def Psubs(clsdict, corpus, minlength=3, maxlength=20):
"""
Generate Psubs - the substring completion of a set of pairs.
Psubs is the association between all substrings of the pairs in classdict.
Parameters
----------
clsdict : ClassDict
corpus : Corpus
minlength : int, optional
minimum number of phones for the substrings
maxlength : int, optional
maximum number of phones for the substrings
Returns
-------
Iterator over (FragmentToken, FragmentToken) pairs
"""
sub_pairs = (pairwise_substring_completion(f1, f2, corpus,
minlength,
maxlength)
for f1, f2 in clsdict.iter_pairs(within=True, order=True))
return unique(flatten(sub_pairs))
def test_different(self):
# fragment1 - fragment3
# abcd - fghi
# expected:
# abcd - fghi
# abc - fgh
# bcd - ghi
e = set([(self.pfragments[0], self.pfragments[10]),
(self.pfragments[2], self.pfragments[12]),
(self.pfragments[3], self.pfragments[13])])
p = set(pairwise_substring_completion(self.fragment1,
self.fragment3,
self.ca, 3, 20))
assert(e == p)
def test_same(self):
# fragment1 - fragment2
# abcd - abcd
# expected:
# abcd - abcd
# abc - abc
# bcd - bcd
e = set([(self.pfragments[0], self.pfragments[5]),
(self.pfragments[2], self.pfragments[7]),
(self.pfragments[3], self.pfragments[8])])
p = set(pairwise_substring_completion(self.fragment1,
self.fragment2,
self.ca, 3, 20))
assert(p == e)
def test_different_and_longer(self):
# fragment3 - fragment4
# fghi - abcde
# expected:
# fghi - abcd
# fgh - abc
# ghi - bcd
# fghi - bcde
# fgh - bcd
# ghi - cde
e = set([(self.pfragments[10], self.pfragments[5]),
(self.pfragments[12], self.pfragments[7]),
(self.pfragments[13], self.pfragments[8]),
(self.pfragments[10], self.pfragments[6]),
(self.pfragments[12], self.pfragments[8]),
(self.pfragments[13], self.pfragments[9])])
p = set(pairwise_substring_completion(self.fragment3,
self.fragment4,
self.ca, 3, 20))
assert (e == p)
def test_longer(self):
# fragment1 - fragment4
# abcd - abcde
# expected:
# abcd - abcd
# abc - abc
# bcd - bcd
# abcd - bcde
# abc - bcd
# bcd - cde
e = set([(self.pfragments[0], self.pfragments[5]),
(self.pfragments[2], self.pfragments[7]),
(self.pfragments[3], self.pfragments[8]),
(self.pfragments[0], self.pfragments[6]),
(self.pfragments[2], self.pfragments[8]),
(self.pfragments[3], self.pfragments[9])])
p = set(
pairwise_substring_completion(self.fragment1, self.fragment4,
self.ca, 3, 20))
assert (e == p)
def test_longer(self):
# fragment1 - fragment4
# abcd - abcde
# expected:
# abcd - abcd
# abc - abc
# bcd - bcd
# abcd - bcde
# abc - bcd
# bcd - cde
e = set([(self.pfragments[0], self.pfragments[5]),
(self.pfragments[2], self.pfragments[7]),
(self.pfragments[3], self.pfragments[8]),
(self.pfragments[0], self.pfragments[6]),
(self.pfragments[2], self.pfragments[8]),
(self.pfragments[3], self.pfragments[9])])
p = set(pairwise_substring_completion(self.fragment1,
self.fragment4,
self.ca, 3, 20))
assert (e == p)
def Psubs(clsdict, corpus, minlength=3, maxlength=20):
"""
Generate Psubs - the substring completion of a set of pairs.
Psubs is the association between all substrings of the pairs in classdict.
Parameters
----------
clsdict : ClassDict
corpus : Corpus
minlength : int, optional
minimum number of phones for the substrings
maxlength : int, optional
maximum number of phones for the substrings
Returns
-------
Iterator over (FragmentToken, FragmentToken) pairs
"""
sub_pairs = (pairwise_substring_completion(f1, f2, corpus, minlength,
maxlength)
for f1, f2 in clsdict.iter_pairs(within=True, order=True))
return unique(flatten(sub_pairs))