Last active
August 29, 2015 14:05
-
-
Save dschuetz/5b210336be091486124e to your computer and use it in GitHub Desktop.
Simple scoring routine for ascii text. Uses Moby Dick as a source for ascii frequencies (only chars 32-127).
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
ASCII_FREQS = [ | |
162.7, 1.5, 2.6, 0.0, 0.0, 0.0, 0.0, 2.4, | |
0.2, 0.2, 0.1, 0.0, 16.0, 5.0, 6.5, 0.0, | |
0.1, 0.2, 0.1, 0.0, 0.0, 0.1, 0.0, 0.1, | |
0.1, 0.0, 0.2, 3.4, 0.0, 0.0, 0.0, 0.8, | |
0.0, 2.2, 1.2, 1.0, 0.7, 1.1, 0.7, 0.6, | |
1.2, 3.0, 0.2, 0.2, 0.8, 0.6, 1.0, 0.9, | |
1.0, 0.3, 0.7, 1.9, 2.1, 0.2, 0.1, 1.1, | |
0.0, 0.3, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, | |
0.0, 62.8, 12.9, 18.1, 31.3, 97.0, 16.8, 16.9, | |
51.1, 51.9, 0.8, 6.6, 34.9, 18.9, 53.9, 57.4, | |
13.6, 1.0, 43.2, 51.7, 71.7, 22.2, 7.0, 17.5, | |
0.9, 13.9, 0.5, 0.0, 0.0, 0.0, 0.0 | |
] | |
def score(s): | |
score = 0 | |
for ch in s: | |
if ord(ch) > 31 and ord(ch) < 127: | |
score += ASCII_FREQS[ord(ch)-32]/100 | |
return score |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment