Estimate training timeSource:
Estimate training time
(integer) how many trees should be fit in order to estimate the time needed to train
object. The default value is 50, as this usually gives a good enough approximation.
a difftime object.
# specify but do not train the model by setting no_fit = TRUE. object <- orsf(pbc_orsf, Surv(time, status) ~ . - id, n_tree = 500, no_fit = TRUE) # grow 50 trees to approximate the time it will take to grow 500 trees time_estimated <- orsf_time_to_train(object, n_tree_subset = 50) print(time_estimated) #> Time difference of 0.2739909 secs # let's see how close the approximation was time_true_start <- Sys.time() fit <- orsf_train(object) time_true_stop <- Sys.time() time_true <- time_true_stop - time_true_start print(time_true) #> Time difference of 0.2489538 secs # error abs(time_true - time_estimated) #> Time difference of 0.02503705 secs