8f4bd9c34eb9f5c148da4da9be0215bab9dd45b1
[cipher-training.git] / language_models.py
1 """Language-specific functions, including models of languages based on data of
2 its use.
3 """
4
5 import string
6 import random
7 import norms
8 import collections
9 import unicodedata
10 import itertools
11 from math import log10
12
13 def letters(text):
14 """Remove all non-alphabetic characters from a text
15 >>> letters('The Quick')
16 'TheQuick'
17 >>> letters('The Quick BROWN fox jumped! over... the (9lazy) DOG')
18 'TheQuickBROWNfoxjumpedoverthelazyDOG'
19 """
20 return ''.join([c for c in text if c in string.ascii_letters])
21
22 def unaccent(text):
23 """Remove all accents from letters.
24 It does this by converting the unicode string to decomposed compatability
25 form, dropping all the combining accents, then re-encoding the bytes.
26
27 >>> unaccent('hello')
28 'hello'
29 >>> unaccent('HELLO')
30 'HELLO'
31 >>> unaccent('héllo')
32 'hello'
33 >>> unaccent('héllö')
34 'hello'
35 >>> unaccent('HÉLLÖ')
36 'HELLO'
37 """
38 return unicodedata.normalize('NFKD', text).\
39 encode('ascii', 'ignore').\
40 decode('utf-8')
41
42 def sanitise(text):
43 """Remove all non-alphabetic characters and convert the text to lowercase
44
45 >>> sanitise('The Quick')
46 'thequick'
47 >>> sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')
48 'thequickbrownfoxjumpedoverthelazydog'
49 >>> sanitise('HÉLLÖ')
50 'hello'
51 """
52 # sanitised = [c.lower() for c in text if c in string.ascii_letters]
53 # return ''.join(sanitised)
54 return letters(unaccent(text)).lower()
55
56
57 def datafile(name, sep='\t'):
58 """Read key,value pairs from file.
59 """
60 with open(name, 'r') as f:
61 for line in f:
62 splits = line.split(sep)
63 yield [splits[0], int(splits[1])]
64
65 english_counts = collections.Counter(dict(datafile('count_1l.txt')))
66 normalised_english_counts = norms.normalise(english_counts)
67
68 with open('words.txt', 'r') as f:
69 keywords = [line.rstrip() for line in f]
70
71
72 class Pdist(dict):
73 """A probability distribution estimated from counts in datafile.
74 Values are stored and returned as log probabilities.
75 """
76 def __init__(self, data=[], estimate_of_missing=None):
77 data1, data2 = itertools.tee(data)
78 self.total = sum([d[1] for d in data1])
79 for key, count in data2:
80 self[key] = log10(count / self.total)
81 self.estimate_of_missing = estimate_of_missing or (lambda k, N: 1./N)
82 def __missing__(self, key):
83 return self.estimate_of_missing(key, self.total)
84
85 def log_probability_of_unknown_word(key, N):
86 """Estimate the probability of an unknown word.
87 """
88 return -log10(N * 10**((len(key) - 2) * 1.4))
89
90 Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
91 Pw_wrong = Pdist(datafile('count_1w.txt'), lambda _k, N: log10(1/N))
92 Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
93 P2l = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
94 P3l = Pdist(datafile('count_3l.txt'), lambda _k, _N: 0)
95
96 def Pwords(words):
97 """The Naive Bayes log probability of a sequence of words.
98 """
99 return sum(Pw[w.lower()] for w in words)
100
101 def Pwords_wrong(words):
102 """The Naive Bayes log probability of a sequence of words.
103 """
104 return sum(Pw_wrong[w.lower()] for w in words)
105
106 def Pletters(letters):
107 """The Naive Bayes log probability of a sequence of letters.
108 """
109 return sum(Pl[l.lower()] for l in letters)
110
111
112 def cosine_similarity_score(text):
113 """Finds the dissimilarity of a text to English, using the cosine distance
114 of the frequency distribution.
115
116 >>> cosine_similarity_score('abcabc') # doctest: +ELLIPSIS
117 0.26228882...
118 """
119 return norms.cosine_similarity(english_counts,
120 collections.Counter(sanitise(text)))
121
122
123 if __name__ == "__main__":
124 import doctest
125 doctest.testmod()