X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=language_models.py;fp=language_models.py;h=5a35b38ec32867dbe00f6fe6e99ada066e858c8e;hb=a9d938167b636e599586ebbc5aeec75c877e120f;hp=19f886fcefcb4384184e0bbad108e6925f029bbf;hpb=923bda393a49b74f09c381746597fa4532c17f67;p=cipher-tools.git diff --git a/language_models.py b/language_models.py index 19f886f..5a35b38 100644 --- a/language_models.py +++ b/language_models.py @@ -5,6 +5,7 @@ import collections import unicodedata import itertools from math import log10 +import os unaccent_specials = ''.maketrans({"’": "'"}) @@ -56,7 +57,7 @@ def sanitise(text): def datafile(name, sep='\t'): """Read key,value pairs from file. """ - with open(name, 'r') as f: + with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), name), 'r') as f: for line in f: splits = line.split(sep) yield [splits[0], int(splits[1])] @@ -70,7 +71,7 @@ normalised_english_bigram_counts = norms.normalise(english_bigram_counts) english_trigram_counts = collections.Counter(dict(datafile('count_3l.txt'))) normalised_english_trigram_counts = norms.normalise(english_trigram_counts) -with open('words.txt', 'r') as f: +with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), 'words.txt'), 'r') as f: keywords = [line.rstrip() for line in f]