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 # The log 10 probabilities of letters
  69 Pl = {l: log10(n) for l, n in normalised_english_counts.items()}
  70
  71 with open('words.txt', 'r') as f:
  72     keywords = [line.rstrip() for line in f]
  73
  74 def Pletters(letters):
  75     """The Naive Bayes log probability of a sequence of letters.
  76     """
  77     return sum(Pl[l.lower()] for l in letters)
  78
  79
  80 def cosine_similarity_score(text):
  81     """Finds the dissimilarity of a text to English, using the cosine distance
  82     of the frequency distribution.
  83
  84     >>> cosine_similarity_score('abcabc') # doctest: +ELLIPSIS
  85     0.26228882...
  86     """
  87     return norms.cosine_similarity(english_counts,
  88                                    collections.Counter(sanitise(text)))
  89
  90
  91 if __name__ == "__main__":
  92     import doctest
  93     doctest.testmod()