Added transposition cipher slides

[cipher-training.git] / language_models.py

diff --git a/language_models.py b/language_models.py
index 929746888d036fb54de3f1fbf228e296e0bcd027..52e7ac43db6f62376735808f030c9d6aaa3ba17f 100644 (file)
--- a/language_models.py
+++ b/language_models.py
@@ -120,6 +120,7 @@ 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)
 
@@ -128,6 +129,12 @@ def Pwords(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.
     """
@@ -140,14 +147,14 @@ def Pbigrams(letters):
     return sum(P2l[p] for p in ngrams(letters, 2))
 
 
-def cosine_distance_score(text):
+def cosine_similarity_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...
+    >>> cosine_similarity_score('abcabc') # doctest: +ELLIPSIS
+    0.26228882...
     """
-    return norms.cosine_distance(english_counts, 
+    return norms.cosine_similarity(english_counts, 
         collections.Counter(sanitise(text)))