X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=segment.py;fp=segment.py;h=ba3ddd7405a91a40c025fcd34b5eadfa7f8d0b11;hb=49dc272d2fc91e7340e56e9e7b96da6ab63514bb;hp=dd0b2a8347ee800c4addf996f369ea0293b47bb7;hpb=7bfededb9542780a13f38527c8ff21e89d6c08af;p=cipher-tools.git

diff --git a/segment.py b/segment.py
index dd0b2a8..ba3ddd7 100644
--- a/segment.py
+++ b/segment.py
@@ -1,7 +1,4 @@
-import string
-import collections
-from math import log10
-import itertools
+import language_models
 import sys
 from functools import lru_cache
 sys.setrecursionlimit(1000000)
@@ -12,7 +9,7 @@ def segment(text):
     """
     if not text: return []
     candidates = ([first]+segment(rest) for first,rest in splits(text))
-    return max(candidates, key=Pwords)
+    return max(candidates, key=language_models.Pwords)
 
 def splits(text, L=20):
     """Return a list of all possible (first, rest) pairs, len(first)<=L.
@@ -20,35 +17,3 @@ def splits(text, L=20):
     return [(text[:i+1], text[i+1:]) 
             for i in range(min(len(text), L))]
 
-def Pwords(words): 
-    """The Naive Bayes log probability of a sequence of words.
-    """
-    return sum(Pw[w.lower()] for w in words)
-
-class Pdist(dict):
-    """A probability distribution estimated from counts in datafile.
-    Values are stored and returned as log probabilities.
-    """
-    def __init__(self, data=[], estimate_of_missing=None):
-        data1, data2 = itertools.tee(data)
-        self.total = sum([int(d[1]) for d in data1])
-        for key, count in data2:
-            self[key] = log10(int(count) / self.total)
-        self.estimate_of_missing = estimate_of_missing or (lambda k, N: 1./N)
-    def __missing__(self, key):
-        return self.estimate_of_missing(key, self.total)
-
-def datafile(name, sep='\t'):
-    """Read key,value pairs from file.
-    """
-    with open(name, 'r') as f:
-        for line in f:
-            yield line.split(sep)
-
-def avoid_long_words(key, N):
-    """Estimate the probability of an unknown word.
-    """
-    return -log10((N * 10**(len(key) - 2)))
-
-Pw  = Pdist(datafile('count_1w.txt'), avoid_long_words)
-