Merge pull request #218 from r-transit/dev/reduce_package_size

Reduce package file size
r-transit · Oct 18, 2024 · af395fb · af395fb
2 parents daf446f + cbb693a
commit af395fb
Show file tree

Hide file tree

Showing 29 changed files with 55 additions and 54 deletions.
diff --git a/NEWS.md b/NEWS.md
@@ -3,6 +3,7 @@
 - `read_gtfs()` can now read `locations.geojson` files according to the updated specifications [#214](https://github.com/r-transit/tidytransit/pull/214)
 - tidytransit 1.7.0 needs `gtfsio` 1.2.0 as it uses json reading capabilities from `gtfsio::import_gtfs()`
 - Internally, the automatically parsed specifications from https://gtfs.org/documentation/schedule/reference/ are now used
+- The example feed `google_transit_nyc_subway.zip` has been modified and renamed to `nyc_subway.zip` [#218](https://github.com/r-transit/tidytransit/pull/218)
 
 
 # tidytransit 1.6.1

diff --git a/R/filters.R b/R/filters.R
@@ -8,7 +8,7 @@
 #' @export
 #' @examples \donttest{
 #' library(dplyr)
-#' local_gtfs_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' local_gtfs_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' nyc <- read_gtfs(local_gtfs_path)
 #' select_service_id <- filter(nyc$calendar, monday==1) %>% pull(service_id)
 #' select_route_id <- sample_n(nyc$routes, 1) %>% pull(route_id)

diff --git a/R/geo.R b/R/geo.R
@@ -13,7 +13,7 @@
 #' \dontrun{
 #' library(dplyr)
 #' 
-#' nyc_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' nyc_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' nyc <- read_gtfs(nyc_path)
 #' 
 #' nyc$stops %>%
@@ -103,7 +103,7 @@ prep_dist_mtrx = function(dist_list) {
 #' \dontrun{
 #' library(dplyr)
 #' 
-#' nyc_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' nyc_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' nyc <- read_gtfs(nyc_path)
 #' 
 #' stop_group_distances(nyc$stops)
@@ -185,7 +185,7 @@ stop_group_distances = function(gtfs_stops, by = "stop_name") {
 #' @importFrom stats kmeans
 #' @examples \donttest{
 #' library(dplyr)
-#' nyc_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' nyc_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' nyc <- read_gtfs(nyc_path)
 #' nyc <- cluster_stops(nyc)
 #' 

diff --git a/R/io.R b/R/io.R
@@ -17,7 +17,7 @@
 #' @seealso [validate_gtfs()], [write_gtfs()]
 #'
 #' @examples \dontrun{
-#' local_gtfs_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' local_gtfs_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' gtfs <- read_gtfs(local_gtfs_path)
 #' summary(gtfs)
 #'

diff --git a/R/plot.R b/R/plot.R
@@ -6,7 +6,7 @@
 #'
 #' @examples \donttest{
 #' local_gtfs_path <- system.file("extdata",
-#'                               "google_transit_nyc_subway.zip",
+#'                               "nyc_subway.zip",
 #'                               package = "tidytransit")
 #' nyc <- read_gtfs(local_gtfs_path)
 #' plot(nyc)

diff --git a/R/raptor.R b/R/raptor.R
@@ -50,7 +50,7 @@
 #' @import data.table
 #' @export
 #' @examples \donttest{
-#' nyc_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' nyc_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' nyc <- read_gtfs(nyc_path)
 #'
 #' # you can use initial walk times to different stops in walking distance (arbitrary example values)

diff --git a/R/summary.R b/R/summary.R
@@ -10,7 +10,7 @@
 #'
 #' @examples  \dontrun{
 #' path = system.file("extdata", 
-#'            "google_transit_nyc_subway.zip", 
+#'            "nyc_subway.zip", 
 #'            package = "tidytransit")
 #'
 #' g = read_gtfs(path)

diff --git a/R/travel_times.R b/R/travel_times.R
@@ -69,7 +69,7 @@
 #'
 #' # 2) separate filtering and travel time calculation for a more granular analysis
 #' # stop_names in this feed are not restricted to an area, create clusters of stops to fix
-#' nyc_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' nyc_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' nyc <- read_gtfs(nyc_path)
 #' nyc <- cluster_stops(nyc, group_col = "stop_name", cluster_colname = "stop_name")
 #' 

diff --git a/R/validate_gtfs.R b/R/validate_gtfs.R
@@ -60,7 +60,7 @@
 #' #> # 2 more variables: validation_status <chr>, validation_details <chr>
 #' 
 #' \dontrun{
-#' local_gtfs_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+#' local_gtfs_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 #' gtfs <- read_gtfs(local_gtfs_path)
 #' attr(gtfs, "validation_result")
 #'

