Merge pull request #77 from mitre/cran-upd

Make updates in preparation for CRAN

DESCRIPTION

@@ -1,16 +1,30 @@
 Package: growthcleanr
 Type: Package
-Title: Growth Measurements Cleaner
-Version: 2.0.0
+Title: Data Cleaner for Anthropometric Measurements
+Version: 2.0.1
 Authors@R: c(
-    person("Daymont","Carrie",,"[email protected]",c("aut","cre")),
-    person("Grundmeier","Robert",,"[email protected]","aut"),
-    person("Miller","Jeffrey",,"[email protected]","aut"),
-    person("Campos","Diego",,"[email protected]","aut")
+    person("Daymont","Carrie", email = "[email protected]", role = "aut"),
+    person("Grundmeier","Robert", role = "aut"),
+    person("Miller","Jeffrey", role = "aut"),
+    person("Campos","Diego", role = "aut"),
+    person("Chudnov","Dan", role = "ctb"),
+    person("De los Santos","Hannah", email = "[email protected]", role = c("ctb","cre")),
+    person("Cao","Lusha", role = "ctb"),
+    person("Silva","Steffani", role = "ctb"),
+    person("Zhang","Hanzhe", role = "ctb"),
+    person("Boyas","Matt", role = "ctb"),
+    person("Freedman","David", role = "ctb"),
+    person("Achilleos","Andreas", role = "ctb"),
+    person("Butts","Jessica", role = "ctb"),
+    person("Nguyen","Sheila", role = "ctb"),
+    person("Soleymani","Taraneh", role = "ctb")
   )
-Maintainer: Robert Grundmeier <[email protected]>
-Description: growthcleanr cleans growth data that may contain implausible data based on unit or data range.
+Description: ‘growthcleanr’ identifies implausible anthropometric (e.g., height,
+    weight) measurements in irregularly spaced longitudinal datasets, such as those from electronic health records.
+URL: https://carriedaymont.github.io/growthcleanr/index.html, https://github.com/carriedaymont/growthcleanr
+BugReports: https://github.com/carriedaymont/growthcleanr/issues
 Imports:
+    R.utils (>= 2.11.0),
     data.table (>= 1.13.0),
     tidyr (>= 1.1.0),
     plyr (>= 1.8.6),
@@ -24,7 +38,6 @@ Depends:
 License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
-RoxygenNote: 7.1.2
 Roxygen: list(markdown = TRUE)
 Suggests:
     argparser (>= 0.6),
@@ -33,3 +46,4 @@ Suggests:
     rmarkdown (>= 2.3),
     testthat (>= 2.3.2)
 VignetteBuilder: knitr
+RoxygenNote: 7.2.0

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2018-2021 Carrie Daymont
+Copyright (c) 2018-2022 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

@@ -12,6 +12,7 @@ export(sd_median)
 export(simple_bmi)
 export(splitinput)
 export(testacf)
+import(R.utils, except = c(extract))
 import(data.table)
 import(doParallel)
 import(dplyr, except = c(last, first, summarize, src, between))

NEWS.md

@@ -1,3 +1,12 @@
+# growthcleanr 2.0.1 - 2021-07-21
+
+## Changed
+
+- Updated DESCRIPTION, including authors, URLS, title, description, and imports
+- Compressed files in `inst/extdata` for size requirements; added `R.utils` as
+  import to support `fread()` for `.gz` files
+- Updated license year
+
 # growthcleanr 2.0.0 - 2021-06-30
 
 ## Added

R/adjustcarryforward.R

@@ -759,6 +759,7 @@ calc_step_15_no_param <- function(
 #' @rawNamespace import(plyr, except = c(failwith, id, summarize, count, desc, mutate, arrange, rename, is.discrete, summarise, summarize))
 #' @rawNamespace import(dplyr, except = c(last, first, summarize, src, between))
 #' @import data.table
+#' @rawNamespace import(R.utils, except = c(extract))
 # NOTE: no examples, since this is a temporary function
 acf_answers <- function(subjid,
                         param,
@@ -805,8 +806,8 @@ acf_answers <- function(subjid,
   # recode column names to match syntactic style ("." rather than "_" in variable names)
   tanner_ht_vel_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/tanner_ht_vel.csv", package = "growthcleanr"),
-    paste(ref.data.path, "tanner_ht_vel.csv", sep =
+    system.file("extdata/tanner_ht_vel.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "tanner_ht_vel.csv.gz", sep =
             "")
   )
   tanner.ht.vel <- fread(tanner_ht_vel_path)
@@ -821,15 +822,15 @@ acf_answers <- function(subjid,
 
   who_max_ht_vel_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/who_ht_maxvel_3sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "who_ht_maxvel_3sd.csv", sep =
+    system.file("extdata/who_ht_maxvel_3sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "who_ht_maxvel_3sd.csv.gz", sep =
             "")
   )
 
   who_ht_vel_3sd_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/who_ht_vel_3sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "who_ht_vel_3sd.csv", sep =
+    system.file("extdata/who_ht_vel_3sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "who_ht_vel_3sd.csv.gz", sep =
             "")
   )
   who.max.ht.vel <- fread(who_max_ht_vel_path)
@@ -851,9 +852,8 @@ acf_answers <- function(subjid,
   # recode column names to match syntactic style ("." rather than "_" in variable names)
   tanner_ht_vel_2sd_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/tanner_ht_vel_with_2sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "tanner_ht_vel_with_2sd.csv", sep =
-            "")
+    system.file("extdata/tanner_ht_vel_with_2sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "tanner_ht_vel_with_2sd.csv.gz", sep = "")
   )
   tanner.ht.vel.2sd <- fread(tanner_ht_vel_2sd_path)
 
@@ -868,15 +868,15 @@ acf_answers <- function(subjid,
 
   who_max_ht_vel_2sd_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/who_ht_maxvel_2sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "who_ht_maxvel_2sd.csv", sep =
+    system.file("extdata/who_ht_maxvel_2sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "who_ht_maxvel_2sd.csv.gz", sep =
             "")
   )
 
   who_ht_vel_2sd_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/who_ht_vel_2sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "who_ht_vel_2sd.csv", sep =
+    system.file("extdata/who_ht_vel_2sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "who_ht_vel_2sd.csv.gz", sep =
             "")
   )
   who.max.ht.vel.2sd <- fread(who_max_ht_vel_2sd_path)
@@ -1226,9 +1226,8 @@ adjustcarryforward <- function(subjid,
   # recode column names to match syntactic style ("." rather than "_" in variable names)
   tanner_ht_vel_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/tanner_ht_vel.csv", package = "growthcleanr"),
-    paste(ref.data.path, "tanner_ht_vel.csv", sep =
-            "")
+    system.file("extdata/tanner_ht_vel.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "tanner_ht_vel.csv.gz", sep = "")
   )
 
   tanner.ht.vel <- fread(tanner_ht_vel_path)
@@ -1243,15 +1242,15 @@ adjustcarryforward <- function(subjid,
 
   who_max_ht_vel_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/who_ht_maxvel_3sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "who_ht_maxvel_3sd.csv", sep =
+    system.file("extdata/who_ht_maxvel_3sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "who_ht_maxvel_3sd.csv.gz", sep =
             "")
   )
 
   who_ht_vel_3sd_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/who_ht_vel_3sd.csv", package = "growthcleanr"),
-    paste(ref.data.path, "who_ht_vel_3sd.csv", sep =
+    system.file("extdata/who_ht_vel_3sd.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "who_ht_vel_3sd.csv.gz", sep =
             "")
   )
   who.max.ht.vel <- fread(who_max_ht_vel_path)

R/cdc.R

@@ -33,7 +33,7 @@ set_cols_first <- function(DT, cols, intersection = TRUE)
   }
 }
 
-#' Calculate extended BMI measures 
+#' Calculate extended BMI measures
 #'
 #' \code{ext_bmiz} Calculates the sigma (scale parameter for the half-normal
 #' distribution), extended BMI percentile, extended BMIz, and the CDC LMS
@@ -101,6 +101,7 @@ set_cols_first <- function(DT, cols, intersection = TRUE)
 #' @import labelled
 #' @import magrittr
 #' @importFrom stats approx pnorm qnorm
+#' @rawNamespace import(R.utils, except = c(extract))
 #' @examples
 #' # Run on a small subset of given data
 #' df <- as.data.frame(syngrowth)
@@ -166,8 +167,8 @@ ext_bmiz <- function(data,
 
   dref_path <- ifelse(
     ref.data.path == "",
-    system.file("extdata/CDCref_d.csv", package = "growthcleanr"),
-    paste(ref.data.path, "CDCref_d.csv", sep = "")
+    system.file("extdata/CDCref_d.csv.gz", package = "growthcleanr"),
+    paste(ref.data.path, "CDCref_d.csv.gz", sep = "")
   )
   # Note: referring to underscore-leading column as `_AGEMOS1`, i.e. with
   # backticks, results in a no visible binding warning, but vars can't start

R/extdata.R

@@ -6,7 +6,7 @@
 #'
 #' @name bmianthro
 #'
-#' @section bmianthro.txt:
+#' @section bmianthro.txt.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -21,7 +21,7 @@ NULL
 #'
 #' @name growth_cdc_ext
 #'
-#' @section growthfile_cdc_ext.csv:
+#' @section growthfile_cdc_ext.csv.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -36,7 +36,7 @@ NULL
 #'
 #' @name lenanthro
 #'
-#' @section lenanthro.txt:
+#' @section lenanthro.txt.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -50,7 +50,7 @@ NULL
 #'
 #' @name nhanes-reference-medians
 #'
-#' @section nhanes-reference-medians.csv:
+#' @section nhanes-reference-medians.csv.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -65,7 +65,7 @@ NULL
 #'
 #' @name tanner_ht_vel
 #'
-#' @section tanner_ht_vel.csv:
+#' @section tanner_ht_vel.csv.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -79,9 +79,9 @@ NULL
 #' Contains velocities for growth pre-calculated by CDC, including those 2
 #' standard deviations away.
 #'
-#' @name tanner_ht_vel_2sd
+#' @name tanner_ht_vel_with_2sd
 #'
-#' @section tanner_ht_vel.csv:
+#' @section tanner_ht_vel_with_2sd.csv.gz:
 #'
 #' Used in function `acf_answers()`
 #'
@@ -96,7 +96,7 @@ NULL
 #'
 #' @name weianthro
 #'
-#' @section weianthro.csv:
+#' @section weianthro.csv.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -112,7 +112,7 @@ NULL
 #'
 #' @name who_ht_maxvel
 #'
-#' @section who_ht_maxvel_3sd.csv:
+#' @section who_ht_maxvel_3sd.csv.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -128,7 +128,7 @@ NULL
 #'
 #' @name who_ht_maxvel_2sd
 #'
-#' @section who_ht_maxvel_2sd.csv:
+#' @section who_ht_maxvel_2sd.csv.gz:
 #'
 #' Used in function `acf_answers()`
 #'
@@ -144,7 +144,7 @@ NULL
 #'
 #' @name who_ht_vel_3sd
 #'
-#' @section who_ht_vel_3sd.csv:
+#' @section who_ht_vel_3sd.csv.gz:
 #'
 #' Used in function `cleangrowth()`
 #'
@@ -160,7 +160,7 @@ NULL
 #'
 #' @name who_ht_vel_2sd
 #'
-#' @section who_ht_vel_2sd.csv:
+#' @section who_ht_vel_2sd.csv.gz:
 #'
 #' Used in function `acf_answers()`
 #'
@@ -173,7 +173,7 @@ NULL
 #'
 #' @name test_syngrowth_wide
 #'
-#' @section test_syngrowth_wide.csv:
+#' @section test_syngrowth_wide.csv.gz:
 #'
 #' Used to test function `ext_bmiz()`
 #'
@@ -186,9 +186,22 @@ NULL
 #'
 #' @name test_syngrowth_sas_output_compare
 #'
-#' @section test_syngrowth_sas_output_compare.csv:
+#' @section test_syngrowth_sas_output_compare.csv.gz:
 #'
 #' Used to test function `ext_bmiz()`
 #'
 #'
 NULL
+
+#' CDC BMI reference data
+#'
+#' Used for extended BMIz computation
+#'
+#' @name CDCref_d
+#'
+#' @section CDCref_d.csv.gz:
+#'
+#' Used for extended BMI computation
+#'
+#'
+NULL