english_counts = collections.Counter(dict(datafile('count_1l.txt')))
normalised_english_counts = norms.normalise(english_counts)
-english_bigram_counts = collections.Counter(dict(datafile('count_2l.txt')))
-normalised_english_bigram_counts = norms.normalise(english_bigram_counts)
-
-english_trigram_counts = collections.Counter(dict(datafile('count_3l.txt')))
-normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
-
with open('words.txt', 'r') as f:
keywords = [line.rstrip() for line in f]
return weighted_choice(normalised_english_counts)
-def ngrams(text, n):
- """Returns all n-grams of a text
-
- >>> ngrams(sanitise('the quick brown fox'), 2) # doctest: +NORMALIZE_WHITESPACE
- ['th', 'he', 'eq', 'qu', 'ui', 'ic', 'ck', 'kb', 'br', 'ro', 'ow', 'wn',
- 'nf', 'fo', 'ox']
- >>> ngrams(sanitise('the quick brown fox'), 4) # doctest: +NORMALIZE_WHITESPACE
- ['theq', 'hequ', 'equi', 'quic', 'uick', 'ickb', 'ckbr', 'kbro', 'brow',
- 'rown', 'ownf', 'wnfo', 'nfox']
- """
- 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.
P2l = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
P3l = Pdist(datafile('count_3l.txt'), lambda _k, _N: 0)
-def Pwords(words):
+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):
+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.
"""
return sum(Pl[l.lower()] for l in letters)
-def Pbigrams(letters):
- """The Naive Bayes log probability of the bigrams formed from a sequence
- of 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
>>> cosine_similarity_score('abcabc') # doctest: +ELLIPSIS
0.26228882...
"""
- return norms.cosine_similarity(english_counts,
- collections.Counter(sanitise(text)))
+ return norms.cosine_similarity(english_counts,
+ collections.Counter(sanitise(text)))
if __name__ == "__main__":