Add 2018-2020 data + Update depreciated code

.gitignore

@@ -4,3 +4,6 @@ docs/
 .RData
 *.xls
 docs
+
+## get rid of check log
+..Rcheck/

DESCRIPTION

@@ -1,13 +1,20 @@
 Package: babynames
-Title: US Baby Names 1880-2017
-Version: 1.0.1
+Title: US Baby Names 1880-2020
+Version: 1.1.1
 Authors@R: 
     c(person(given = "Hadley",
              family = "Wickham",
              role = c("aut", "cre"),
              email = "hadley@rstudio.com"),
       person(given = "RStudio",
-             role = "cph"))
+             role = "cph"),
+      person(
+        given = "Francis", 
+        middle = "Robert",
+        family = "Kovacs",
+        role = c("ctb"),
+        email = "frankkovacs8@gmail.com"
+      ))
 Description: US baby names provided by the SSA. This package contains all
     names used for at least 5 children of either sex.
 License: CC0
@@ -22,5 +29,5 @@ Suggests:
 Encoding: UTF-8
 LazyData: true
 LazyDataCompression: xz
-RoxygenNote: 7.1.1
+RoxygenNote: 7.1.2
 Config/testthat/edition: 3

NEWS.md

@@ -1,3 +1,9 @@
+# babynames 1.1.1
+
+* Updated data up to and including 2020
+* Removed depreciated code in `data-raw` scripts
+* Minor updates to old data caused by re-running `data-raw` scripts
+
 # babynames 1.0.1
 
 * Fix for R CMD check change

R/data.R

@@ -51,5 +51,5 @@ NULL
 #' @format A data frame:
 #' \describe{
 #' \item{year}{Year}
-#' \item{births}{Number of live births, rounded to nearest 1000}}
+#' \item{births}{Number of live births, rounded to nearest 1000 for all years prior to 1959}}
 "births"

README.md

@@ -5,7 +5,7 @@
 
 This package contains three datasets provided by the USA social security administration:
 
-* `babynames`: For each year from 1880 to 2017, the number of children of 
+* `babynames`: For each year from 1880 to 2020, 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)
 
@@ -18,9 +18,12 @@ 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, up to 2017.
+* `births`: Number of live births by year, up to 2020.
   (Source: an Excel spreadsheet from the Census that has since been removed
-  from their website and https://www.cdc.gov/nchs/data/nvsr/nvsr66/nvsr66_01.pdf)
+  from their website and https://www.cdc.gov/nchs/data/nvsr/nvsr66/nvsr66_01.pdf. 
+  Data for 2017-2020 obtained from https://www.cdc.gov/nchs/data/nvsr/nvsr68/nvsr68_13-508.pdf, 
+  https://www.cdc.gov/nchs/data/nvsr/nvsr70/nvsr70-02-508.pdf and
+  https://www.cdc.gov/nchs/data/nvsr/nvsr70/nvsr70-17.pdf.)
 
 ## Installation
 

data-raw/applicants.R

@@ -8,12 +8,13 @@ library(usethis)
 
 page <- read_html("https://www.ssa.gov/oact/babynames/numberUSbirths.html")
 
-ssa <- page %>% html_nodes("table") %>% .[[2]] %>% html_table() %>% tbl_df()
+
+ssa <- page %>% html_nodes("table") %>% .[[1]] %>% html_table() %>% tibble::as_tibble()
 names(ssa) <- c("year", "M", "F", "total")
 ssa$total <- NULL
 
-ssa$M <- parse_number(ssa$M)
-ssa$F <- parse_number(ssa$F)
+ssa$M <- readr::parse_number(ssa$M)
+ssa$F <- readr::parse_number(ssa$F)
 
 applicants <- ssa %>%
   gather(sex, n_all, M:F) %>%