def get_raw_score(self, string1, string2):
"""Computes the raw Levenshtein distance between two strings.
Args:
string1,string2 (str): Input strings.
Returns:
Levenshtein distance (int).
Raises:
TypeError : If the inputs are not strings.
Examples:
>>> lev = Levenshtein()
>>> lev.get_raw_score('a', '')
1
>>> lev.get_raw_score('example', 'samples')
3
>>> lev.get_raw_score('levenshtein', 'frankenstein')
6
"""
# input validations
utils.sim_check_for_none(string1, string2)
# convert input to unicode.
string1 = utils.convert_to_unicode(string1)
string2 = utils.convert_to_unicode(string2)
utils.tok_check_for_string_input(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0.0
return levenshtein(string1, string2)
def levenshtein(string1, string2):
"""
Computes the Levenshtein distance between two strings.
Levenshtein distance computes the minimum cost of transforming one string into the other. Transforming a string
is carried out using a sequence of the following operators: delete a character, insert a character, and
substitute one character for another.
Args:
string1,string2 (str): Input strings
Returns:
Levenshtein distance (int)
Raises:
TypeError : If the inputs are not strings
Examples:
>>> levenshtein('a', '')
1
>>> levenshtein('example', 'samples')
3
>>> levenshtein('levenshtein', 'frankenstein')
6
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0.0
ins_cost, del_cost, sub_cost, trans_cost = (1, 1, 1, 1)
len_str1 = len(string1)
len_str2 = len(string2)
if len_str1 == 0:
return len_str2 * ins_cost
if len_str2 == 0:
return len_str1 * del_cost
d_mat = np.zeros((len_str1 + 1, len_str2 + 1), dtype=np.int)
for i in _range(len_str1 + 1):
d_mat[i, 0] = i * del_cost
for j in _range(len_str2 + 1):
d_mat[0, j] = j * ins_cost
for i in _range(len_str1):
for j in _range(len_str2):
d_mat[i + 1, j + 1] = min(
d_mat[i + 1, j] + ins_cost, d_mat[i, j + 1] + del_cost,
d_mat[i, j] + (sub_cost if string1[i] != string2[j] else 0))
return d_mat[len_str1, len_str2]
def get_raw_score(self, string1, string2):
"""Computes the raw Levenshtein distance between two strings.
Args:
string1,string2 (str): Input strings.
Returns:
Levenshtein distance (int).
Raises:
TypeError : If the inputs are not strings.
Examples:
>>> lev = Levenshtein()
>>> lev.get_raw_score('a', '')
1
>>> lev.get_raw_score('example', 'samples')
3
>>> lev.get_raw_score('levenshtein', 'frankenstein')
6
"""
# input validations
utils.sim_check_for_none(string1, string2)
# convert input to unicode.
string1 = utils.convert_to_unicode(string1)
string2 = utils.convert_to_unicode(string2)
utils.tok_check_for_string_input(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0.0
return levenshtein(string1, string2)
def monge_elkan(bag1, bag2, sim_func=jaro_winkler):
"""
Compute Monge-Elkan similarity measure between two bags (lists).
The Monge-Elkan similarity measure is a type of Hybrid similarity measure that combine the benefits of
sequence-based and set-based methods. This can be effective for domains in which more control is needed
over the similarity measure. It implicitly uses a secondary similarity measure, such as levenshtein to compute
over all similarity score.
Args:
bag1,bag2 (list): Input lists
sim_func (function): Secondary similarity function. This is expected to be a sequence-based
similarity measure (defaults to levenshtein)
Returns:
Monge-Elkan similarity score (float)
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None
Examples:
>>> monge_elkan(['Niall'], ['Neal'])
0.8049999999999999
>>> monge_elkan(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
0.8677218614718616
>>> monge_elkan(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'], sim_func=needleman_wunsch)
2.0
>>> monge_elkan(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'], sim_func=affine)
2.25
>>> monge_elkan([''], ['a'])
0.0
>>> monge_elkan(['Niall'], ['Nigel'])
0.7866666666666667
References:
* Principles of Data Integration book
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# aggregated sum of all the max sim score of all the elements in bag1
# with elements in bag2
sum_of_maxes = 0
for t1 in bag1:
max_sim = float('-inf')
for t2 in bag2:
max_sim = max(max_sim, sim_func(t1, t2))
sum_of_maxes += max_sim
sim = float(sum_of_maxes) / float(len(bag1))
return sim
def monge_elkan(bag1, bag2, sim_func=jaro_winkler):
"""
Compute Monge-Elkan similarity measure between two bags (lists).
The Monge-Elkan similarity measure is a type of Hybrid similarity measure that combine the benefits of
sequence-based and set-based methods. This can be effective for domains in which more control is needed
over the similarity measure. It implicitly uses a secondary similarity measure, such as levenshtein to compute
over all similarity score.
Args:
bag1,bag2 (list): Input lists
sim_func (function): Secondary similarity function. This is expected to be a sequence-based
similarity measure (defaults to levenshtein)
Returns:
Monge-Elkan similarity score (float)
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None
Examples:
>>> monge_elkan(['Niall'], ['Neal'])
0.8049999999999999
>>> monge_elkan(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
0.8677218614718616
>>> monge_elkan(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'], sim_func=needleman_wunsch)
2.0
>>> monge_elkan(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'], sim_func=affine)
2.25
>>> monge_elkan([''], ['a'])
0.0
>>> monge_elkan(['Niall'], ['Nigel'])
0.7866666666666667
References:
* Principles of Data Integration book
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# aggregated sum of all the max sim score of all the elements in bag1
# with elements in bag2
sum_of_maxes = 0
for t1 in bag1:
max_sim = float('-inf')
for t2 in bag2:
max_sim = max(max_sim, sim_func(t1, t2))
sum_of_maxes += max_sim
sim = float(sum_of_maxes) / float(len(bag1))
return sim
def get_raw_score(self, bag1, bag2):
"""Computes the raw Monge-Elkan score between two bags (lists).
Args:
bag1,bag2 (list): Input lists.
Returns:
Monge-Elkan similarity score (float).
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> me = MongeElkan()
>>> me.get_raw_score(['Niall'], ['Neal'])
0.8049999999999999
>>> me.get_raw_score(['Niall'], ['Nigel'])
0.7866666666666667
>>> me.get_raw_score(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
0.8677218614718616
>>> me.get_raw_score([''], ['a'])
0.0
>>> me = MongeElkan(sim_func=NeedlemanWunsch().get_raw_score)
>>> me.get_raw_score(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
2.0
>>> me = MongeElkan(sim_func=Affine().get_raw_score)
>>> me.get_raw_score(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
2.25
References:
* Principles of Data Integration book
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# aggregated sum of all the max sim score of all the elements in bag1
# with elements in bag2
sum_of_maxes = 0
for el1 in bag1:
max_sim = float('-inf')
for el2 in bag2:
max_sim = max(max_sim, self.sim_func(el1, el2))
sum_of_maxes += max_sim
sim = float(sum_of_maxes) / float(len(bag1))
return sim
def get_raw_score(self, bag1, bag2):
"""Computes the raw Monge-Elkan score between two bags (lists).
Args:
bag1,bag2 (list): Input lists.
Returns:
Monge-Elkan similarity score (float).
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> me = MongeElkan()
>>> me.get_raw_score(['Niall'], ['Neal'])
0.8049999999999999
>>> me.get_raw_score(['Niall'], ['Nigel'])
0.7866666666666667
>>> me.get_raw_score(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
0.8677218614718616
>>> me.get_raw_score([''], ['a'])
0.0
>>> me = MongeElkan(sim_func=NeedlemanWunsch().get_raw_score)
>>> me.get_raw_score(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
2.0
>>> me = MongeElkan(sim_func=Affine().get_raw_score)
>>> me.get_raw_score(['Comput.', 'Sci.', 'and', 'Eng.', 'Dept.,', 'University', 'of', 'California,', 'San', 'Diego'], ['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
2.25
References:
* Principles of Data Integration book
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# aggregated sum of all the max sim score of all the elements in bag1
# with elements in bag2
sum_of_maxes = 0
for el1 in bag1:
max_sim = float('-inf')
for el2 in bag2:
max_sim = max(max_sim, self.sim_func(el1, el2))
sum_of_maxes += max_sim
sim = float(sum_of_maxes) / float(len(bag1))
return sim
def get_raw_score(self, set1, set2):
"""
Computes the Tversky index similarity between two sets.
