Skip to contents

Pre-processing Delayed Data

Dawid Kałędkowski

15.05.2022

preprocessing-delayed-data.Rmd

When creating apps which do not use DDL, once the datasets are created there is often some pre-processing required before initializing the teal app. Similarly, in the case of delayed data additional code instructions to pre-process data can be added to DDL objects which will be run after the data is loaded, which may happen after the launching of the shiny app or when the pull() method is called.

  • mutate_dataset: Individual datasets can be processed using the mutate_dataset function. For reproducibility to be maintained with mutate_dataset, all pre-processing code should modify one dataset at a time.
library(scda)
## 
library(teal.data)
## Loading required package: shiny
library(magrittr)

adsl_cf <- callable_function(function() synthetic_cdisc_data("latest")$adsl)
adsl <- cdisc_dataset_connector(
  dataname = "ADSL",
  pull_callable = adsl_cf,
  keys = get_cdisc_keys("ADSL")
) %>%
  mutate_dataset("ADSL$SEX <- as.factor(ADSL$SEX)")


adae_cf <- callable_function(function() synthetic_cdisc_data("latest")$adae)
adae <- cdisc_dataset_connector(
  dataname = "ADAE",
  pull_callable = adae_cf,
  keys = get_cdisc_keys("ADAE")
) %>%
  mutate_dataset("ADAE$X <- rep(ADSL$SEX[1])", vars = list(ADSL = adsl))

