Move Lahman and hflights back to suggests.

Closes #508

DESCRIPTION

@@ -16,9 +16,7 @@ Imports:
     utils,
     R6,
     Rcpp,
-    magrittr,
-    Lahman,
-    hflights
+    magrittr
 Suggests:
     RSQLite,
     RSQLite.extfuns,
@@ -31,7 +29,9 @@ Suggests:
     knitr,
     microbenchmark,
     ggplot2,
-    mgcv
+    mgcv,
+    Lahman,
+    hflights
 VignetteBuilder: knitr
 LazyData: yes
 LinkingTo: Rcpp (>= 0.11.1),

NEWS.md

@@ -1,5 +1,9 @@
 # dplyr 0.2.0.99
 
+* Lahman and hflights have are (once again) suggested packages. This means 
+  many demos will not work unless you explicitly install them with
+  `install.packages(c("Lahman", "hflights"))` (#508).
+
 * Switched from RC to R6.
 
 * Change first argument name of `group_by()` to `.data` so you can create

R/bench-compare.r

@@ -28,8 +28,8 @@
 #' @seealso \code{\link{src_local}} for working with local data
 #' @examples
 #' \donttest{
-#' if (require("microbenchmark")) {
-#' lahman_local <- lahman_srcs("df", "dt", "cpp")
+#' if (require("microbenchmark") && has_lahman()) {
+#' lahman_local <- lahman_srcs("df", "dt")
 #' teams <- lapply(lahman_local, function(x) x %>% tbl("Teams"))
 #'
 #' compare_tbls(teams, function(x) x %>% filter(yearID == 2010))
@@ -38,7 +38,7 @@
 #' # You can also supply arbitrary additional arguments to bench_tbls
 #' # if there are other operations you'd like to compare.
 #' bench_tbls(teams, function(x) x %>% filter(yearID == 2010),
-#'    base = subset(Teams, yearID == 2010))
+#'    base = subset(Lahman::Teams, yearID == 2010))
 #'
 #' # A more complicated example using multiple tables
 #' setup <- function(src) {

R/chain.r

@@ -26,7 +26,7 @@
 #' @export
 #' @examples
 #' # If you're performing many operations you can either do step by step
-#' data("hflights", package = "hflights")
+#' if (require("hflights")) {
 #' a1 <- group_by(hflights, Year, Month, DayofMonth)
 #' a2 <- select(a1, Year:DayofMonth, ArrDelay, DepDelay)
 #' a3 <- summarise(a2,
@@ -61,6 +61,7 @@
 #'     dep = mean(DepDelay, na.rm = TRUE)
 #'   ) %>%
 #'   filter(arr > 30 | dep > 30)
+#' }
 chain <- function(..., env = parent.frame()) {
   # Defunct 0.3. Remove in 0.4
   stop("Chain is defunct Please use %>%", call. = FALSE)

R/data-lahman.r

@@ -117,6 +117,9 @@ cache_lahman <- function(type, ...) {
 #' @rdname lahman
 #' @export
 has_lahman <- function(type, ...) {
+  if (!requireNamespace("Lahman", quietly = TRUE)) return(FALSE)
+  if (missing(type)) return(TRUE)
+
   succeeds(lahman_src(type, ...), quiet = TRUE)
 }
 

R/data-temp.r

@@ -13,8 +13,6 @@
 #'
 #' temp_srcs(local)
 #' temp_srcs(db)
-#'
-#' mtcars_tbls <- temp_tbls(local, mtcars)
 #' }
 temp_srcs <- function(..., quiet = NULL) {
   load_srcs(temp_src, c(...), quiet = quiet)

R/do.r

@@ -58,9 +58,9 @@
 #' compare <- models %>% do(aov = anova(.$mod_linear, .$mod_quad))
 #' # compare %>% summarise(p.value = aov$`Pr(>F)`)
 #'
+#' if (require("hflights")) {
 #' # You can use it to do any arbitrary computation, like fitting a linear
 #' # model. Let's explore how carrier departure delays vary over the time
-#' data("hflights", package = "hflights")
 #' carriers <- group_by(hflights, UniqueCarrier)
 #' group_size(carriers)
 #'
@@ -74,6 +74,7 @@
 #' library(mgcv)
 #' by_dest %>% do(smooth = gam(ArrDelay ~ s(DepTime) + Month, data = .))
 #' }
+#' }
 do <- function(.data, ...) UseMethod("do")
 
 #' @export

R/group-size.r

@@ -1,11 +1,9 @@
 #' Calculate group sizes.
 #'
-#'
-#'
 #' @param x a grouped tbl
 #' @export
 #' @examples
-#' data("hflights", package = "hflights")
+#' if (require("hflights")) {
 #'
 #' by_day <- hflights %>% group_by(Year, Month, DayofMonth)
 #' n_groups(by_day)
@@ -14,6 +12,7 @@
 #' by_dest <- hflights %>% group_by(Dest)
 #' n_groups(by_dest)
 #' group_size(by_dest)
+#' }
 group_size <- function(x) UseMethod("group_size")
 
 #' @export

R/grouped-dt.r

@@ -8,8 +8,7 @@
 #' @param vars a list of quoted variables.
 #' @export
 #' @examples
-#' if (require("data.table")) {
-#' data("hflights", package = "hflights")
+#' if (require("data.table") && require("hflights")) {
 #' hflights_dt <- tbl_dt(hflights)
 #' group_size(group_by(hflights_dt, Year, Month, DayofMonth))
 #' group_size(group_by(hflights_dt, Dest))

R/join-df.r

@@ -13,9 +13,7 @@
 #'   \code{copy} is \code{TRUE}, \code{y} will be converted into a data frame
 #' @param ... included for compatibility with the generic; otherwise ignored.
 #' @examples
-#' data("Batting", package = "Lahman")
-#' data("Master", package = "Lahman")
-#'
+#' if (require("Lahman")) {
 #' batting_df <- tbl_df(Batting)
 #' person_df <- tbl_df(Master)
 #'
@@ -32,6 +30,7 @@
 #' anti_join(batting_df, person_df)
 #' # or people who didn't bat
 #' anti_join(person_df, batting_df)
+#' }
 #' @name join.tbl_df
 NULL
 

R/join-dt.r

@@ -7,10 +7,7 @@
 #' @param x,y tbls to join
 #' @param ... Included for compatibility with generic; otherwise ignored.
 #' @examples
-#' if (require("RSQLite") && require("RSQLite.extfuns")) {
-#' data("Batting", package = "Lahman")
-#' data("Master", package = "Lahman")
-#'
+#' if (require("data.table") && require("Lahman")) {
 #' batting_dt <- tbl_dt(Batting)
 #' person_dt <- tbl_dt(Master)
 #'

R/manip-dt.r

@@ -7,9 +7,8 @@
 #' @param .env The environment in which to evaluate arguments not included
 #'   in the data. The default should suffice for ordinary usage.
 #' @examples
-#' if (require("data.table")) {
+#' if (require("data.table") && require("hflights")) {
 #' # If you start with a data table, you end up with a data table
-#' data("hflights", package = "hflights")
 #' hflights <- as.data.table(hflights)
 #' filter(hflights, Month == 1, DayofMonth == 1, Dest == "DFW")
 #' head(select(hflights, Year:DayOfWeek))

R/manip-grouped-dt.r

@@ -5,8 +5,7 @@
 #' @param inplace if \code{FALSE} (the default) the data frame will be copied
 #'   prior to modification to avoid changes propagating via reference.
 #' @examples
-#' if (require("data.table")) {
-#' data("hflights", package = "hflights")
+#' if (require("data.table") && require("hflights")) {
 #' hflights2 <- tbl_dt(hflights)
 #' by_dest <- group_by(hflights2, Dest)
 #'

R/partial-eval.r

@@ -25,7 +25,7 @@
 #' @export
 #' @keywords internal
 #' @examples
-#' data("Batting", package = "Lahman")
+#' if (require("Lahman")) {
 #' bdf <- tbl_df(Batting)
 #' partial_eval(quote(year > 1980), bdf)
 #'
@@ -48,6 +48,7 @@
 #' partial_eval(quote(1 + 2 * 3))
 #' x <- 1
 #' partial_eval(quote(x ^ y))
+#' }
 partial_eval <- function(call, tbl = NULL, env = parent.frame()) {
   if (is.atomic(call)) return(call)
 

