X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=segment.py;h=712895b6b0d7f1563ee4149fe7d94445a3931233;hb=e6332a16567643e66c2a491b94994f9482384d34;hp=e4b0d8ba3d70654650756a131f4d5dc7800e166e;hpb=5010cde507d2b6b25ee549efd3dec8d663937e15;p=cipher-tools.git

diff --git a/segment.py b/segment.py
index e4b0d8b..712895b 100644
--- a/segment.py
+++ b/segment.py
@@ -2,23 +2,17 @@
 import string
 import collections
 from math import log10
+import itertools
+import sys
+from functools import lru_cache
+sys.setrecursionlimit(1000000)
 
-def memo(f):
-    "Memoize function f."
-    table = {}
-    def fmemo(*args):
-        if args not in table:
-            table[args] = f(*args)
-        return table[args]
-    fmemo.memo = table
-    return fmemo
-
-@memo
+@lru_cache()
 def segment(text):
     """Return a list of words that is the best segmentation of text.
     """
     if not text: return []
-    candidates = ([first]+segment(rem) for first,rem in splits(text))
+    candidates = ([first]+segment(rest) for first,rest in splits(text))
     return max(candidates, key=Pwords)
 
 def splits(text, L=20):
@@ -30,22 +24,20 @@ def splits(text, L=20):
 def Pwords(words): 
     """The Naive Bayes log probability of a sequence of words.
     """
-    return sum(Pw(w) for w in words)
+    return sum(Pw[w] 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):
-        self.total = sum([int(d[1]) for d in data])
-        for key, count in data:
+        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 __call__(self, key): 
-        if key in self: 
-            return self[key]  
-        else: 
-            return self.estimate_of_missing(key, self.total)
+    def __missing__(self, key):
+        return self.estimate_of_missing(key, self.total)
 
 def datafile(name, sep='\t'):
     """Read key,value pairs from file.
@@ -59,6 +51,5 @@ def avoid_long_words(key, N):
     """
     return -log10((N * 10**(len(key) - 2)))
 
-N = 1024908267229 ## Number of tokens
-
 Pw  = Pdist(datafile('count_1w.txt'), avoid_long_words)
+