class Tests(WithTempDir):
def setUp(self):
WithTempDir.setUp(self)
self.lex = LexStat(test_data('KSL.qlc'))
self.part = Partial(test_data('partial_cognates.tsv'),
segments='segments')
self.part.add_entries('pid1', 'partial_cognate_sets', lambda x: x)
self.part.add_entries('pid2', 'partialids2',
lambda x: [int(y) for y in x.split(' ')])
def test_bcubes(self):
from lingpy.evaluate.acd import bcubes
res = bcubes(self.lex, test='cogid', pprint=False)
self.assertAlmostEquals(res, (1.0, 1.0, 1.0))
res = bcubes(self.lex, 'cogid', 'cogid', pprint=True, per_concept=True)
def test_partial_bcubes(self):
from lingpy.evaluate.acd import partial_bcubes
res = partial_bcubes(self.part, 'pid1', 'pid2', pprint=False)
assert [round(x, 2) for x in res] == [0.92, 0.98, 0.95]
res = partial_bcubes(self.part, 'pid1', 'pid2', pprint=True)
def test_pairs(self):
from lingpy.evaluate.acd import pairs
res = pairs(self.lex, test='cogid', pprint=False)
self.assertAlmostEquals(res, (1.0, 1.0, 1.0))
def test_diff(self):
from lingpy.evaluate.acd import diff
res = diff(self.lex, test='cogid', tofile=False, pprint=False)
self.assertAlmostEquals(res, ((1.0, 1.0, 1.0), (1.0, 1.0, 1.0)))
self.lex.add_entries('cugid', 'cogid', lambda x: x + 1
if x % 2 else x * x)
d1 = diff(self.lex,
gold='cogid',
test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False)
d2 = diff(self.lex,
gold='cugid',
test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False,
tofile=False)
d3 = diff(self.lex,
gold='cugid',
test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False,
tofile=True)
assert d2[0] != 1
class Tests(WithTempDir):
def setUp(self):
WithTempDir.setUp(self)
self.lex = LexStat(test_data('KSL.qlc'))
self.part = Partial(test_data('partial_cognates.tsv'),
segments='segments')
self.part.add_entries('pid1', 'partial_cognate_sets', lambda x: x)
self.part.add_entries('pid2', 'partialids2',
lambda x: [int(y) for y in x.split(' ')])
def test_bcubes(self):
res = bcubes(self.lex, test='cogid', pprint=False)
self.assertAlmostEqual(res, (1.0, 1.0, 1.0))
_ = bcubes(self.lex, 'cogid', 'cogid', pprint=True, per_concept=True)
def test_partial_bcubes(self):
res = partial_bcubes(self.part, 'pid1', 'pid2', pprint=False)
assert [round(x, 2) for x in res] == [0.92, 0.98, 0.95]
_ = partial_bcubes(self.part, 'pid1', 'pid2', pprint=True)
def test_pairs(self):
res = pairs(self.lex, test='cogid', pprint=False)
self.assertAlmostEqual(res, (1.0, 1.0, 1.0))
def test_diff(self):
res = diff(self.lex, test='cogid', tofile=False, pprint=False)
self.assertAlmostEqual(res, ((1.0, 1.0, 1.0), (1.0, 1.0, 1.0)))
self.lex.add_entries('cugid', 'cogid',
lambda x: x + 1 if x % 2 else x * x)
_ = diff(self.lex, gold='cogid', test='cogid',
filename='%s' % self.tmp_path('test_acd'), pprint=False)
d2 = diff(self.lex, gold='cugid', test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False, tofile=False)
_ = diff(self.lex, gold='cugid', test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False, tofile=True)
assert d2[0] != 1
def test_random_cognates(self):
random_cognates(self.lex, ref='randomid')
assert 'randomid' in self.lex.header
def test_extreme_cognates(self):
extreme_cognates(self.lex, ref="lumperid", bias='lumper')
assert self.lex[1, 'lumperid'] == self.lex[2, 'lumperid']
extreme_cognates(self.lex, ref='splitterid', bias='splitter')
assert self.lex[1, 'splitterid'] != self.lex[2, 'splitterid']
assert_raises(ValueError, extreme_cognates, self.lex, bias='')
class Tests(WithTempDir):
def setUp(self):
WithTempDir.setUp(self)
self.lex = LexStat(test_data('KSL.qlc'))
self.part = Partial(test_data('partial_cognates.tsv'),
segments='segments')
self.part.add_entries('pid1', 'partial_cognate_sets', lambda x: x)
self.part.add_entries('pid2', 'partialids2',
lambda x: [int(y) for y in x.split(' ')])
def test_bcubes(self):
res = bcubes(self.lex, test='cogid', pprint=False)
self.assertAlmostEquals(res, (1.0, 1.0, 1.0))
_ = bcubes(self.lex, 'cogid', 'cogid', pprint=True, per_concept=True)
def test_partial_bcubes(self):
res = partial_bcubes(self.part, 'pid1', 'pid2', pprint=False)
assert [round(x, 2) for x in res] == [0.92, 0.98, 0.95]
_ = partial_bcubes(self.part, 'pid1', 'pid2', pprint=True)
def test_pairs(self):
res = pairs(self.lex, test='cogid', pprint=False)
