def datafile(name, sep='\t'):
"""Read key,value pairs from file.
"""
def datafile(name, sep='\t'):
"""Read key,value pairs from file.
"""
english_trigram_counts = collections.Counter(dict(datafile('count_3l.txt')))
normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
english_trigram_counts = collections.Counter(dict(datafile('count_3l.txt')))
normalised_english_trigram_counts = norms.normalise(english_trigram_counts)
- """Generate random item from a dictionary of item counts
- """
- target = random.uniform(0, sum(d.values()))
- cuml = 0.0
- for (l, p) in d.items():
- cuml += p
- if cuml > target:
- return l
- return None
+ """Generate random item from a dictionary of item counts
+ """
+ target = random.uniform(0, sum(d.values()))
+ cuml = 0.0
+ for (l, p) in d.items():
+ cuml += p
+ if cuml > target:
+ return l
+ return None
- """Generate a random letter based on English letter counts
- """
- return weighted_choice(normalised_english_counts)
+ """Generate a random letter based on English letter counts
+ """
+ return weighted_choice(normalised_english_counts)
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
-Pl2 = Pdist(datafile('count_2l.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 cosine_distance_score(text):
"""Finds the dissimilarity of a text to English, using the cosine distance
of the frequency distribution.
>>> cosine_distance_score('abcabc') # doctest: +ELLIPSIS
def cosine_distance_score(text):
"""Finds the dissimilarity of a text to English, using the cosine distance
of the frequency distribution.
>>> cosine_distance_score('abcabc') # doctest: +ELLIPSIS
- return norms.cosine_distance(english_counts,
+ # return norms.cosine_distance(english_counts,
+ # collections.Counter(sanitise(text)))
+ return 1 - norms.cosine_similarity(english_counts,