Bifid ciphers from development branch

[cipher-training.git] / language_models.py

diff --git a/language_models.py b/language_models.py
index 02d48bd89a3cf820ebb7f62212eb8c6fa18d1ca4..bf00875c43e134fd2b46327e80c56c8468c60e58 100644 (file)
--- a/language_models.py
+++ b/language_models.py
@@ -9,6 +9,9 @@ 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
@@ -35,7 +38,8 @@ 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')
 
@@ -57,7 +61,7 @@ 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])]
@@ -65,7 +69,13 @@ def datafile(name, sep='\t'):
 english_counts = collections.Counter(dict(datafile('count_1l.txt')))
 normalised_english_counts = norms.normalise(english_counts)
 
-with open('words.txt', 'r') as f:
+english_bigram_counts = collections.Counter(dict(datafile('count_2l.txt')))
+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(os.path.join(os.path.dirname(os.path.realpath(__file__)), 'words.txt'), 'r') as f:
     keywords = [line.rstrip() for line in f]
 
 
@@ -86,6 +96,19 @@ 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.
@@ -125,6 +148,18 @@ 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 Ptrigrams(letters):
+    """The Naive Bayes log probability of the trigrams formed from a sequence
+    of letters.
+    """
+    return sum(P3l[p] for p in ngrams(letters, 3))
+
 
 def cosine_similarity_score(text):
     """Finds the dissimilarity of a text to English, using the cosine distance