The Tversky index is an asymmetric similarity measure on sets that compares a variant to a prototype. The
Tversky index can be seen as a generalization of Dice's coefficient and Tanimoto coefficient.
For sets X and Y the Tversky index is a number between 0 and 1 given by:
:math:`tversky_index(X, Y) = \\frac{|X \\cap Y|}{|X \\cap Y| + \alpha |X-Y| + \beta |Y-X|}`
where, :math: \alpha, \beta >=0
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Tversly index similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> tvi = TverskyIndex()
>>> tvi.get_raw_score(['data', 'science'], ['data'])
0.6666666666666666
>>> tvi.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.5
>>> tvi.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> tvi = TverskyIndex(0.5, 0.5)
>>> tvi.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> tvi = TverskyIndex(beta=0.5)
>>> tvi.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.5
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
intersection = float(len(set1 & set2))
return 1.0 * intersection / (intersection +
(self.alpha * len(set1 - set2)) +
(self.beta * len(set2 - set1)))
def get_raw_score(self, set1, set2):
"""
Computes the Tversky index similarity between two sets.
The Tversky index is an asymmetric similarity measure on sets that compares a variant to a prototype. The
Tversky index can be seen as a generalization of Dice's coefficient and Tanimoto coefficient.
For sets X and Y the Tversky index is a number between 0 and 1 given by:
:math:`tversky_index(X, Y) = \\frac{|X \\cap Y|}{|X \\cap Y| + \alpha |X-Y| + \beta |Y-X|}`
where, :math: \alpha, \beta >=0
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Tversly index similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> tvi = TverskyIndex()
>>> tvi.get_raw_score(['data', 'science'], ['data'])
0.6666666666666666
>>> tvi.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.5
>>> tvi.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> tvi = TverskyIndex(0.5, 0.5)
>>> tvi.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> tvi = TverskyIndex(beta=0.5)
>>> tvi.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.5
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
intersection = float(len(set1 & set2))
return 1.0 * intersection / (intersection +
(self.alpha * len(set1 - set2)) + (self.beta * len(set2 - set1)))
def get_raw_score(self, string1, string2):
"""
Computes the bag distance between two strings.
For two strings X and Y, the Bag distance is:
:math:`max( |bag(string1)-bag(string2)|, |bag(string2)-bag(string1)| )`
Args:
string1,string2 (str): Input strings
Returns:
Bag distance (int)
Raises:
TypeError : If the inputs are not strings
Examples:
>>> bd = BagDistance()
>>> bd.get_raw_score('cat', 'hat')
1
>>> bd.get_raw_score('Niall', 'Neil')
2
>>> bd.get_raw_score('aluminum', 'Catalan')
5
>>> bd.get_raw_score('ATCG', 'TAGC')
0
>>> bd.get_raw_score('abcde', 'xyz')
5
References:
* String Matching with Metric Trees Using an Approximate Distance: http://www-db.disi.unibo.it/research/papers/SPIRE02.pdf
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0
len_str1 = len(string1)
len_str2 = len(string2)
if len_str1 == 0:
return len_str2
if len_str2 == 0:
return len_str1
bag1 = collections.Counter(string1)
bag2 = collections.Counter(string2)
size1 = sum((bag1 - bag2).values())
size2 = sum((bag2 - bag1).values())
# returning the max of difference of sets
return max(size1, size2)
def get_raw_score(self, string1, string2):
"""
Computes the bag distance between two strings.
For two strings X and Y, the Bag distance is:
:math:`max( |bag(string1)-bag(string2)|, |bag(string2)-bag(string1)| )`
Args:
string1,string2 (str): Input strings
Returns:
Bag distance (int)
Raises:
TypeError : If the inputs are not strings
Examples:
>>> bd = BagDistance()
>>> bd.get_raw_score('cat', 'hat')
1
>>> bd.get_raw_score('Niall', 'Neil')
2
>>> bd.get_raw_score('aluminum', 'Catalan')
5
>>> bd.get_raw_score('ATCG', 'TAGC')
0
>>> bd.get_raw_score('abcde', 'xyz')
5
References:
* http://www.icmlc.org/icmlc2011/018_icmlc2011.pdf
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0
len_str1 = len(string1)
len_str2 = len(string2)
if len_str1 == 0:
return len_str2
if len_str2 == 0:
return len_str1
bag1 = collections.Counter(string1)
bag2 = collections.Counter(string2)
size1 = sum((bag1 - bag2).values())
size2 = sum((bag2 - bag1).values())
# returning the max of difference of sets
return max(size1, size2)
def get_word_vector_similarities_simple(self, bag1, bag2):
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# if corpus is not provided treat input string as corpus
curr_df, corpus_size = (self.__document_frequency, self.__corpus_size)
# calculating the term sim score against the input string 2,
# construct similarity map
similarity_map = {}
for term_x in tf_x:
max_score = 0.0
for term_y in tf_y:
score = self.sim_func(term_x, term_y)
# adding sim only if it is above threshold and
# highest for this element
if score > self.threshold and score > max_score:
similarity_map[term_x] = (term_x, term_y, score)
max_score = score
# position of first string, second string and sim score
# in the tuple
first_string_pos = 0
second_string_pos = 1
sim_score_pos = 2
# create a word vector with all the words in the document collection for every comparision.
# if the word exist in this similarity-map, add the soft TF/ID value. If not, add a 0
word_similarities_vector = np.zeros(len(curr_df))
for idx, element in enumerate(curr_df.keys()):
if element in similarity_map:
sim = similarity_map[element]
word_similarities_vector[idx] = sim[sim_score_pos]
else:
word_similarities_vector[idx] = 0
return word_similarities_vector
def overlap_coefficient(set1, set2):
"""
Computes the overlap coefficient between two sets.
The overlap coefficient is a similarity measure related to the Jaccard
measure that measures the overlap between two sets, and is defined as the size of the intersection divided by
the smaller of the size of the two sets.
For two sets X and Y, the overlap coefficient is:
:math:`overlap\\_coefficient(X, Y) = \\frac{|X \\cap Y|}{\\min(|X|, |Y|)}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Overlap coefficient (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> (overlap_coefficient([], [])
1.0
>>> overlap_coefficient([], ['data'])
0
>>> overlap_coefficient(['data', 'science'], ['data'])
1.0
References:
* Wikipedia article : https://en.wikipedia.org/wiki/Overlap_coefficient
* Simmetrics library
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / min(len(set1), len(set2))
def overlap_coefficient(set1, set2):
"""
Computes the overlap coefficient between two sets.
The overlap coefficient is a similarity measure related to the Jaccard
measure that measures the overlap between two sets, and is defined as the size of the intersection divided by
the smaller of the size of the two sets.
For two sets X and Y, the overlap coefficient is:
:math:`overlap\\_coefficient(X, Y) = \\frac{|X \\cap Y|}{\\min(|X|, |Y|)}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Overlap coefficient (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> (overlap_coefficient([], [])
1.0
>>> overlap_coefficient([], ['data'])
0
>>> overlap_coefficient(['data', 'science'], ['data'])
1.0
References:
* Wikipedia article : https://en.wikipedia.org/wiki/Overlap_coefficient
* Simmetrics library
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / min(len(set1), len(set2))
def jaccard(set1, set2):
"""
Computes the Jaccard measure between two sets.
The Jaccard measure, also known as the Jaccard similarity coefficient, is a statistic used for comparing
the similarity and diversity of sample sets. The Jaccard coefficient measures similarity between finite sample
sets, and is defined as the size of the intersection divided by the size of the union of the sample sets.
For two sets X and Y, the Jaccard measure is:
:math:`jaccard(X, Y) = \\frac{|X \\cap Y|}{|X| \\cup |Y|}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Jaccard similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> jaccard(['data', 'science'], ['data'])
0.5
>>> jaccard({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.375
>>> jaccard(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / float(len(set1 | set2))
def cosine(set1, set2):
"""
Computes the cosine similarity between two sets.
For two sets X and Y, the cosine similarity is:
:math:`cosine(X, Y) = \\frac{|X \\cap Y|}{\\sqrt{|X| \\cdot |Y|}}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Cosine similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> cosine(['data', 'science'], ['data'])
0.7071067811865475
>>> cosine(['data', 'data', 'science'], ['data', 'management'])
0.4999999999999999
>>> cosine([], ['data'])
0.0
References:
* String similarity joins: An Experimental Evaluation (VLDB 2014)
* Project flamingo : Mike carey, Vernica
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / (math.sqrt(float(len(set1))) *
math.sqrt(float(len(set2))))
def jaccard(set1, set2):
"""
Computes the Jaccard measure between two sets.
The Jaccard measure, also known as the Jaccard similarity coefficient, is a statistic used for comparing
the similarity and diversity of sample sets. The Jaccard coefficient measures similarity between finite sample
sets, and is defined as the size of the intersection divided by the size of the union of the sample sets.
For two sets X and Y, the Jaccard measure is:
:math:`jaccard(X, Y) = \\frac{|X \\cap Y|}{|X| \\cup |Y|}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Jaccard similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> jaccard(['data', 'science'], ['data'])
0.5
>>> jaccard({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.375
>>> jaccard(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / float(len(set1 | set2))
def get_raw_score(self, set1, set2):
"""Computes the raw Dice score between two sets. This score is already in [0,1].
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Dice similarity score (float).
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> dice = Dice()
>>> dice.get_raw_score(['data', 'science'], ['data'])
0.6666666666666666
>>> dice.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> dice.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.5
References:
* Wikipedia article : https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Dice%27s_coefficient
* SimMetrics library.
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return 2.0 * float(len(set1 & set2)) / float(len(set1) + len(set2))
def get_raw_score(self, set1, set2):
"""Computes the raw overlap coefficient score between two sets.
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Overlap coefficient (float).
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> oc = OverlapCoefficient()
>>> oc.get_raw_score(['data', 'science'], ['data'])
1.0
>>> oc.get_raw_score([], [])
1.0
>>> oc.get_raw_score([], ['data'])
0
References:
* Wikipedia article : https://en.wikipedia.org/wiki/Overlap_coefficient
* SimMetrics library
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / min(len(set1), len(set2))
def cosine(set1, set2):
"""
Computes the cosine similarity between two sets.
For two sets X and Y, the cosine similarity is:
:math:`cosine(X, Y) = \\frac{|X \\cap Y|}{\\sqrt{|X| \\cdot |Y|}}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Cosine similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> cosine(['data', 'science'], ['data'])
0.7071067811865475
>>> cosine(['data', 'data', 'science'], ['data', 'management'])
0.4999999999999999
>>> cosine([], ['data'])
0.0
References:
* String similarity joins: An Experimental Evaluation (VLDB 2014)
* Project flamingo : Mike carey, Vernica
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / (math.sqrt(float(len(set1))) * math.sqrt(float(len(set2))))
def get_raw_score(self, set1, set2):
"""Computes the raw Dice score between two sets. This score is already in [0,1].
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Dice similarity score (float).
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> dice = Dice()
>>> dice.get_raw_score(['data', 'science'], ['data'])
0.6666666666666666
>>> dice.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> dice.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.5
References:
* Wikipedia article : https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Dice%27s_coefficient
* SimMetrics library.
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return 2.0 * float(len(set1 & set2)) / float(len(set1) + len(set2))
def get_raw_score(self, set1, set2):
"""Computes the raw cosine score between two sets.
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Cosine similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> cos = Cosine()
>>> cos.get_raw_score(['data', 'science'], ['data'])
0.7071067811865475
>>> cos.get_raw_score(['data', 'data', 'science'], ['data', 'management'])
0.4999999999999999
>>> cos.get_raw_score([], ['data'])
0.0
References:
* String similarity joins: An Experimental Evaluation (a paper appearing in the VLDB 2014 Conference).
* Project Flamingo at http://flamingo.ics.uci.edu.
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / (math.sqrt(float(len(set1))) *
math.sqrt(float(len(set2))))
def get_raw_score(self, set1, set2):
"""Computes the raw Jaccard score between two sets.
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Jaccard similarity score (float).
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> jac = Jaccard()
>>> jac.get_raw_score(['data', 'science'], ['data'])
0.5
>>> jac.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.375
>>> jac.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / float(len(set1 | set2))
def get_raw_score(self, set1, set2):
"""Computes the raw Jaccard score between two sets.
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Jaccard similarity score (float).
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> jac = Jaccard()
>>> jac.get_raw_score(['data', 'science'], ['data'])
0.5
>>> jac.get_raw_score({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.375
>>> jac.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return float(len(set1 & set2)) / float(len(set1 | set2))
def dice(set1, set2):
"""
Computes the Dice similarity coefficient between two sets.
The similarity is defined as twice the shared information (intersection) divided by sum of cardinalities.
For two sets X and Y, the Dice similarity coefficient is:
:math:`dice(X, Y) = \\frac{2 * |X \\cap Y|}{|X| + |Y|}`
Args:
set1,set2 (set or list): Input sets (or lists). Input lists are converted to sets.
Returns:
Dice similarity coefficient (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
Examples:
>>> dice(['data', 'science'], ['data'])
0.6666666666666666
>>> dice({1, 1, 2, 3, 4}, {2, 3, 4, 5, 6, 7, 7, 8})
0.5454545454545454
>>> dice(['data', 'management'], ['data', 'data', 'science'])
0.5
References:
* Wikipedia article : https://en.wikibooks.org/wiki/Algorithm_Implementation/Strings/Dice%27s_coefficient
* Simmetrics library
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
return 2.0 * float(len(set1 & set2)) / float(len(set1) + len(set2))
def tfidf(bag1, bag2, corpus_list=None, dampen=False):
"""
Compute tfidf measures between two lists given the corpus information.
This measure employs the notion of TF/IDF score commonly used in information retrieval (IR) to find documents that
are relevant to keyword queries.
The intuition underlying the TF/IDF measure is that two strings are similar if they share distinguishing terms.
Args:
bag1,bag2 (list): Input lists
corpus_list (list of lists): Corpus list (default is set to None) of strings. If set to None,
the input list are considered the only corpus.
dampen (boolean): Flag to indicate whether 'log' should be applied to tf and idf measure.
Returns:
TF-IDF measure between the input lists (float)
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None
Examples:
>>> tfidf(['a', 'b', 'a'], ['a', 'c'], [['a', 'b', 'a'], ['a', 'c'], ['a']])
0.17541160386140586
>>> tfidf(['a', 'b', 'a'], ['a', 'c'], [['a', 'b', 'a'], ['a', 'c'], ['a'], ['b']], True)
0.11166746710505392
>>> tfidf(['a', 'b', 'a'], ['a'], [['a', 'b', 'a'], ['a', 'c'], ['a']])
0.5547001962252291
>>> tfidf(['a', 'b', 'a'], ['a'], [['x', 'y'], ['w'], ['q']])
0.0
>>> tfidf(['a', 'b', 'a'], ['a'], [['x', 'y'], ['w'], ['q']], True)
0.0
>>> tfidf(['a', 'b', 'a'], ['a'])
0.7071067811865475
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# if corpus is not provided treat input string as corpus
if corpus_list is None:
corpus_list = [bag1, bag2]
corpus_size = len(corpus_list)
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# number of documents an element appeared
element_freq = {}
# set of unique element
total_unique_elements = set()
for document in corpus_list:
temp_set = set()
for element in document:
# adding element only if it is present in one of two input string
if element in bag1 or element in bag2:
temp_set.add(element)
total_unique_elements.add(element)
# update element document frequency for this document
for element in temp_set:
element_freq[element] = element_freq[element] + 1 if element in element_freq else 1
idf_element, v_x, v_y, v_x_y, v_x_2, v_y_2 = 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
# tfidf calculation
for element in total_unique_elements:
idf_element = corpus_size * 1.0 / element_freq[element]
v_x = 0 if element not in tf_x else (math.log(idf_element) * math.log(tf_x[element] + 1)) if dampen else (
idf_element * tf_x[element])
v_y = 0 if element not in tf_y else (math.log(idf_element) * math.log(tf_y[element] + 1)) if dampen else (
idf_element * tf_y[element])
v_x_y += v_x * v_y
v_x_2 += v_x * v_x
v_y_2 += v_y * v_y
return 0.0 if v_x_y == 0 else v_x_y / (math.sqrt(v_x_2) * math.sqrt(v_y_2))
def get_raw_score(self, bag1, bag2):
"""Computes the raw TF/IDF score between two lists.
Args:
bag1,bag2 (list): Input lists.
Returns:
TF/IDF score between the input lists (float).
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> # here the corpus is a list of three strings that
>>> # have been tokenized into three lists of tokens
>>> tfidf = TfIdf([['a', 'b', 'a'], ['a', 'c'], ['a']])
>>> tfidf.get_raw_score(['a', 'b', 'a'], ['b', 'c'])
0.7071067811865475
>>> tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.0
>>> tfidf = TfIdf([['x', 'y'], ['w'], ['q']])
>>> tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.0
>>> tfidf = TfIdf([['a', 'b', 'a'], ['a', 'c'], ['a'], ['b']], False)
>>> tfidf.get_raw_score(['a', 'b', 'a'], ['a', 'c'])
0.25298221281347033
>>> tfidf = TfIdf(dampen=False)
>>> tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.7071067811865475
>>> tfidf = TfIdf()
>>> tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.0
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# find unique elements in the input lists and their document frequency
local_df = {}
for element in tf_x:
local_df[element] = local_df.get(element, 0) + 1
for element in tf_y:
local_df[element] = local_df.get(element, 0) + 1
# if corpus is not provided treat input string as corpus
curr_df, corpus_size = (local_df, 2) if self.__corpus_list is None else (
(self.__document_frequency, self.__corpus_size))
idf_element, v_x, v_y, v_x_y, v_x_2, v_y_2 = (0.0, 0.0, 0.0,
0.0, 0.0, 0.0)
# tfidf calculation
for element in local_df.keys():
df_element = curr_df.get(element)
if df_element is None:
continue
idf_element = corpus_size * 1.0 / df_element
v_x = 0 if element not in tf_x else (log(idf_element) * log(tf_x[element] + 1)) if self.dampen else (
idf_element * tf_x[element])
v_y = 0 if element not in tf_y else (log(idf_element) * log(tf_y[element] + 1)) if self.dampen else (
idf_element * tf_y[element])
v_x_y += v_x * v_y
v_x_2 += v_x * v_x
v_y_2 += v_y * v_y
return 0.0 if v_x_y == 0 else v_x_y / (sqrt(v_x_2) * sqrt(v_y_2))
def get_raw_score(self, bag1, bag2):
"""Computes the raw soft TF/IDF score between two lists given the corpus information.
Args:
bag1,bag2 (list): Input lists
Returns:
Soft TF/IDF score between the input lists (float).
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> soft_tfidf = SoftTfIdf([['a', 'b', 'a'], ['a', 'c'], ['a']], sim_func=Jaro().get_raw_score, threshold=0.8)
>>> soft_tfidf.get_raw_score(['a', 'b', 'a'], ['a', 'c'])
0.17541160386140586
>>> soft_tfidf = SoftTfIdf([['a', 'b', 'a'], ['a', 'c'], ['a']], threshold=0.9)
>>> soft_tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.5547001962252291
>>> soft_tfidf = SoftTfIdf([['x', 'y'], ['w'], ['q']])
>>> soft_tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.0
>>> soft_tfidf = SoftTfIdf(sim_func=Affine().get_raw_score, threshold=0.6)
>>> soft_tfidf.get_raw_score(['aa', 'bb', 'a'], ['ab', 'ba'])
0.81649658092772592
References:
* the string matching chapter of the "Principles of Data Integration" book.
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# find unique elements in the input lists and their document frequency
local_df = {}
for element in tf_x:
local_df[element] = local_df.get(element, 0) + 1
for element in tf_y:
local_df[element] = local_df.get(element, 0) + 1
# if corpus is not provided treat input string as corpus
curr_df, corpus_size = (local_df, 2) if self.__corpus_list is None else (
(self.__document_frequency, self.__corpus_size))
# calculating the term sim score against the input string 2,
# construct similarity map
similarity_map = {}
for term_x in tf_x:
max_score = 0.0
for term_y in tf_y:
score = self.sim_func(term_x, term_y)
# adding sim only if it is above threshold and
# highest for this element
if score > self.threshold and score > max_score:
similarity_map[term_x] = (term_x, term_y, score)
max_score = score
# position of first string, second string and sim score
# in the tuple
first_string_pos = 0
second_string_pos = 1
sim_score_pos = 2
result, v_x_2, v_y_2 = 0.0, 0.0, 0.0
# soft-tfidf calculation
for element in local_df.keys():
if curr_df.get(element) is None:
continue
# numerator
if element in similarity_map:
sim = similarity_map[element]
idf_first = corpus_size / curr_df.get(sim[first_string_pos], 1)
idf_second = corpus_size / curr_df.get(sim[second_string_pos], 1)
v_x = log(idf_first) * log(tf_x.get(sim[first_string_pos], 0) + 1) if self.dampen else idf_first * tf_x.get(sim[first_string_pos], 0)
v_y = log(idf_second) * log(tf_y.get(sim[second_string_pos], 0) + 1) if self.dampen else idf_second * tf_y.get(sim[second_string_pos], 0)
result += v_x * v_y * sim[sim_score_pos]
# denominator
idf = corpus_size / curr_df[element]
v_x = log(idf) * log(tf_x.get(element, 0) + 1) if self.dampen else idf * tf_x.get(element, 0)
v_x_2 += v_x * v_x
v_y = log(idf) * log(tf_y.get(element, 0) + 1) if self.dampen else idf * tf_y.get(element, 0)
v_y_2 += v_y * v_y
return result if v_x_2 == 0 else result / (sqrt(v_x_2) * sqrt(v_y_2))
def get_raw_score(self, string1, string2):
"""
Computes the editex distance between two strings.
As described on pages 3 & 4 of
Zobel, Justin and Philip Dart. 1996. Phonetic string matching: Lessons from
information retrieval. In: Proceedings of the ACM-SIGIR Conference on
Research and Development in Information Retrieval, Zurich, Switzerland.
