def pw_align(
seqA,
seqB,
gop=-1,
scale=0.5,
scorer=False,
mode='global',
distance=False,
**keywords):
"""
Align two sequences in various ways.
Parameters
----------
seqA, seqB : {text_type, list, tuple}
The input strings. These should be iterables, so you can use tuples,
lists, or strings.
scorer : dict (default=False)
If set to c{False} a scorer will automatically be calculated,
otherwise, the scorer needs to be passed as a dictionary that covers
all segment matches between the input strings.
gop : int (default=-1)
The gap opening penalty.
scale : float (default=0.5)
The gap extension scale. This scale is similar to the gap extension
penalty, but in contrast to the traditional GEP, it "scales" the gap
opening penalty.
mode : {"global", "local", "dialign", "overlap"} (default="global")
Select between one of the four different alignment modes regularly
implemented in LingPy, see :evobib:`List2012a` for details.
distance : bool (default=False)
If set to c{True} return the distance score following the formula by
:evobib:`Downey2008`. Otherwise, return the basic similarity score.
Examples
--------
Align two words using the dialign algorithm::
>>> seqA = 'fat cat'
>>> seqB = 'catfat'
>>> pw_align(seqA, seqB, mode='dialign')
(['f', 'a', 't', ' ', 'c', 'a', 't', '-', '-', '-'],
['-', '-', '-', '-', 'c', 'a', 't', 'f', 'a', 't'],
3.0)
"""
seqA, seqB = _as_lists(seqA, seqB)
distance = 1 if distance else 0
if not scorer and distance == 0:
scorer = _get_scorer(seqA, seqB)
elif not scorer and distance == 1:
scorer = {}
for a, b in multicombinations2(sorted(set(seqA + seqB))):
scorer[b, a] = scorer[a, b] = 1.0 if a == b else -1.0
# start alignment
return talign.align_pair(seqA, seqB, gop, scale, scorer, mode, distance)
def pw_align(
seqA,
seqB,
gop=-1,
scale=0.5,
scorer=False,
mode='global',
distance=False,
**keywords):
"""
Align two sequences in various ways.
Parameters
----------
seqA, seqB : {text_type, list, tuple}
The input strings. These should be iterables, so you can use tuples,
lists, or strings.
scorer : dict (default=False)
If set to c{False} a scorer will automatically be calculated,
otherwise, the scorer needs to be passed as a dictionary that covers
all segment matches between the input strings.
gop : int (default=-1)
The gap opening penalty.
scale : float (default=0.5)
The gap extension scale. This scale is similar to the gap extension
penalty, but in contrast to the traditional GEP, it "scales" the gap
opening penalty.
mode : {"global", "local", "dialign", "overlap"} (default="global")
Select between one of the four different alignment modes regularly
implemented in LingPy, see :evobib:`List2012a` for details.
distance : bool (default=False)
If set to c{True} return the distance score following the formula by
:evobib:`Downey2008`. Otherwise, return the basic similarity score.
Examples
--------
Align two words using the dialign algorithm::
>>> seqA = 'fat cat'
>>> seqB = 'catfat'
>>> pw_align(seqA, seqB, mode='dialign')
(['f', 'a', 't', ' ', 'c', 'a', 't', '-', '-', '-'],
['-', '-', '-', '-', 'c', 'a', 't', 'f', 'a', 't'],
3.0)
"""
seqA, seqB = _as_lists(seqA, seqB)
distance = 1 if distance else 0
if not scorer and distance == 0:
scorer = _get_scorer(seqA, seqB)
elif not scorer and distance == 1:
scorer = {}
for a, b in multicombinations2(sorted(set(seqA + seqB))):
scorer[b, a] = scorer[a, b] = 1.0 if a == b else -1.0
# start alignment
return talign.align_pair(seqA, seqB, gop, scale, scorer, mode, distance)