Then OP also need to control the max value(check its max >0 or <0) ? But OP only mentioned the ranges [-5,20] and [5,20]. ... View more

No need it I think. If the min value less than 0 , &min. would be its min value. Otherwise, &min would be 0. Of course, you could make it more complicated if you need to control MAX value too. ... View more

Yeah. Agree. It is all depend on what OP want. This example maybe is just an example, only OP know the real demand and real data . ... View more

As Tom pointed out ,using strip to get rid of trailing blanks: pos1 = find(string, strip( char_substring )); Otherwise ,sas would take 3000 as 3000blankblank..... Not 3000 ... View more

If these files have the same data constructure, that would be easy by FILEVAR= option.   data path; input path $80.; cards; c:\temp\a\PRJ__20221201_13227_MF.txt c:\temp\a\PRJ__20221201_13228_MF.txt ; data MF; set path; length from_file file $ 80; infile dummy filevar=path end=last filename=file truncover; from_file=file; do until(last); input a $ b $ c $; output; end; run;       If you don't like to type file name by hand, try this one:   /* data path; input path $80.; cards; c:\temp\a\PRJ__20221201_13227_MF.txt c:\temp\a\PRJ__20221201_13228_MF.txt ; */ %let path= c:\temp\a ; data path; length path $ 200; rc=filename('x',"&path."); did=dopen('x'); do i=1 to dnum(did); file=dread(did,i); if prxmatch('/.+MF\.txt$/i',strip(file)) then do; path=catx('\',"&path.",file); output; end; end; keep path; run; data MF; set path; length from_file file $ 200; infile dummy filevar=path end=last filename=file truncover; from_file=file; do until(last); input a $ b $ c $; output; end; run; ... View more

Also could check PROC MIXED or PROC GLIMMIX . ... View more

Yes. Make a macro to deal with it.   proc sql noprint; select ifn(min(ind_off25_min)>0,0,min(ind_off25_min)) into :min trimmed from _dif_temp_coll; quit; %put &=min; proc sgplot data=_dif_temp_coll; series x=endrange_n y=ind_min_dif / lineattrs=( color=blue thickness=2 pattern=solid); series x=endrange_n y=ind_off25_min / y2axis lineattrs=( color=red thickness=2 pattern=solid); refline &endind./axis=y lineattrs=(color=lime thickness=1 pattern=solid); refline 0/axis=x lineattrs=(color=lime thickness=1 pattern=solid); y2axis min=&min. ; run;quit; ... View more

