def test_setitem(self):
wl = make_wordlist()
with self.assertRaises(ValueError):
wl[1] = []
with self.assertRaises(ValueError):
wl[1, 'id'] = 'x'
def test_get_etymdict(self):
wl = make_wordlist()
self.assertEqual(
wl.get_etymdict(ref='concept'), {
'foot': [['6'], ['7'], ['8'], ['9'], ['10']],
'hand, arm': [['1'], ['2'], ['3'], ['4'], ['5']],
'knee': [['11'], [], [], [], []]
})
def test_run_and_dump(self):
from lingpy3.ops import run_and_dump
from lingpy3.jsonlib import path_from_checksum
with patch('lingpy3.ops.CACHE_DIR', self.tmp_path()):
wl = make_wordlist()
res, checksum = run_and_dump('distances', wl)
run_and_dump('distances', wl, __checksum__=checksum)
self.assertTrue(
path_from_checksum(checksum, outdir=self.tmp_path()).exists())
def test_operation(self):
wl = write('csv',
make_wordlist(),
_outdir=self.tmp_path(),
delimiter=',')
args = '-o {0} operation distances csv:IWordlist:{1}:delimiter=,'.format(
self.tmp_path(), wl)
with capture(cli.main, *args.split()) as out:
self.assertIn('written', out)
self.assertTrue(bool(list(self.tmp_path().glob('*.json'))))
def test_distances(self):
from lingpy3.ops.wordlist import distances
wl = make_wordlist()
self.assertEquals(distances(wl),
[[0, 1.0, 0.5, 1.0, 0.5], [1.0, 0, 1.0, 0.0, 1.0],
[0.5, 1.0, 0, 1.0, 0.0], [1.0, 0.0, 1.0, 0, 1.0],
[0.5, 1.0, 0.0, 1.0, 0]])
self.assertEquals(distances(wl, mode='jaccard'),
[[0, 1.0, 0.75, 1.0, 0.75], [1.0, 0, 0.8, 0.0, 0.8],
[0.75, 0.8, 0, 0.8, 0.0], [1.0, 0.0, 0.8, 0, 0.8],
[0.75, 0.8, 0.0, 0.8, 0]])
distances(wl, mode='shared', refB='x')
# No shared concepts between languages:
rows = [
['1', 'l1', 'hand', 'hand', 'a', 'abera'],
['2', 'l2', 'arm', 'arm', 'b', 'aberb'],
]
distances(make_wordlist(rows=rows))
def test_add_col(self):
wl = make_wordlist()
with self.assertRaises(ValueError):
wl.add_col('id', lambda x: 'x')
wl.add_col('xcol', lambda x: 'x')
self.assertEqual(wl['1', 'xcol'], 'x')
self.assertEqual(wl.header[-1], 'xcol')
with self.assertRaises(ValueError):
wl.add_col('xcol', lambda x: 'x')
wl.add_col('xcol', lambda x: 'y', override=True)
self.assertEqual(wl['1', 'xcol'], 'y')
wl.add_col('zcol', lambda x: x['xcol'])
self.assertEqual(wl['1', 'zcol'], 'y')
wl['1', 'xcol'] = 'z'
self.assertEqual(wl['1', 'xcol'], 'z')
def test_misc(self):
from lingpy3.io import write, read, list_writers_doc, get, list_readers_doc
self.assertTrue(bool(list_readers_doc(IWordlist, self.tmp_path())))
wl = make_wordlist()
out = write('csv',
wl,
_outdir=self.tmp_path(),
_stem='test',
delimiter='\t')
self.assertTrue(out.exists())
wl2 = read('csv', Wordlist, out, delimiter='\t')
self.assertEqual(wl[1], wl2[1])
with out.open(encoding='utf8') as fp:
wl3 = read('csv', IWordlist, fp.read(), delimiter='\t')
self.assertEqual(wl[1], wl3[1])
for name, _, mod in list_writers_doc(wl):
get(name, wl)
scm = registry.get(ISoundClassModel, 'asjp')
self.assertIn('Brown', get('txt', scm))
def test_iter_paps(self):
wl = make_wordlist()
self.assertEqual(list(wl.iter_paps(missing=-1)),
[('a', [1, 1, 1, 1, 1]), ('b', [0, 1, 0, 1, 0]),
('fa', [0, 0, 1, 0, 1]), ('fb', [0, 1, 0, 1, 0]),
('gc', [1, -1, -1, -1, -1])])
def test_get_by_concept(self):
wl = make_wordlist()
self.assertEqual(len(wl.get_by_concept()), 3)
def test_get_by_language(self):
wl = make_wordlist()
self.assertEqual(len(wl.get_by_language()), 5)
self.assertEqual(len(wl.get_by_language(language='l1')), 1)
def test_filter(self):
wl = make_wordlist()
self.assertEqual(len(list(wl.filter(language='l1', concept='knee'))),
1)
def test_get_slices(self):
wl = make_wordlist()
self.assertEqual(wl.get_slices([]), list(wl))
self.assertEqual(wl.get_slices(1)[0], wl[1, 'id'])
def test_init(self):
wl = make_wordlist()
self.assertEqual(wl.concepts, ['foot', 'hand, arm', 'knee'])
# invalid data type for header:
with self.assertRaises(ValueError):
make_wordlist(header=['id', 'concept', 'doculect', 5, 6, 7])
# duplicate column names in header:
with self.assertRaises(ValueError):
make_wordlist(header=['id', 'concept', 'doculect', 'id'])
# missing columns in header:
with self.assertRaises(ValueError):
make_wordlist(header=[])
# row length not matching header length:
with self.assertRaises(ValueError):
make_wordlist(rows=[[1, 2]])
# duplicate row ID:
with self.assertRaises(ValueError):
make_wordlist(rows=[[1, 2, 3, 4, 5, 6], [1, 2, 3, 4, 5, 6]])
def test_dump_load_custom(self):
from lingpy3.jsonlib import load, dump
wl = make_wordlist()
out = dump(wl, outdir=self.tmp_path())
self.assertEqual(wl, load(out, Wordlist))
def test_misc(self):
from lingpy3.ops import run, list_ops_doc
wl = make_wordlist()
self.assertIn('distances', set(spec[0] for spec in list_ops_doc(wl)))
self.assertIsInstance(run('distances', wl), list)