all data parsing and formatting has been seperated in individual functions

man/ds2dd_detailed.Rd

@@ -15,10 +15,7 @@ ds2dd_detailed(
   field.label = NULL,
   field.label.attr = "label",
   field.validation = NULL,
-  metadata = names(REDCapCAST::redcapcast_meta),
-  validate.time = FALSE,
-  time.var.sel.pos = "[Tt]i[d(me)]",
-  time.var.sel.neg = "[Dd]at[eo]"
+  metadata = names(REDCapCAST::redcapcast_meta)
 )
 }
 \arguments{
@@ -58,14 +55,6 @@ file with `haven::read_dta()`).}
 
 \item{metadata}{redcap metadata headings. Default is
 REDCapCAST:::metadata_names.}
-
-\item{validate.time}{Flag to validate guessed time columns}
-
-\item{time.var.sel.pos}{Positive selection regex string passed to
-`gues_time_only_filter()` as sel.pos.}
-
-\item{time.var.sel.neg}{Negative selection regex string passed to
-`gues_time_only_filter()` as sel.neg.}
 }
 \value{
 list of length 2
@@ -84,7 +73,6 @@ Ensure, that the data set is formatted with as much information as possible.
 }
 \examples{
 data <- REDCapCAST::redcapcast_data
-data |> ds2dd_detailed(validate.time = TRUE)
 data |> ds2dd_detailed()
 iris |> ds2dd_detailed(add.auto.id = TRUE)
 iris |>

man/guess_time_only.Rd

@@ -0,0 +1,33 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ds2dd_detailed.R
+\name{guess_time_only}
+\alias{guess_time_only}
+\title{Guess time variables based on naming pattern}
+\usage{
+guess_time_only(
+  data,
+  validate.time = FALSE,
+  time.var.sel.pos = "[Tt]i[d(me)]",
+  time.var.sel.neg = "[Dd]at[eo]"
+)
+}
+\arguments{
+\item{data}{data.frame or tibble}
+
+\item{validate.time}{Flag to validate guessed time columns}
+
+\item{time.var.sel.pos}{Positive selection regex string passed to
+`gues_time_only_filter()` as sel.pos.}
+
+\item{time.var.sel.neg}{Negative selection regex string passed to
+`gues_time_only_filter()` as sel.neg.}
+}
+\value{
+data.frame or tibble
+}
+\description{
+This is for repairing data with time variables with appended "1970-01-01"
+}
+\examples{
+redcapcast_data |> guess_time_only(validate.time = TRUE)
+}

man/haven_all_levels.Rd

@@ -0,0 +1,24 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ds2dd_detailed.R
+\name{haven_all_levels}
+\alias{haven_all_levels}
+\title{Finish incomplete haven attributes substituting missings with values}
+\usage{
+haven_all_levels(data)
+}
+\arguments{
+\item{data}{haven labelled variable}
+}
+\value{
+named vector
+}
+\description{
+Finish incomplete haven attributes substituting missings with values
+}
+\examples{
+ds <- structure(c(1, 2, 3, 2, 10, 9),
+  labels = c(Unknown = 9, Refused = 10),
+  class = "haven_labelled"
+)
+ds |> haven_all_levels()
+}

man/numchar2fct.Rd

@@ -0,0 +1,29 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ds2dd_detailed.R
+\name{numchar2fct}
+\alias{numchar2fct}
+\title{Applying var2fct across data set}
+\usage{
+numchar2fct(data, numeric.threshold = 6, character.throshold = 6)
+}
+\arguments{
+\item{data}{dataset. data.frame or tibble}
+
+\item{numeric.threshold}{threshold for var2fct for numeric columns. Default
+is 6.}
+
+\item{character.throshold}{threshold for var2fct for character columns.
+Default is 6.}
+}
+\value{
+data.frame or tibble
+}
+\description{
+Individual thresholds for character and numeric columns
+}
+\examples{
+mtcars |> str()
+mtcars |>
+  numchar2fct(numeric.threshold = 6) |>
+  str()
+}

man/parse_data.Rd

@@ -0,0 +1,39 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ds2dd_detailed.R
+\name{parse_data}
+\alias{parse_data}
+\title{Helper to auto-parse un-formatted data with haven and readr}
+\usage{
+parse_data(
+  data,
+  guess_type = TRUE,
+  col_types = NULL,
+  locale = readr::default_locale(),
+  ignore.vars = "cpr",
+  ...
+)
+}
+\arguments{
+\item{data}{data.frame or tibble}
+
+\item{guess_type}{logical to guess type with readr}
+
+\item{col_types}{specify col_types using readr semantics. Ignored if guess_type is TRUE}
+
+\item{locale}{option to specify locale. Defaults to readr::default_locale().}
+
+\item{ignore.vars}{specify column names of columns to ignore when parsing}
+
+\item{...}{ignored}
+}
+\value{
+data.frame or tibble
+}
+\description{
+Helper to auto-parse un-formatted data with haven and readr
+}
+\examples{
+mtcars |>
+  parse_data() |>
+  str()
+}

man/var2fct.Rd

@@ -0,0 +1,29 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/ds2dd_detailed.R
+\name{var2fct}
+\alias{var2fct}
+\title{Convert vector to factor based on threshold of number of unique levels}
+\usage{
+var2fct(data, unique.n)
+}
+\arguments{
+\item{data}{vector or data.frame column}
+
+\item{unique.n}{threshold to convert class to factor}
+}
+\value{
+vector
+}
+\description{
+This is a wrapper of forcats::as_factor, which sorts numeric vectors before
+factoring, but levels character vectors in order of appearance.
+}
+\examples{
+sample(seq_len(4), 20, TRUE) |>
+  var2fct(6) |>
+  summary()
+sample(letters, 20) |>
+  var2fct(6) |>
+  summary()
+sample(letters[1:4], 20, TRUE) |> var2fct(6)
+}