Bug: slice_derivation() return non-meaningful dataset when input dataset is of 0 row

[clarkliming]

What happened?

using empty (0-row) data set and call slice_derivation will give strange result

advs <- tibble::tribble(
    ~USUBJID, ~VSDTC,       ~VSTPT,             ~VSSEQ,
    "1",      "2020-04-16", NA_character_,      1,
    "1",      "2020-04-16", "BEFORE TREATMENT", 2
  )

  actual <- slice_derivation(
    advs[c(-1, -2), ],
    derivation = derive_vars_dtm,
    args = params(
      dtc = VSDTC,
      new_vars_prefix = "A"
    ),
    derivation_slice(
      filter = str_detect(VSTPT, "PRE|BEFORE"),
      args = params(time_imputation = "first")
    ),
    derivation_slice(
      filter = TRUE,
      args = params(time_imputation = "last")
    )
  )

> actual
# A tibble: 0 × 1
# ℹ 1 variable: data <???>

it breaks down the data structure and cause issues (when there are just no records in the dataset)

Session Information

R version 4.3.3 (2024-02-29)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 22.04.4 LTS

Matrix products: default
BLAS:   /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 
LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.20.so;  LAPACK version 3.10.0

locale:
 [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
 [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
 [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
 [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
 [9] LC_ADDRESS=C               LC_TELEPHONE=C            
[11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       

time zone: Etc/UTC
tzcode source: system (glibc)

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] admiral_1.2.0.9002 testthat_3.2.0    

loaded via a namespace (and not attached):
 [1] htmlwidgets_1.6.4     devtools_2.4.5        remotes_2.5.0        
 [4] processx_3.8.2        callr_3.7.3           vctrs_0.6.4          
 [7] tools_4.3.3           ps_1.7.5              generics_0.1.3       
[10] tibble_3.2.1          fansi_1.0.5           pkgconfig_2.0.3      
[13] desc_1.4.2            lifecycle_1.0.3       compiler_4.3.3       
[16] stringr_1.5.0         brio_1.1.3            httpuv_1.6.15        
[19] htmltools_0.5.8.1     usethis_2.2.2         later_1.4.1          
[22] pillar_1.9.0          crayon_1.5.2          urlchecker_1.0.1     
[25] tidyr_1.3.0           ellipsis_0.3.2        cachem_1.1.0         
[28] sessioninfo_1.2.2     mime_0.12             tidyselect_1.2.0     
[31] digest_0.6.33         stringi_1.7.12        rematch2_2.1.2       
[34] diffobj_0.3.5         dplyr_1.1.3           purrr_1.0.2          
[37] rprojroot_2.0.3       fastmap_1.2.0         cli_3.6.3            
[40] magrittr_2.0.3        pkgbuild_1.4.2        utf8_1.2.3           
[43] withr_2.5.1           admiraldev_1.2.0.9001 diffdf_1.0.4         
[46] prettyunits_1.2.0     waldo_0.5.3           promises_1.3.2       
[49] lubridate_1.9.3       timechange_0.2.0      hms_1.1.3            
[52] memoise_2.0.1         shiny_1.10.0          miniUI_0.1.1.1       
[55] profvis_0.3.8         rlang_1.1.1           Rcpp_1.0.11          
[58] xtable_1.8-4          glue_1.8.0            pkgload_1.3.3        
[61] rstudioapi_0.17.1     R6_2.5.1              fs_1.6.3 

Reproducible Example

advs <- tibble::tribble(
~USUBJID, ~VSDTC, ~VSTPT, ~VSSEQ,
"1", "2020-04-16", NA_character_, 1,
"1", "2020-04-16", "BEFORE TREATMENT", 2
)

actual <- slice_derivation(
advs[c(-1, -2), ],
derivation = derive_vars_dtm,
args = params(
dtc = VSDTC,
new_vars_prefix = "A"
),
derivation_slice(
filter = str_detect(VSTPT, "PRE|BEFORE"),
args = params(time_imputation = "first")
),
derivation_slice(
filter = TRUE,
args = params(time_imputation = "last")
)
)