remove the strsimpy dependency

delftdata · May 18, 2023 · 30b96b2 · 30b96b2
1 parent ac35d1f
commit 30b96b2
Show file tree

Hide file tree

Showing 3 changed files with 0 additions and 12 deletions.
diff --git a/requirements.txt b/requirements.txt
@@ -3,7 +3,6 @@ numpy==1.24.3
 pandas==2.0.1
 nltk==3.8.1
 anytree==2.8.0
-strsimpy==0.2.1
 networkx==3.1
 chardet==5.1.0
 levenshtein==0.21.0

diff --git a/setup.py b/setup.py
@@ -32,7 +32,6 @@
         'pandas>=1.3,<2.1',
         'nltk>=3.6,<4.0',
         'anytree>=2.8,<2.9',
-        'strsimpy==0.2.1',
         'networkx>=2.8,<4.0',
         'chardet>=5.0.0,<6.0.0',
         'levenshtein>=0.20.7,<1.0',

diff --git a/valentine/algorithms/cupid/linguistic_matching.py b/valentine/algorithms/cupid/linguistic_matching.py
@@ -9,7 +9,6 @@
 from nltk.corpus import stopwords
 from nltk.corpus import wordnet as wn
 from Levenshtein import ratio
-from strsimpy.ngram import NGram
 
 from . import DATATYPE_COMPATIBILITY_TABLE
 from .schema_element import SchemaElement, Token, TokenTypes
@@ -212,15 +211,6 @@ def compute_similarity_wordnet(word1,
     return best
 
 
-# the lower, the better
-def compute_similarity_ngram(word1,
-                             word2,
-                             n):
-    ngram = NGram(n)
-    sim = ngram.distance(word1, word2)
-    return sim
-
-
 # Higher the better
 def compute_similarity_leven(word1,
                              word2):