The most simple way is using OS command like Patrick did. If you are unable to run OS command, the best choice is using macro %dtree written by Tom . https://github.com/sasutils/macros/blob/master/dirtree.sas This macro list all the file under a path include its sub-path. And you need to filter the output to fit  *.zipx extension .   And I quoted: /* https://github.com/sasutils/macros/blob/master/dirtree.sas */ %macro dirtree /*--------------------------------------------------------------------------- Build dataset of files in directory tree(s) ----------------------------------------------------------------------------*/ (directory /* Pipe delimited directory list (default=.) */ ,out=dirtree /* Output dataset name */ ,maxdepth=120 /* Maximum tree depth */ ); /*--------------------------------------------------------------------------- Use SAS functions to gather list of files and directories directory - Pipe delimited list of top level directories out - Dataset to create maxdepth - Maximum depth of subdirectories to query Output dataset structure --NAME-- Len Format Description FILENAME $256 Name of file in directory TYPE $1 File or Directory? (F/D) SIZE 8 COMMA20. Filesize in bytes DATE 4 YYMMDD10. Date file last modified TIME 4 TOD8. Time of day file last modified DEPTH 3 Tree depth PATH $256 Directory name Size is not available for the directories. LASTMOD timestamp is only available on Unix for directories. Will not scan the subtree of a directory with a path that is longer then 256 bytes. For such nodes TYPE will be set to L . ----------------------------------------------------------------------------*/ %local fileref ; %let fileref=__FL__ ; %if 0=%length(&directory) %then %let directory=. ; * Setup dataset and seed with starting directory list ; data &out; length filename $256 type $1 size 8 date time 4 depth 3 path $256 ; retain filename ' ' depth 0 type ' ' date . time . size . ; format size comma20. date yymmdd10. time tod8. ; do _n_=1 to countw(symget('directory'),'|'); path=scan(symget('directory'),_n_,'|'); output; end; run; %* Allow use of empty OUT= dataset parameter ; %let out=&syslast; data &out; modify &out; retain sep "%sysfunc(ifc(&sysscp=WIN,\,/))"; retain maxdepth &maxdepth; * Create FILEREF pointing to current file/directory ; rc1=filename("&fileref",catx('/',path,filename)); if rc1 then do; length message $256; message=sysmsg(); put 'ERROR: Unable to create fileref for ' path= filename= ; put 'ERROR- ' message ; stop; end; * Try to open as a directory to determine type ; did=dopen("&fileref"); type = ifc(did,'D','F'); if type='D' then do; * Make sure directory name is not too long to store. ; if length(catx('/',path,filename)) > vlength(path) then do; put 'NOTE: Directory name too long. ' path= filename= ; type='L'; rc3=dclose(did); end; else do; * Move filename into the PATH and if on Unix set lastmod ; path=catx(sep,path,filename); filename=' '; if sep='/' then do; lastmod = input(dinfo(did,doptname(did,5)),nldatm100.); date=datepart(lastmod); time=timepart(lastmod); end; end; end; else do; * For a file try to open file and get file information ; fid=fopen("&fileref",'i',0,'b'); if fid then do; lastmod = input(finfo(fid,foptname(fid, 5)), nldatm100.); date=datepart(lastmod); time=timepart(lastmod); size = input(finfo(fid,foptname(fid,ifn(sep='/',6,4))),32.); rc2 = fclose(fid); end; end; * Update the observation in the dataset ; replace; if type='D' then do; * When current file is a directory add directory members to dataset ; depth=depth+1; if depth > maxdepth then put 'NOTE: ' maxdepth= 'reached, not reading members of ' path= ; else do i=1 to dnum(did); filename=dread(did,i); output; end; rc3=dclose(did); end; * Clear the fileref ; rc4=filename("&fileref"); run; %mend dirtree;   ... View more

"For longer strings the array size must increase correct? " Nope. array is used for checking sub-string ,not whole string. Here I check sub-string which's length is 1,2,3,4,...10. "Also the string length can and is quite long, what other adjustments are required to account for that?" You need to change the following line: length new_a new_b str_short str_long $ 200; As I commented that max length of string is 200. if you have string longer, change 200 into other number. "Lastly, is a lower score a better match or a higher one?" A higher score match better. I already sort it by WEIGHT decending. The first obs in each group (a.obs) is the best match , you can just keep it and drop others . ... View more

Your LAG() is safe. a.k.a LAG() is not executed under IF condition. About the LAG() in IF statement, LAG() would executed every time(or data loop) , therefore you do not need to worry about it . If you know the exactly logic behind LAG(), you would also get the right code or result. For example: If you want last obs subtract the first obs in each group when each group has at least 2 obs, you could code like:   data x; input a b; cards; 1 1 1 2 1 3 1 4 2 12 2 13 2 14 ; data y; set x; by a; if first.a or last.a then first=lag(b); if last.a then diff=b-first; run;   ... View more

And the most simple way is if you know the number of obs in each group you need to remove, just assign them in PROC SURVEYSELECT.   /******************/ data samplesize; input group samplesize; cards; 1 2 2 1 3 1 4 1 5 1 6 2 7 3 8 1 9 1 10 1 11 1 ; proc surveyselect data=have sampsize=samplesize seed=123 out=want; strata group; run; ... View more

