format=best32. into :s from sales;
quit;

proc format;
value pctSales
    0-.33='High'
    .33-.67='Medium'
    .67-1='Low';
run;

data sales;
set sales;
retain total 0;
format pctSales percent8.2;
total = total + sales;
pctSales = total/&s;
bucket = put(pctSales,pctSales.);
drop total;
run;

---

我知道我们可以从proc-Freq的输出数据集中使用Cumul-Freq，但不确定它是否完全符合我的目的