Partly refactored

[cipher-tools.git] / language_models.py

diff --git a/language_models.py b/language_models.py
index 929746888d036fb54de3f1fbf228e296e0bcd027..a6a711f1562d8c70f091165fa15330a825a48559 100644 (file)
--- a/language_models.py
+++ b/language_models.py
@@ -5,55 +5,14 @@ import collections
 import unicodedata
 import itertools
 from math import log10
+import os 
 
-def letters(text):
-    """Remove all non-alphabetic characters from a text
-    >>> letters('The Quick')
-    'TheQuick'
-    >>> letters('The Quick BROWN fox jumped! over... the (9lazy) DOG')
-    'TheQuickBROWNfoxjumpedoverthelazyDOG'
-    """
-    return ''.join([c for c in text if c in string.ascii_letters])
-
-def unaccent(text):
-    """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.
-
-    >>> unaccent('hello')
-    'hello'
-    >>> unaccent('HELLO')
-    'HELLO'
-    >>> unaccent('héllo')
-    'hello'
-    >>> unaccent('héllö')
-    'hello'
-    >>> unaccent('HÉLLÖ')
-    'HELLO'
-    """
-    return unicodedata.normalize('NFKD', text).\
-        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')
-    'thequickbrownfoxjumpedoverthelazydog'
-    >>> sanitise('HÉLLÖ')
-    'hello'
-    """
-    # sanitised = [c.lower() for c in text if c in string.ascii_letters]
-    # return ''.join(sanitised)
-    return letters(unaccent(text)).lower()
 
 
 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])]
@@ -67,25 +26,25 @@ normalised_english_bigram_counts = norms.normalise(english_bigram_counts)
 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]
 
 
 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):
@@ -122,6 +81,7 @@ def log_probability_of_unknown_word(key, N):
 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)
+P3l = Pdist(datafile('count_3l.txt'), lambda _k, _N: 0)
 
 def Pwords(words): 
     """The Naive Bayes log probability of a sequence of words.
@@ -139,15 +99,23 @@ def Pbigrams(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)))