Last active
January 6, 2017 20:55
-
-
Save jtilly/ac00ef85e0d5766a63c31637d4ac79ea to your computer and use it in GitHub Desktop.
This file contains 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
rm(list = ls()) | |
dict.orig = unique(readLines("https://raw.githubusercontent.com/first20hours/google-10000-english/master/google-10000-english.txt")) | |
txt2numeric = function(word.orig, return.orig = TRUE) { | |
word = tolower(word.orig) | |
word = gsub("([^a-z]){1}", 1, word) | |
word = gsub("(a|b|c){1}", 2, word) | |
word = gsub("(d|e|f){1}", 3, word) | |
word = gsub("(g|h|i){1}", 4, word) | |
word = gsub("(j|k|l){1}", 5, word) | |
word = gsub("(m|n|o){1}", 6, word) | |
word = gsub("(p|q|r|s){1}", 7, word) | |
word = gsub("(t|u|v){1}", 8, word) | |
word = gsub("(w|x|y|z){1}", 9, word) | |
if(return.orig) { | |
return(c(word, word.orig)) | |
} else { | |
return(word) | |
} | |
} | |
dict.numeric = matrix(unlist(lapply(X = as.list(dict.orig), FUN = txt2numeric)), ncol = 2, byrow = TRUE) | |
text.numeric = txt2numeric(unlist(strsplit(x = "Hello, how is it going? Does this actually work or what?", | |
split = "([\\ ,;\\?]{1})", | |
perl = TRUE)), return.orig = FALSE) | |
text.numeric = text.numeric[text.numeric != ""] | |
result = lapply(X = as.list(text.numeric), FUN = function(x) dict.numeric[dict.numeric[, 1] == x, 2]) | |
print(result) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment