+"""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):
return -log10(N * 10**((len(key) - 2) * 1.4))
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
+Pw_wrong = Pdist(datafile('count_1w.txt'), lambda _k, N: log10(1/N))
Pl = Pdist(datafile('count_1l.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(Pw[w.lower()] for w in 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(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):
+def cosine_similarity_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...
+ >>> cosine_similarity_score('abcabc') # doctest: +ELLIPSIS
+ 0.26228882...
"""
- return norms.cosine_distance(english_counts,
+ return norms.cosine_similarity(english_counts,
collections.Counter(sanitise(text)))