The first thing is combining all the variables into one variables . a.k.a make a column for a row. Here could give you a start.   data have; set sashelp.heart(obs=100); length row $ 200; obs+1; row=catx('|',of _all_); keep obs row; run; proc fcmp outlib=work.math.func; function fuzz_match(a $,b $) ; length new_a new_b str_short str_long $ 200; /*only support the max length of string is 200*/ new_a=kcompress(a,'|','kad'); new_b=kcompress(b,'|','kad'); if klength(a)<klength(b) then do; str_short=new_a;str_long=new_b; end; else do; str_short=new_b;str_long=new_a; end; array count{10} _temporary_ (0 0 0 0 0 0 0 0 0 0); /*The count of one string ,two string , three string....*/ array weight{10} _temporary_ (2 4 8 16 32 64 128 256 512 1024); /*The weight of one string ,two string , three string....*/ max_str_len=min(10,klength(a),klength(b)); /*Search the max length of str is 10*/ do len=1 to max_str_len; /*Search string which's length is 1, 2, 3.......*/ n=0; do start=1 to klength(str_short)+1-len; /*Search sub-string in long string*/ if kfind(str_long,strip(ksubstr(str_short,start,len))) then n+1; end; count{len}=n; end; sum=0;w=0;mean=0; do k=1 to max_str_len; if count{k} ne 0 then do;sum+count{k}*weight{k}; w+weight{k};end; end; /*Calculated weight mean if w=0 then mean=0; else mean=sum/w; */ if a=b then sum=constant('exactint'); return (sum); /*return weight sum or weight mean(mean)*/ endsub; run; options cmplib=work.math; proc sql; create table want as select a.obs,a.row as row1,b.obs as obs2,b.row as row2,fuzz_match(a.row,b.row) as weight from have as a,have as b where a.obs ne b.obs order by a.obs,weight desc; quit;     ... View more

OK. Assuming each group at least has 3 obs. And this code could give you a start. I think there were many scenarios you would not like to see. E.X. this code is work for n=10 not for n=15. How would you to do when n=14 or n=15 or n=16?     proc plan seed=34721; factors group=11 / noprint; output out=have; run; data have(drop=size); set have curobs=tmp; if tmp<=2 then size = 4; else size = 3; do observation = 1 to size; output; end; run; proc sort data=have; by group; run; %macro sample(n=); data have2; set have; run; %do i=1 %to &n.; /*Randomly pick up an obs and output it*/ proc surveyselect data=have2 out=one sampsize=1 seed=123 noprint; run; proc append base=want data=one;run; proc sql; /*exclude this obs from have*/ create table rest as select * from have2 except select * from one ; quit; /*calcuate the count of each group*/ proc freq data=rest noprint; table group/out=freq nocum nopercent; run; proc sql; /*exclue the group when its count equal 2*/ create table have2 as select * from rest where group not in (select distinct group from freq where count=2); quit; %end; %mend; proc delete data=want;run; %sample(n=10) /*Check the result, The want dataset is the obs you want to exclude*/ proc print data=want;run;     ... View more

Using CALL EXECUTE(), your macro variable's max length is 65534.  Once you have lots of variable label, your code is unable to work.   data labels_info_tbl; infile datalines dlm="," dsd; length label $100 Var_name $10; input Var_name $ label; cards; custID,Customer Id number Wealth,wealth in bank in USD education,level of education ; run; data have; /*label*/ /*custID= 'Customer Id number'*/ /*Wealth= 'wealth in bank in USD'*/ /*education= 'level of education'*/ /*;*/ input custID Wealth education; cards; 111 30000 15 222 7000 12 333 350000 21 ; Run; data _null_; set labels_info_tbl end=last; if _n_=1 then call execute('proc datasets library=work nodetails nolist;modify have;label '); call execute(catt(var_name,"='",label,"'")); if last then call execute(';quit;'); run;   ... View more