projects
/
cipher-training.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Started 2015 challenges
[cipher-training.git]
/
language_models.py
diff --git
a/language_models.py
b/language_models.py
index 929746888d036fb54de3f1fbf228e296e0bcd027..f1877b70d8169ee12372cf028e284f4d14f6183b 100644
(file)
--- a/
language_models.py
+++ b/
language_models.py
@@
-1,11
+1,17
@@
+"""Language-specific functions, including models of languages based on data of
+its use.
+"""
+
import string
import string
-import norms
import random
import random
+import norms
import collections
import unicodedata
import itertools
from math import log10
import collections
import unicodedata
import itertools
from math import log10
+unaccent_specials = ''.maketrans({"’": "'"})
+
def letters(text):
"""Remove all non-alphabetic characters from a text
>>> letters('The Quick')
def letters(text):
"""Remove all non-alphabetic characters from a text
>>> letters('The Quick')
@@
-16,7
+22,7
@@
def letters(text):
return ''.join([c for c in text if c in string.ascii_letters])
def unaccent(text):
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.
It does this by converting the unicode string to decomposed compatability
form, dropping all the combining accents, then re-encoding the bytes.
@@
-31,13
+37,14
@@
def unaccent(text):
>>> unaccent('HÉLLÖ')
'HELLO'
"""
>>> 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 sanitise(text):
"""Remove all non-alphabetic characters and convert the text to lowercase
encode('ascii', 'ignore').\
decode('utf-8')
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')
>>> sanitise('The Quick')
'thequick'
>>> sanitise('The Quick BROWN fox jumped! over... the (9lazy) DOG')
@@
-72,30
+79,30
@@
with open('words.txt', 'r') as f:
def weighted_choice(d):
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():
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
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
'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)]
'rown', 'ownf', 'wnfo', 'nfox']
"""
return [text[i:i+n] for i in range(len(text)-n+1)]
@@
-120,35
+127,48
@@
def log_probability_of_unknown_word(key, N):
return -log10(N * 10**((len(key) - 2) * 1.4))
Pw = Pdist(datafile('count_1w.txt'), log_probability_of_unknown_word)
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)
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):
+def Pwords(words):
"""The Naive Bayes log probability of a sequence of words.
"""
return sum(Pw[w.lower()] for w in 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(Pl[l.lower()] for l in letters)
def Pbigrams(letters):
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))
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.
"""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,
- collections.Counter(sanitise(text)))
+ return norms.cosine_
similarity(english_counts,
+
collections.Counter(sanitise(text)))
if __name__ == "__main__":
if __name__ == "__main__":