Last active
July 26, 2025 20:50
-
-
Save bbolker/2046e47505cccb6c12a3077638797376 to your computer and use it in GitHub Desktop.
tabulate ending strings of chemical elements
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
## https://help.displayr.com/hc/en-us/articles/360003582875-How-to-Import-a-Wikipedia-Table-Using-R | |
library(rvest) | |
page = read_html("https://en.wikipedia.org/wiki/List_of_chemical_elements") | |
my.table = html_node(page, ".wikitable") |> | |
html_table(fill = TRUE) | |
nm_vec <- my.table[[3]][-1] | |
vowels <- c("a","e","i","o","u") | |
consonants <- setdiff(letters, vowels) | |
cc <- function(x) paste(x, collapse = "") | |
str <- sprintf("^.*[%s]([%s]+[%s]*)$", cc(consonants), cc(vowels), cc(consonants)) | |
endings <- gsub(str, "\\1", nm_vec, ignore.case = TRUE) | |
tt <- table(endings) | |
endings[endings %in% names(tt[tt==1])] <- "other" | |
ss <- sort(table(endings), decreasing = TRUE) | |
paste(sprintf('"%s"=%d', names(ss), ss), collapse = ";") |> cat(quote=FALSE) | |
## endings | |
## ium other on e en um er | |
## 79 13 9 7 4 4 2 | |
get_els <- function(s) { | |
nm_vec[which(substr(nm_vec, nchar(nm_vec)-(nchar(s)-1), nchar(nm_vec)) == s)] | |
} | |
get_els("er") | |
get_els("en") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment