def hamming_sim(s1, s2):
"""
This function computes the Hamming similarity between the two input
strings.
Args:
s1,s2 (string): The input strings for which the similarity measure should
be computed.
Returns:
The Hamming similarity if both the strings are not missing (i.e NaN),
else returns NaN.
"""
if s1 is None or s2 is None:
return pd.np.NaN
if pd.isnull(s1) or pd.isnull(s2):
return pd.np.NaN
# if isinstance(s1, six.string_types):
# s1 = gh.remove_non_ascii(s1)
# if isinstance(s2, six.string_types):
# s2 = gh.remove_non_ascii(s2)
# Create the similarity measure object
measure = sm.HammingDistance()
if not (isinstance(s1, six.string_types) or isinstance(s1, bytes)):
s1 = str(s1)
if not (isinstance(s2, six.string_types) or isinstance(s2, bytes)):
s2 = str(s2)
# Call the function to compute the similarity score.
return measure.get_sim_score(s1, s2)
def hamming_sim(s1, s2):
"""
This function computes the Hamming similarity between the two input
strings.
Args:
s1,s2 (string): The input strings for which the similarity measure should
be computed.
Returns:
The Hamming similarity if both the strings are not missing (i.e NaN),
else returns NaN.
Examples:
>>> import py_entitymatching as em
>>> em.hamming_sim('alex', 'alxe')
0.5
>>> em.hamming_sim(None, 'alex')
nan
"""
if s1 is None or s2 is None:
return pd.np.NaN
if pd.isnull(s1) or pd.isnull(s2):
return pd.np.NaN
# Create the similarity measure object
measure = sm.HammingDistance()
s1 = gh.convert_to_str_unicode(s1)
s2 = gh.convert_to_str_unicode(s2)
# Call the function to compute the similarity score.
return measure.get_sim_score(s1, s2)
def hamming_score(self, str_pair, sim_score=True):
"""
calculate hamming similarity between two strings
:return: similarity score or raw score
"""
s1, s2 = self._check_input(str_pair)
if len(s1) != len(s2):
return 0
hamming = sm.HammingDistance()
return hamming.get_sim_score(
s1, s2) if sim_score else hamming.get_raw_score(s1, s2)
def hamming_sim(s1, s2):
if s1 is None or s2 is None:
return pd.np.NaN
if pd.isnull(s1) or pd.isnull(s2):
return pd.np.NaN
s1 = helper.convert_to_str_unicode(s1)
s2 = helper.convert_to_str_unicode(s2)
measure = sm.HammingDistance()
return measure.get_sim_score(s1, s2)
def hamming_sim(s1, s2):
if s1 is None or s2 is None:
return pd.np.NaN
if pd.isnull(s1) or pd.isnull(s2):
return pd.np.NaN
# if isinstance(s1, six.string_types):
# s1 = gh.remove_non_ascii(s1)
# if isinstance(s2, six.string_types):
# s2 = gh.remove_non_ascii(s2)
# Create the similarity measure object
measure = sm.HammingDistance()
if not(isinstance(s1, six.string_types) or isinstance(s1, bytes)):
s1 = str(s1)
if not(isinstance(s2, six.string_types) or isinstance(s2, bytes)):
s2 = str(s2)
# Call the function to compute the similarity score.
return measure.get_sim_score(s1, s2)
def hamming_dist(s1, s2):
"""
This function computes the Hamming distance between the two input
strings.
Args:
s1,s2 (string): The input strings for which the similarity measure should
be computed.
Returns:
The Hamming distance if both the strings are not missing (i.e NaN),
else returns NaN.
Examples:
>>> import py_entitymatching as em
>>> em.hamming_dist('alex', 'john')
4
>>> em.hamming_dist(None, 'john')
nan
"""
if s1 is None or s2 is None:
return pd.np.NaN
if pd.isnull(s1) or pd.isnull(s2):
return pd.np.NaN
# if isinstance(s1, six.string_types):
# s1 = gh.remove_non_ascii(s1)
# if isinstance(s2, six.string_types):
# s2 = gh.remove_non_ascii(s2)
# Create the similarity measure object
measure = sm.HammingDistance()
if not (isinstance(s1, six.string_types) or isinstance(s1, bytes)):
s1 = str(s1)
if not (isinstance(s2, six.string_types) or isinstance(s2, bytes)):
s2 = str(s2)
# Call the function to compute the distance
return measure.get_raw_score(s1, s2)