diff --git a/inst/extdata/google_transit_nyc_subway.zip b/inst/extdata/google_transit_nyc_subway.zip
diff --git a/inst/extdata/nyc_subway.zip b/inst/extdata/nyc_subway.zip
diff --git a/man/cluster_stops.Rd b/man/cluster_stops.Rd
diff --git a/man/filter_stops.Rd b/man/filter_stops.Rd
diff --git a/man/plot.tidygtfs.Rd b/man/plot.tidygtfs.Rd
diff --git a/man/print.tidygtfs.Rd b/man/print.tidygtfs.Rd
diff --git a/man/raptor.Rd b/man/raptor.Rd
diff --git a/man/read_gtfs.Rd b/man/read_gtfs.Rd
diff --git a/man/stop_distances.Rd b/man/stop_distances.Rd
diff --git a/man/stop_group_distances.Rd b/man/stop_group_distances.Rd
diff --git a/man/travel_times.Rd b/man/travel_times.Rd
diff --git a/man/validate_gtfs.Rd b/man/validate_gtfs.Rd
diff --git a/tests/testthat/test-read-gtfs.R b/tests/testthat/test-read-gtfs.R
@@ -14,7 +14,7 @@ test_that("read_gtfs() imports a local file to a list of
 
 test_that("reading a real feed", {
   skip_on_cran()
-  g_nyc_path = system.file("extdata", "google_transit_nyc_subway.zip", 
+  g_nyc_path = system.file("extdata", "nyc_subway.zip", 
                            package = "tidytransit")
   gtfs_obj = read_gtfs(g_nyc_path)
 

diff --git a/tests/testthat/test-spatial.R b/tests/testthat/test-spatial.R
@@ -149,7 +149,7 @@ test_that("stop_group_distances", {
 
 test_that("stop_group_distances real feed", {
   skip_on_cran()
-  g_nyc = read_gtfs(system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit"))
+  g_nyc = read_gtfs(system.file("extdata", "nyc_subway.zip", package = "tidytransit"))
 
   x1 = stop_group_distances(g_nyc$stops)
 
@@ -170,7 +170,7 @@ test_that("stop_group_distances real feed", {
 test_that("stops cluster", {
   skip_on_cran()
 
-  g_nyc = read_gtfs(system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit"))
+  g_nyc = read_gtfs(system.file("extdata", "nyc_subway.zip", package = "tidytransit"))
   g_nyc2 <- filter_feed_by_area(g_nyc, c(-74.0144, 40.7402, -73.9581, 40.7696))
 
   x1 = cluster_stops(g_nyc2$stops)

diff --git a/tests/testthat/test-travel_times.R b/tests/testthat/test-travel_times.R
@@ -158,7 +158,7 @@ test_that("feed without transfers", {
 
 test_that("nyc feed", {
   skip_on_cran()
-  nyc_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+  nyc_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
   nyc <- read_gtfs(nyc_path)
 
   .child_index = which(nyc$stops$location_type == 0)

diff --git a/tests/testthat/test-utils.R b/tests/testthat/test-utils.R
@@ -80,7 +80,7 @@ test_that("filter_feed with shapes", {
 
 test_that("filter_feed_by_date", {
   skip_on_cran()
-  g0 = read_gtfs(system.file("extdata", "google_transit_nyc_subway.zip",
+  g0 = read_gtfs(system.file("extdata", "nyc_subway.zip",
                              package = "tidytransit"))
   g1 = filter_feed_by_date(g0, "2018-06-28")
   g2 = filter_feed_by_date(g0, "2018-10-30")

diff --git a/vignettes/frequency.Rmd b/vignettes/frequency.Rmd
@@ -24,7 +24,7 @@ options(dplyr.summarise.inform=F)
 ## Introduction
 
 The focus of this vignette is on how to use R to make graphics about where and how often 
-transit service operates based on schedule data published in the [General Transit Feed Specification](https://gtfs.org/). 
+transit services operate based on schedule data published in the [General Transit Feed Specification](https://gtfs.org/). 
 We'll focus on the New York City Metropolitan Transit Agency's Subway schedule for this 
 vignette, but you can easily apply it to thousands of other GTFS data sources. See the 
 [tidytransit introductory vignette](https://r-transit.github.io/tidytransit/articles/introduction.html#finding-more-gtfs-feeds) 
@@ -50,12 +50,13 @@ We'll start by importing a snapshot of the NYC MTA's subway schedule, which is i
 with the package when [installed](https://r-transit.github.io/tidytransit/index.html#installation).  
 
 ```{r}
-local_gtfs_path <- system.file("extdata", "google_transit_nyc_subway.zip", package = "tidytransit")
+local_gtfs_path <- system.file("extdata", "nyc_subway.zip", package = "tidytransit")
 gtfs <- read_gtfs(local_gtfs_path)
 ```
 
