collect_metrics() doesn't return .weight_time and .pred_censored

[EmilHvitfeldt]

I expected to get those columns back in the .pred column. Especially since they are used to calculate the metrics

library(tidymodels)
library(censored)
#> Loading required package: survival

set.seed(1)
sim_dat <- prodlim::SimSurv(500) %>%
  mutate(event_time = Surv(time, event)) %>%
  select(event_time, X1, X2) %>%
  as_tibble()

set.seed(2)
split <- initial_split(sim_dat)
sim_tr <- training(split)
sim_te <- testing(split)
sim_rs <- vfold_cv(sim_tr)

time_points <- c(10, 1, 5, 15)

mod_spec <-
  proportional_hazards(penalty = tune(), mixture = 1) %>%
  set_engine("glmnet") %>%
  set_mode("censored regression")

grid <- tibble(penalty = 10^c(-4, -2, -1))

gctrl <- control_grid(save_pred = TRUE)

mix_mtrc <- metric_set(brier_survival, brier_survival_integrated, concordance_survival)

set.seed(2193)
tune_res <-
  mod_spec %>%
  tune_grid(
    event_time ~ X1 + X2,
    resamples = sim_rs,
    grid = grid,
    metrics = mix_mtrc,
    eval_time = time_points,
    control = gctrl
  )

collect_predictions(tune_res) %>%
  slice(1) %>%
  pull(.pred)
#> [[1]]
#> # A tibble: 4 × 3
#>   .eval_time .pred_survival .weight_censored
#>        <dbl>          <dbl>            <dbl>
#> 1         10        0.227               1.12
#> 2          1        0.983               1.02
#> 3          5        0.618               1.12
#> 4         15        0.00746             1.12

[hfrick]

Chatting with Max, this is still how we want it to be: .weight_time and .pred_censored are used to calculate the metrics but not metrics themselves thus not showing up here!

[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.