@alepage wrote: I want to map company ='A' if the macro variable &cie = b1 and map company ='B' if the macro variable &cie=b2   Of course even with this brief description, we don't know if b1 is a variable in your data set or a value of the variable. Similarly for b2. And we don't know if the value of &cie is supposed to be a text string or the name of a variable or something else. These very brief problem descriptions are rarely sufficient.   Please explain in words the problem you are trying to solve using the macro variable, making it clear what &cie contains and what b1 and b2 represent.   Also, you didn't provide a data set (which you should always do), so that would make things clearer. Use these instructions and examples to provide a data set. ... View more

Your hours must be character variables, not numeric variables. You can't sum character variables. You can convert these into actual numbers. If you can show us how the variable hours appears in your data (just type in an example), we can advise further. ... View more

Any method in SAS that sums a numeric variable will work.    Almost no one here will download Excel files as they can be security threats. The best way to include data in your example is via working SAS data step  code (instructions and examples).   For example, here is code using PROC SUMMARY which does the summing. I have made up variable names since I don't know the variable names in your Excel file. This assumes that 1:30 (one hour 30 minutes) is numeric and unformatted appears as 5400 (which is 60 seconds per minute * 60 minutes per hour * 1.5 hours). It gives the sum of the number of seconds. It also works if 1 hour and 30 minutes is represented as 1.5, then it gives the sum of the number of hours.   proc summary data = ____________; class stype year student_id; var hours; output out=sums sum=sum_hours; run;   ... View more

I can think of two reasons why you still might want to use PROC PLS instead of PROC NOMINALDR.   You don't have access to SAS Viya, so you cannot run PROC NOMINALDR PROC PLS has a built in feature which lets you replace missing values using the EM algorithm. ... View more

PROC PLS is designed for partial least squares regression, which seeks linear combinations of predictor variables that explain as much variation as possible in the response variables. In PROC PLS, the response (Y) variables must be numeric. Therefore, when predictors are binary or categorical, they can be specified in the CLASS statement, but they cannot be used as response variables in the MODEL statement (otherwise an error is returned). As a result, you cannot make the X-variables identical to the Y-variables when the inputs are binary or categorical specified in CLASS statement.     Binary or categorical variables can be replaced by dummy variables as responses in PROC PLS. And then you use the same dummy variables on both sides of the PLS equation. So it can be done. Whether or not it is a good idea, I can't say. ... View more

This article shows how to do it. It imports all .csv files in a folder, but since your files are .txt then you can just change .csv to .txt   https://www.lexjansen.com/mwsug/2013/RF/MWSUG-2013-RF01.pdf ... View more

Please show us the FULL COMPLETE log for this PROC SQL.   In the future, please always (that's 100% of the time, don't wait for us to ask) show us the FULL COMPLETE log for any PROC that gives you an error. ... View more

Regarding supervised methods, PLS and variations such as PLS-DA (discriminant analysis), hazard analysis PLS and logistic PLS work as supervised methods (but those are not available in SAS as far as I know).  ... View more

What about using PROC PLS to perform a principal components analysis on either binary, categorical or continuous input (or any mix thereof)? If you make the x-variables identical to the y-variables in PROC PLS, you get PCA, and dimension reduction is then possible.   How would this compare to any of the above? ... View more

Do NOT show us partial logs!!   Show us the COMPLETE log for this PROC SQL — showing the PROC SQL statement in the log all the way down to the last note after the PROC SQL. Always show us the complete log for whatever PROC is causing the problem — always.   Clearly, you are either accessing a data set which has zero observations, or you have a WHERE clause in PROC SQL that selects zero observations (or both). That's why you get the messages you are seeing. ... View more

Why so complicated?   Why create a temporary data set named _XTEMP? Why not just use the data set TRXTB._XTEMP in the macro? ... View more

Yes, which is why I complained to the OP that we need rules, not examples.  We cannot determine the full scope of the requirements by working from 2 examples, so I usually try to be comprehensive and handle all cases in my reply. In any event, the OP is silent on whether or not both the min and the max can be negative, and he/she can decide if the code needs to handle the case where both are negative. ... View more

If the min value is negative and the max value is negative, you need a separate case to handle this. In this case, you want MAX=0, not MIN=0.   ... View more