소스 검색

Merge pull request #4 from luozhouyang/revert-3-zero-division-solution

Revert "added regex prior to profiles calculation"
luozhouyang 6 년 전
부모
커밋
9a7479517b
2개의 변경된 파일0개의 추가작업 그리고 13개의 파일을 삭제
  1. 0 7
      similarity/cosine.py
  2. 0 6
      similarity/jaccard.py

+ 0 - 7
similarity/cosine.py

@@ -24,9 +24,6 @@ from .shingle_based import ShingleBased
 from .string_distance import NormalizedStringDistance
 from .string_similarity import NormalizedStringSimilarity
 
-import re
-_SPACE_PATTERN = re.compile("\\s+")
-
 
 class Cosine(ShingleBased, NormalizedStringDistance,
              NormalizedStringSimilarity):
@@ -44,10 +41,6 @@ class Cosine(ShingleBased, NormalizedStringDistance,
             raise TypeError("Argument s1 is NoneType.")
         if s0 == s1:
             return 1.0
-            
-        s0 = _SPACE_PATTERN.sub("", s0)
-        s1 = _SPACE_PATTERN.sub("", s1)
-        
         if len(s0) < self.get_k() or len(s1) < self.get_k():
             return 0.0
         profile0 = self.get_profile(s0)

+ 0 - 6
similarity/jaccard.py

@@ -22,8 +22,6 @@ from .shingle_based import ShingleBased
 from .string_distance import NormalizedStringDistance, MetricStringDistance
 from .string_similarity import NormalizedStringSimilarity
 
-import re
-_SPACE_PATTERN = re.compile("\\s+")
 
 class Jaccard(ShingleBased, MetricStringDistance, NormalizedStringDistance, NormalizedStringSimilarity):
 
@@ -40,10 +38,6 @@ class Jaccard(ShingleBased, MetricStringDistance, NormalizedStringDistance, Norm
             raise TypeError("Argument s1 is NoneType.")
         if s0 == s1:
             return 1.0
-            
-        s0 = _SPACE_PATTERN.sub("", s0)
-        s1 = _SPACE_PATTERN.sub("", s1)
-        
         if len(s0) < self.get_k() or len(s1) < self.get_k():
             return 0.0
         profile0 = self.get_profile(s0)