CohortDiagnostics
CohortDiagnostics copied to clipboard
Published
20 hours ago •
OHDSI
OHDSI
Use of formals() in CohortDiagnostics::executeDiagnostics
When parsing the arguments of executDiagnostics() here, only default parameters will be passed to variable callingArgsJson.
Here is an example showing this using an example function foo():
foo <- function(bar = 10, baz = 20) {
args <- formals(foo)
return(list(bar = args$bar, baz = args$baz))
}
foo()
#> $bar
#> [1] 10
#>
#> $baz
#> [1] 20
foo(1, 2)
#> $bar
#> [1] 10
#>
#> $baz
#> [1] 20
Created on 2023-08-18 with reprex v2.0.2
Session info
sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#> setting value
#> version R version 4.3.1 (2023-06-16 ucrt)
#> os Windows 11 x64 (build 22621)
#> system x86_64, mingw32
#> ui RTerm
#> language (EN)
#> collate Dutch_Netherlands.utf8
#> ctype Dutch_Netherlands.utf8
#> tz Europe/Amsterdam
#> date 2023-08-18
#> pandoc 3.1.1 @ C:/Program Files/RStudio/resources/app/bin/quarto/bin/tools/ (via rmarkdown)
#>
#> ─ Packages ───────────────────────────────────────────────────────────────────
#> package * version date (UTC) lib source
#> cli 3.6.1 2023-03-23 [1] CRAN (R 4.3.1)
#> digest 0.6.33 2023-07-07 [1] CRAN (R 4.3.1)
#> evaluate 0.21 2023-05-05 [1] CRAN (R 4.3.1)
#> fastmap 1.1.1 2023-02-24 [1] CRAN (R 4.3.1)
#> fs 1.6.3 2023-07-20 [1] CRAN (R 4.3.1)
#> glue 1.6.2 2022-02-24 [1] CRAN (R 4.3.1)
#> htmltools 0.5.5 2023-03-23 [1] CRAN (R 4.3.1)
#> knitr 1.43 2023-05-25 [1] RSPM (R 4.3.0)
#> lifecycle 1.0.3 2022-10-07 [1] CRAN (R 4.3.1)
#> magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.3.1)
#> purrr 1.0.1 2023-01-10 [1] CRAN (R 4.3.1)
#> R.cache 0.16.0 2022-07-21 [1] CRAN (R 4.3.1)
#> R.methodsS3 1.8.2 2022-06-13 [1] CRAN (R 4.3.0)
#> R.oo 1.25.0 2022-06-12 [1] CRAN (R 4.3.0)
#> R.utils 2.12.2 2022-11-11 [1] CRAN (R 4.3.1)
#> reprex 2.0.2 2022-08-17 [1] CRAN (R 4.3.1)
#> rlang 1.1.1 2023-04-28 [1] CRAN (R 4.3.1)
#> rmarkdown 2.23 2023-07-01 [1] CRAN (R 4.3.1)
#> rstudioapi 0.15.0 2023-07-07 [1] CRAN (R 4.3.1)
#> sessioninfo 1.2.2 2021-12-06 [1] CRAN (R 4.3.1)
#> styler 1.10.1 2023-06-05 [1] CRAN (R 4.3.1)
#> vctrs 0.6.3 2023-06-14 [1] CRAN (R 4.3.1)
#> withr 2.5.0 2022-03-03 [1] CRAN (R 4.3.1)
#> xfun 0.39 2023-04-20 [1] CRAN (R 4.3.1)
#> yaml 2.3.7 2023-01-23 [1] CRAN (R 4.3.0)
#>
#> [1] C:/R/R-4.3.1/library
#>
#> ──────────────────────────────────────────────────────────────────────────────
In the following example I've simplified executDiagnostics() definition to only produce json and cut down the variables to only use those that are passed to formals().
