X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=language_models.py;h=da5d2d07fa2003a3bf95a4a6629c1eafd666382b;hb=d0a53e974970bc915d94280b5158b50f93054dc3;hp=8824bca4597327623798382288c2bcffb9d8005b;hpb=5184c96f06f9f97d6af9b3d994e9b227cbb8b76c;p=cipher-tools.git

diff --git a/language_models.py b/language_models.py
index 8824bca..da5d2d0 100644
--- a/language_models.py
+++ b/language_models.py
@@ -76,20 +76,20 @@ with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), 'words.txt')
 
 
 def weighted_choice(d):
-	"""Generate random item from a dictionary of item counts
-	"""
-	target = random.uniform(0, sum(d.values()))
-	cuml = 0.0
-	for (l, p) in d.items():
-		cuml += p
-		if cuml > target:
-			return l
-	return None
+    """Generate random item from a dictionary of item counts
+    """
+    target = random.uniform(0, sum(d.values()))
+    cuml = 0.0
+    for (l, p) in d.items():
+        cuml += p
+        if cuml > target:
+            return l
+    return None
 
 def random_english_letter():
-	"""Generate a random letter based on English letter counts
-	"""
-	return weighted_choice(normalised_english_counts)
+    """Generate a random letter based on English letter counts
+    """
+    return weighted_choice(normalised_english_counts)
 
 
 def ngrams(text, n):
@@ -126,6 +126,7 @@ 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)
+P3l = Pdist(datafile('count_3l.txt'), lambda _k, _N: 0)
 
 def Pwords(words): 
     """The Naive Bayes log probability of a sequence of words.
@@ -143,15 +144,23 @@ def Pbigrams(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_distance_score(text):
     """Finds the dissimilarity of a text to English, using the cosine distance
     of the frequency distribution.
 
     >>> cosine_distance_score('abcabc') # doctest: +ELLIPSIS
-    0.370847405...
+    0.73777...
     """
-    return norms.cosine_distance(english_counts, 
+    # return norms.cosine_distance(english_counts, 
+    #     collections.Counter(sanitise(text)))
+    return 1 - norms.cosine_similarity(english_counts, 
         collections.Counter(sanitise(text)))