change name from ggmissing to naniar

DESCRIPTION

@@ -1,10 +1,10 @@
-Package: ggmissing
+Package: naniar
 Type: Package
-Title: enables ggplot to plot missing data
+Title: Enables ggplot to plot missing data
 Version: 0.2.9000
 Author: Nicholas Tierney, Miles McBain, Di Cook,
 Maintainer: <nicholas.tierney@gmail.com>
-Description: ggmissing helps display missing data in ggplot
+Description: naniar helps display missing data in ggplot
 License: MIT + file LICENSE
 LazyData: TRUE
 Suggests:

R/geom_missing_histogram.R

@@ -2,7 +2,7 @@
 #' @name geom_missing_histogram
 #' @description geom_missing_histogram adds a point geometry for displaying missingness.
 #' @note Very first attempt at creating a geom that is compatible with ggplot2.
-#' 
+#'
 #' Data plotting works. Still todo:
 #' manipulate the colour aes so that the colours and legend appear.
 #' fix awful default point sizes.
@@ -39,10 +39,10 @@ geom_missing_histogram <- function(mapping = NULL,
       ...
     )
   )
-  
+
 }
 
-#' @rdname ggmissing-ggproto
+#' @rdname naniar-ggproto
 #' @export
 GeomMissingHistogram <- ggproto("GeomMissingHistogram", GeomRect,
 required_aes = "x",

R/geom_missing_point.R

@@ -11,7 +11,7 @@
 #'
 # this code messes up the documentation
 # library(ggplot2)
-# library(ggmissing)
+# library(naniar)
 #
 #  ggplot(data = brfss,
 #         aes(x = PHYSHLTH,
@@ -50,7 +50,7 @@ geom_missing_point <- function(mapping = NULL,
 
 }
 
-#' @rdname ggmissing-ggproto
+#' @rdname naniar-ggproto
 #' @export
 GeomMissingPoint <- ggproto("GeomMissingPoint", GeomPoint,
                             required_aes = c("x", "y"),

R/missing_data_tidiers.R

@@ -13,7 +13,7 @@
 #'
 #' @examples
 #'
-#' library(ggmissing)
+#' library(naniar)
 #' percent_missing_df(airquality)
 #'
 percent_missing_df <- function(dat){
@@ -36,7 +36,7 @@ percent_missing_df <- function(dat){
 #'
 #' @examples
 #'
-#' library(ggmissing)
+#' library(naniar)
 #'
 #' percent_missing_var(airquality)
 #'
@@ -65,7 +65,7 @@ percent_missing_var <- function(dat){
 #'
 #' @examples
 #'
-#' library(ggmissing)
+#' library(naniar)
 #' percent_missing_case(airquality)
 #'
 percent_missing_case <- function(dat){

R/naniar-ggproto.R

@@ -0,0 +1,6 @@
+#' @name naniar-ggproto
+#' @title naniar-ggroto
+#'
+#' @description These are the stat and geom overrides using ggproto from ggplot2 that make naniar work.
+#'
+NULL

R/revealers.R

@@ -0,0 +1,18 @@
+# derive_shadows:
+# helpers to clear up common representations of missing values
+# such as "NA", "N/A", etc.
+# and might allow for an easier way for users to describe different
+# missing data codes, such as -99, which might indicate missing, but
+# some other kind of missing value, perhaps a different mechanism of
+# missingness
+# ideas for function names:
+# narify (play on clarify)
+# darken ()
+# shade
+# refract
+
+# Other commands that might be useful?
+# `is_na`
+# `fill_na`
+# `drop_na`
+# `is_null`

R/shadows.R

@@ -0,0 +1,87 @@
+
+# give NAs a more meaningful label
+is_na <- function(x) {
+  factor(is.na(x), levels = c(FALSE, TRUE), labels = c("!NA", "NA"))
+}
+
+# append some shadow cols
+
+# return a tibble that is a shadow matrix form.
+
+as_shadow <- function(data){
+
+  data_shadow <- purrr::map_df(data, is_na)
+
+  names(data_shadow) <- paste0(names(data),"_NA")
+
+  data_shadow
+
+}
+
+# as_shadow(airquality)
+
+bind_shadow <- function(data){
+
+  # data_shadow <- map_df(data, is_na)
+  # names(data_shadow) <- paste0(names(data),"_NA")
+  data_shadow <- as_shadow(data)
+
+  bound_shadow <- tibble::as_tibble(dplyr::bind_cols(data, data_shadow))
+
+  bound_shadow
+
+}
+
+ggplot(data = bind_shadow(airquality),
+       aes(x = Ozone)) +
+  geom_histogram() +
+  facet_wrap(~Solar.R_NA,
+             ncol = 1)
+#
+ggplot(data = airquality,
+       aes(x = Ozone)) +
+  geom_histogram() +
+  facet_wrap(~is_na(Solar.R),
+             ncol = 1)
+#
+# ggplot(bind_shadow(airquality),
+#        aes(x = Ozone,
+#            colour = Solar.R_NA)) +
+#   geom_density() +
+#   geom_rug()
+#
+# ggplot(airquality,
+#        aes(x = Ozone,
+#            colour = is_na(Solar.R))) +
+#   geom_density() +
+#   geom_rug()
+
+# other "long" shadow format
+
+# shadow_join exists as we want to include this extra metadata about the rows that have missing data, but I also wanted to include some extra information about the class of the data, in case we need to gather the data back into a wider, rather than long, format. Here it takes a function `visdat`, `visdat:::fingerprint`, which is currently not a particularly complex function.
+
+gather_shadow <- function(df){
+
+  df_val_type <- df %>%
+    as_data_frame() %>%
+    purrr::dmap(visdat:::fingerprint) %>%
+    mutate(rows = row_number()) %>%
+    tidyr::gather_(key_col = "variable",
+                   value_col = "valueType",
+                   gather_cols = names(.)[-length(.)])
+
+  # df_shadow
+  df_shadow <- df %>%
+    as_data_frame() %>%
+    mutate(rows = row_number()) %>%
+    gather(key = variable,
+           value = value,
+           -rows) %>%
+    mutate(shadow_matrix = is_na(value)) %>%
+    left_join(df_val_type)
+
+  # perhaps define some attributes
+
+}
+
+aq_shadow <- gather_shadow(airquality)

R/stat_missing_histogram.R

@@ -29,11 +29,11 @@ stat_missing_histogram <- function(mapping = NULL,
     inherit.aes = inherit.aes,
     params = list(na.rm = na.rm, ...)
   )
-  
+
 }
 
 
-#' @rdname ggmissing-ggproto
+#' @rdname naniar-ggproto
 #' @export
 StatMissingHistogram <- ggproto("StatMissingHistogram", Stat,
                             required_aes = c("x"),

R/stat_missing_point.R

@@ -31,7 +31,7 @@ stat_missing_point <- function(mapping = NULL,
 
 }
 
-#' @rdname ggmissing-ggproto
+#' @rdname naniar-ggproto
 #' @export
 StatMissingPoint <- ggproto("StatMissingPoint", Stat,
     required_aes = c("x", "y"),

