Last active
December 14, 2015 01:38
-
-
Save ykarikos/5007399 to your computer and use it in GitHub Desktop.
Select random letters according to the distribution of letters in Finnish language
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
#!/usr/bin/python | |
# Select random letters according to the distribution of letters in Finnish language: | |
# https://docs.google.com/spreadsheet/ccc?key=0AiZHeDrg3BuddFZfTXVnclQ5UWNkaGVuWmdVT3dzMEE&usp=sharing | |
# Ignore the uncommon letters c, z, w, q, x and ao | |
import random | |
from itertools import repeat | |
from collections import Counter | |
random.seed() | |
alphabet = ((0.11607, "I"), (0.23011, "A"), (0.31651, "T"), (0.39098, "S"), (0.45836, "E"), | |
(0.52488, "U"), (0.59058, "K"), (0.65494, "N"), (0.71334, "L"), (0.76748, "O"), (0.80699, "R"), | |
(0.83889, "AE"), (0.86920, "P"), (0.89892, "M"), (0.92313, "V"), (0.94481, "H"), (0.96644, "Y"), | |
(0.97941, "J"), (0.98683, "D"), (0.99417, "OE"), (0.99682, "G"), (0.99847, "F"), (1.00000, "B")) | |
def find(list, f): | |
head, tail = list[0], list[1:] | |
if (f(head)): | |
return head | |
else: | |
return find(tail, f) | |
def getLetter(alphabet): | |
r = random.random() | |
return find(alphabet, lambda x: x[0] > r)[1] | |
letters = Counter([getLetter(alphabet) for i in range(1000000)]).most_common() | |
for a,b in letters: | |
print(a, b/10000.0) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment