SAS - proc sql - select columns belonging together? - sas

I want to split a table with many (454) columns in a PROC SQL (perhaps using a macro?) by column names.
For example: a column is starting with "Column21....T", "Column22....T", etc.
I want to write all those columns starting with "Column21...T" to a data set called First, and all the columns starting with "Column22....T" to a data set called Second, etc.
I want to retain the first and second column of the transposed table because they contain the descriptional rows.
I cannot use select column1, column2.... Column454 because of the large number of columns.
How do I do this?
(#Mod: thanks for the clean-up :))
Edit, one picture to say it all:
This is my transposed table with 454 columns
PROC SORT
DATA=work.stat(KEEP=A_ B_ C_ D_ Vx G Vy)
OUT=work.stat2;
BY G;
RUN;
PROC TRANSPOSE DATA=work.stat2
OUT=WORK.x(LABEL="Transposed")
PREFIX=Column
LET
NAME=Source
LABEL=Label;
BY G;
ID Vx;
IDLABEL Vy;
VAR A_ B_ C_ D_;
RUN;

You can use : suffix to make a variable list.
data first ;
set have ;
keep id1 id2 column21: ;
run;
data second ;
set have ;
keep id1 id2 column22: ;
run;
Updated given more details in question.
So why not just transpose each group separately? Make a macro to transpose one value of Vx.
%macro split(value);
PROC TRANSPOSE DATA=work.stat2
OUT=WORK.Column&value (LABEL="Transposed Vx=&value")
PREFIX=Column
LET
NAME=Source
LABEL=Label
;
BY G;
WHERE Vx=&value ;
ID Vx;
IDLABEL Vy;
VAR A_ B_ C_ D_;
RUN;
%mend split ;
Then call it once for each value of Vx.
proc sort data=work.stat2(keep=Vx) nodupkey out=Vx_list ;
by Vx ;
run;
data _null_;
set Vx_list;
call execute(cats('%nrstr(%split)(',Vx,')'));
run;

Macro program:
%macro split(data,outdata);
%do i=21 %to 121;
data &outdata.&i;
set &data;
keep id1 id2 col&i:;
run;
%end;
%mend;

Related

SAS Macro: How can I record proc means output in one dataset?

[I have this piece of code. However, the Macro in proc univariate generate too many separate dataset due to loop t from 1 to 310. How can I modify this code to include all proc univariate output into one dataset and then modify the rest of the code for a more efficient run?]
%let L=10; %* 10th percentile *;
%let H=%eval(100 - &L); %* 90th percentile*;
%let wlo=V1&L V2&L V3&L ;
%let whi=V1&H V2&H V3&H ;
%let wval=wV1 wV2 wV3 ;
%let val=V1 V2 V3;
%macro winsorise();
%do v=1 %to %sysfunc(countw(&val));
%do t=1 %to 310;
proc univariate data=regressors noprint;
var &val;
output out=_winsor&t._V&v pctlpts=&H &L
prtlpre=&val&t._V&v;
where time_count<=&t;run;
%end;
data regressors (drop=__:);
set regressors;
if _n_=1 then set _winsor&t._V&v;
&wval&t._V&v=min(max(&val&t._V&v,&wlo&t._V&v),&whi&t._V&v);
run;
%end;
%mend;
Thank you.
Presume you have data time_count, x1, x2, x3 with samples at every 0.5 time unit.
data regressors;
call streaminit(123);
do time_count = 0 to 310 by .5;
x1 = 2 ** (sin(time_count/6) * log(time_count+1));
x2 = log2 (time_count+1) + log(time_count/10+.1);
x3 = rand('normal',
output;
end;
format x: 7.3;
run;
Stack the data into groups based on integer time_count levels. The stack is constructed from a full outer join with a less than (<=) criteria. Each group is identified by the top time_count in the group.
proc sql;
create table stack as
select
a.time_count
, a.x1
, a.x2
, a.x3
, b.time_count as time_count_group /* save top value in group variable */
from regressors as a
full join regressors as b /* self full join */
on a.time_count <= b.time_count /* triangular criteria */
where
int(b.time_count)=b.time_count /* select integer top values */
order by
b.time_count, a.time_count
;
quit;
Now compute ALL your stats for ALL your variables for ALL your groups in one go. No macro, no muss, no fuss.
proc univariate data=stack noprint;
by time_count_group;
var x1 x2 x3;
output out=_winsor n=group_size pctlpts=90 10 pctlpre=x1_ x2_ x3_;
run;

SAS: Replace rare levels in variable with new level "Other"

I've got pretty big table where I want to replace rare values (for this example that have less than 10 occurancies but real case is more complicated- it might have 1000 levels while I want to have only 15). This list of possible levels might change so I don't want to hardcode anything.
My code is like:
%let var = Make;
proc sql;
create table stage1_ as
select &var.,
count(*) as count
from sashelp.cars
group by &var.
having count >= 10
order by count desc
;
quit;
/* Join table with table including only top obs to replace rare
values with "other" category */
proc sql;
create table stage2_ as
select t1.*,
case when t2.&var. is missing then "Other_&var." else t1.&var. end as &var._new
from sashelp.cars t1 left join
stage1_ t2 on t1.&var. = t2.&var.
;
quit;
/* Drop old variable and rename the new as old */
data result;
set stage2_(drop= &var.);
rename &var._new=&var.;
run;
It works, but unfortunately it is not very officient as it needs to make a join for each variable (in real case I am doing it in loop).
Is there a better way to do it? Maybe some smart replace function?
Thanks!!
You probably don't want to change the actual data values. Instead consider creating a custom format for each variable that will map the rare values to an 'Other' category.
The FREQ procedure ODS can be used to capture the counts and percentages of every variable listed into a single table. NOTE: Freq table/out= captures only the last listed variable. Those counts can be used to construct the format according to the 'othering' rules you want to implement.
data have;
do row = 1 to 1000;
array x x1-x10;
do over x;
if row < 600
then x = ceil(100*ranuni(123));
else x = ceil(150*ranuni(123));
end;
output;
end;
run;
ods output onewayfreqs=counts;
proc freq data=have ;
table x1-x10;
run;
data count_stack;
length name $32;
set counts;
array x x1-x10;
do over x;
name = vname(x);
value = x;
if value then output;
end;
keep name value frequency;
run;
proc sort data=count_stack;
by name descending frequency ;
run;
data cntlin;
do _n_ = 1 by 1 until (last.name);
set count_stack;
by name;
length fmtname $32;
fmtname = trim(name)||'top';
start = value;
label = cats(value);
if _n_ < 11 then output;
end;
hlo = 'O';
label = 'Other';
output;
run;
proc format cntlin=cntlin;
run;
ods html;
proc freq data=have;
table x1-x10;
format
x1 x1top.
x2 x2top.
x3 x3top.
x4 x4top.
x5 x5top.
x6 x6top.
x7 x7top.
x8 x8top.
x9 x9top.
x10 x10top.
;
run;

Converting data set in SAS for 1-way anova

Essentially I need to reorder my data set.
The data consists of 4 columns, one for each treatment group. I'm trying to run a simple 1-way anova in SAS but I don't know how to reorder the data so that there are two columns, one with the responses and one with the treatments.
Here is some example code to create example data sets.
data have;
input A B C D;
cards;
26.72 37.42 11.23 44.33
28.58 56.46 29.63 76.86
29.71 51.91 . .
;
run;
data want;
input Response Treatment $;
cards;
26.72 A
28.58 A
29.71 A
37.42 B
56.46 B
51.91 B
11.23 C
29.63 C
44.33 D
76.86 D
;
run;
I'm sure this is a very simple solution but I didn't see the same thing asked elsewhere on the site. I'm typically an R user but have to use SAS for this analysis so I could be looking for the wrong keywords.
I have used proc transpose for this, see below
/*1. create row numbers for each obs*/
data have1;
set have;
if _n_=1 then row=1;
else row+1;
run;
proc sort data=have1; by row; run;
/*Transpose the dataset by row number*/
proc transpose data=have1 out=want0;
by row;
run;
/*Final dataset by removing missing values*/
data want;
set want0;
drop row;
if COL1=. then delete;
rename _NAME_=Response
COL1=Treatment;
run;
proc sort data=want; by Response; run;
proc print data=want; run;
If that is your data for which you must use SAS just read so that you get the structure required for ANOVA.
data have;
do rep=1 to 3;
do trt='A','B','C','D';
input y #;
output;
end;
end;
cards;
26.72 37.42 11.23 44.33
28.58 56.46 29.63 76.86
29.71 51.91 . .
;;;;
run;
proc print;
run;

How to write a concise list of variables in table of a freq when the variables are differentiated only by a suffix?

