How do I get a LIME explanation for a specific observation is sas viya 3.5? I want to be able to explain why a specific customer has a high probability value on a model.   ... View more

I am working on a SAS viya 3.5 job. I am using the tasks UI xml to define the inputs. The first input is organization number. I want to set the next input, sector, to the organizations sector from the same table. But I still want the user to be able to override the default value in case the information is dated. I now have a filter that filters out and return the correct sector, but I can't change the value. Is there a way to only let the filter determine the default value for each organization number, but still be able to change sector?    One way to solve this would be to have two boxes, one that filters out the default, and another optional box with an unfiltered list of all sector that overrides the macro value if present. But ideally, I want the value to just be a default that ban be overridden.  ... View more

I have some grouped bar charts. I want one of the categories (Blue/1) to be the bottom color in each bar. But the default seems to be the category with the highest frequency count. This makes it really hard and annoying to compare the columns:   The same problem in bar charts for different variables: How can I have the same color/value in the same order, so that 1/Blue is always the bottom color? ... View more

I am trying to update a table in a sql database from viya, using proc sql insert. However, the characters have turned into Chinese on the way from VIYA to the sql database.   Is this a known issue? I would guess this has something to do with encoding.   The same code works from SAS 9.4.     ... View more

Is there any way to change the threshold for missing values after in Model Studio after the initial project has been created?    If I create a project by point and click, I can go to Advanced and increase the threshold for missing values. But when creating a project through the API, there doesn't seem to be a way to use anything other than the default settings. And I can't find any way to change the settings after the project has been created. I could use a data preprocessing step to change the metadata, but I don't have access to the table with the missing percetages and reasons for rejected variables. I guess I could do a count in the data step, but it seems very strange that there is no option to override this in the API or change the settings after the project is created.  ... View more

I want to set up some data drift monitoring. My first inclination was to write some code to get missing, mean, median, min, max etc for each column in my datasets (aobut 2000 variables). But the Run profile in Data explorer does most of what I want, so I was wondering if there is a way to use the Profiling to create a dataset that allows me to monitor how a dataset changes from day to day. The relevant dataset is uploaded each day as part of scoring data, so I would somehow need to call the Run Profile task e.g. via the VIYA API, and store the profile results for each day.  I couldn't find anything about running data profiles on developer.sas.com. Is this a dead end? Am I better off just writing some proc meas and transposes? Or are the data profiles meant to be used as a means to monitor data drift?   ... View more