Bits of tinkering

[cipher-training.git] / language_models.py

diff --git a/language_models.py b/language_models.py
index ceb4596eb2fd87d3d2375f338892f9652525f2d4..63aac6bab48daf56f1bcec1fd649121d1d86f17b 100644 (file)
--- 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.
@@ -120,14 +120,22 @@ def log_probability_of_unknown_word(key, N):
     return -log10(N * 10**((len(key) - 2) * 1.4))
 
 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.
     """
     return sum(Pw[w.lower()] for w in words)
 
+def Pwords_wrong(words): 
+    """The Naive Bayes log probability of a sequence of words.
+    """
+    return sum(Pw_wrong[w.lower()] for w in words)
+
+
 def Pletters(letters):
     """The Naive Bayes log probability of a sequence of letters.
     """
@@ -139,6 +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