Merge pull request #64 from mitre/main

Merging version 2.0, see NEWS.md for details.

Author: dchud

.Rbuildignore

@@ -11,3 +11,6 @@ Dockerfile
 ^README\.Rmd$
 ^\.github$
 ^\.lintr$
+^_pkgdown\.yml$
+^docs$
+^pkgdown$

.gitignore

@@ -43,7 +43,10 @@ inst/doc
 packrat/lib*/
 packrat/src/
 
+*.swo
 *.swp
 output
 .Rproj.user
 .Rprofile
+docs/reference/*.csv
+docs/reference/*.log

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: growthcleanr
 Type: Package
 Title: Growth Measurements Cleaner
-Version: 1.2.5
+Version: 2.0.0
 Authors@R: c(
     person("Daymont","Carrie",,"[email protected]",c("aut","cre")),
     person("Grundmeier","Robert",,"[email protected]","aut"),

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2018 Carrie Daymont
+Copyright (c) 2018-2021 Carrie Daymont
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

NAMESPACE

@@ -9,6 +9,7 @@ export(longwide)
 export(read_anthro)
 export(recode_sex)
 export(sd_median)
+export(simple_bmi)
 export(splitinput)
 import(data.table)
 import(doParallel)
@@ -19,3 +20,12 @@ import(magrittr)
 import(parallel)
 import(plyr, except = c(failwith, id, summarize, count, desc, mutate, arrange, rename, is.discrete, summarise, summarize))
 import(tidyr, except = extract)
+importFrom(stats,approx)
+importFrom(stats,median)
+importFrom(stats,pnorm)
+importFrom(stats,qnorm)
+importFrom(stats,setNames)
+importFrom(utils,read.csv)
+importFrom(utils,read.table)
+importFrom(utils,tail)
+importFrom(utils,write.csv)

NEWS.md

@@ -1,18 +1,41 @@
-# growthcleanr
+# growthcleanr 2.0.0 - 2021-06-30
 
-## [1.2.6] - 2021-06-10
+## Added
 
-### Changed
+- Support for cleaning adult (18-65) observations with `adult_cutpoint` and
+  `weightcap` options (https://github.com/mitre/growthcleanr/pull/17, others)
+- Added documentation describing adult algorithm, examples, and exclusions
+  (#30), next steps (#63)
+- Added tests supporting adult observations (#49)
+
+## Changed
+
+- Removed BMI calculation from `longwide()`, added `simple_bmi()` (#47)
+- Enhanced `gcdriver.R` to support adult options, parallel operation
+  (https://github.com/mitre/growthcleanr/pull/23)
+- Refreshed `syngrowth` synthetic test data, now includes adults (#50)
+- Reorganized documentation from README, now using
+  [pkgdown](https://pkgdown.r-lib.org/) (#30)
+- Improved code layout to pass `CHECK` cleanly (#18, #60)
+
+# growthcleanr 1.2.6 - 2021-06-10
+
+## Changed
 
 - Corrected four duplicated age-rows in NHANES reference medians (#40)
 - Added missing non-newborn constraint in 14h.ii (thanks Lusha Cao)
 - Removed `Hmisc` dependency (#36)
 - Replaced `clean_value` result column name in docs with `gcr_result` for
   clarity (#35)
 
-## [1.2.5] - 2021-02-26
+# growthcleanr 1.2.5 - 2021-02-26
+
+## Added
+
+- Added `inst/extdata/nhanes-reference-medians.csv`, reference medians for
+  recentering derived from NHANES (described in README)
 
-### Changed
+## Changed
 
 - Updated behavior of `sd.recenter` option to include new NHANES reference
   medians and explicit specification with "NHANES" or "derive"
@@ -21,24 +44,36 @@
   @mcanouil) (#17)
 - Switched to use `file.path()` more consistently in `R/growth.R`
 
-### Added
+# growthcleanr 1.2.4 - 2021-01-14
 
-- Added `inst/extdata/nhanes-reference-medians.csv`, reference medians for
-  recentering derived from NHANES (described in README)
+## Changed
+
+- Minor update to WHO HT velocity 3SD files to correct a small number of errors
+  (#24). Affected files were:
+
+  - `inst/extdata/who_ht_maxvel_3sd.csv`
+  - `inst/extdata/who_ht_vel_3sd.csv`
 
-## [1.2.4] - 2021-01-14
+  Although these changes were very minor, it is possible that results on data
+  cleaned after this change may vary from previous results. The prior version of
+  these files may be obtained by visiting the tagged release version 1.2.3 at
+  https://github.com/carriedaymont/growthcleanr/releases/tag/1.2.3.
 
