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]
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.
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
Pl = Pdist(datafile('count_1l.txt'), lambda _k, _N: 0)
+P2l = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
def Pwords(words):
"""The Naive Bayes log probability of a sequence of words.
"""
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 cosine_distance_score(text):