[英]SAS Proc Import CSV and missing data
所以,我试图在 SAS 中导入一些数据集并加入它们,唯一的问题是加入它们后我收到了这个错误 -
proc import datafile='filepath/datasetA.csv'
out = dataA
dbms= csv
replace;
run;
proc import datafile='filepath\datasetB.csv'
out = dataB
dbms= csv
replace;
run;
/* combine them all into one dataset*/
data DataC;
set &dataA. &dataB;
run;
ERROR: Variable column_k has been defined as both character and numeric
在我尝试加入的两个数据集中,有问题的列看起来像这样 -
+----------+
| column_k |
+----------+
| 0 |
| 1 |
| 5 |
| 4 |
| NA |
| NA |
| 4 |
| 3 |
| NA |
+----------+
基本上,如果可能的话,我想将该列中的 NA 数据导入为“缺失”? 我需要整个列保持数字,因为我计划对该列中的数据进行一些数学运算。
谢谢你的帮助!
如果您希望继续使用Proc IMPORT
那么您需要确保列的类型相同。 在您的情况下,您知道column_k
应该是数字,因此DATA
步骤可以使用INPUT
函数将字符值转换为数字。
proc import … out = dataA;
proc import … out = dataB;
data dataA;
set dataA;
_num = input(column_k, best12.);
drop column_k;
rename _num = column_k;
run;
data dataB;
set dataB;
_num = input(column_k, best12.);
drop column_k;
rename _num = column_k;
run;
data want;
set dataA dataB;
run;
在更大范围内,列名的数据类型不匹配可能发生在处理多年导入等场景中。
假设不能重新读取旧数据并且新数据具有不同的列类型。
对于需要数值的情况,一种方法是使用宏编写源代码,必要时将指定的变量从字符转换为数字。
例子:
%enforce_num (perm.loans2015, age amount remaining, out=work.loans2015)
%enforce_num (perm.loans2016, age amount remaining, out=work.loans2016)
%enforce_num (perm.loans2017, age amount remaining, out=work.loans2017)
data loans_3yrs;
set work.loans2015-loans2017;
run;
回到你更简单的案例:
proc import … out = dataA;
proc import … out = dataB;
%enforce_num(dataA, column_k)
%enforce_num(dataB, column_k)
data want;
set dataA dataB;
run;
宏enforce_num
会是什么样子? 它必须:
%macro enforce_num(data, vars, out=&data);
/*
* Arguments:
* data - name of input data set
* vars - space separated list of variables that must be numeric, convert type if necessary
* out - name of output data set, default same as input data set
*
* Output:
* - Unchanged data set if data and out are the same and no conversion needed
* - Changed data set if some columns in data need conversion to numeric
* - replaces data if out is same as data
* - replaces out if out is different then data
* - the column order of the changed data set will be the same as the original data set
*/
%local dsid index index2 vars varname vartype varnames debug;
%let index2 = 0; %* number of variables determined to be requiring conversion;
%let debug = 0;
%if &debug %then %put NOTE: &SYSMACRONAME: data=%superq(data);
%let dsid = %sysfunc(open(&data));
%if &dsid %then %do;
%do index = 1 %to %sysfunc(attrn(&dsid, nvars));
%let varname = %sysfunc(varname(&dsid, &index));
%let varnames = &varnames &varname;
%if %sysfunc(indexw(&varname, &vars)) %then %do;
%if C = %sysfunc(vartype(&dsid, &index)) %then %do;
%* Data contains character variable requiring enforcement;
%let index2 = %eval(&index2+1);
%local convert&index2;
%let convert&index2 = &varname;
%let varnames = &varnames ___&index2 ; %* Variables that will be converted will be named __<#> during conversion;
%end;
%end;
%end;
%let dsid = %sysfunc(close(&dsid));
%end;
%else
%put %sysfunc(sysmsg());
%*put NOTE: &=vars;
%*put NOTE: &=varnames;
%if &index2 = 0 %then %do;
%* No columns need to be converted to numeric, copy to out if necessary;
%if &data ne &out %then %do;
data &out;
set &data;
run;
%end;
%return;
%end;
%* Some columns need to be converted to numeric;
%* Ensure the converted column is at the same position (varnum) as in the original data set;
data &out;
retain &varnames;
set &data;
%do index = 1 %to &index2;
___&index = input(&&convert&index,?? best12.);
%end;
drop
%do index = 1 %to &index2;
&&convert&index
%end;
;
rename
%do index = 1 %to &index2;
___&index = &&convert&index
%end;
;
run;
%put NOTE: ------------------------------------------------;
%put NOTE: &data has been subjected to numeric enforcement.;
%put NOTE: ------------------------------------------------;
%mend enforce_num;
proc import
是一个猜测过程,通过检查几行数据来工作。这是一个问题,因为 Excel 数据单元格没有任何数据类型。 一列可以在不同的单元格中包含文本、日期、日期时间和数值。
因此,最好使用具有指定变量类型的infile
语句:
filename input 'filepath/datasetA.csv';
data dataA;
infile input truncover firstobs=2/*reads from the second line*/;
input column_k;/*here you should specify input variables. If you want to read column_k as character, use : "input column_k $100." with specified length*/
run;
filename input clear;
输入(csv文件):
+----------+
| column_k |
+----------+
| 0 |
| 1 |
| 5 |
| 4 |
| NA |
| NA |
| 4 |
| 3 |
| NA |
+----------+
输出(作为数据集dataA):
+----------+
| column_k |
+----------+
| 0 |
| 1 |
| 5 |
| 4 |
| . |
| . |
| 4 |
| 3 |
| . |
+----------+
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.