import unicodedata
import itertools
from math import log10
+import os
+
+unaccent_specials = ''.maketrans({"’": "'", '“': '"', '”': '"'})
def letters(text):
"""Remove all non-alphabetic characters from a text
>>> unaccent('HÉLLÖ')
'HELLO'
"""
- return unicodedata.normalize('NFKD', text).\
+ translated_text = text.translate(unaccent_specials)
+ return unicodedata.normalize('NFKD', translated_text).\
encode('ascii', 'ignore').\
decode('utf-8')
def datafile(name, sep='\t'):
"""Read key,value pairs from file.
"""
- with open(name, 'r') as f:
+ with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), name), 'r') as f:
for line in f:
splits = line.split(sep)
yield [splits[0], int(splits[1])]
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:
+with open(os.path.join(os.path.dirname(os.path.realpath(__file__)), 'words.txt'), 'r') as f:
keywords = [line.rstrip() for line in f]
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 Pwords(words):
"""The Naive Bayes log probability of a sequence of words.
"""
return sum(P2l[p] for p in ngrams(letters, 2))
+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_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
- 0.370847405...
+ 0.73777...
"""
- return norms.cosine_distance(english_counts,
+ # return norms.cosine_distance(english_counts,
+ # collections.Counter(sanitise(text)))
+ return 1 - norms.cosine_similarity(english_counts,
collections.Counter(sanitise(text)))