Speed up predictions of survival probabilities for proportional hazards models?

[hfrick]

this applies to the survival and glmnet engines

[EmilHvitfeldt]

It appears that at least some of the slowness comes from interpolate_km_values, but it seems to come mostly from error handling

reprex

set.seed(1234)
.times <- c(100, 200)
x <- tibble::tibble(
  .time = cumsum(sample(1:6, 100, TRUE)),
  .pred_survival = c(1, sort(runif(99), TRUE)),
  .pred_survival_lower = NA,
  .pred_survival_upper = NA,
  .pred_hazard_cumulative = cumsum(runif(100))
)

for (i in 1:1000)
  censored:::interpolate_km_values(x, .times)

[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.