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
# Simplified dummy function definition
executeDiagnostics <- function(runInclusionStatistics = TRUE,
runIncludedSourceConcepts = TRUE,
runOrphanConcepts = TRUE,
runTimeSeries = FALSE,
runVisitContext = TRUE,
runBreakdownIndexEvents = TRUE,
runIncidenceRate = TRUE,
runCohortRelationship = TRUE,
runTemporalCohortCharacterization = TRUE,
minCellCount = 5,
minCharacterizationMean = 0.01,
incremental = FALSE
) {
callingArgs <- formals(executeDiagnostics)
callingArgsJson <-
list(
runInclusionStatistics = callingArgs$runInclusionStatistics,
runIncludedSourceConcepts = callingArgs$runIncludedSourceConcepts,
runOrphanConcepts = callingArgs$runOrphanConcepts,
runTimeSeries = callingArgs$runTimeSeries,
runVisitContext = callingArgs$runVisitContext,
runBreakdownIndexEvents = callingArgs$runBreakdownIndexEvents,
runIncidenceRate = callingArgs$runIncidenceRate,
runTemporalCohortCharacterization = callingArgs$runTemporalCohortCharacterization,
minCellCount = callingArgs$minCellCount,
minCharacterizationMean = callingArgs$minCharacterizationMean,
incremental = callingArgs$incremental
) %>%
RJSONIO::toJSON(digits = 23, pretty = TRUE)
return(callingArgsJson)
}
# Running dummy with defaults
res1 <- executeDiagnostics()
# Running with flipped defaults
res2 <- executeDiagnostics(runInclusionStatistics = !TRUE,
runIncludedSourceConcepts = !TRUE,
runOrphanConcepts = !TRUE,
runTimeSeries = !FALSE,
runVisitContext = !TRUE,
runBreakdownIndexEvents = !TRUE,
runIncidenceRate = !TRUE,
runCohortRelationship = !TRUE,
runTemporalCohortCharacterization = !TRUE,
minCellCount = -5,
minCharacterizationMean = -0.01,
incremental = !FALSE)
res1
#> [1] "{\n\t\"runInclusionStatistics\" : true,\n\t\"runIncludedSourceConcepts\" : true,\n\t\"runOrphanConcepts\" : true,\n\t\"runTimeSeries\" : false,\n\t\"runVisitContext\" : true,\n\t\"runBreakdownIndexEvents\" : true,\n\t\"runIncidenceRate\" : true,\n\t\"runTemporalCohortCharacterization\" : true,\n\t\"minCellCount\" : 5,\n\t\"minCharacterizationMean\" : 0.010000000000000000208167,\n\t\"incremental\" : false\n}"
res2
#> [1] "{\n\t\"runInclusionStatistics\" : true,\n\t\"runIncludedSourceConcepts\" : true,\n\t\"runOrphanConcepts\" : true,\n\t\"runTimeSeries\" : false,\n\t\"runVisitContext\" : true,\n\t\"runBreakdownIndexEvents\" : true,\n\t\"runIncidenceRate\" : true,\n\t\"runTemporalCohortCharacterization\" : true,\n\t\"minCellCount\" : 5,\n\t\"minCharacterizationMean\" : 0.010000000000000000208167,\n\t\"incremental\" : false\n}"
# Check if results are identical
identical(res1, res2)
#> [1] TRUE
Created on 2023-08-18 with reprex v2.0.2
Session info
sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#> setting value
#> version R version 4.3.1 (2023-06-16 ucrt)
#> os Windows 11 x64 (build 22621)
#> system x86_64, mingw32
#> ui RTerm
#> language (EN)
#> collate Dutch_Netherlands.utf8
#> ctype Dutch_Netherlands.utf8
