fix bayes

chensian · Mar 24, 2014 · 796eeeb · 796eeeb
1 parent 4512349
commit 796eeeb
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 5 deletions.
diff --git a/README.md b/README.md
@@ -14,7 +14,7 @@ s.tags          # [(u'这个', u'r'), (u'东西', u'n'),
                 #  (u'真心', u'd'), (u'很', u'd'),
                 #  (u'赞', u'Vg')]
 
-s.sentiments    # 0.9830157237610916 positive的概率
+s.sentiments    # 0.9769663402895832 positive的概率
 
 s.pinyin        # [u'zhe', u'ge', u'dong', u'xi',
                 #  u'zhen', u'xin', u'hen', u'zan']

diff --git a/setup.py b/setup.py
@@ -45,7 +45,7 @@ def read(fname):
 
 setup(
     name='snownlp',
-    version='0.9.9',
+    version='0.9.10',
     description='Python library for processing Chinese text',
     author='isnowfy',
     url='https://github.com/isnowfy/snownlp',

diff --git a/snownlp/classification/bayes.py b/snownlp/classification/bayes.py
@@ -46,10 +46,9 @@ def train(self, data):
     def classify(self, x):
         tmp = {}
         for k in self.d:
-            tmp[k] = 0
+            tmp[k] = log(self.d[k].getsum()) - log(self.total)
             for word in x:
-                tmp[k] += log(self.d[k].getsum()) - log(self.total)\
-                    + log(self.d[k].freq(word))
+                tmp[k] += log(self.d[k].freq(word))
         ret, prob = 0, 0
         for k in self.d:
             now = 0