adsl$pull() %>%
  get_raw_data() %>%
  head(n = 3)
##   STUDYID               USUBJID SUBJID SITEID AGE  AGEU SEX
## 1 AB12345  AB12345-CHN-3-id-128 id-128  CHN-3  32 YEARS   M
## 2 AB12345 AB12345-CHN-15-id-262 id-262 CHN-15  35 YEARS   M
## 3 AB12345  AB12345-RUS-3-id-378 id-378  RUS-3  30 YEARS   F
##                        RACE                 ETHNIC COUNTRY DTHFL         INVID
## 1                     ASIAN NOT HISPANIC OR LATINO     CHN     N  INV ID CHN-3
## 2 BLACK OR AFRICAN AMERICAN NOT HISPANIC OR LATINO     CHN     N INV ID CHN-15
## 3                     ASIAN NOT HISPANIC OR LATINO     RUS     N  INV ID RUS-3
##           INVNAM            ARM ARMCD         ACTARM ACTARMCD         TRT01P
## 1  Dr. CHN-3 Doe      A: Drug X ARM A      A: Drug X    ARM A      A: Drug X
## 2 Dr. CHN-15 Doe C: Combination ARM C C: Combination    ARM C C: Combination
## 3  Dr. RUS-3 Doe C: Combination ARM C C: Combination    ARM C C: Combination
##           TRT01A REGION1 STRATA1 STRATA2    BMRKR1 BMRKR2 ITTFL SAFFL BMEASIFL
## 1      A: Drug X    Asia       C      S2 14.424934 MEDIUM     Y     Y        Y
## 2 C: Combination    Asia       C      S1  4.055463    LOW     Y     Y        N
## 3 C: Combination Eurasia       A      S1  2.803240   HIGH     Y     Y        Y
##   BEP01FL     RANDDT             TRTSDTM             TRTEDTM    EOSSTT
## 1       Y 2019-02-22 2019-02-24 11:09:18 2021-02-23 22:47:42 COMPLETED
## 2       N 2019-02-26 2019-02-26 09:05:00 2021-02-25 20:43:24 COMPLETED
## 3       N 2019-02-24 2019-02-28 03:19:08 2021-02-27 14:57:32 COMPLETED
##      EOTSTT      EOSDT EOSDY DCSREAS DTHDT DTHCAUS DTHCAT LDDTHELD LDDTHGR1
## 1 COMPLETED 2021-02-23   731    <NA>  <NA>    <NA>   <NA>       NA     <NA>
## 2 COMPLETED 2021-02-25   731    <NA>  <NA>    <NA>   <NA>       NA     <NA>
## 3 COMPLETED 2021-02-27   731    <NA>  <NA>    <NA>   <NA>       NA     <NA>
##     LSTALVDT DTHADY study_duration_secs
## 1 2021-03-05     NA            63113904
## 2 2021-03-15     NA            63113904
## 3 2021-03-15     NA            63113904
adae$pull() %>%
  get_raw_data() %>%
  head(n = 3)
##   STUDYID              USUBJID SUBJID SITEID AGE  AGEU SEX  RACE
## 1 AB12345 AB12345-BRA-1-id-134 id-134  BRA-1  47 YEARS   M WHITE
## 2 AB12345 AB12345-BRA-1-id-134 id-134  BRA-1  47 YEARS   M WHITE
## 3 AB12345 AB12345-BRA-1-id-134 id-134  BRA-1  47 YEARS   M WHITE
##                   ETHNIC COUNTRY DTHFL        INVID        INVNAM       ARM
## 1 NOT HISPANIC OR LATINO     BRA     N INV ID BRA-1 Dr. BRA-1 Doe A: Drug X
## 2 NOT HISPANIC OR LATINO     BRA     N INV ID BRA-1 Dr. BRA-1 Doe A: Drug X
## 3 NOT HISPANIC OR LATINO     BRA     N INV ID BRA-1 Dr. BRA-1 Doe A: Drug X
##   ARMCD    ACTARM ACTARMCD    TRT01P    TRT01A       REGION1 STRATA1 STRATA2
## 1 ARM A A: Drug X    ARM A A: Drug X A: Drug X South America       B      S2
## 2 ARM A A: Drug X    ARM A A: Drug X A: Drug X South America       B      S2
## 3 ARM A A: Drug X    ARM A A: Drug X A: Drug X South America       B      S2
##     BMRKR1 BMRKR2 ITTFL SAFFL BMEASIFL BEP01FL     RANDDT             TRTSDTM
## 1 6.462991    LOW     Y     Y        Y       N 2020-11-03 2020-11-04 03:50:33
## 2 6.462991    LOW     Y     Y        Y       N 2020-11-03 2020-11-04 03:50:33
## 3 6.462991    LOW     Y     Y        Y       N 2020-11-03 2020-11-04 03:50:33
##               TRTEDTM    EOSSTT    EOTSTT      EOSDT EOSDY DCSREAS DTHDT
## 1 2022-11-04 15:28:57 COMPLETED COMPLETED 2022-11-04   731    <NA>  <NA>
## 2 2022-11-04 15:28:57 COMPLETED COMPLETED 2022-11-04   731    <NA>  <NA>
## 3 2022-11-04 15:28:57 COMPLETED COMPLETED 2022-11-04   731    <NA>  <NA>
##   DTHCAUS DTHCAT LDDTHELD LDDTHGR1   LSTALVDT DTHADY study_duration_secs ASEQ
## 1    <NA>   <NA>       NA     <NA> 2022-11-15     NA            63113904    1
## 2    <NA>   <NA>       NA     <NA> 2022-11-15     NA            63113904    2
## 3    <NA>   <NA>       NA     <NA> 2022-11-15     NA            63113904    3
##   AESEQ        AETERM         AELLT       AEDECOD       AEHLT     AEHLGT
## 1     1 trm B.2.1.2.1 llt B.2.1.2.1 dcd B.2.1.2.1 hlt B.2.1.2 hlgt B.2.1
## 2     2 trm D.1.1.4.2 llt D.1.1.4.2 dcd D.1.1.4.2 hlt D.1.1.4 hlgt D.1.1
## 3     3 trm A.1.1.1.2 llt A.1.1.1.2 dcd A.1.1.1.2 hlt A.1.1.1 hlgt A.1.1
##   AEBODSYS AESOC    AESEV AESER            AEACN AEREL
## 1   cl B.2  cl B MODERATE     N DOSE NOT CHANGED     N
## 2   cl D.1  cl D MODERATE     N DOSE NOT CHANGED     N
## 3   cl A.1  cl A MODERATE     Y DOSE NOT CHANGED     N
##                              AEOUT AESDTH TRTEMFL AECONTRT     ASTDTM
## 1               RECOVERED/RESOLVED      N       Y        N 2021-07-13
## 2             RECOVERING/RESOLVING      N       Y        N 2021-09-04
## 3 RECOVERED/RESOLVED WITH SEQUELAE      N       Y        Y 2022-03-15
##       AENDTM ASTDY AENDY AETOXGR SMQ01NAM SMQ02NAM SMQ01SC SMQ02SC CQ01NAM
## 1 2022-04-05   251   517       3     <NA>     <NA>    <NA>    <NA>    <NA>
## 2 2022-05-16   304   558       3     <NA>     <NA>    <NA>    <NA>    <NA>
## 3 2022-10-29   496   724       2     <NA>     <NA>    <NA>    <NA>    <NA>
##   ANL01FL            AERELNST          AEACNOTH X
## 1       Y               OTHER PROCEDURE/SURGERY M
## 2       Y DISEASE UNDER STUDY        MEDICATION M
## 3       Y DISEASE UNDER STUDY              NONE M
  • mutate_data: Collections of datasets should only be processed using the mutate_data function:
cdisc_data(adsl, adae, check = TRUE) %>%
  mutate_data("ADAE$x <- ADSL$SUBJID[1]")

