Movies data moved to ggplot2 movies.

.travis.yml

@@ -4,6 +4,7 @@ warnings_are_errors: true
 
 r_github_packages:
   - hadley/staticdocs
+  - hadley/ggplot2movies
   - jimhester/covr
 
 before_script:

DESCRIPTION

@@ -24,6 +24,7 @@ Imports:
     scales (>= 0.2.3),
     stats
 Suggests:
+    ggplot2movies,
     hexbin,
     Hmisc,
     knitr,

NEWS

@@ -1,6 +1,11 @@
 ggplot2 1.0.1.9xxx
 ----------------------------------------------------------------
 
+* The movies dataset has been moved into its own package, ggplot2movies,
+  because it was large and not terribly useful. If you've used the movies
+  dataset, you'll now need to explicitly load the package with
+  `library(ggplot2movies)`.
+
 * The default legend will now allocate multiple rows (if vertical) or
   columns (if horizontal) in order to make a legend that is more likely to
   fit on the screen. You can override with the `nrow`/`ncol` arguments

R/aes-colour-fill-alpha.r

@@ -25,9 +25,9 @@
 #' k + geom_bar()
 #'
 #' # Fill aesthetic can also be used with a continuous variable
-#' m <- ggplot(movies, aes(x = rating))
-#' m + geom_histogram()
-#' m + geom_histogram(aes(fill = ..count..))
+#' m <- ggplot(faithfuld, aes(waiting, eruptions))
+#' m + geom_raster()
+#' m + geom_raster(aes(fill = density))
 #'
 #' # Some geoms don't use both aesthetics (i.e. geom_point or geom_line)
 #' b <- ggplot(economics, aes(x = date, y = unemploy))

R/coord-polar.r

@@ -41,6 +41,7 @@
 #'   labs(title = "Pac man")
 #'
 #' # Windrose + doughnut plot
+#' if (require("ggplot2movies")) {
 #' movies$rrating <- cut_interval(movies$rating, length = 1)
 #' movies$budgetq <- cut_number(movies$budget, 4)
 #'
@@ -51,6 +52,7 @@
 #' # Race track plot
 #' doh + geom_bar(width = 0.9, position = "fill") + coord_polar(theta = "y")
 #' }
+#' }
 coord_polar <- function(theta = "x", start = 0, direction = 1) {
   theta <- match.arg(theta, c("x", "y"))
   r <- if (theta == "x") "y" else "x"

R/geom-bar-histogram.r

@@ -14,7 +14,7 @@
 #' @export
 #' @inheritParams geom_point
 #' @examples
-#' \donttest{
+#' if (require("ggplot2movies")) {
 #' set.seed(5689)
 #' movies <- movies[sample(nrow(movies), 1000), ]
 #' # Basic example

R/geom-blank.r

@@ -6,7 +6,7 @@
 #' @export
 #' @inheritParams geom_point
 #' @examples
-#' ggplot(movies, aes(length, rating)) + geom_blank()
+#' ggplot(mtcars, aes(wt, mpg)) + geom_blank()
 #' # Nothing to see here!
 #'
 #' # Take the following scatter plot

R/geom-boxplot.r

@@ -71,6 +71,7 @@
 #' # Scale transformations occur before the boxplot statistics are computed.
 #' # Coordinate transformations occur afterwards.  Observe the effect on the
 #' # number of outliers.
+#' if (require("ggplot2movies")) {
 #' library(plyr) # to access round_any
 #' m <- ggplot(movies, aes(y = votes, x = rating,
 #'    group = round_any(rating, 0.5)))
@@ -86,6 +87,7 @@
 #'
 #' ggplot(movies, aes(year, budget)) +
 #'   geom_boxplot(aes(group=round_any(year, 10, floor)))
+#' }
 #'
 #' # Using precomputed statistics
 #' # generate sample data
@@ -100,7 +102,6 @@
 #' p + geom_boxplot(varwidth = TRUE)
 #'
 #' # Update the defaults for the outliers by changing the defaults for geom_point
-#'
 #' p <- ggplot(mtcars, aes(factor(cyl), mpg))
 #' p + geom_boxplot()
 #'

R/geom-path-.r

@@ -15,6 +15,7 @@
 #' @examples
 #' \donttest{
 #' # Generate data
+#' if (require("ggplot2movies")) {
 #' library(plyr)
 #' myear <- ddply(movies, .(year), colwise(mean, .(length, rating)))
 #' p <- ggplot(myear, aes(length, rating))
@@ -29,6 +30,7 @@
 #'
 #' # Set aesthetics to fixed value
 #' p + geom_path(colour = "green")
+#' }
 #'
 #' # Control line join parameters
 #' df <- data.frame(x = 1:3, y = c(4, 1, 9))

