From a1ee6a828137e06e24bd8ecc81e856470dcb69b3 Mon Sep 17 00:00:00 2001
From: Garrick Aden-Buie <gadenbuie@mail.usf.edu>
Date: Thu, 31 Jan 2019 12:15:43 -0500
Subject: [PATCH] Add pre_sort() and sorting_hat()

---
 DESCRIPTION        | 11 ++++++++---
 NAMESPACE          |  8 ++++++--
 R/sorting_hat.R    | 32 ++++++++++++++++++++++++++++++++
 man/pipe.Rd        | 12 ++++++++++++
 man/pre_sort.Rd    | 14 ++++++++++++++
 man/sorting_hat.Rd | 14 ++++++++++++++
 6 files changed, 86 insertions(+), 5 deletions(-)
 create mode 100644 R/sorting_hat.R
 create mode 100644 man/pipe.Rd
 create mode 100644 man/pre_sort.Rd
 create mode 100644 man/sorting_hat.Rd

diff --git a/DESCRIPTION b/DESCRIPTION
index 6dcf326..88a5661 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -2,10 +2,13 @@ Package: tricks
 Title: Performs statistical tricks
 Version: 0.0.0.9000
 Authors@R: 
-    person(given = "Travis",
+    c(person(given = "Travis",
            family = "Gerke",
            role = c("aut", "cre"),
-           email = "travis.gerke@moffitt.org")
+           email = "travis.gerke@moffitt.org"),
+      person("Garrick", 
+             "Aden-Buie",
+             email = "garrick.aden-buie@moffitt.org"))
 Description: What the package does (one paragraph)
 License: What license it uses
 Encoding: UTF-8
@@ -18,6 +21,8 @@ Suggests:
 Language: en-US
 Imports: 
     magrittr,
-    broom
+    broom,
+    purrr,
+    dplyr
 URL: https://github.com/GerkeLab/tricks
 BugReports: https://github.com/GerkeLab/tricks/issues
diff --git a/NAMESPACE b/NAMESPACE
index 884a631..2b50e3c 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -1,2 +1,6 @@
-# Generated by roxygen2: fake comment so roxygen2 overwrites silently.
-exportPattern("^[^\\.]")
+# Generated by roxygen2: do not edit by hand
+
+export("%>%")
+export(pre_sort)
+export(sorting_hat)
+importFrom(magrittr,"%>%")
diff --git a/R/sorting_hat.R b/R/sorting_hat.R
new file mode 100644
index 0000000..c47a14e
--- /dev/null
+++ b/R/sorting_hat.R
@@ -0,0 +1,32 @@
+#' Gather information about the data variables
+#'
+#' @param df The input data frame
+#' @export
+sorting_hat <- function(df) {
+  x <- purrr::map(df, class) %>%
+    purrr::map_dfr(~ data.frame(type = ., stringsAsFactors = FALSE), .id = "col_name") %>%
+    dplyr::mutate(
+      n_unique   = purrr::map_int(df, ~ length(unique(.))),
+      n_complete = purrr::map_int(df, ~ length(.x[!is.na(.x)]))
+    )
+
+  x$cv <- purrr::map_dbl(x$col_name, ~ cov(df[[.]]))
+
+  x
+}
+
+cov <- function(x) {
+  if (!inherits(x, "numeric")) return(NA_real_)
+  sd(x, TRUE)/mean(x, na.rm = TRUE)
+}
+
+#' Pre-sorting processing of data
+#'
+#' Cast character columns to factors.
+#'
+#' @param df The input data frame
+#' @export
+pre_sort <- function(df) {
+  df %>%
+    dplyr::mutate_if(is.character, as.factor)
+}
diff --git a/man/pipe.Rd b/man/pipe.Rd
new file mode 100644
index 0000000..b7daf6a
--- /dev/null
+++ b/man/pipe.Rd
@@ -0,0 +1,12 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/utils-pipe.R
+\name{\%>\%}
+\alias{\%>\%}
+\title{Pipe operator}
+\usage{
+lhs \%>\% rhs
+}
+\description{
+See \code{magrittr::\link[magrittr]{\%>\%}} for details.
+}
+\keyword{internal}
diff --git a/man/pre_sort.Rd b/man/pre_sort.Rd
new file mode 100644
index 0000000..42b2106
--- /dev/null
+++ b/man/pre_sort.Rd
@@ -0,0 +1,14 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/sorting_hat.R
+\name{pre_sort}
+\alias{pre_sort}
+\title{Pre-sorting processing of data}
+\usage{
+pre_sort(df)
+}
+\arguments{
+\item{df}{The input data frame}
+}
+\description{
+Cast character columns to factors.
+}
diff --git a/man/sorting_hat.Rd b/man/sorting_hat.Rd
new file mode 100644
index 0000000..c9579f5
--- /dev/null
+++ b/man/sorting_hat.Rd
@@ -0,0 +1,14 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/sorting_hat.R
+\name{sorting_hat}
+\alias{sorting_hat}
+\title{Gather information about the data variables}
+\usage{
+sorting_hat(df)
+}
+\arguments{
+\item{df}{The input data frame}
+}
+\description{
+Gather information about the data variables
+}