Merge branch 'master' of github.com:hadley/babynames

R/data.R

@@ -8,7 +8,8 @@ NULL
 #'
 #' @format A data frame with five variables: \code{year}, \code{sex},
 #'   \code{name}, \code{n} and \code{prop} (\code{n} divided by total number
-#'   of applicants in that year).
+#'   of applicants in that year, which means proportions are of people of
+#'   that gender with that name born in that year).
 "babynames"
 
 #' Applicants.

README.md

@@ -4,7 +4,7 @@
 
 This package contains three datasets provided by the USA social security administration:
 
-* `babynames`: For each year from 1880 to 2013, the number of children of 
+* `babynames`: For each year from 1880 to 2015, the number of children of 
   each sex given each name. All names with more than 5 uses are given.
   (Source: http://www.ssa.gov/oact/babynames/limits.html)
 
@@ -17,7 +17,7 @@ This package contains three datasets provided by the USA social security adminis
 
 It also includes the following data set from the US Census:
 
-* `births`: Number of live births by year.
+* `births`: Number of live births by year, up to 2014.
   (Source: http://www.census.gov/statab/hist/02HS0013.xls and
   http://www.cdc.gov/nchs/data/nvsr/nvsr62/nvsr62_09.pdf)
 

data-raw/applicants.R

@@ -16,7 +16,8 @@ ssa$F <- parse_number(ssa$F)
 
 applicants <- ssa %>%
   gather(sex, n_all, M:F) %>%
-  arrange(year, sex)
+  arrange(year, sex) %>%
+  mutate(n_all = as.integer(n_all))
 
 write_csv(applicants, "data-raw/applicants.csv")
 devtools::use_data(applicants, overwrite = TRUE)