166–173. http://goanna.cs.rmit.edu.au/~jz/fulltext/sigir96.pdf
The local variant is based on
Ring, Nicholas and Alexandra L. Uitdenbogerd. 2009. Finding ‘Lucy in
Disguise’: The Misheard Lyric Matching Problem. In: Proceedings of the 5th
Asia Information Retrieval Symposium, Sapporo, Japan. 157-167.
http://www.seg.rmit.edu.au/research/download.php?manuscript=404
Args:
string1,string2 (str): Input strings
Returns:
Editex distance (int)
Raises:
TypeError : If the inputs are not strings
Examples:
>>> ed = Editex()
>>> ed.get_raw_score('cat', 'hat')
2
>>> ed.get_raw_score('Niall', 'Neil')
2
>>> ed.get_raw_score('aluminum', 'Catalan')
12
>>> ed.get_raw_score('ATCG', 'TAGC')
6
References:
* Abydos Library - https://github.com/chrislit/abydos/blob/master/abydos/distance.py
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0
# convert both the strings to NFKD normalized unicode
string1 = unicodedata.normalize('NFKD', text_type(string1.upper()))
string2 = unicodedata.normalize('NFKD', text_type(string2.upper()))
# convert ß to SS (for Python2)
string1 = string1.replace('ß', 'SS')
string2 = string2.replace('ß', 'SS')
if len(string1) == 0:
return len(string2) * self.mismatch_cost
if len(string2) == 0:
return len(string1) * self.mismatch_cost
d_mat = np.zeros((len(string1) + 1, len(string2) + 1), dtype=np.int)
len1 = len(string1)
len2 = len(string2)
string1 = ' ' + string1
string2 = ' ' + string2
editex_helper = EditexHelper(self.match_cost, self.mismatch_cost,
self.group_cost)
if not self.local:
for i in xrange(1, len1 + 1):
d_mat[i, 0] = d_mat[i - 1, 0] + editex_helper.d_cost(
string1[i - 1], string1[i])
for j in xrange(1, len2 + 1):
d_mat[0, j] = d_mat[0, j - 1] + editex_helper.d_cost(string2[j - 1],
string2[j])
for i in xrange(1, len1 + 1):
for j in xrange(1, len2 + 1):
d_mat[i, j] = min(d_mat[i - 1, j] + editex_helper.d_cost(
string1[i - 1], string1[i]),
d_mat[i, j - 1] + editex_helper.d_cost(
string2[j - 1], string2[j]),
d_mat[i - 1, j - 1] + editex_helper.r_cost(
string1[i], string2[j]))
return d_mat[len1, len2]
def tfidf(bag1, bag2, corpus_list=None, dampen=False):
"""
Compute tfidf measures between two lists given the corpus information.
This measure employs the notion of TF/IDF score commonly used in information retrieval (IR) to find documents that
are relevant to keyword queries.
The intuition underlying the TF/IDF measure is that two strings are similar if they share distinguishing terms.
Args:
bag1,bag2 (list): Input lists
corpus_list (list of lists): Corpus list (default is set to None) of strings. If set to None,
the input list are considered the only corpus.
dampen (boolean): Flag to indicate whether 'log' should be applied to tf and idf measure.
Returns:
TF-IDF measure between the input lists (float)
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None
Examples:
>>> tfidf(['a', 'b', 'a'], ['a', 'c'], [['a', 'b', 'a'], ['a', 'c'], ['a']])
0.17541160386140586
>>> tfidf(['a', 'b', 'a'], ['a', 'c'], [['a', 'b', 'a'], ['a', 'c'], ['a'], ['b']], True)
0.11166746710505392
>>> tfidf(['a', 'b', 'a'], ['a'], [['a', 'b', 'a'], ['a', 'c'], ['a']])
0.5547001962252291
>>> tfidf(['a', 'b', 'a'], ['a'], [['x', 'y'], ['w'], ['q']])
0.0
>>> tfidf(['a', 'b', 'a'], ['a'], [['x', 'y'], ['w'], ['q']], True)
0.0
>>> tfidf(['a', 'b', 'a'], ['a'])
0.7071067811865475
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# if corpus is not provided treat input string as corpus
if corpus_list is None:
corpus_list = [bag1, bag2]
corpus_size = len(corpus_list)
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# number of documents an element appeared
element_freq = {}
# set of unique element
total_unique_elements = set()
for document in corpus_list:
temp_set = set()
for element in document:
# adding element only if it is present in one of two input string
if element in bag1 or element in bag2:
temp_set.add(element)
total_unique_elements.add(element)
# update element document frequency for this document
for element in temp_set:
element_freq[element] = element_freq[element] + 1 if element in element_freq else 1
idf_element, v_x, v_y, v_x_y, v_x_2, v_y_2 = 0.0, 0.0, 0.0, 0.0, 0.0, 0.0
# tfidf calculation
for element in total_unique_elements:
idf_element = corpus_size * 1.0 / element_freq[element]
v_x = 0 if element not in tf_x else (math.log(idf_element) * math.log(tf_x[element] + 1)) if dampen else (
idf_element * tf_x[element])
v_y = 0 if element not in tf_y else (math.log(idf_element) * math.log(tf_y[element] + 1)) if dampen else (
idf_element * tf_y[element])
v_x_y += v_x * v_y
v_x_2 += v_x * v_x
v_y_2 += v_y * v_y
return 0.0 if v_x_y == 0 else v_x_y / (math.sqrt(v_x_2) * math.sqrt(v_y_2))
def get_raw_score(self, string1, string2):
"""
Computes the Soundex phonetic similarity between two strings.
Phonetic measure such as soundex match string based on their sound. These
measures have been especially effective in matching names, since names are
often spelled in different ways that sound the same. For example, Meyer, Meier,
and Mire sound the same, as do Smith, Smithe, and Smythe.
Soundex is used primarily to match surnames. It does not work as well for names
of East Asian origins, because much of the discriminating power of these names
resides in the vowel sounds, which the code ignores.
Args:
string1,string2 (str): Input strings
Returns:
Soundex similarity score (int) is returned
Raises:
TypeError : If the inputs are not strings
Examples:
>>> s = Soundex()
>>> s.get_raw_score('Robert', 'Rupert')
1
>>> s.get_raw_score('Sue', 's')
1
>>> s.get_raw_score('Gough', 'Goff')
0
>>> s.get_raw_score('a,,li', 'ali')
1
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
# remove all chars but alphanumeric characters
string1 = re.sub("[^a-zA-Z0-9]", "", string1)
string2 = re.sub("[^a-zA-Z0-9]", "", string2)
utils.sim_check_for_zero_len(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 1
string1, string2 = string1.upper(), string2.upper()
first_letter1, first_letter2 = string1[0], string2[0]
string1, string2 = string1[1:], string2[1:]
# remove occurrences of vowels, 'y', 'w' and 'h'
string1 = re.sub('[AEIOUYWH]', '', string1)
string2 = re.sub('[AEIOUYWH]', '', string2)
# replace (B,F,P,V)->1 (C,G,J,K,Q,S,X,Z)->2 (D,T)->3 (L)->4
# (M,N)->5 (R)->6
string1 = re.sub('[BFPV]', '1', string1)
string1 = re.sub('[CGJKQSXZ]', '2', string1)
string1 = re.sub('[DT]', '3', string1)
string1 = re.sub('[L]', '4', string1)
string1 = re.sub('[MN]', '5', string1)
string1 = re.sub('[R]', '6', string1)
string2 = re.sub('[BFPV]', '1', string2)
string2 = re.sub('[CGJKQSXZ]', '2', string2)
string2 = re.sub('[DT]', '3', string2)
string2 = re.sub('[L]', '4', string2)
string2 = re.sub('[MN]', '5', string2)
string2 = re.sub('[R]', '6', string2)
string1 = first_letter1 + string1[:3]
string2 = first_letter2 + string2[:3]
return 1 if string1 == string2 else 0
def get_raw_score(self, bag1, bag2):
"""Computes the raw soft TF/IDF score between two lists given the corpus information.
Args:
bag1,bag2 (list): Input lists
Returns:
Soft TF/IDF score between the input lists (float).
