Merge pull request #49 from rudeboybert/v0.5.0-release

v0.5.0 release
rudeboybert · Jul 31, 2019 · 436d697 · 436d697
2 parents 964f257 + dd94903
commit 436d697
Show file tree

Hide file tree

Showing 22 changed files with 139 additions and 1,766 deletions.
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -11,3 +11,4 @@
 ^images_for_guide$
 ^doc$
 ^Meta$
+^CRAN-RELEASE$
diff --git a/CRAN-RELEASE b/CRAN-RELEASE
@@ -0,0 +1,2 @@
+This package was submitted to CRAN on 2019-07-30.
+Once it is accepted, delete this file and tag the release (commit bb6db3fa30).
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -4,7 +4,7 @@ Description: Datasets and code published by the data journalism website
     'FiveThirtyEight' available at <https://github.com/fivethirtyeight/data>. 
     Note that while we received guidance from editors at 'FiveThirtyEight', this 
     package is not officially published by 'FiveThirtyEight'.
-Version: 0.4.0.9000
+Version: 0.5.0
 Authors@R: c(
     person("Albert Y.", "Kim", email = "albert.ys.kim@gmail.com", role = c("aut", "cre")),
     person("Chester", "Ismay", email = "chester.ismay@gmail.com", role = "aut"),
@@ -33,6 +33,7 @@ Suggests:
     ggplot2,
     dplyr,
     tidyr,
+    curl,
     readr,
     tibble,
     lubridate,
@@ -44,15 +45,5 @@ Suggests:
     scales,
     broom,
     magrittr,
-    rmarkdown,
-    slam (>= 0.1-42),
-    highcharter (>= 0.7),
-    tidytext,
-    textdata,
-    hunspell,
-    fmsb,
-    wordcloud,
-    corrplot,
-    ggraph,
-    igraph
+    rmarkdown
 VignetteBuilder: knitr
diff --git a/NEWS.md b/NEWS.md
@@ -1,4 +1,4 @@
-# fivethirtyeight 0.4.0.9000
+# fivethirtyeight 0.5.0
 
 * Added vignette corresponding to Technology Innovations in Statistics Education [paper](https://escholarship.org/uc/item/0rx1231m#main)
 * Removed tidyverse from `DESCRIPTION` Depends, Imports, or Suggests fields

diff --git a/R/data_meredith.R b/R/data_meredith.R
@@ -284,20 +284,18 @@
 #' Data was collected on August 27, 2017 between 12:05 a.m. and 1:15 a.m. EDT
 #' using the Twitter streaming API. \url{https://github.com/fivethirtyeight/data/tree/master/mayweather-mcgregor}
 #' @examples
-#' # To obtain the entire dataset, run the code inside the following if statement:
-#' if(FALSE){
-#'   library(dplyr)
-#'   library(tidyr)
-#'   library(readr)
-#'   url <-
-#'    "https://raw.githubusercontent.com/fivethirtyeight/data/master/mayweather-mcgregor/tweets.csv"
-#'   mayweather_mcgregor_tweets <- read_csv(url) %>%
-#'     mutate(
-#'       emojis = as.logical(emojis),
-#'       retweeted = as.logical(retweeted),
-#'       id = as.character(id)
-#'     )
-#' }
+#' # To obtain the entire dataset, run the following code:
+#' library(dplyr)
+#' library(readr)
+#' 
+#' mayweather_mcgregor_tweets <-
+#'   "https://raw.githubusercontent.com/fivethirtyeight/data/master/mayweather-mcgregor/tweets.csv" %>%
+#'   read_csv() %>%
+#'   mutate(
+#'     emojis = as.logical(emojis),
+#'     retweeted = as.logical(retweeted),
+#'     id = as.character(id)
+#'   )
 "mayweather_mcgregor_tweets"
 
 

diff --git a/R/data_starry.R b/R/data_starry.R
@@ -150,9 +150,9 @@
 #' \url{https://projects.fivethirtyeight.com/2018-midterm-election-forecast/house/}
 #'
 #' @format Because of R package size restrictions, only a preview of the
-#' first 10 rows of this dataset is included; to obtain the entire dataset 
-#' see Examples below. The preview is a data frame with 10 rows representing 
-#' district-level results of the classic, lite, and deluxe house forecasts 
+#' first 10 rows of this dataset is included; to obtain the entire dataset
+#' see Examples below. The preview is a data frame with 10 rows representing
+#' district-level results of the classic, lite, and deluxe house forecasts
 #' since 2018/08/01 and 11 variables.
 #' \describe{
 #' \item{forecastdate}{date of the forecast}
@@ -172,14 +172,16 @@
 #' Methodology:
 #' \url{https://fivethirtyeight.com/methodology/how-fivethirtyeights-house-and-senate-models-work/}
 #' @seealso \code{\link{house_national_forecast}}
-#' @examples 
+#' @examples
+#' if(FALSE){
+#'
 #' # To obtain the entire dataset, run the following code:
 #' library(readr)
 #' library(dplyr)
 #' library(janitor)
-#' 
-#' house_district_forecast <- 
-#'   "https://projects.fivethirtyeight.com/congress-model-2018/house_district_forecast.csv" %>% 
+#'
+#' house_district_forecast <-
+#'   "https://projects.fivethirtyeight.com/congress-model-2018/house_district_forecast.csv" %>%
 #'   read_csv() %>%
 #'   clean_names() %>%
 #'   mutate(
@@ -189,6 +191,8 @@
 #'     model = as.factor(model)
 #'   ) %>%
 #'   select(-special)
+#'
+#' }
 "house_district_forecast"
 
