Expose sentence to vector fn

chatopera · Sep 21, 2018 · 9979984 · 9979984
1 parent 5a37ca5
commit 9979984
Show file tree

Hide file tree

Showing 4 changed files with 29 additions and 1 deletion.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,4 +1,14 @@
 # 3.8
+* 获得一个分词后句子的向量，向量以BoW方式组成
+
+
+```
+    sentence: 句子是分词后通过空格联合起来
+    ignore: 是否忽略OOV，False时，随机生成一个向量
+```
+
+
+# 3.7
 * change import path of utils in word2vec.py to local path
 * expose vector fn
 

diff --git a/README.md b/README.md
@@ -127,6 +127,15 @@ array([-2.412167  ,  2.2628384 , -7.0214124 ,  3.9381874 ,  0.8219283 ,
       dtype=float32)
 ```
 
+### synonyms#sv(sentence, ignore=False)
+获得一个分词后句子的向量，向量以BoW方式组成
+
+```
+    sentence: 句子是分词后通过空格联合起来
+    ignore: 是否忽略OOV，False时，随机生成一个向量
+```
+
+
 ## PCA
 以“人脸”为例主要成分分析：
 

diff --git a/setup.py b/setup.py
@@ -13,7 +13,7 @@
 
 setup(
     name='synonyms',
-    version='3.7.0',
+    version='3.8.0',
     description='Chinese Synonyms for Natural Language Processing and Understanding',
     long_description=LONGDOC,
     author='Hai Liang Wang, Hu Ying Xi',

diff --git a/synonyms/synonyms.py b/synonyms/synonyms.py
@@ -206,6 +206,15 @@ def _levenshtein_distance(sentence1, sentence2):
     # print("smoothing[%s| %s]: %s -> %s" % (sentence1, sentence2, d, s))
     return s
 
+def sv(sentence, ignore=False):
+    '''
+    获得一个分词后句子的向量，向量以BoW方式组成
+    sentence: 句子是分词后通过空格联合起来
+    ignore: 是否忽略OOV，False时，随机生成一个向量
+    '''
+    return _get_wv(sentence, ignore = ignore)
+
+
 def v(word):
     '''
     获得一个词语的向量，OOV时抛出 KeyError 异常