self.assertAlmostEquals(res, (1.0, 1.0, 1.0))
def test_diff(self):
res = diff(self.lex, test='cogid', tofile=False, pprint=False)
self.assertAlmostEquals(res, ((1.0, 1.0, 1.0), (1.0, 1.0, 1.0)))
self.lex.add_entries('cugid', 'cogid',
lambda x: x + 1 if x % 2 else x * x)
_ = diff(self.lex, gold='cogid', test='cogid',
filename='%s' % self.tmp_path('test_acd'), pprint=False)
d2 = diff(self.lex, gold='cugid', test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False, tofile=False)
_ = diff(self.lex, gold='cugid', test='cogid',
filename='%s' % self.tmp_path('test_acd'),
pprint=False, tofile=True)
assert d2[0] != 1
def test_random_cognates(self):
random_cognates(self.lex, ref='randomid')
assert 'randomid' in self.lex.header
def test_extreme_cognates(self):
extreme_cognates(self.lex, ref="lumperid", bias='lumper')
assert self.lex[1, 'lumperid'] == self.lex[2, 'lumperid']
extreme_cognates(self.lex, ref='splitterid', bias='splitter')
assert self.lex[1, 'splitterid'] != self.lex[2, 'splitterid']
assert_raises(ValueError, extreme_cognates, self.lex, bias='')
class Tests(WithTempDir):
def setUp(self):
WithTempDir.setUp(self)
self.lex = LexStat(test_data('KSL.qlc'))
self.part = Partial(test_data('partial_cognates.tsv'),
segments='segments')
self.part.add_entries('pid1', 'partial_cognate_sets', lambda x: x)
self.part.add_entries('pid2', 'partialids2', lambda x: [int(y)
for y in x.split(' ')])
def test_bcubes(self):
from lingpy.evaluate.acd import bcubes
res = bcubes(self.lex, test='cogid', pprint=False)
self.assertAlmostEquals(res, (1.0, 1.0, 1.0))
res = bcubes(self.lex, 'cogid', 'cogid', pprint=True,
per_concept=True)
def test_partial_bcubes(self):
from lingpy.evaluate.acd import partial_bcubes
res = partial_bcubes(self.part, 'pid1', 'pid2', pprint=False)
assert [round(x, 2) for x in res] == [0.92, 0.98, 0.95]
res = partial_bcubes(self.part, 'pid1', 'pid2', pprint=True)
def test_pairs(self):
from lingpy.evaluate.acd import pairs
res = pairs(self.lex, test='cogid', pprint=False)
self.assertAlmostEquals(res, (1.0, 1.0, 1.0))
def test_diff(self):
from lingpy.evaluate.acd import diff
res = diff(self.lex, test='cogid', tofile=False, pprint=False)
self.assertAlmostEquals(res, ((1.0, 1.0, 1.0), (1.0, 1.0, 1.0)))
self.lex.add_entries('cugid', 'cogid', lambda x: x+1 if x % 2 else x*x)
d1 = diff(self.lex, gold='cogid', test='cogid', filename='%s' % self.tmp_path('test_acd'), pprint=False)
d2 = diff(self.lex, gold='cugid', test='cogid', filename='%s' %
self.tmp_path('test_acd'), pprint=False, tofile=False)
d3 = diff(self.lex, gold='cugid', test='cogid', filename='%s' %
self.tmp_path('test_acd'), pprint=False, tofile=True)
assert d2[0] != 1
def part(test_data):
p = Partial(str(test_data / 'partial_cognates.tsv'), segments='segments')
p.add_entries('pid1', 'partial_cognate_sets', lambda x: x)
p.add_entries('pid2', 'partialids2',
lambda x: [int(y) for y in x.split(' ')])
return p
from lingpy import *
from lingpy.compare.partial import Partial
try:
part = Partial('hm-111-17.bin.tsv', segments='segments')
except:
part = Partial('hm-111-17.tsv', segments='segments')
part.get_scorer(runs=10000)
part.output('tsv', filename='hm-111-17.bin')
# manually correct error in data
part.partial_cluster(method='lexstat',
cluster_method='infomap',
threshold=0.6,
ref='cogids')
part.add_entries('note', 'cogid', lambda x: '')
part.add_entries('morphemes', 'cogid', lambda x: '')
part.output('tsv', filename='hm-111-17-t06', ignore='all', prettify=False)
from lingpy.compare.partial import Partial
from lingpy.convert.plot import plot_tree
from sys import argv
from clldutils.text import strip_brackets, split_text
from collections import defaultdict
from lingpy import basictypes
if 'all' in argv:
fname='../output/A_Deepadung_'
else:
fname='../output/D_Deepadung_'
part = Partial(fname+'crossids.tsv')
part.add_cognate_ids('crossids', 'crossid', idtype='strict')
part.add_entries('cog', 'crossid,concept', lambda x, y: str(x[y[0]])+x[y[1]])
part.renumber('cog')
part.calculate('distance', ref='cogid')
part.calculate('tree', tree_calc='neighbor')
part.output('dst', filename=fname+'distance')
part.output('tre', filename=fname+'tree')
if 'plot' in argv:
plot_tree(str(part.tree), degree=350, filename=fname+'tree')