 But note that you can also just uncomment the line below and import the data from the NYC 
-MTA's URL directly. 
+MTA's URL directly. Note that some routes and services have been removed from the exmaple feed 
+to reduce package size.
 
 ```{r}
 # gtfs <- read_gtfs("http://web.mta.info/developers/data/nyct/subway/google_transit.zip")
@@ -65,10 +66,10 @@ MTA's URL directly.
 
 GTFS feeds typically contain a schedule of all the schedules of service for a given system. 
 Selecting a schedule of service in NYC allows us to focus on, for example, non-holiday 
-weekday service, in the Fall of 2019. In some feeds, service selection can be more or less 
+weekday service, in the Fall of 2018. In some feeds, service selection can be more or less 
 complicated than NYC. In any case, you'll want to read the [service patterns](https://r-transit.github.io/tidytransit/articles/servicepatterns.html) 
 vignette included in this package in order to see how you can select the right service for 
-your needs. 
+your needs.
 
 We use one of the functions described in that vignette to create a table on the gtfs feed 
 that lets us filter by weekday/weekend service. 
@@ -171,7 +172,7 @@ system on weekdays.
 
 ```{r}
 am_stop_freq <- get_stop_frequency(gtfs, start_time = 6*3600, end_time = 10*3600, 
-                              service_ids = service_ids, by_route = TRUE)
+                                   service_ids = service_ids, by_route = TRUE)
 ```
 
 ```{r}
@@ -196,7 +197,7 @@ stop_name.
 
 ```{r}
 one_line_stops <- am_stop_freq %>% 
-    filter(route_id == 1 & direction_id == 0) %>%
+    filter(route_id == "1" & direction_id == 0) %>%
     left_join(gtfs$stops, by ="stop_id") %>% 
     mutate(mean_headway_minutes = mean_headway/60)
 ```
@@ -295,7 +296,7 @@ routes_sf <- routes_sf %>%
 
 And finally, lets plot the routes with median headways of less than 10 minutes in the morning.
 
-```{r, fig.width=6, fig.height=10, warn=FALSE}
+```{r, fig.width=6, fig.height=8, warn=FALSE}
 # convert to an appropriate coordinate reference system
 routes_sf_crs <- sf::st_transform(routes_sf, 26919) 
 routes_sf_crs %>% 
@@ -337,7 +338,7 @@ routes_sf_buffer <- st_buffer(routes_sf,
 Next, when we render the map, we'll make sure to make the borders around each route 
 transparent, and set the opacity for the fill of all the polygons high again. 
 
-```{r, fig.width=6, fig.height=10}
+```{r, fig.width=6, fig.height=7}
 routes_sf_buffer %>% 
   ggplot() + 
   geom_sf(colour = alpha("white", 0), fill = alpha("red",0.2)) +
@@ -378,7 +379,7 @@ am_stop_name_departures <- am_stop_name_departures %>%
 
 Finally, we can plot both the route line counts and the stop departure counts on one map:
 
-```{r, fig.width=6, fig.height=10}
+```{r, fig.width=6, fig.height=7}
 ggplot() + 
   geom_sf(data = routes_sf_buffer, 
           colour = alpha("white",0), fill = alpha("red",0.3)) +

diff --git a/vignettes/introduction.Rmd b/vignettes/introduction.Rmd
@@ -62,9 +62,9 @@ a list of the tables in each feed.
 Below we use the tidytransit `read_gtfs` function in order to read a feed from the NYC MTA 
 into R.
 
-We use a feed included in the package in the example below. But note that you can read 
+We use an example feed included in the package in the example below. But note that you can read 
 directly from the New York City Metropolitan Transit Authority, as shown in the commented 
-code below. 
+code below.
 
 You can also read from any other URL. This is useful because there are many sources for 
 GTFS data, and often the best source is transit service providers themselves. See the next 
@@ -74,7 +74,7 @@ section on "Finding More GTFS Feeds" for more sources of feeds.
 # nyc <- read_gtfs("http://web.mta.info/developers/data/nyct/subway/google_transit.zip")
 
 local_gtfs_path <- system.file("extdata", 
-                               "google_transit_nyc_subway.zip", 
+                               "nyc_subway.zip", 
                                package = "tidytransit")
 nyc <- read_gtfs(local_gtfs_path)
 ```
@@ -187,14 +187,13 @@ MobilityData_sf = MobilityData_feedlist %>%
   ungroup() %>% st_as_sf()
 ```
 
-Now show the feeds on a map:
+These boxes could now be shown on an interactive map.
 
-```{r, fig.width=7}
+```{r, fig.width=7, eval=FALSE}
 library(leaflet)
 leaflet() %>% 
   addProviderTiles(provider = providers$CartoDB.Positron) %>% 
   addPolygons(data = MobilityData_sf, weight = 2, 
               fillOpacity = 0.1, label = substr(MobilityData_sf$provider, 0, 60))
 
 ```
-