R/geom-path-line.r

@@ -10,6 +10,7 @@
 #' @export
 #' @examples
 #' # Summarise number of movie ratings by year of movie
+#' if (require("ggplot2movies")) {
 #' mry <- do.call(rbind, by(movies, round(movies$rating), function(df) {
 #'   nums <- tapply(df$length, df$year, length)
 #'   data.frame(rating=round(df$rating[1]), year = as.numeric(names(nums)), number=as.vector(nums))
@@ -28,6 +29,7 @@
 #'
 #' # Set aesthetics to fixed value
 #' p + geom_line(colour = "red", size = 1)
+#' }
 #'
 #' # Using a time series
 #' ggplot(economics, aes(date, pop)) + geom_line()

R/geom-ribbon-.r

@@ -29,14 +29,6 @@
 #' huron[huron$year > 1900 & huron$year < 1910, "level"] <- NA
 #' h <- ggplot(huron, aes(x=year))
 #' h + geom_ribbon(aes(ymin=level-1, ymax=level+1)) + geom_line(aes(y=level))
-#'
-#' # Another data set, with multiple y's for each x
-#' m <- ggplot(movies, aes(y=votes, x=year))
-#' (m <- m + geom_point())
-#'
-#' # The default summary isn't that useful
-#' m + stat_summary(geom="ribbon", fun.ymin="min", fun.ymax="max")
-#' m + stat_summary(geom="ribbon", fun.data="median_hilow")
 #' }
 geom_ribbon <- function (mapping = NULL, data = NULL, stat = "identity",
   position = "identity", na.rm = FALSE, show_guide = NA, inherit.aes = TRUE, ...)

R/geom-violin.r

@@ -42,6 +42,7 @@
 #' p + geom_violin(fill = "grey80", colour = "#3366FF")
 #'
 #' # Scales vs. coordinate transforms -------
+#' if (require("ggplot2movies")) {
 #' # Scale transformations occur before the density statistics are computed.
 #' # Coordinate transformations occur afterwards.  Observe the effect on the
 #' # number of outliers.
@@ -59,6 +60,7 @@
 #' ggplot(movies, aes(year, budget)) +
 #'   geom_violin(aes(group = round_any(year, 10, floor)))
 #' }
+#' }
 geom_violin <- function (mapping = NULL, data = NULL, stat = "ydensity",
   position = "dodge", trim = TRUE, scale = "area", show_guide = NA,
   inherit.aes = TRUE, ...)

R/ggplot2.r

@@ -88,36 +88,6 @@ NULL
 "midwest"
 
 
-#' Movie information and user ratings from IMDB.com.
-#'
-#' The internet movie database, \url{http://imdb.com/}, is a website devoted
-#' to collecting movie data supplied by studios and fans.  It claims to be the
-#' biggest movie database on the web and is run by amazon.  More about
-#' information imdb.com can be found online,
-#' \url{http://imdb.com/help/show_leaf?about}, including information about
-#' the data collection process,
-#' \url{http://imdb.com/help/show_leaf?infosource}.
-#'
-#' Movies were selected for inclusion if they had a known length and had been
-#' rated by at least one imdb user.
-#'
-#' @format A data frame with 28819 rows and 24 variables
-#' \itemize{
-#'   \item title.  Title of the movie.
-#'   \item year.  Year of release.
-#'   \item budget.  Total budget (if known) in US dollars
-#'   \item length.  Length in minutes.
-#'   \item rating.  Average IMDB user rating.
-#'   \item votes.  Number of IMDB users who rated this movie.
-#'   \item r1-10.  Multiplying by ten gives percentile (to nearest 10\%) of
-#'      users who rated this movie a 1.
-#'   \item mpaa.  MPAA rating.
-#'   \item action, animation, comedy, drama, documentary, romance, short.
-#'     Binary variables representing if movie was classified as belonging to that genre.
-#' }
-#' @references \url{http://had.co.nz/data/movies/}
-"movies"
-
 #' Fuel economy data from 1999 and 2008 for 38 popular models of car
 #'
 #' This dataset contains a subset of the fuel economy data that the EPA makes

R/save.r

@@ -25,16 +25,16 @@
 #' @export
 #' @examples
 #' \dontrun{
-#' ggplot(movies, aes(rating)) + geom_histogram(binwidth = 0.1)
+#' ggplot(mtcars, aes(mpg, wt)) + geom_point()
 #'
-#' ggsave("ratings.pdf")
-#' ggsave("ratings.png")
+#' ggsave("mtcars.pdf")
+#' ggsave("mtcars.png")
 #'
-#' ggsave("ratings.pdf", width = 4, height = 4)
-#' ggsave("ratings.pdf", width = 20, height = 20, units = "cm")
+#' ggsave("mtcars.pdf", width = 4, height = 4)
+#' ggsave("mtcars.pdf", width = 20, height = 20, units = "cm")
 #'
-#' unlink("ratings.pdf")
-#' unlink("ratings.png")
+#' unlink("mtcars.pdf")
+#' unlink("mtcars.png")
 #'
 #' # specify device when saving to a file with unknown extension
 #' # (for example a server supplied temporary file)