The code is processed in the order the datasets are pulled so if there are dependencies between datasets it matters the order in which pre-processing code is added to the CDISCTealData object just as order matters when the arguments are inputted to the cdisc_data function to create the CDISCTealData object.

Finally, the code argument directly in teal_data and cdisc_data call does not need to be used for DDL because data loaded with DDL are reproducible by design. Because of this, it is recommended to set argument check = TRUE inside cdisc_data function when creating apps with DDL.

Processing dependencies

It may be required to generate a delayed data object that is dependent on some other delayed object or some constant value.

For this, when creating your delayed data object it’s possible to supply the additional variables that are to be accessed during the data loading (pull) using additional arguments through ...:

get_code(adsl)
## [1] "ADSL <- (function() synthetic_cdisc_data(\"latest\")$adsl)()\nADSL$SEX <- as.factor(ADSL$SEX)"
pull_fun_adae <- callable_function(
  function() {
    synthetic_cdisc_data("latest")$adae
  }
)
adae <- dataset_connector(
  dataname = "ADAE",
  pull_callable = pull_fun_adae,
  keys = get_cdisc_keys("ADAE")
)

get_code(adae)
## [1] "ADAE <- (function() {\n    synthetic_cdisc_data(\"latest\")$adae\n})()"

It’s also possible to supply these additional variables after creating your object using the mutate_dataset function.

last_run <- Sys.Date() # constant value stored as a variable in the current session

adsl_cf <- callable_function(function() synthetic_cdisc_data("latest")$adsl)
adsl <- cdisc_dataset_connector(
  dataname = "ADSL",
  pull_callable = adsl_cf,
  keys = get_cdisc_keys("ADSL")
) %>%
  mutate_dataset("ADSL$last_run <- last_run", vars = list(last_run = last_run))

cat(get_code(adsl))
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## last_run <- structure(19165, class = "Date")
## ADSL$last_run <- last_run
# compared to evaluating the variable at the time of loading
adsl_cf <- callable_function(function() synthetic_cdisc_data("latest")$adsl)
adsl <- cdisc_dataset_connector(
  dataname = "ADSL",
  pull_callable = adsl_cf,
  keys = get_cdisc_keys("ADSL")
) %>%
  mutate_dataset("last_run <- Sys.Date()\nADSL$last_run <- last_run")

adsl %>%
  get_code() %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## last_run <- Sys.Date()
## ADSL$last_run <- last_run

This is also required when creating the object depends on another delayed data object:

adsl <- synthetic_cdisc_data("latest")$adsl
adae_cf <- callable_function(function() synthetic_cdisc_data("latest")$adae)
adae <- cdisc_dataset_connector(
  dataname = "ADAE",
  pull_callable = adae_cf,
  keys = get_cdisc_keys("ADAE")
) %>%
  mutate_dataset("ADAE$n <- nrow(ADSL)")

cat(get_code(adae)) # the code returned by `adae` is not sufficient to reproduce `adae`
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADAE$n <- nrow(ADSL)
adsl_cf <- callable_function(function() synthetic_cdisc_data("latest")$adsl)
adsl <- cdisc_dataset_connector(
  dataname = "ADSL",
  pull_callable = adsl_cf,
  keys = get_cdisc_keys("ADSL")
)
adae_cf <- callable_function(function() synthetic_cdisc_data("latest")$adae)
adae <- cdisc_dataset_connector(
  dataname = "ADAE",
  pull_callable = adae_cf,
  keys = get_cdisc_keys("ADAE")
) %>%
  mutate_dataset("ADAE$n <- nrow(ADSL)", vars = list(ADSL = adsl))

cat(get_code(adae)) # this code can be run independently
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## ADAE$n <- nrow(ADSL)