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> soft_tfidf = SoftTfIdf([['a', 'b', 'a'], ['a', 'c'], ['a']], sim_func=Jaro().get_raw_score, threshold=0.8)
>>> soft_tfidf.get_raw_score(['a', 'b', 'a'], ['a', 'c'])
0.17541160386140586
>>> soft_tfidf = SoftTfIdf([['a', 'b', 'a'], ['a', 'c'], ['a']], threshold=0.9)
>>> soft_tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.5547001962252291
>>> soft_tfidf = SoftTfIdf([['x', 'y'], ['w'], ['q']])
>>> soft_tfidf.get_raw_score(['a', 'b', 'a'], ['a'])
0.0
>>> soft_tfidf = SoftTfIdf(sim_func=Affine().get_raw_score, threshold=0.6)
>>> soft_tfidf.get_raw_score(['aa', 'bb', 'a'], ['ab', 'ba'])
0.81649658092772592
References:
* the string matching chapter of the "Principles of Data Integration" book.
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# find unique elements in the input lists and their document frequency
local_df = {}
for element in tf_x:
local_df[element] = local_df.get(element, 0) + 1
for element in tf_y:
local_df[element] = local_df.get(element, 0) + 1
# if corpus is not provided treat input string as corpus
curr_df, corpus_size = (local_df, 2) if self.__corpus_list is None else (
(self.__document_frequency, self.__corpus_size))
# calculating the term sim score against the input string 2,
# construct similarity map
similarity_map = {}
for term_x in tf_x:
max_score = 0.0
for term_y in tf_y:
score = self.sim_func(term_x, term_y)
# adding sim only if it is above threshold and
# highest for this element
if score > self.threshold and score > max_score:
similarity_map[term_x] = (term_x, term_y, score)
max_score = score
# position of first string, second string and sim score
# in the tuple
first_string_pos = 0
second_string_pos = 1
sim_score_pos = 2
result, v_x_2, v_y_2 = 0.0, 0.0, 0.0
# soft-tfidf calculation
for element in local_df.keys():
if curr_df.get(element) is None:
continue
# numerator
if element in similarity_map:
sim = similarity_map[element]
idf_first = corpus_size / curr_df.get(sim[first_string_pos], 1)
idf_second = corpus_size / curr_df.get(sim[second_string_pos], 1)
v_x = idf_first * tf_x.get(sim[first_string_pos], 0)
v_y = idf_second * tf_y.get(sim[second_string_pos], 0)
result += v_x * v_y * sim[sim_score_pos]
# denominator
idf = corpus_size / curr_df[element]
v_x = idf * tf_x.get(element, 0)
v_x_2 += v_x * v_x
v_y = idf * tf_y.get(element, 0)
v_y_2 += v_y * v_y
return result if v_x_2 == 0 else result / (sqrt(v_x_2) * sqrt(v_y_2))
def generalized_jaccard(set1, set2, sim_func=jaro, threshold=0.5):
"""
Computes the Generalized Jaccard measure between two sets.
This similarity measure is softened version of the Jaccard measure. The Jaccard measure is
promising candidate for tokens which exactly match across the sets. However, in practice tokens
are often misspelled, such as energy vs. eneryg. THe generalized Jaccard measure will enable
matching in such cases.
Args:
set1,set2 (set or list): Input sets (or lists) of strings. Input lists are converted to sets.
sim_func (func): similarity function. This should return a similarity score between two strings in set (optional),
default is jaro similarity measure
threshold (float): Threshold value (defaults to 0.5). If the similarity of a token pair exceeds the threshold,
then the token pair is considered a match.
Returns:
Generalized Jaccard similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
ValueError : If the similarity measure doesn't return values in the range [0.1]
Examples:
>>> generalized_jaccard(['data', 'science'], ['data'])
0.5
>>> generalized_jaccard(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
>>> generalized_jaccard(['Niall'], ['Neal', 'Njall'])
0.43333333333333335
>>> generalized_jaccard(['Comp', 'Sci.', 'and', 'Engr', 'Dept.,', 'Universty', 'of', 'Cal,', 'San', 'Deigo'],
['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'],
sim_func=jaro_winkler, threshold=0.8)
0.45810185185185187
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
set1_x = set()
set2_y = set()
match_score = 0.0
match_count = 0
list_matches = []
for element in set1:
for item in set2:
score = sim_func(element, item)
if score > 1 or score < 0:
raise ValueError('Similarity measure should return value in the range [0,1]')
if score > threshold:
list_matches.append(utils.Similarity(element, item, score))
# sort the score of all the pairs
list_matches.sort(key=lambda x: x.similarity_score, reverse=True)
# select score in increasing order of their weightage, do not reselect the same element from either set.
for element in list_matches:
if element.first_string not in set1_x and element.second_string not in set2_y:
set1_x.add(element.first_string)
set2_y.add(element.second_string)
match_score += element.similarity_score
match_count += 1
return float(match_score) / float(len(set1) + len(set2) - match_count)
def soundex(string1, string2):
"""
Computes the Soundex phonetic similarity between two strings.
Phonetic measure such as soundex match string based on their sound. These
measures have been especially effective in matching names, since names are
often spelled in different ways that sound the same. For example, Meyer, Meier,
and Mire sound the same, as do Smith, Smithe, and Smythe.
Soundex is used primarily to match surnames. It does not work as well for names
of East Asian origins, because much of the discriminating power of these names
resides in the vowel sounds, which the code ignores.
Args:
string1,string2 (str): Input strings
Returns:
Soundex similarity score (int) is returned
Raises:
TypeError : If the inputs are not strings
Examples:
>>> soundex('Robert', 'Rupert')
1
>>> soundex('Sue', 's')
1
>>> soundex('Gough', 'Goff')
0
>>> soundex('a,,li', 'ali')
1
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 1
utils.sim_check_for_zero_len(string1, string2)
string1, string2 = string1.upper(), string2.upper()
firstLetter1, firstLetter2 = string1[0], string2[0]
string1, string2 = string1[1:], string2[1:]
# remove occurrences of vowels, 'y', 'w' and 'h'
string1 = re.sub('[AEIOUYWH]', '', string1)
string2 = re.sub('[AEIOUYWH]', '', string2)
# replace (B,F,P,V)->1 (C,G,J,K,Q,S,X,Z)->2 (D,T)->3 (L)->4 (M,N)->5 (R)->6
string1 = re.sub('[BFPV]', '1', string1)
string1 = re.sub('[CGJKQSXZ]', '2', string1)
string1 = re.sub('[DT]', '3', string1)
string1 = re.sub('[L]', '4', string1)
string1 = re.sub('[MN]', '5', string1)
string1 = re.sub('[R]', '6', string1)
string2 = re.sub('[BFPV]', '1', string2)
string2 = re.sub('[CGJKQSXZ]', '2', string2)
string2 = re.sub('[DT]', '3', string2)
string2 = re.sub('[L]', '4', string2)
string2 = re.sub('[MN]', '5', string2)
string2 = re.sub('[R]', '6', string2)
# remove all chars but digits
string1 = re.sub("\D", "", string1)
string2 = re.sub("\D", "", string2)
string1 = firstLetter1 + string1[:3]
string2 = firstLetter2 + string2[:3]
return 1 if string1 == string2 else 0
def editex(string1, string2, match_cost=0, group_cost=1, mismatch_cost=2, local=False):
"""
Computes the editex distance between two strings.
As described on pages 3 & 4 of
Zobel, Justin and Philip Dart. 1996. Phonetic string matching: Lessons from
information retrieval. In: Proceedings of the ACM-SIGIR Conference on
Research and Development in Information Retrieval, Zurich, Switzerland.