 #' 2018 House Forecast
@@ -197,7 +201,7 @@
 #' 'Forecasting the race for the House'
 #' \url{https://projects.fivethirtyeight.com/2018-midterm-election-forecast/house/}
 #'
-#' @format A dataframe with 588 rows representing district-level results of the 
+#' @format A dataframe with 588 rows representing district-level results of the
 #' classic, lite, and deluxe house forecasts since 2018/08/01 and 11 variables.
 #' \describe{
 #' \item{forecastdate}{date of the forecast}

diff --git a/README.Rmd b/README.Rmd
@@ -10,6 +10,7 @@ knitr::opts_chunk$set(
   comment = "#>",
   fig.path = "README-"
 )
+library(fivethirtyeight)
 ```
 
 
@@ -53,15 +54,13 @@ library(fivethirtyeight)
 data(bechdel)
 head(bechdel)
 ?bechdel
+
 # If using RStudio:
 View(bechdel)
+```
 
-# To see a list of all data sets:
-data(package = "fivethirtyeight")
+To see a detailed list of all `r nrow(data(package = "fivethirtyeight")[[3]])` datasets, including information on the corresponding articles published on FiveThirtyEight.com, click [here](https://fivethirtyeight-r.netlify.com/articles/fivethirtyeight.html).
 
-# To see a more detailed list of all data sets, see the package vignette:
-vignette("fivethirtyeight", package = "fivethirtyeight")
-```
 
 
 ## Article in "Technology Innovations in Statistics Education"

diff --git a/README.md b/README.md
@@ -42,16 +42,15 @@ library(fivethirtyeight)
 data(bechdel)
 head(bechdel)
 ?bechdel
+
 # If using RStudio:
 View(bechdel)
-
-# To see a list of all data sets:
-data(package = "fivethirtyeight")
-
-# To see a more detailed list of all data sets, see the package vignette:
-vignette("fivethirtyeight", package = "fivethirtyeight")
 ```
 
+To see a detailed list of all 127 datasets, including information on the
+corresponding articles published on FiveThirtyEight.com, click
+[here](https://fivethirtyeight-r.netlify.com/articles/fivethirtyeight.html).
+
 ## Article in “Technology Innovations in Statistics Education”
 
 The `fivethirtyeight` package was featured in [The fivethirtyeight R

diff --git a/cran-comments.md b/cran-comments.md
@@ -2,15 +2,25 @@
 
 This is a resubmission. In this version I have:
 
-* Fixed the DESCRIPTION file:
-* Lowered the size of the package tarball
-* Replaced all instances of FiveThirtyEight and 538 with `FiveThirtyEight`
+* Fixed the NOTEs involving URLs with spaces
+* Fixed the ERROR involving reading a CSV file off the web
+
 
 ## Test environments
 
-* local OS X install, R 3.4.1
-* win-builder (release)
+* local OS X install, R 3.6.1.
+* ubuntu 14.04 (on travis-ci), R 3.6.1.
+* Rhub
+    + Windows Server 2008 R2 SP1, R-devel, 32/64 bit
+    + Ubuntu Linux 16.04 LTS, R-release, GCC
+    + Fedora Linux, R-devel, clang, gfortran
+* win-builder (devel and release)
+
 
 ## R CMD check results
 
-There were no ERRORs, only two NOTES on package size.
+There were originally no ERRORs or WARNINGs. There were 3 NOTEs:
+
+* From Rhub (R-devel): one example had CPU or elapsed time > 5s (`comic_characters`), but this NOTE did not occur in any other test environment.
+* From Rhub (R-release): one example had CPU or elapsed time > 5s (`ratings`), but this NOTE did not occur in any other test environment.
+* From win-builder (both devel and release), it said that 4 URLs were possibly invalid, however upon testing them individually, they all worked fine. 
diff --git a/data-raw/process_data_sets_meredith.R b/data-raw/process_data_sets_meredith.R
@@ -120,7 +120,8 @@ mayweather_mcgregor_tweets <- read_csv("data-raw/mayweather-mcgregor/tweets.csv"
     emojis = as.logical(emojis),
     retweeted = as.logical(retweeted),
     id = as.character(id)
-  )
+  ) %>% 
+  slice(1:10)
 usethis::use_data(mayweather_mcgregor_tweets, overwrite = TRUE)
 
 

diff --git a/man/house_district_forecast.Rd b/man/house_district_forecast.Rd
diff --git a/man/house_national_forecast.Rd b/man/house_national_forecast.Rd
diff --git a/man/mayweather_mcgregor_tweets.Rd b/man/mayweather_mcgregor_tweets.Rd
diff --git a/vignettes/NBA.Rmd b/vignettes/NBA.Rmd