X-Git-Url: https://git.njae.me.uk/?a=blobdiff_plain;f=segment.py;h=dd0b2a8347ee800c4addf996f369ea0293b47bb7;hb=3906e8a686e3d1943e22746b65c394a4def34fc0;hp=f90af1d92c8fe0046b4f5c7a4975f53e7011e6ea;hpb=269665fe76e7aeb87165a87d3a1cbb755a5e3768;p=cipher-tools.git

diff --git a/segment.py b/segment.py
index f90af1d..dd0b2a8 100644
--- a/segment.py
+++ b/segment.py
@@ -1,54 +1,54 @@
-# import re, string, random, glob, operator, heapq
 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."
+    """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):
-    "Return a list of all possible (first, rem) pairs, len(first)<=L."
+    """Return a list of all possible (first, rest) pairs, len(first)<=L.
+    """
     return [(text[:i+1], text[i+1:]) 
             for i in range(min(len(text), L))]
 
 def Pwords(words): 
-    "The Naive Bayes probability of a sequence of words."
-    return product(Pw(w) for w in 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."
-    def __init__(self, data=[], N=None, missingfn=None):
-        for key,count in data:
-            self[key] = self.get(key, 0) + int(count)
-        self.N = float(N or sum(self.itervalues()))
-        self.missingfn = missingfn or (lambda k, N: 1./N)
-    def __call__(self, key): 
-        if key in self: return self[key]/self.N  
-        else: return self.missingfn(key, self.N)
+    """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."
-    for line in file(name):
-        yield line.split(sep)
+    """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 10./(N * 10**len(key))
-
-N = 1024908267229 ## Number of tokens
+    """Estimate the probability of an unknown word.
+    """
+    return -log10((N * 10**(len(key) - 2)))
 
-Pw  = Pdist(datafile('count_1w.txt'), N, avoid_long_words)
+Pw  = Pdist(datafile('count_1w.txt'), avoid_long_words)
+