X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=language_models.py;h=8824bca4597327623798382288c2bcffb9d8005b;hb=881e6da407d16c42b13458764f7531e8ba578f23;hp=d45738657a356a38c5139838da665044fe9257e6;hpb=49dc272d2fc91e7340e56e9e7b96da6ab63514bb;p=cipher-tools.git

diff --git a/language_models.py b/language_models.py
index d457386..8824bca 100644
--- a/language_models.py
+++ b/language_models.py
@@ -5,6 +5,9 @@ import collections
 import unicodedata
 import itertools
 from math import log10
+import os 
+
+unaccent_specials = ''.maketrans({"’": "'", '“': '"', '”': '"'})
 
 def letters(text):
     """Remove all non-alphabetic characters from a text
@@ -31,7 +34,8 @@ def unaccent(text):
     >>> unaccent('HÉLLÖ')
     'HELLO'
     """
-    return unicodedata.normalize('NFKD', text).\
+    translated_text = text.translate(unaccent_specials)
+    return unicodedata.normalize('NFKD', translated_text).\
         encode('ascii', 'ignore').\
         decode('utf-8')
 
@@ -53,7 +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])]
@@ -67,7 +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]
 
 
@@ -88,6 +92,19 @@ def random_english_letter():
 	return weighted_choice(normalised_english_counts)
 
 
+def ngrams(text, n):
+    """Returns all n-grams of a text
+    
+    >>> ngrams(sanitise('the quick brown fox'), 2) # doctest: +NORMALIZE_WHITESPACE
+    ['th', 'he', 'eq', 'qu', 'ui', 'ic', 'ck', 'kb', 'br', 'ro', 'ow', 'wn', 
+     'nf', 'fo', 'ox']
+    >>> ngrams(sanitise('the quick brown fox'), 4) # doctest: +NORMALIZE_WHITESPACE
+    ['theq', 'hequ', 'equi', 'quic', 'uick', 'ickb', 'ckbr', 'kbro', 'brow', 
+     'rown', 'ownf', 'wnfo', 'nfox']
+    """
+    return [text[i:i+n] for i in range(len(text)-n+1)]
+
+
 class Pdist(dict):
     """A probability distribution estimated from counts in datafile.
     Values are stored and returned as log probabilities.
@@ -108,6 +125,7 @@ def log_probability_of_unknown_word(key, N):
 
 Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
 Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
+P2l = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
 
 def Pwords(words): 
     """The Naive Bayes log probability of a sequence of words.
@@ -119,6 +137,11 @@ def Pletters(letters):
     """
     return sum(Pl[l.lower()] for l in letters)
 
+def Pbigrams(letters):
+    """The Naive Bayes log probability of the bigrams formed from a sequence 
+    of letters.
+    """
+    return sum(P2l[p] for p in ngrams(letters, 2))
 
 
 def cosine_distance_score(text):