Cannot predict on new data after using weights during fit

[mfansler]

Problem

The predict function does not work if a weights argument is specified during model fitting and the newdata argument is of different length than the original data.

Reproducible Example

library(DirichletReg)
data("ArcticLake")

ArcticLake$Y <- DR_data(ArcticLake[,c(1,2,3)])
wts <- sample(c(1,2), nrow(df_al), replace=TRUE)

model_al <- DirichReg(Y ~ depth, ArcticLake, weights=wts)

predict(model_al, newdata=ArcticLake[1:10,])

which results in the error:

Error in model.frame.default(terms(formula, lhs = lhs, rhs = rhs, data = data,  : 
  variable lengths differ (found for '(weights)')

Additional Info

If data is the same length as the original data it works fine. To verify that the weights make no difference to the actual prediction, we can shuffle the data before or after, observing the same results:

idx_shuffle <- sample.int(nrow(ArcticLake))

pred1 <- predict(model_al, newdata=ArcticLake)[idx_shuffle,]
pred2 <- predict(model_al, newdata=ArcticLake[idx_shuffle,])

all(pred1 == pred2)
## TRUE

System Details

> sessionInfo()
R version 4.1.3 (2022-03-10)
Platform: x86_64-apple-darwin13.4.0 (64-bit)
Running under: macOS Big Sur 11.6.7

Matrix products: default
LAPACK: /Users/mfansler/miniconda3/envs/brms_r41/lib/libopenblasp-r0.3.20.dylib

locale:
[1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] DirichletReg_0.7-1 Formula_1.2-4     

loaded via a namespace (and not attached):
 [1] zoo_1.8-10       compiler_4.1.3   generics_0.1.2   miscTools_0.6-26 sandwich_3.0-2   tools_4.1.3      maxLik_1.5-2    
 [8] grid_4.1.3       digest_0.6.29    lattice_0.20-45