166–173. http://goanna.cs.rmit.edu.au/~jz/fulltext/sigir96.pdf
The local variant is based on
Ring, Nicholas and Alexandra L. Uitdenbogerd. 2009. Finding ‘Lucy in
Disguise’: The Misheard Lyric Matching Problem. In: Proceedings of the 5th
Asia Information Retrieval Symposium, Sapporo, Japan. 157-167.
http://www.seg.rmit.edu.au/research/download.php?manuscript=404
Args:
string1,string2 (str): Input strings
match_cost (int): Weight to give the correct char match, default=0
group_cost (int): Weight to give if the chars are in the same editex group, default=1
mismatch_cost (int): Weight to give the incorrect char match, default=2
local (boolean): Local variant on/off, default=False
Returns:
Editex distance (int)
Raises:
TypeError : If the inputs are not strings
Examples:
>>> editex('cat', 'hat')
2
>>> editex('Niall', 'Neil')
2
>>> editex('aluminum', 'Catalan')
12
>>> editex('ATCG', 'TAGC')
6
References:
* Abydos Library - https://github.com/chrislit/abydos/blob/master/abydos/distance.py
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0
# convert both the strings to NFKD normalized unicode
string1 = unicodedata.normalize('NFKD', _unicode(string1.upper()))
string2 = unicodedata.normalize('NFKD', _unicode(string2.upper()))
# convert ß to SS (for Python2)
string1 = string1.replace('ß', 'SS')
string2 = string2.replace('ß', 'SS')
if string1 == string2:
return 0
if len(string1) == 0:
return len(string2) * mismatch_cost
if len(string2) == 0:
return len(string1) * mismatch_cost
d_mat = np.zeros((len(string1) + 1, len(string2) + 1), dtype=np.int)
len1 = len(string1)
len2 = len(string2)
string1 = ' ' + string1
string2 = ' ' + string2
editex_helper = utils.Editex(match_cost, mismatch_cost, group_cost)
if not local:
for i in _range(1, len1 + 1):
d_mat[i, 0] = d_mat[i - 1, 0] + editex_helper.d_cost(string1[i - 1], string1[i])
for j in _range(1, len2 + 1):
d_mat[0, j] = d_mat[0, j - 1] + editex_helper.d_cost(string2[j - 1], string2[j])
for i in _range(1, len1 + 1):
for j in _range(1, len2 + 1):
d_mat[i, j] = min(d_mat[i - 1, j] + editex_helper.d_cost(string1[i - 1], string1[i]),
d_mat[i, j - 1] + editex_helper.d_cost(string2[j - 1], string2[j]),
d_mat[i - 1, j - 1] + editex_helper.r_cost(string1[i], string2[j]))
return d_mat[len1, len2]
def soft_tfidf(bag1, bag2, corpus_list=None, sim_func=jaro, threshold=0.5):
"""
Compute Soft-tfidf measures between two lists given the corpus information.
Args:
bag1,bag2 (list): Input lists
corpus_list (list of lists): Corpus list (default is set to None) of strings. If set to None,
the input list are considered the only corpus
sim_func (func): Secondary similarity function. This should return a similarity score between two strings (optional),
default is jaro similarity measure
threshold (float): Threshold value for the secondary similarity function (defaults to 0.5). If the similarity
of a token pair exceeds the threshold, then the token pair is considered a match.
Returns:
Soft TF-IDF measure between the input lists
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> soft_tfidf(['a', 'b', 'a'], ['a', 'c'], [['a', 'b', 'a'], ['a', 'c'], ['a']], sim_func=jaro, threshold=0.8)
0.17541160386140586
>>> soft_tfidf(['a', 'b', 'a'], ['a'], [['a', 'b', 'a'], ['a', 'c'], ['a']], threshold=0.9)
0.5547001962252291
>>> soft_tfidf(['a', 'b', 'a'], ['a'], [['x', 'y'], ['w'], ['q']])
0.0
>>> soft_tfidf(['aa', 'bb', 'a'], ['ab', 'ba'], sim_func=affine, threshold=0.6)
0.81649658092772592
References:
* Principles of Data Integration book
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# if corpus is not provided treat input string as corpus
if corpus_list is None:
corpus_list = [bag1, bag2]
corpus_size = len(corpus_list) * 1.0
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# number of documents an element appeared
element_freq = {}
# set of unique element
total_unique_elements = set()
for document in corpus_list:
temp_set = set()
for element in document:
# adding element only if it is present in one of two input string
if element in bag1 or element in bag2:
temp_set.add(element)
total_unique_elements.add(element)
# update element document frequency for this document
for element in temp_set:
element_freq[element] = element_freq[element] + 1 if element in element_freq else 1
similarity_map = {}
# calculating the term sim score against the input string 2, construct similarity map
for x in bag1:
if x not in similarity_map:
max_score = 0.0
for y in bag2:
score = sim_func(x, y)
# adding sim only if it is above threshold and highest for this element
if score > threshold and score > max_score:
similarity_map[x] = utils.Similarity(x, y, score)
max_score = score
result, v_x_2, v_y_2 = 0.0, 0.0, 0.0
# soft-tfidf calculation
for element in total_unique_elements:
# numerator
if element in similarity_map:
sim = similarity_map[element]
idf_first = corpus_size if sim.first_string not in element_freq else corpus_size / \
element_freq[sim.first_string]
idf_second = corpus_size if sim.second_string not in element_freq else corpus_size / \
element_freq[sim.second_string]
v_x = 0 if sim.first_string not in tf_x else idf_first * tf_x[sim.first_string]
v_y = 0 if sim.second_string not in tf_y else idf_second * tf_y[sim.second_string]
result += v_x * v_y * sim.similarity_score
# denominator
idf = corpus_size if element not in element_freq else corpus_size / element_freq[element]
v_x = 0 if element not in tf_x else idf * tf_x[element]
v_x_2 += v_x * v_x
v_y = 0 if element not in tf_y else idf * tf_y[element]
v_y_2 += v_y * v_y
return result if v_x_2 == 0 else result / (math.sqrt(v_x_2) * math.sqrt(v_y_2))
def get_raw_score(self, set1, set2):
"""
Computes the Generalized Jaccard measure between two sets.
This similarity measure is softened version of the Jaccard measure. The Jaccard measure is
promising candidate for tokens which exactly match across the sets. However, in practice tokens
are often misspelled, such as energy vs. eneryg. THe generalized Jaccard measure will enable
matching in such cases.
Args:
set1,set2 (set or list): Input sets (or lists) of strings. Input lists are converted to sets.
Returns:
Generalized Jaccard similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
ValueError : If the similarity measure doesn't return values in the range [0,1]
Examples:
>>> gj = GeneralizedJaccard()
>>> gj.get_raw_score(['data', 'science'], ['data'])
0.5
>>> gj.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
>>> gj.get_raw_score(['Niall'], ['Neal', 'Njall'])
0.43333333333333335
>>> gj = GeneralizedJaccard(sim_func=JaroWinkler().get_raw_score, threshold=0.8)
>>> gj.get_raw_score(['Comp', 'Sci.', 'and', 'Engr', 'Dept.,', 'Universty', 'of', 'Cal,', 'San', 'Deigo'],
['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
0.45810185185185187
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
set1_x = set()
set2_y = set()
match_score = 0.0
match_count = 0
list_matches = []
for element in set1:
for item in set2:
score = self.sim_func(element, item)
if score > 1 or score < 0:
raise ValueError('Similarity measure should' + \
' return value in the range [0,1]')
if score > self.threshold:
list_matches.append((element, item, score))
# position of first string, second string and sim score in tuple
first_string_pos = 0
second_string_pos = 1
sim_score_pos = 2
# sort the score of all the pairs
list_matches.sort(key=lambda x: x[sim_score_pos], reverse=True)
# select score in increasing order of their weightage,
# do not reselect the same element from either set.
for element in list_matches:
if (element[first_string_pos] not in set1_x
and element[second_string_pos] not in set2_y):
set1_x.add(element[first_string_pos])
set2_y.add(element[second_string_pos])
match_score += element[sim_score_pos]
match_count += 1
return float(match_score) / float(len(set1) + len(set2) - match_count)
def levenshtein(string1, string2):
"""
Computes the Levenshtein distance between two strings.
Levenshtein distance computes the minimum cost of transforming one string into the other. Transforming a string
is carried out using a sequence of the following operators: delete a character, insert a character, and
substitute one character for another.
