find_ and get_ methods with models of multiple formula components like clm() & lme()

[strengejacke]

Fixes #727

[vincentarelbundock]

@strengejacke, nlme::lme() are kind of weird with the indexing, and I don’t know them well enough to say exactly what the best strategy is. But there are still some issues. For example, consider this model from the nlme docs:

library(nlme)
library(insight)
model <- lme(distance ~ age + Sex, data = Orthodont, random = ~ 1)

dat <- get_data(model)

head(Orthodont)
# Grouped Data: distance ~ age | Subject
#   distance age Subject  Sex
# 1     26.0   8     M01 Male
# 2     25.0  10     M01 Male
# 3     29.0  12     M01 Male
# 4     31.0  14     M01 Male
# 5     21.5   8     M02 Male
# 6     22.5  10     M02 Male

head(dat)
#   distance age  Sex
# 1     26.0   8 Male
# 2     25.0  10 Male
# 3     29.0  12 Male
# 4     31.0  14 Male
# 5     21.5   8 Male
# 6     22.5  10 Male

predict(model, newdata = dat)
# Error in predict.lme(model, newdata = dat): cannot evaluate groups for desired levels on 'newdata'

Which fails because get_data does not retrieve the Subject column, which is required for the random effects, even though it is not explicitly given to random=~1

[strengejacke]

ok, that issue should be fixed (wait for commit, I'm, fixing tests). Can you then please check this example?

  # from easystats/insight/482
  cr <- corAR1(form = ~ 1 | Mare)
  m4 <- lme(follicles ~ Time, Ovary, correlation = cr)