I have a dataset with some variables named sx for x = 1 to n.
Is it possible to write a freq which gives the same result as:
proc freq data=prova;
table s1 * s2 * s3 * ... * sn /list missing;
run;
but without listing all the names of the variables?
I would like an output like this:
S1 S2 S3 S4 Frequency
A 10
A E 100
A E J F 300
B 10
B E 100
B E J F 300
but with an istruction like this (which, of course, is invented):
proc freq data=prova;
table s1:sn /list missing;
run;
Why not just use PROC SUMMARY instead?
Here is an example using two variables from SASHELP.CARS.
So this is PROC FREQ code.
proc freq data=sashelp.cars;
where make in: ('A','B');
tables make*type / list;
run;
Here is way to get counts using PROC SUMMARY
proc summary missing nway data=sashelp.cars ;
where make in: ('A','B');
class make type ;
output out=want;
run;
proc print data=want ;
run;
If you need to calculate the percentages you can instead use the WAYS statement to get both the overall and the individual cell counts. And then add a data step to calculate the percentages.
proc summary missing data=sashelp.cars ;
where make in: ('A','B');
class make type ;
ways 0 2 ;
output out=want;
run;
data want ;
set want ;
retain total;
if _type_=0 then total=_freq_;
percent=100*_freq_/total;
run;
So if you have 10 variables you would use
ways 0 10 ;
class s1-s10 ;
If you just want to build up the string "S1*S2*..." then you could use a DO loop or a macro %DO loop and put the result into a macro variable.
data _null_;
length namelist $200;
do i=1 to 10;
namelist=catx('*',namelist,cats('S',i));
end;
call symputx('namelist',namelist);
run;
But here is an easy way to make such a macro variable from ANY variable list not just those with numeric suffixes.
First get the variables names into a dataset. PROC TRANSPOSE is a good way if you use the OBS=0 dataset option so that you only get the _NAME_ column.
proc transpose data=have(obs=0) ;
var s1-s10 ;
run;
Then use PROC SQL to stuff the names into a macro variable.
proc sql noprint;
select _name_
into :namelist separated by '*'
from &syslast
;
quit;
Then you can use the macro variable in your TABLES statement.
proc freq data=have ;
tables &namelist / list missing ;
run;
Car':
In short, no. There is no shortcut syntax for specifying a variable list that crosses dimension.
In long, yes -- if you create a surrogate variable that is an equivalent crossing.
Discussion
Sample data generator:
%macro have(top=5);
%local index;
data have;
%do index = 1 %to &top;
do s&index = 1 to 2+ceil(3*ranuni(123));
%end;
array V s:;
do _n_ = 1 to 5*ranuni(123);
x = ceil(100*ranuni(123));
if ranuni(123) < 0.1 then do;
ix = ceil(&top*ranuni(123));
h = V(ix);
V(ix) = .;
output;
V(ix) = h;
end;
else
output;
end;
%do index = 1 %to &top;
end;
%end;
run;
%mend;
%have;
As you probably noticed table s: created one freq per s* variable.
For example:
title "One table per variable";
proc freq data=have;
tables s: / list missing ;
run;
There is no shortcut syntax for specifying a variable list that crosses dimension.
NOTE: If you specify out=, the column names in the output data set will be the last variable in the level. So for above, the out= table will have a column "s5", but contain counts corresponding to combinations for each s1 through s5.
At each dimensional level you can use a variable list, as in level1 * (sublev:) * leaf. The same caveat for out= data applies.
Now, reconsider the original request discretely (no-shortcut) crossing all the s* variables:
title "1 table - 5 columns of crossings";
proc freq data=have;
tables s1*s2*s3*s4*s5 / list missing out=outEach;
run;
And, compare to what happens when a data step view uses a variable list to compute a surrogate value corresponding to the discrete combinations reported above.
data haveV / view=haveV;
set have;
crossing = catx(' * ', of s:); * concatenation of all the s variables;
keep crossing;
run;
title "1 table - 1 column of concatenated crossings";
proc freq data=haveV;
tables crossing / list missing out=outCat;
run;
Reality check with COMPARE, I don't trust eyeballs. If zero rows with differences (per noequal) then the out= data sets have identical counts.
proc compare noprint base=outEach compare=outCat out=diffs outnoequal;
var count;
run;
----- Log -----
NOTE: There were 31 observations read from the data set WORK.OUTEACH.
NOTE: There were 31 observations read from the data set WORK.OUTCAT.
NOTE: The data set WORK.DIFFS has 0 observations and 3 variables.
NOTE: PROCEDURE COMPARE used (Total process time)