Args:
string1,string2 (str): Input strings
Returns:
Levenshtein distance (int)
Raises:
TypeError : If the inputs are not strings
Examples:
>>> levenshtein('a', '')
1
>>> levenshtein('example', 'samples')
3
>>> levenshtein('levenshtein', 'frankenstein')
6
"""
# input validations
utils.sim_check_for_none(string1, string2)
utils.sim_check_for_string_inputs(string1, string2)
if utils.sim_check_for_exact_match(string1, string2):
return 0.0
ins_cost, del_cost, sub_cost, trans_cost = (1, 1, 1, 1)
len_str1 = len(string1)
len_str2 = len(string2)
if len_str1 == 0:
return len_str2 * ins_cost
if len_str2 == 0:
return len_str1 * del_cost
d_mat = np.zeros((len_str1 + 1, len_str2 + 1), dtype=np.int)
for i in _range(len_str1 + 1):
d_mat[i, 0] = i * del_cost
for j in _range(len_str2 + 1):
d_mat[0, j] = j * ins_cost
for i in _range(len_str1):
for j in _range(len_str2):
d_mat[i + 1, j + 1] = min(
d_mat[i + 1, j] + ins_cost,
d_mat[i, j + 1] + del_cost,
d_mat[i, j] + (sub_cost if string1[i] != string2[j] else 0)
)
return d_mat[len_str1, len_str2]
def soft_tfidf(bag1, bag2, corpus_list=None, sim_func=jaro, threshold=0.5):
"""
Compute Soft-tfidf measures between two lists given the corpus information.
Args:
bag1,bag2 (list): Input lists
corpus_list (list of lists): Corpus list (default is set to None) of strings. If set to None,
the input list are considered the only corpus
sim_func (func): Secondary similarity function. This should return a similarity score between two strings (optional),
default is jaro similarity measure
threshold (float): Threshold value for the secondary similarity function (defaults to 0.5). If the similarity
of a token pair exceeds the threshold, then the token pair is considered a match.
Returns:
Soft TF-IDF measure between the input lists
Raises:
TypeError : If the inputs are not lists or if one of the inputs is None.
Examples:
>>> soft_tfidf(['a', 'b', 'a'], ['a', 'c'], [['a', 'b', 'a'], ['a', 'c'], ['a']], sim_func=jaro, threshold=0.8)
0.17541160386140586
>>> soft_tfidf(['a', 'b', 'a'], ['a'], [['a', 'b', 'a'], ['a', 'c'], ['a']], threshold=0.9)
0.5547001962252291
>>> soft_tfidf(['a', 'b', 'a'], ['a'], [['x', 'y'], ['w'], ['q']])
0.0
>>> soft_tfidf(['aa', 'bb', 'a'], ['ab', 'ba'], sim_func=affine, threshold=0.6)
0.81649658092772592
References:
* Principles of Data Integration book
"""
# input validations
utils.sim_check_for_none(bag1, bag2)
utils.sim_check_for_list_or_set_inputs(bag1, bag2)
# if the strings match exactly return 1.0
if utils.sim_check_for_exact_match(bag1, bag2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(bag1, bag2):
return 0
# if corpus is not provided treat input string as corpus
if corpus_list is None:
corpus_list = [bag1, bag2]
corpus_size = len(corpus_list) * 1.0
# term frequency for input strings
tf_x, tf_y = collections.Counter(bag1), collections.Counter(bag2)
# number of documents an element appeared
element_freq = {}
# set of unique element
total_unique_elements = set()
for document in corpus_list:
temp_set = set()
for element in document:
# adding element only if it is present in one of two input string
if element in bag1 or element in bag2:
temp_set.add(element)
total_unique_elements.add(element)
# update element document frequency for this document
for element in temp_set:
element_freq[element] = element_freq[element] + 1 if element in element_freq else 1
similarity_map = {}
# calculating the term sim score against the input string 2, construct similarity map
for x in bag1:
if x not in similarity_map:
max_score = 0.0
for y in bag2:
score = sim_func(x, y)
# adding sim only if it is above threshold and highest for this element
if score > threshold and score > max_score:
similarity_map[x] = utils.Similarity(x, y, score)
max_score = score
result, v_x_2, v_y_2 = 0.0, 0.0, 0.0
# soft-tfidf calculation
for element in total_unique_elements:
# numerator
if element in similarity_map:
sim = similarity_map[element]
idf_first = corpus_size if sim.first_string not in element_freq else corpus_size / \
element_freq[sim.first_string]
idf_second = corpus_size if sim.second_string not in element_freq else corpus_size / \
element_freq[sim.second_string]
v_x = 0 if sim.first_string not in tf_x else idf_first * tf_x[sim.first_string]
v_y = 0 if sim.second_string not in tf_y else idf_second * tf_y[sim.second_string]
result += v_x * v_y * sim.similarity_score
# denominator
idf = corpus_size if element not in element_freq else corpus_size / element_freq[element]
v_x = 0 if element not in tf_x else idf * tf_x[element]
v_x_2 += v_x * v_x
v_y = 0 if element not in tf_y else idf * tf_y[element]
v_y_2 += v_y * v_y
return result if v_x_2 == 0 else result / (math.sqrt(v_x_2) * math.sqrt(v_y_2))
def get_raw_score(self, set1, set2):
"""
Computes the Generalized Jaccard measure between two sets.
This similarity measure is softened version of the Jaccard measure. The Jaccard measure is
promising candidate for tokens which exactly match across the sets. However, in practice tokens
are often misspelled, such as energy vs. eneryg. THe generalized Jaccard measure will enable
matching in such cases.
Args:
set1,set2 (set or list): Input sets (or lists) of strings. Input lists are converted to sets.
Returns:
Generalized Jaccard similarity (float)
Raises:
TypeError : If the inputs are not sets (or lists) or if one of the inputs is None.
ValueError : If the similarity measure doesn't return values in the range [0,1]
Examples:
>>> gj = GeneralizedJaccard()
>>> gj.get_raw_score(['data', 'science'], ['data'])
0.5
>>> gj.get_raw_score(['data', 'management'], ['data', 'data', 'science'])
0.3333333333333333
>>> gj.get_raw_score(['Niall'], ['Neal', 'Njall'])
0.43333333333333335
>>> gj = GeneralizedJaccard(sim_func=JaroWinkler().get_raw_score, threshold=0.8)
>>> gj.get_raw_score(['Comp', 'Sci.', 'and', 'Engr', 'Dept.,', 'Universty', 'of', 'Cal,', 'San', 'Deigo'],
['Department', 'of', 'Computer', 'Science,', 'Univ.', 'Calif.,', 'San', 'Diego'])
0.45810185185185187
"""
# input validations
utils.sim_check_for_none(set1, set2)
utils.sim_check_for_list_or_set_inputs(set1, set2)
# if exact match return 1.0
if utils.sim_check_for_exact_match(set1, set2):
return 1.0
# if one of the strings is empty return 0
if utils.sim_check_for_empty(set1, set2):
return 0
if not isinstance(set1, set):
set1 = set(set1)
if not isinstance(set2, set):
set2 = set(set2)
set1_x = set()
set2_y = set()
match_score = 0.0
match_count = 0
list_matches = []
for element in set1:
for item in set2:
score = self.sim_func(element, item)
if score > 1 or score < 0:
raise ValueError('Similarity measure should' + \
' return value in the range [0,1]')
if score > self.threshold:
list_matches.append((element, item, score))
# position of first string, second string and sim score in tuple
first_string_pos = 0
second_string_pos = 1
sim_score_pos = 2
# sort the score of all the pairs
list_matches.sort(key=lambda x: x[sim_score_pos], reverse=True)
# select score in increasing order of their weightage,
# do not reselect the same element from either set.
for element in list_matches:
if (element[first_string_pos] not in set1_x and
element[second_string_pos] not in set2_y):
set1_x.add(element[first_string_pos])
set2_y.add(element[second_string_pos])
match_score += element[sim_score_pos]
match_count += 1
return float(match_score) / float(len(set1) + len(set2) - match_count)
