+"""Language-specific functions, including models of languages based on data of
+its use.
+"""
+
import string
-import norms
import random
+import norms
import collections
import unicodedata
import itertools
return ''.join([c for c in text if c in string.ascii_letters])
def unaccent(text):
- """Remove all accents from letters.
+ """Remove all accents from letters.
It does this by converting the unicode string to decomposed compatability
form, dropping all the combining accents, then re-encoding the bytes.
def sanitise(text):
"""Remove all non-alphabetic characters and convert the text to lowercase
-
+
>>> sanitise('The Quick')
'thequick'
>>> sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')
def weighted_choice(d):
- """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
def random_english_letter():
- """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)
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',
+ ['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',
+ ['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)]
P2l = Pdist(datafile('count_2l.txt'), lambda _k, _N: 0)
P3l = Pdist(datafile('count_3l.txt'), lambda _k, _N: 0)
-def Pwords(words):
+def Pwords(words):
"""The Naive Bayes log probability of a sequence of words.
"""
return sum(Pw[w.lower()] for w in words)
-def Pwords_wrong(words):
+def Pwords_wrong(words):
"""The Naive Bayes log probability of a sequence of words.
"""
return sum(Pw_wrong[w.lower()] for w in words)
-
def Pletters(letters):
"""The Naive Bayes log probability of a sequence of letters.
"""
return sum(Pl[l.lower()] for l in letters)
def Pbigrams(letters):
- """The Naive Bayes log probability of the bigrams formed from a sequence
+ """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
+ """The Naive Bayes log probability of the trigrams formed from a sequence
of letters.
"""
return sum(P3l[p] for p in ngrams(letters, 3))
>>> cosine_similarity_score('abcabc') # doctest: +ELLIPSIS
0.26228882...
"""
- return norms.cosine_similarity(english_counts,
- collections.Counter(sanitise(text)))
+ return norms.cosine_similarity(english_counts,
+ collections.Counter(sanitise(text)))
if __name__ == "__main__":