R/src-local.r

@@ -12,12 +12,15 @@
 #' @keywords internal
 #' @export
 #' @examples
+#' if (require("Lahman")) {
 #' src_dt("Lahman")
-#' src_df("Lahman")
 #'
 #' batting_df <- tbl(src_df("Lahman"), "Batting")
+#'
 #' if (require("data.table")) {
-#' batting_dt <- tbl(src_dt("Lahman"), "Batting")
+#'   src_df("Lahman")
+#'   batting_dt <- tbl(src_dt("Lahman"), "Batting")
+#' }
 #' }
 src_local <- function(tbl, pkg = NULL, env = NULL) {
   if (!xor(is.null(pkg), is.null(env))) {

R/tally.R

@@ -11,7 +11,7 @@
 #' @param sort if \code{TRUE} will sort output in descending order of \code{n}
 #' @export
 #' @examples
-#' library(Lahman)
+#' if (require("Lahman")) {
 #' batting_tbl <- tbl_df(Batting)
 #' tally(group_by(batting_tbl, yearID))
 #' tally(group_by(batting_tbl, yearID), sort = TRUE)
@@ -23,6 +23,7 @@
 #'
 #' # This looks a little nicer if you use the infix %>% operator
 #' batting_tbl %>% group_by(playerID) %>% tally(sort = TRUE)
+#' }
 tally <- function(x, wt, sort = FALSE) {
   if (missing(wt)) {
     if ("n" %in% names(x)) {

R/tbl-df.r

@@ -12,7 +12,7 @@
 #' ds
 #' as.data.frame(ds)
 #'
-#' data("Batting", package = "Lahman")
+#' if (require("Lahman")) {
 #' batting <- tbl_df(Batting)
 #' dim(batting)
 #' colnames(batting)
@@ -43,7 +43,6 @@
 #' # mutate(stints, cumsum(stints))
 #'
 #' # Joins ---------------------------------------------------------------------
-#' data("Master", "HallOfFame", package = "Lahman")
 #' player_info <- select(tbl_df(Master), playerID, hofID, birthYear)
 #' hof <- select(filter(tbl_df(HallOfFame), inducted == "Y"),
 #'  hofID, votedBy, category)
@@ -56,6 +55,7 @@
 #' semi_join(player_info, hof)
 #' # Find players not in hof
 #' anti_join(player_info, hof)
+#' }
 tbl_df <- function(data) {
   assert_that(is.data.frame(data))
   tbl_df_impl(data)

R/top-n.R

@@ -13,7 +13,7 @@
 #' @export
 #' @examples
 #' # Find 10 players with most games
-#' data("Batting", package = "Lahman")
+#' if (require("Lahman")) {
 #' players <- group_by(tbl_df(Batting), playerID)
 #' games <- tally(players, G)
 #' top_n(games, 10, n)
@@ -26,6 +26,7 @@
 #'
 #' # Find year with most games for each player
 #' tbl_df(Batting) %>% group_by(playerID) %>% top_n(1, G)
+#' }
 top_n <- function(x, n, wt) {
   if (missing(wt)) {
     vars <- tbl_vars(x)

README.md

@@ -27,6 +27,8 @@ You can install:
     devtools::install_github("hadley/dplyr")
     ```
 
+You'll probably also want to install the data packages used in most examples: `install.packages(c("hflights", "Lahman"))`.
+
 To get started, read the notes below, then read the intro vignette: `vignette("introduction", package = "dplyr")`. To make the most of dplyr, I also recommend that you familiarise yourself with the principles of [tidy data](http://vita.had.co.nz/papers/tidy-data.html): this will help you get your data into a form that works well with dplyr, ggplot2 and R's many modelling functions.
 