-### Changed
+  The released version of `growthcleanr` available at that link contains the
+  older version of both files; that older version may be used to verify
+  reproducibility.
 
-- Minor update to WHO HT velocity 3SD files (#24)
+  Alternatively, a more recent version of `growthcleanr` may be used with only
+  the affected files replaced with their older versions available at the 1.2.3
+  tag link above. This must be done manually.
 
-## [1.2.3] - 2021-01-07
+# growthcleanr 1.2.3 - 2021-01-07
 
-### Added
+## Added
 
 - New exclusion handling option on experimental carry forward adjustment
 
-### Changed
+## Changed
 
 - Improved experimental carry forward adjustment handling of strings of
   CF values, output handling, and documentation; renamed "Missing" values
@@ -49,13 +84,13 @@
 - Improved Dockerfile to standardize user/path, simplify install (thanks
   @mcanouil)
 
-## [1.2.2] - 2020-09-29
+# growthcleanr 1.2.2 - 2020-09-29
 
-### Added
+## Added
 
 - CITATION file, now `citation("growthcleanr")` works as expected
 
-### Changed
+## Changed
 
 - Standardized on arrow assignment
 - Moved functions previously within other functions to top level
@@ -70,20 +105,20 @@
 - Improved and corrected documentation
 - Re-compressed synthetic sample data (`syngrowth`) to improve compression
 
-## [1.2.1] - 2020-08-14
+# growthcleanr 1.2.1 - 2020-08-14
 
-### Added
+## Added
 
 - New tests in `tests/testthat/test-utils.R` and `tests/testthat/test-cdc.R`
   to support newly added functions
 
-### Changed
+## Changed
 
 - Improved error handling in `longwide()`; fixed missing import in DESCRIPTION
 
-## [1.2] - 2020-07-24
+# growthcleanr 1.2 - 2020-07-24
 
-### Added
+## Added
 
 - New CDC BMI calculation function `ext_bmiz()`, comparable to SAS program
   published at https://www.cdc.gov/nccdphp/dnpao/growthcharts/resources/sas.htm
@@ -101,16 +136,16 @@
   and driver script `exec/testadjustcf.R` (see README-adjustcarryforward.md for
   details)
 
-### Changed
+## Changed
 
 - Reorganized code from `R/growth.R` into separate files for clarity and easier
   maintenance (all utility functions not directly used by `cleangrowth()` are
   now in `R/utils.R`)
 - Updated README with details and examples for added functions
 
-## [1.1] - 2020-02-07
+# growthcleanr 1.1 - 2020-02-07
 
-### Added
+## Added
 
 - New options to add flexibility:
   - `error.load.mincount` and `error.load.threshold`
@@ -120,16 +155,16 @@
 - New `splitinput()` function
 - New example synthetic data set `syngrowth` loads automatically.
 
-### Changed
+## Changed
 
 - Several updates to improve performance, including eliminating use of
   data.table in ewma function.
 - Updated README with link to paper, detailed introduction, more installation
   details, examples, notes on handling large datasets, lists of parameters
   and exclusions.
 
-## [1.0.0] - 2018-09-11
+# growthcleanr 1.0.0 - 2018-09-11
 
-### Added
+## Added
 
 - Initial version posted to GitHub.

R/adjustcarryforward.R

@@ -15,6 +15,21 @@ calc_temp_exclusion_15 <- function(
   ewma.fields, tanner.ht.vel, who.ht.vel, exclude.levels,
   ewma.exp, minfactor, maxfactor, banddiff, banddiff_plus,
   min_ht.exp_under, min_ht.exp_over, max_ht.exp_under, max_ht.exp_over){
+
+  # avoid "no visible binding" warnings
+  abs.tbc.sd <- abs.tbc.sd.next <- abs.tbc.sd.prev <- aft.g.befp1 <- NULL
+  agedays <- agedays.next <- bef.g.aftm1 <- delta.agedays.next <- NULL
+  delta.next.ht <- delta.prev.ht <- dewma.after <- dewma.after.prev <- NULL
+  dewma.before <- dewma.before.next <- ewma.after <- ewma.all <- ewma.before <- NULL
+  ht.exp <- index <- max.ht.vel <- max.whoinc.1.ht <- max.whoinc.2.ht <- max.whoinc.3.ht <- NULL
+  max.whoinc.4.ht <- max.whoinc.6.ht <- maxdiff.next.ht <- maxdiff.prev.ht <- NULL
+  mid.agedays <- min.ht.vel <- mindiff.next.ht <- mindiff.prev.ht <- pair <- NULL
+  pair.next <- pair.prev <- sex <- tanner.months <- tbc.sd <- temp.diff <- temp.exclude <- NULL
+  v <- v.next <- v.prev <- who.maxdiff.next.ht <- who.mindiff.next.ht <- whoagegrp.ht <- NULL
+  whoinc.1.ht <- whoinc.2.ht <- whoinc.3.ht <- whoinc.4.ht <- whoinc.6.ht <- NULL
+  whoinc.age.ht <- NULL
+
+
   # initialize fields
   df[, (ewma.fields) := as.double(NaN)]
   df[, `:=`(
@@ -374,6 +389,18 @@ calc_step_15_no_param <- function(
   ewma.fields, tanner.ht.vel, who.ht.vel, exclude.levels,
   ewma.exp){
 
