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(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