In Using Proc SurveySelect (from SAS 9.4)  for sampling Train and Validation data-sets in an 80-20 split, I find that the number of records does not exactly correspond to 80% of the original for the Train set (or exactly 20% in the Validation set). Is this normal ? One of my strata variables contains missing values (about 2% of variable D is missing).   The original data-set, overall_new, contains 15,573 rows and 80% of it is 12458 rows. In the resulting data-sets , the Train set , intime_TR, has 12475 rows, which is more than 12,458. Any ideas why this might be so?   Thanks!       proc surveyselect data=overall_new out=sorted_intime noprint seed=1234 method=srs samprate=80 outall; strata A B C D; run; /*12475 rows*/ data intime_TR; set sorted_intime; if selected =1; run; /*3098 rows*/ data intime_VAL; set sorted_intime; if selected =0; run;   ... View more

Hi, I previously generated two stratified random sample  Train and Validation data-sets using a fixed seed value(=1234).   However, on a subsequent run of the same code, I am unable to replicate the same data-sets exactly. I find that on this second run, some records in the original train set are now in validation and vice versa.The number of rows in each Train and Validation pair is a constant, though (each time its 12,475 and 3098 rows each). Could this be due to some weird sort order in the input data being different? I can't think of anything else. Here is roughly the code I used: proc sort data=overall_new; by A B C D; /* A,B,C,D are strata variables */ run;   proc surveyselect data=overall_new out=sorted_intime noprint seed=1234 method=srs samprate=80 outall; strata A B C D; run; /*Train data - 12475 rows*/ data local.intime_TR0516; set sorted_intime; if selected =1; run; /*Validation data - 3098 rows*/ data local.intime_VAL0516; set sorted_intime; if selected =0; run;   ... View more

Hi all, My problem is to break up a large data-set into smaller ones as below. I have a data set containing about ~1000 variables. I converted each of these variable names to macro-variables called: varname1,varname2,,,varname100,...etc.   Now I need to generate smaller data-sets , each containing only 5 variables. For example, I tried the following SAS macro code but I get an error.   %macro batch_Chk(start,fin); %do i =&start %to &fin by 5; %let res=%evalf(&i. + 4); %do j =&i. %to &res. by 1; data words_&i.; /* Words_i are the sub-data-sets with 5 variables each */ set transf_vars; /* Transf_vars is the Original data */ %put &res; /* check res value...*/ keep &&varname&i.- &&varname&res.; %end; run; %end; %mend; %batch_Chk (1,10);       SYMBOLGEN: Macro variable START resolves to 1 SYMBOLGEN: Macro variable FIN resolves to 10 ERROR: A character operand was found in the %EVAL function or %IF condition where a numeric operand is required. The condition was: &fin by 5 ERROR: The %TO value of the %DO I loop is invalid. ERROR: The macro BATCH_CHK will stop executing.   My goal is to have the 1000 variables (along with their content)  broken into smaller data-sets with just 5 variables each. I initially thought I could change the variable names to macro-variables and manipulate them inside a DO loop - but I am not getting the results I hoped for. Would really appreciate any advise or help about this problem! Thanks very much! ... View more

Dear all,   I am using Chris Hemedinger's code posted here: http://blogs.sas.com/content/sasdummy/2013/06/12/correlations-matrix-heatmap-with-sas/   to get a heat map of my correlation matrix. The only problem is I have too many variables(>40) so the labels on the axis all overlap and aren't readable anymore.   I think there should be a fix - manipulating the X axis or Y axis display options --- but I'm a total novice with SAS graphics and am not sure what to do. The heat map itself is generated just fine, only the variable names are all lost. Maybe I should try truncating the varaible names?    Thanks for any advice! ... View more