X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=language_models.py;h=63aac6bab48daf56f1bcec1fd649121d1d86f17b;hb=34ba3d687eb48af30929b4550f14d1a599179efd;hp=52e7ac43db6f62376735808f030c9d6aaa3ba17f;hpb=317066e6551d143e38d093a55c4645dbd53c1c57;p=cipher-training.git

diff --git a/language_models.py b/language_models.py
index 52e7ac4..63aac6b 100644
--- a/language_models.py
+++ b/language_models.py
@@ -100,7 +100,7 @@ def ngrams(text, n):
     """
     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.
@@ -123,6 +123,7 @@ Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
 Pw_wrong = Pdist(datafile('count_1w.txt'), lambda _k, N: log10(1/N))
 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.
@@ -146,6 +147,12 @@ 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_similarity_score(text):
     """Finds the dissimilarity of a text to English, using the cosine distance