Error with Default Temporal Covariate Settings + PLP Lasso Logistic Regression

[bechlerk]

When using settings = CreateDefaultTemporalCovariateSettings(), running the getPlpData + createStudyPopulation works fine, but when running the lasso logistic regression model I receive the error below. Error still occurs even when segment to different subsets of temporal covariates (i.e. just demographics and condition). However, when using settings = CreateDefaultCovariateSettings(), the lasso logistic regression model runs smoothly with no error.

[jreps]

Hello. This error is expected, but we should have an input check to warn people and clearer documentation. The majority of the PLP classifiers only support 2d (patient x covariate) data, the CreateDefaultTemporalCovariateSettings() creates 3d (patient x covariate x time) data. The deep learning classifiers generally accept 3d data, but those are the only ones that will. I'll add in an input check and stop() to make sure the plpData are 2d for the non-deep learning classifiers. I'll also make sure this is clear in the PLP manual files. Thanks, Jenna.