Saving results from SAS proc freq with multiple tables

I'm a beginner in SAS and I have the following problem.
I need to calculate counts and percents of several variables (A B C) from one dataset and save the results to another dataset.
my code is:
proc freq data=mydata;
tables A B C / out=data_out ; run;
the result of the procedure for each variable appears in the SAS output window, but data_out contains the results only for the last variable. How to save them all in data_out?
Any help is appreciated.
ODS OUTPUT is your answer. You can't output directly using the OUT=, but you can output them like so:
ods output OneWayFreqs=freqs;
proc freq data=sashelp.class;
tables age height weight;
run;
ods output close;
OneWayFreqs is the one-way tables, (n>1)-way tables are CrossTabFreqs:
ods output CrossTabFreqs=freqs;
ods trace on;
proc freq data=sashelp.class;
tables age*height*weight;
run;
ods output close;
You can find out the correct name by running ods trace on; and then running your initial proc whatever (to the screen); it will tell you the names of the output in the log. (ods trace off; when you get tired of seeing it.)
Lots of good basic sas stuff to learn here
1) Run three proc freq statements (one for each variable a b c) with a different output dataset name so the datasets are not over written.
2) use a rename option on the out = statement to change the count and percent variables for when you combine the datasets
3) sort by category and merge all datasets together
(I'm assuming there are values that appear in in multiple variables, if not you could just stack the data sets)
data mydata;
input a $ b $ c$;
datalines;
r r g
g r b
b b r
r r r
g g b
b r r
;
run;
proc freq noprint data = mydata;
tables a / out = data_a
(rename = (a = category count = count_a percent = percent_a));
run;
proc freq noprint data = mydata;
tables b / out = data_b
(rename = (b = category count = count_b percent = percent_b));
run;
proc freq noprint data = mydata;
tables c / out = data_c
(rename = (c = category count = count_c percent = percent_c));
run;
proc sort data = data_a; by category; run;
proc sort data = data_b; by category; run;
proc sort data = data_c; by category; run;
data data_out;
merge data_a data_b data_c;
by category;
run;
As ever, there are lots of different ways of doing this sort of thing in SAS. Here are a couple of other options:
1. Use proc summary rather than proc freq:
proc summary data = sashelp.class;
class age height weight;
ways 1;
output out = freqs;
run;
2. Use multiple table statements in a single proc freq
This is more efficient than running 3 separate proc freq statements, as SAS only has to read the input dataset once rather than 3 times:
proc freq data = sashelp.class noprint;
table age /out = freq_age;
table height /out = freq_height;
table weight /out = freq_weight;
run;
data freqs;
informat age height weight count percent;
set freq_age freq_height freq_weight;
run;
This is a question I've dealt with many times and I WISH SAS had a better way of doing this.
My solution has been a macro that is generalized, provide your input data, your list of variables and the name of your output dataset. I take into consideration the format/type/label of the variable which you would have to do
Hope it helps:
https://gist.github.com/statgeek/c099e294e2a8c8b5580a
/*
Description: Creates a One-Way Freq table of variables including percent/count
Parameters:
dsetin - inputdataset
varlist - list of variables to be analyzed separated by spaces
dsetout - name of dataset to be created
Author: F.Khurshed
Date: November 2011
*/
%macro one_way_summary(dsetin, varlist, dsetout);
proc datasets nodetails nolist;
delete &dsetout;
quit;
*loop through variable list;
%let i=1;
%do %while (%scan(&varlist, &i, " ") ^=%str());
%let var=%scan(&varlist, &i, " ");
%put &i &var;
*Cross tab;
proc freq data=&dsetin noprint;
table &var/ out=temp1;
run;
*Get variable label as name;
data _null_;
set &dsetin (obs=1);
call symput('var_name', vlabel(&var.));
run;
%put &var_name;
*Add in Variable name and store the levels as a text field;
data temp2;
keep variable value count percent;
Variable = "&var_name";
set temp1;
value=input(&var, $50.);
percent=percent/100; * I like to store these as decimals instead of numbers;
format percent percent8.1;
drop &var.;
run;
%put &var_name;
*Append datasets;
proc append data=temp2 base=&dsetout force;
run;
/*drop temp tables so theres no accidents*/
proc datasets nodetails nolist;
delete temp1 temp2;
quit;
*Increment counter;
%let i=%eval(&i+1);
%end;
%mend;
%one_way_summary(sashelp.class, sex age, summary1);
proc report data=summary1 nowd;
column variable value count percent;
define variable/ order 'Variable';
define value / format=$8. 'Value';
define count/'N';
define percent/'Percentage %';
run;
EDIT (2022):
Better way of doing this is to use the ODS Tables:
/*This code is an example of how to generate a table with
Variable Name, Variable Value, Frequency, Percent, Cumulative Freq and Cum Pct
No macro's are required
Use Proc Freq to generate the list, list variables in a table statement if only specific variables are desired
Use ODS Table to capture the output and then format the output into a printable table.
*/
*Run frequency for tables;
ods table onewayfreqs=temp;
proc freq data=sashelp.class;
table sex age;
run;
*Format output;
data want;
length variable $32. variable_value $50.;
set temp;
Variable=scan(table, 2);
Variable_Value=strip(trim(vvaluex(variable)));
keep variable variable_value frequency percent cum:;
label variable='Variable'
variable_value='Variable Value';
run;
*Display;
proc print data=want(obs=20) label;
run;
The option STACKODS(OUTPUT) added to PROC MEANS in 9.3 makes this a much simpler task.
proc means data=have n nmiss stackods;
ods output summary=want;
run;
| Variable | N | NMiss |
| ------ | ----- | ----- |
| a | 4 | 3 |
| b | 7 | 0 |
| c | 6 | 1 |