README.Rmd

@@ -12,32 +12,32 @@ knitr::opts_chunk$set(
 )
 ```
 
-# ggmissing
-[![AppVeyor Build Status](https://ci.appveyor.com/api/projects/status/github/njtierney/ggmissing?branch=master&svg=true)](https://ci.appveyor.com/project/njtierney/ggmissing) [![Travis-CI Build Status](https://travis-ci.org/njtierney/ggmissing.svg?branch=master)](https://travis-ci.org/njtierney/ggmissing)
+# naniar
+[![AppVeyor Build Status](https://ci.appveyor.com/api/projects/status/github/njtierney/naniar?branch=master&svg=true)](https://ci.appveyor.com/project/njtierney/naniar) [![Travis-CI Build Status](https://travis-ci.org/njtierney/naniar.svg?branch=master)](https://travis-ci.org/njtierney/naniar)
 
-`ggmissing` adds ggplot `geom`s to display missingness. 
+`naniar` adds ggplot `geom`s to display missingness. 
 
 ## Why?
 
 Missing data is ubiquitous in data analysis. However, vis  points are omitted in ggplot, and although it does provides a warning message telling you that you have missing data, it is tricky to visualise missing data.
 
-`ggmissing` is part of a larger plan for a set of tidy-verse packages focussing on how to tidy, transform, visualise, model, and communicate missing data.
+`naniar` is part of a larger plan for a set of tidy-verse packages focussing on how to tidy, transform, visualise, model, and communicate missing data.
 
 It is still very much under development, and may have unknown bugs, due to the fact that ggplot was not initially built to handle missing data in this way. We will see more active development over the next 6 months.
 
 Please note that this project is released with a [Contributor Code of Conduct](CONDUCT.md). By participating in this project you agree to abide by its terms.
 
 ## What does it do?
 
-`ggmissing` provides:
+`naniar` provides:
 
 1. Missing data geoms for ggplot (`geom_missing_point`)
 
 2. Tidyverse summary functions for missing data (`summarise_missingness` and friends)
 
 3. ggplots for exploring missing data (`gg_missing_var`, `gg_missing_case`, `gg_missing_which`)
 
-## Using ggmissing {#ggplot}
+## Using naniar {#ggplot}
 
 ### How does it work?
 
@@ -46,8 +46,8 @@ Plotting missing data might sound a little strange - how do you visualise someth
 To illustrate, let's explore the relationship between Ozone and Solar radiation from the airquality dataset.
 
 ```{r messages = FALSE, error = FALSE}
-library(ggmissing)
-# devtools::install_github("njtierney/ggmissing")
+library(naniar)
+# devtools::install_github("njtierney/naniar")
 library(ggplot2)
 library(dplyr)
 
@@ -68,7 +68,7 @@ We can instead use the `geom_missing_point()` to display the missing data
 
 ```{r}
 
-library(ggmissing)
+library(naniar)
 library(ggplot2)
 
 ggplot(data = airquality,
@@ -105,7 +105,7 @@ p1 + theme_bw()
 
 # Missing data tidying functions {#tidying}
 
-`ggmissing` uses some missingness transformation functions to set up tables for visualisation.  
+`naniar` uses some missingness transformation functions to set up tables for visualisation.  
 
 ```{r}
 
@@ -207,7 +207,7 @@ vis_miss(airquality)
 
 # Future Work
 
-`ggmissing` has not seen much attention for the past 6 months or so, and so will be undergoing more changes over the next 6 months, with plans to have the package in CRAN before the end of 2016. 
+`naniar` has not seen much attention for the past 6 months or so, and so will be undergoing more changes over the next 6 months, with plans to have the package in CRAN before the end of 2016. 
 
 As such, we plan to extend the `geom_missing` family to include:
 

tests/testthat/test-missingness-tidiers.R

@@ -1,17 +1,20 @@
 context("missingness_tidiers")
 
 test_that("percent_missing_* produces a single, numeric number", {
-  expect_length(ggmissing::percent_missing_df(airquality), 1)
-  testthat::expect_type(ggmissing::percent_missing_df(airquality), "double")
-  expect_length(ggmissing::percent_missing_var(airquality), 1)
-  testthat::expect_type(ggmissing::percent_missing_var(airquality), "double")
-  expect_length(ggmissing::percent_missing_case(airquality), 1)
-  testthat::expect_type(ggmissing::percent_missing_case(airquality), "double")
+
+  expect_length(percent_missing_df(airquality), 1)
+  testthat::expect_type(percent_missing_df(airquality), "double")
+
+  expect_length(percent_missing_var(airquality), 1)
+  testthat::expect_type(percent_missing_var(airquality), "double")
+
+  expect_length(percent_missing_case(airquality), 1)
+  testthat::expect_type(percent_missing_case(airquality), "double")
 })
 
 test_that("table_missing_* produces a data_frame", {
-  testthat::expect_is(ggmissing::table_missing_var(airquality), "tbl_df")
-  testthat::expect_is(ggmissing::table_missing_case(airquality), "tbl_df")
+  testthat::expect_is(table_missing_var(airquality), "tbl_df")
+  testthat::expect_is(table_missing_case(airquality), "tbl_df")
 })