#> tz Europe/Amsterdam
#> date 2023-08-18
#> pandoc 3.1.1 @ C:/Program Files/RStudio/resources/app/bin/quarto/bin/tools/ (via rmarkdown)
#>
#> ─ Packages ───────────────────────────────────────────────────────────────────
#> package * version date (UTC) lib source
#> cli 3.6.1 2023-03-23 [1] CRAN (R 4.3.1)
#> digest 0.6.33 2023-07-07 [1] CRAN (R 4.3.1)
#> dplyr * 1.1.2 2023-04-20 [1] CRAN (R 4.3.1)
#> evaluate 0.21 2023-05-05 [1] CRAN (R 4.3.1)
#> fansi 1.0.4 2023-01-22 [1] CRAN (R 4.3.1)
#> fastmap 1.1.1 2023-02-24 [1] CRAN (R 4.3.1)
#> fs 1.6.3 2023-07-20 [1] CRAN (R 4.3.1)
#> generics 0.1.3 2022-07-05 [1] CRAN (R 4.3.1)
#> glue 1.6.2 2022-02-24 [1] CRAN (R 4.3.1)
#> htmltools 0.5.5 2023-03-23 [1] CRAN (R 4.3.1)
#> knitr 1.43 2023-05-25 [1] RSPM (R 4.3.0)
#> lifecycle 1.0.3 2022-10-07 [1] CRAN (R 4.3.1)
#> magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.3.1)
#> pillar 1.9.0 2023-03-22 [1] CRAN (R 4.3.1)
#> pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 4.3.1)
#> purrr 1.0.1 2023-01-10 [1] CRAN (R 4.3.1)
#> R.cache 0.16.0 2022-07-21 [1] CRAN (R 4.3.1)
#> R.methodsS3 1.8.2 2022-06-13 [1] CRAN (R 4.3.0)
#> R.oo 1.25.0 2022-06-12 [1] CRAN (R 4.3.0)
#> R.utils 2.12.2 2022-11-11 [1] CRAN (R 4.3.1)
#> R6 2.5.1 2021-08-19 [1] CRAN (R 4.3.1)
#> reprex 2.0.2 2022-08-17 [1] CRAN (R 4.3.1)
#> RJSONIO 1.3-1.8 2023-01-31 [1] CRAN (R 4.3.0)
#> rlang 1.1.1 2023-04-28 [1] CRAN (R 4.3.1)
#> rmarkdown 2.23 2023-07-01 [1] CRAN (R 4.3.1)
#> rstudioapi 0.15.0 2023-07-07 [1] CRAN (R 4.3.1)
#> sessioninfo 1.2.2 2021-12-06 [1] CRAN (R 4.3.1)
#> styler 1.10.1 2023-06-05 [1] CRAN (R 4.3.1)
#> tibble 3.2.1 2023-03-20 [1] CRAN (R 4.3.1)
#> tidyselect 1.2.0 2022-10-10 [1] CRAN (R 4.3.1)
#> utf8 1.2.3 2023-01-31 [1] CRAN (R 4.3.1)
#> vctrs 0.6.3 2023-06-14 [1] CRAN (R 4.3.1)
#> withr 2.5.0 2022-03-03 [1] CRAN (R 4.3.1)
#> xfun 0.39 2023-04-20 [1] CRAN (R 4.3.1)
#> yaml 2.3.7 2023-01-23 [1] CRAN (R 4.3.0)
#>
#> [1] C:/R/R-4.3.1/library
#>
#> ──────────────────────────────────────────────────────────────────────────────
Original post in the DARWIN fork
@mvankessel-EMC thanks for this - I'm not quite sure what we use the json for?
@gowthamrao is it used in the meta data to check what the calling arguments set by the user were? If so calling as.list(environment()) %>% RJSONIO::toJSON(digits = 23, pretty = TRUE) would achieve this more elegantly.
@azimov I took the liberty to trace down the path callingArgsJson is used for. From what I can gather it follows this path:
-
executeDiagnostics()RunDiagnostics.R a. L217-L232 b. L962-L1014, Specifically: L973 c. L1015-L1020 d. L1021-L1025 -
makeDataExportable()Private.R L121-L250 -
enforceMinCellValueDataframe()Private.R L252-L273 -
enforceMinCellValue()Private.R L57-L80
Yes - i looks like this is just stored in the metadata result - we just need to create a list that stores the relevant arguments (and doesn't leak user data, e.g. connectionDetails)