A fix for an issue related to #35. Still not clear, why this happens.…

… If is.zoo(y) and data.table is loaded, the extraction of y leads to a weird class and sort of distruction of the object.

DESCRIPTION

@@ -1,8 +1,8 @@
 Package: greybox
 Type: Package
 Title: Toolbox for Model Building and Forecasting
-Version: 0.6.8.41001
-Date: 2021-02-24
+Version: 0.6.8.41002
+Date: 2021-03-03
 Authors@R: c(person("Ivan", "Svetunkov", email = "[email protected]", role = c("aut", "cre"),
                   comment="Lecturer at Centre for Marketing Analytics and Forecasting, Lancaster University, UK"),
              person("Yves R.", "Sagaert", role = c("ctb"),

NEWS

@@ -1,9 +1,12 @@
-greybox v0.6.8 (Release data: 2021-02-14)
+greybox v0.6.8 (Release data: 2021-03-03)
 ==============
 
 Changes:
 * MAE, MSE etc now have parameter "holdout" instead of "actual". This is needed for consistency purposes with measures() function.
 
+Bugfixes:
+* A fix for an exotic case of zoo + data.table, resulting in destruction of response variable.
+
 
 greybox v0.6.7 (Release data: 2021-02-14)
 ==============

R/alm.R

@@ -994,7 +994,8 @@ alm <- function(formula, data, subset, na.action,
 
     dataWork <- eval(mf, parent.frame());
     dataTerms <- terms(dataWork);
-    y <- dataWork[,1];
+    # Make this numeric, to address potential issues with zoo + data.table
+    y <- as.numeric(dataWork[,1]);
 
     interceptIsNeeded <- attr(terms(dataWork),"intercept")!=0;
     # Create a model from the provided stuff. This way we can work with factors