 If you encounter a clear bug, please file a minimal reproducible example on [github](https://github.com/hadley/dplyr/issues). For questions and other discussion, please use the [manipulatr mailing list](https://groups.google.com/group/manipulatr).

man/bench_compare.Rd

@@ -47,8 +47,8 @@ multiple sources.
 }
 \examples{
 \donttest{
-if (require("microbenchmark")) {
-lahman_local <- lahman_srcs("df", "dt", "cpp")
+if (require("microbenchmark") && has_lahman()) {
+lahman_local <- lahman_srcs("df", "dt")
 teams <- lapply(lahman_local, function(x) x \%>\% tbl("Teams"))
 
 compare_tbls(teams, function(x) x \%>\% filter(yearID == 2010))
@@ -57,7 +57,7 @@ bench_tbls(teams, function(x) x \%>\% filter(yearID == 2010))
 # You can also supply arbitrary additional arguments to bench_tbls
 # if there are other operations you'd like to compare.
 bench_tbls(teams, function(x) x \%>\% filter(yearID == 2010),
-   base = subset(Teams, yearID == 2010))
+   base = subset(Lahman::Teams, yearID == 2010))
 
 # A more complicated example using multiple tables
 setup <- function(src) {

man/chain.Rd

@@ -46,7 +46,7 @@ standardised and \code{\%.\%} is much more popular.
 }
 \examples{
 # If you're performing many operations you can either do step by step
-data("hflights", package = "hflights")
+if (require("hflights")) {
 a1 <- group_by(hflights, Year, Month, DayofMonth)
 a2 <- select(a1, Year:DayofMonth, ArrDelay, DepDelay)
 a3 <- summarise(a2,
@@ -82,4 +82,5 @@ hflights \%>\%
   ) \%>\%
   filter(arr > 30 | dep > 30)
 }
+}
 

man/do.Rd

@@ -76,9 +76,9 @@ models
 compare <- models \%>\% do(aov = anova(.$mod_linear, .$mod_quad))
 # compare \%>\% summarise(p.value = aov$`Pr(>F)`)
 
+if (require("hflights")) {
 # You can use it to do any arbitrary computation, like fitting a linear
 # model. Let's explore how carrier departure delays vary over the time
-data("hflights", package = "hflights")
 carriers <- group_by(hflights, UniqueCarrier)
 group_size(carriers)
 
@@ -93,4 +93,5 @@ library(mgcv)
 by_dest \%>\% do(smooth = gam(ArrDelay ~ s(DepTime) + Month, data = .))
 }
 }
+}
 

man/group_size.Rd

@@ -15,7 +15,7 @@ n_groups(x)
 Calculate group sizes.
 }
 \examples{
-data("hflights", package = "hflights")
+if (require("hflights")) {
 
 by_day <- hflights \%>\% group_by(Year, Month, DayofMonth)
 n_groups(by_day)
@@ -25,4 +25,5 @@ by_dest <- hflights \%>\% group_by(Dest)
 n_groups(by_dest)
 group_size(by_dest)
 }
+}
 

man/grouped_dt.Rd

@@ -21,8 +21,7 @@ method on a data table or tbl: this will take care of capturing
 the unevalated expressions for you.
 }
 \examples{
-if (require("data.table")) {
-data("hflights", package = "hflights")
+if (require("data.table") && require("hflights")) {
 hflights_dt <- tbl_dt(hflights)
 group_size(group_by(hflights_dt, Year, Month, DayofMonth))
 group_size(group_by(hflights_dt, Dest))

man/join.tbl_df.Rd

@@ -34,9 +34,7 @@ See \code{\link{join}} for a description of the general purpose of the
 functions.
 }
 \examples{
-data("Batting", package = "Lahman")
-data("Master", package = "Lahman")
-
+if (require("Lahman")) {
 batting_df <- tbl_df(Batting)
 person_df <- tbl_df(Master)
 
@@ -54,4 +52,5 @@ anti_join(batting_df, person_df)
 # or people who didn't bat
 anti_join(person_df, batting_df)
 }
+}
 

man/join.tbl_dt.Rd

@@ -39,10 +39,7 @@ See \code{\link{join}} for a description of the general purpose of the
 functions.
 }
 \examples{
-if (require("RSQLite") && require("RSQLite.extfuns")) {
-data("Batting", package = "Lahman")
-data("Master", package = "Lahman")
-
+if (require("data.table") && require("Lahman")) {
 batting_dt <- tbl_dt(Batting)
 person_dt <- tbl_dt(Master)