def overlap_coeff(arr1, arr2):
"""
This function computes the overlap coefficient between the two input
lists/sets.
Args:
arr1,arr2 (list or set): The input lists or sets for which the overlap
coefficient should be computed.
Returns:
The overlap coefficient if both the lists/sets are not None and do not
have any missing tokens (i.e NaN), else returns NaN.
"""
if arr1 is None or arr2 is None:
return pd.np.NaN
if not isinstance(arr1, list):
arr1 = [arr1]
if any(pd.isnull(arr1)):
return pd.np.NaN
if not isinstance(arr2, list):
arr2 = [arr2]
if any(pd.isnull(arr2)):
return pd.np.NaN
# Create overlap coefficient measure object
measure = sm.OverlapCoefficient()
# Call the function to return the overlap coefficient
return measure.get_raw_score(arr1, arr2)
def matchHeaders(headers):
jac = sm.Jaccard()
lev = sm.Levenshtein()
oc = sm.OverlapCoefficient()
i = 0
j = 0
header_len = len(headers)
for i in range(0, header_len - 1):
for first in headers[i]:
j = i + 1
if j == header_len:
break
for second in headers[j]:
# print(first, '' , second, '')
# i = i + 1
# if(i == header_len):
# continue
x = first
y = second
delim_tok = sm.DelimiterTokenizer(delim_set=['_'])
jacScore = jac.get_sim_score(delim_tok.tokenize(x),
delim_tok.tokenize(y))
levScore = lev.get_sim_score(x, y)
ocScore = oc.get_sim_score(delim_tok.tokenize(x),
delim_tok.tokenize(y))
if (ocScore == 1 or levScore >= 0.5 or jacScore >= 0.5):
print(first + ' of Table' + str(i + 1) + ' and ' + second +
' of Table' + str(j + 1) + ' matched')
def get_similarity(s1, s2):
#TODO add lematization/stemming and tokenization using (spaCy|nltk|gensim)
oc = sm.OverlapCoefficient()
list1 = simple_preprocess(s1, deacc=True, min_len=1, max_len=25)
list2 = simple_preprocess(s2, deacc=True, min_len=1, max_len=25)
# print(list1)
# print(list2)
return oc.get_raw_score(list1, list2)
def overlap_coeff(arr1, arr2):
if arr1 is None or arr2 is None:
return pd.np.NaN
if not isinstance(arr1, list):
arr1 = [arr1]
if any(pd.isnull(arr1)):
return pd.np.NaN
if not isinstance(arr2, list):
arr2 = [arr2]
if any(pd.isnull(arr2)):
return pd.np.NaN
# Create overlap coefficient measure object
measure = sm.OverlapCoefficient()
# Call the function to return the overlap coefficient
return measure.get_raw_score(arr1, arr2)
def __init__(self):
self.similarity_function = [
sm.BagDistance(),
sm.Cosine(),
sm.Dice(),
sm.Editex(),
sm.GeneralizedJaccard(),
sm.Jaccard(),
sm.Jaro(),
sm.JaroWinkler(),
sm.Levenshtein(),
sm.OverlapCoefficient(),
sm.TverskyIndex()
]
self.alphanumeric_tokenizer = sm.AlphanumericTokenizer(return_set=True)
def overlap_coeff(arr1, arr2):
"""
This function computes the overlap coefficient between the two input
lists/sets.
Args:
arr1,arr2 (list or set): The input lists or sets for which the overlap
coefficient should be computed.
Returns:
The overlap coefficient if both the lists/sets are not None and do not
have any missing tokens (i.e NaN), else returns NaN.
Examples:
>>> import py_entitymatching as em
>>> em.overlap_coeff(['data', 'science'], ['data'])
1.0
>>> em.overlap_coeff(['data', 'science'], None)
nan
"""
#print "arr1:", arr1
#print "arr2:", arr2
if arr1 is None or arr2 is None:
return pd.np.NaN
if not isinstance(arr1, list):
arr1 = [arr1]
if any(pd.isnull(arr1)):
return pd.np.NaN
if not isinstance(arr2, list):
arr2 = [arr2]
if any(pd.isnull(arr2)):
return pd.np.NaN
# Create overlap coefficient measure object
measure = sm.OverlapCoefficient()
# Call the function to return the overlap coefficient
return measure.get_raw_score(arr1, arr2)
cos = sm.Cosine()
df['Cosine'] = df.apply(
lambda x: cos.get_sim_score(x['aTokens'], x['bTokens']), axis=1)
df.head()
# In[32]:
dice = sm.Dice()
df['Dice'] = df.apply(lambda x: dice.get_sim_score(x['aTokens'], x['bTokens']),
axis=1)
df.head()
# In[33]:
oc = sm.OverlapCoefficient()
df['Overlap'] = df.apply(
lambda x: oc.get_sim_score(x['aTokens'], x['bTokens']), axis=1)
df.head()
# In[34]:
# Set alpha beta https://en.wikipedia.org/wiki/Tversky_index
# Setting alpha beta as 0.5 is same as Dice Similarity
tvi = sm.TverskyIndex(0.3, 0.6)
df['Tversky'] = df.apply(
lambda x: tvi.get_sim_score(x['aTokens'], x['bTokens']), axis=1)
df.head()
# In[35]:
