Uninformative error for `predict()` when default type isn't available

[EmilHvitfeldt]

The glmnet engine doesn't at this time have a time prediction module, which is the default. The error message is not quite clear.

It was initially unclear to me what prediction module was referring to and that it could be fixed by setting a different type.

library(censored)
library(survival)

lung2 <- lung[-14, ]

  # penalty specification: in predict()
  cox_spec <- proportional_hazards() %>%
    set_mode("censored regression") %>%
    set_engine("glmnet")

f_fit <- fit(cox_spec, Surv(time, status) ~ age + ph.ecog, data = lung2)

predict(f_fit, 
        new_data = lung2[1, ], 
         penalty = 0.123)
#> Error: No prediction module defined for this model.

^{Created on 2021-04-27 by the reprex package (v1.0.0)}

[github-actions]

This issue has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex: https://reprex.tidyverse.org) and link to this issue.