+  # avoid "no visible binding for global variable" warnings
+  agedays <- tbc.sd <- ewma.all <- ewma.before <- ewma.after <- v <- dewma.before <- NULL
+  abs.tbc.sd <- sex <- tanner.months <- ht.exp <- delta.agedays.next <- mindiff.next.ht <- NULL
+  min.ht.vel <- maxdiff.next.ht <- max.ht.vel <- minhtvel.exp <- min.ht.vel.2sd <- NULL
+  max.ht.vel.2sd <- whoagegrp.ht <- whoinc.age.ht <- index <- who.mindiff.next.ht <- NULL
+  whoinc.1.ht <- whoinc.2.ht <- whoinc.3.ht <- whoinc.4.ht <- whoinc.6.ht <- NULL
+  who.maxdiff.next.ht <- max.whoinc.1.ht <- max.whoinc.2.ht <- max.whoinc.3.ht <- NULL
+  max.whoinc.4.ht <- max.whoinc.6.ht <- dewma.after <- v.prev <- v.next <- pair <- NULL
+  delta.prev.ht <- mindiff.prev.ht <- delta.next.ht <- maxdiff.prev.ht <- NULL
+  dewma.after.prev <- pair.prev <- dewma.before.next <- pair.next <- temp.diff <- NULL
+  bef.g.aftm1 <- aft.g.befp1 <- abs.tbc.sd.prev <- abs.tbc.sd.next <- temp.exclude <- NULL
+
   # initialize fields
   df[, (ewma.fields) := as.double(NaN)]
   df[, `:=`(
@@ -743,6 +770,11 @@ acf_answers <- function(subjid,
                         ewma.exp = -1.5,
                         ref.data.path = "",
                         quietly = T){
+
+  # avoid "no visible binding for global variable" warnings
+  tanner.months <- whoagegrp_ht <- whoagegrp.ht <- z.orig <- z.orig <- v <- sd.orig <- NULL
+  index <- exclude <- tbc.sd <- sd.median <- acf_answer <- NULL
+
   # process ----
   # organize data into a dataframe along with a line "index" so the original data order can be recovered
   data.all <- data.table(
@@ -1088,6 +1120,20 @@ adjustcarryforward <- function(subjid,
                                min_ht.exp_over = 0,
                                max_ht.exp_under = 0.33,
                                max_ht.exp_over = 1.5) {
+
+  # Avoid "undefined global functions/variables" warnings
+  v <- sd.orig <- sd.median <- tbc.sd <- agedays.next <- mid.agedays <- min.ht.vel <- NULL
+  delta.agedays.next <- ht.exp <- max.ht.vel <- mindiff.next.ht <- temp.exclude <- NULL
+  ecf_tmp <- ewma.all <- ewma.before <- ewma.after <- abs.tbc.sd <- whoinc.1.ht <- NULL
+  whoinc.2.ht <- whoinc.3.ht <- whoinc.4.ht <- whoinc.6.ht <- max.whoinc.1.ht <- NULL
+  max.whoinc.2.ht <- max.whoinc.3.ht <- max.whoinc.4.ht <- max.whoinc.6.ht <- NULL
+  whoinc.age.ht <- whoinc.age.ht <- who.mindiff.next.ht <- who.maxdiff.next.ht <- NULL
+  dewma.after <- maxdiff.next.ht <- v.prev <- v.next <- delta.prev.ht <- NULL
+  mindiff.prev.ht <- delta.next.ht <- maxdiff.prev.ht <- pair <- dewma.after.prev <- NULL
+  pair.prev <- dewma.before.next <- pair.next <- bef.g.aftm1 <- aft.g.befp1 <- NULL
+  abs.tbc.sd.prev <- abs.tbc.sd.next <- exclude <- n <- dewma.before <- NULL
+  tanner.months <- whoagegrp_ht <- whoagegrp.ht <- z.orig <- index <- temp.diff <- NULL
+
   # check option is valid
   if (!exclude_opt %in% 0:3){
     stop("Invalid exclude_opt. Enter a number from 0 to 3.")