Error in using robyn_run

[Paul-Bell-1992]

Hi,

I've been seeing the below error when trying to run robyn_run and build an initial model, with 7000 iterations and 7 trials. I've tried running less iterations/trials to see if this avoids the error with no luck. It ran fine yesterday on the same data. All I've changed since then, is I've set the hyperparameters to those of yesterday's model, while setting the train size to 1, for the purposes of a test. Any help would be greatly appreciated.

Thanks!

R version 4.4.1
Robyn version: 3.11.1

Error in mutate(): ℹ In argument: nrmse = lares::winsorize(.data$nrmse, nrmse_win). Caused by error in quantile.default()`:
! missing values and NaN's not allowed if 'na.rm' is FALSE

Backtrace:
▆

1. ├─Robyn::robyn_run(...)
2. │ └─Robyn::robyn_converge(OutputModels, ...)
3. │ └─... %>% ...
4. ├─ggplot2::ggplot(...)
5. ├─dplyr::mutate(...)
6. ├─dplyr:::mutate.data.frame(., nrmse = lares::winsorize(.data$nrmse, nrmse_win), na.rm = TRUE)
7. │ └─dplyr:::mutate_cols(.data, dplyr_quosures(...), by)
8. │ ├─base::withCallingHandlers(...)
9. │ └─dplyr:::mutate_col(dots[[i]], data, mask, new_columns)
10. │ └─mask$eval_all_mutate(quo)
11. │ └─dplyr (local) eval()
12. └─lares::winsorize(.data$nrmse, nrmse_win)
13. ├─stats::quantile(x, thresh[1], na.rm = na.rm)
14. └─stats:::quantile.default(x, thresh[1], na.rm = na.rm)

15. └─base::stop("missing values and NaN's not allowed if 'na.rm' is FALSE")
    

Run rlang::last_trace(drop = FALSE) to see 3 hidden frames.

sessionInfo()
R version 4.4.1 (2024-06-14 ucrt)
Platform: x86_64-w64-mingw32/x64
Running under: Windows 10 x64 (build 19045)`