R/scale-continuous.r

@@ -11,6 +11,7 @@
 #' @export
 #' @examples
 #' \donttest{
+#' if (require(ggplot2movies)) {
 #' m <- ggplot(subset(movies, votes > 1000), aes(rating, votes)) +
 #'   geom_point(na.rm = TRUE)
 #' m
@@ -72,6 +73,7 @@
 #'   scale_x_log10() +
 #'   scale_y_log10()
 #' }
+#' }
 scale_x_continuous <- function(name = NULL, breaks = waiver(),
                                minor_breaks = waiver(), labels = waiver(),
                                limits = NULL, expand = waiver(), oob = censor,

R/stat-bin.r

@@ -29,19 +29,16 @@
 #' # If right = TRUE, and intervals are of the form (a, b]
 #' base + stat_bin(binwidth = 1, drop = FALSE, right = TRUE, col = "black")
 #'
-#' m <- ggplot(movies, aes(x=rating))
-#' m + stat_bin()
-#' m + stat_bin(binwidth=0.1)
-#' m + stat_bin(breaks=seq(4,6, by=0.1))
+#' d <- ggplot(diamonds, aes(carat))
+#' d + stat_bin()
+#' d + stat_bin(binwidth = 0.1)
+#' d + stat_bin(breaks=seq(0, 2, by = 0.01))
 #' # See geom_histogram for more histogram examples
 #'
 #' # To create a unit area histogram, use aes(y = ..density..)
-#' (linehist <- m + stat_bin(aes(y = ..density..), binwidth=0.1,
-#'   geom="line", position="identity"))
-#' linehist + stat_density(colour="blue", fill=NA)
-#'
-#' # Also works with categorical variables
-#' ggplot(movies, aes(x=mpaa)) + stat_bin()
+#' linehist <- d + geom_freqpoly(aes(y = ..density..), binwidth = 0.1)
+#' linehist
+#' linehist + stat_density(colour = "blue", fill = NA)
 #' }
 stat_bin <- function (mapping = NULL, data = NULL, geom = "bar",
   position = "stack", width = 0.9, drop = FALSE, right = FALSE,

R/stat-density.r

@@ -24,6 +24,7 @@
 #' @export
 #' @examples
 #' \donttest{
+#' if (require("ggplot2movies")) {
 #' m <- ggplot(movies, aes(x = rating))
 #' m + geom_density()
 #'
@@ -88,6 +89,7 @@
 #' m + geom_density(fill=NA)
 #' m + geom_density(fill=NA) + aes(y = ..count..)
 #' }
+#' }
 stat_density <- function (mapping = NULL, data = NULL, geom = "area",
   position = "stack", adjust = 1, kernel = "gaussian", trim = FALSE,
   na.rm = FALSE, show_guide = NA, inherit.aes = TRUE, ...)

R/stat-quantile.r

@@ -15,6 +15,7 @@
 #' @export
 #' @examples
 #' \donttest{
+#' if (require("ggplot2movies")) {
 #' msamp <- movies[sample(nrow(movies), 1000), ]
 #' m <- ggplot(msamp, aes(year, rating)) + geom_point()
 #' m + stat_quantile()
@@ -40,6 +41,7 @@
 #' # Set aesthetics to fixed value
 #' m + stat_quantile(colour = "red", size = 2, linetype = 2)
 #' }
+#' }
 stat_quantile <- function (mapping = NULL, data = NULL, geom = "quantile",
   position = "identity", quantiles = c(0.25, 0.5, 0.75), formula = NULL,
   method = "rq", na.rm = FALSE, show_guide = NA, inherit.aes = TRUE, ...)

R/stat-summary.r

@@ -91,6 +91,7 @@
 #'        xlab("cyl")
 #' m
 #' # An example with highly skewed distributions:
+#' if (require("ggplot2movies")) {
 #' set.seed(596)
 #' mov <- movies[sample(nrow(movies), 1000), ]
 #'  m2 <- ggplot(mov, aes(x= factor(round(rating)), y=votes)) + geom_point()
@@ -111,6 +112,7 @@
 #' # standard errors.
 #' m2 + coord_trans(y="log10")
 #' }
+#' }
 stat_summary <- function (mapping = NULL, data = NULL, geom = "pointrange",
   position = "identity", show_guide = NA, inherit.aes = TRUE, ...)
 {

R/translate-qplot-lattice.r

@@ -9,6 +9,7 @@
 #' \dontrun{
 #' library(lattice)
 #'
+#' if (require("ggplot2movies")) {
 #' xyplot(rating ~ year, data=movies)
 #' qplot(year, rating, data=movies)
 #'
@@ -35,6 +36,7 @@
 #'
 #' xyplot(wt ~ mpg, mtcars, type = c("p","r"))
 #' qplot(mpg, wt, data = mtcars, geom = c("point","smooth"), method = "lm")
+#' }
 #'
 #' # The capabilities for scale manipulations are similar in both ggplot2 and
 #' # lattice, although the syntax is a little different.