Related to this idea, it is possible to provide the code on a Data level. However, this will always return all the code used to generate all the datasets in the object:

adsl_adae <- cdisc_data(
  adsl,
  adae
) %>% mutate_data("ADAE$avg_age <- mean(ADAE$AGE)")

# the output for all 3 are the same
adsl_adae %>%
  get_code() %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADAE$n <- nrow(ADSL)
## ADAE$avg_age <- mean(ADAE$AGE)
adsl_adae %>%
  get_code(dataname = "ADAE") %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADAE$n <- nrow(ADSL)
## ADAE$avg_age <- mean(ADAE$AGE)
adsl_adae %>%
  get_code(dataname = "ADSL") %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADAE$n <- nrow(ADSL)
## ADAE$avg_age <- mean(ADAE$AGE)

The better approach would be to supply the code on a Dataset level. This ensures that the code accessed on a dataset level only contains the snippets that pertains to itself:

adsl_adae <- cdisc_data(
  adsl,
  adae %>% mutate_dataset("ADAE$avg_age <- mean(ADAE$AGE)")
)

adsl_adae %>%
  get_code() %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADAE$n <- nrow(ADSL)
## ADAE$avg_age <- mean(ADAE$AGE)
adsl_adae %>%
  get_code("ADAE") %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()
## ADAE <- (function() synthetic_cdisc_data("latest")$adae)()
## ADAE$n <- nrow(ADSL)
## ADAE$avg_age <- mean(ADAE$AGE)
adsl_adae %>%
  get_code("ADSL") %>%
  cat()
## ADSL <- (function() synthetic_cdisc_data("latest")$adsl)()

Related to this idea, the delayed data object needs to be supplied with the code needed to reproduce the data. This can be provided at the Dataset level or the Data level.

Below is a comparison of these two approaches:

adsl <- synthetic_cdisc_data("latest")$adsl
cdisc_dataset("ADSL", adsl) %>% get_code() # no reproducible code
## [1] ""
# provide the code to reproduce the data:
cdisc_dataset("ADSL", adsl,
  code = "ADSL <- synthetic_cdisc_data(\"latest\")$adsl"
) %>%
  get_code()
## [1] "ADSL <- synthetic_cdisc_data(\"latest\")$adsl"
# it's possible to supply the code at the `Data` level:
adae <- synthetic_cdisc_data("latest")$adae
adsl_adae <- cdisc_data(
  cdisc_dataset("ADSL", adsl),
  cdisc_dataset("ADAE", adae),
  code = "ADSL <- synthetic_cdisc_data(\"latest\")$adsl\nADAE <- synthetic_cdisc_data(\"latest\")$adae"
)

adsl_adae %>%
  get_code() %>%
  cat()
## ADSL <- synthetic_cdisc_data("latest")$adsl
## ADAE <- synthetic_cdisc_data("latest")$adae
# but it's not possible then to access the code at a `Dataset` level:
adsl_adae %>%
  get_code("ADSL") %>%
  cat()
## ADSL <- synthetic_cdisc_data("latest")$adsl
## ADAE <- synthetic_cdisc_data("latest")$adae
# this can be avoided by storing the code like so:
adsl_adae <- cdisc_data(
  cdisc_dataset("ADSL", adsl, code = "ADSL <- synthetic_cdisc_data(\"latest\")$adsl"),
  cdisc_dataset("ADAE", adae, code = "ADAE <- synthetic_cdisc_data(\"latest\")$adsl")
)

adsl_adae %>%
  get_code("ADSL") %>%
  cat()
## ADSL <- synthetic_cdisc_data("latest")$adsl