from lexibank_deepadungpalaung import Dataset
from lingpy import *
from lingpy.compare.partial import Partial
from lingpy.evaluate.acd import bcubes
columns=('concept_name', 'language_id',
'value', 'form', 'segments', 'language_glottocode', 'cogid_cognateset_id'
)
namespace=(('concept_name', 'concept'), ('language_id',
'doculect'), ('segments', 'tokens'), ('language_glottocode',
'glottolog'), ('concept_concepticon_id', 'concepticon'),
('language_latitude', 'latitude'), ('language_longitude',
'longitude'), ('cognacy', 'cognacy'),
('cogid_cognateset_id', 'cog'))
part = Partial.from_cldf(Dataset().cldf_dir.joinpath('cldf-metadata.json'),
columns=columns, namespace=namespace)
part.renumber('cog')
method = input('method: ')
# type 'cogid' or 'cog' for method to see a tree based on Deepadung et al.'s
# cognate judgements
if method == 'lexstatcogids':
part.get_partial_scorer(runs=10000)
part.partial_cluster(method='lexstat', ref="lexstatcogids", threshold=0.55)
elif method == 'lexstatcogid':
part.get_scorer(runs=10000)
from lexibank_deepadungpalaung import Dataset
from lingpy import *
wl = Wordlist.from_cldf(Dataset().cldf_dir.joinpath('cldf-metadata.json'))
for idx, tokens in wl.iter_rows('tokens'):
for segment in tokens.n:
if not segment:
print(idx, tokens)
Mmatrix.append(NewM)
return Mmatrix
def average_of_lists(list1, list2, wti, wtj):
list3 = []
for a in range(len(list1)):
summ = (list1[a] * wti + list2[a] * wtj) / (wti + wtj)
list3.append(summ)
return list3
root_node = None
if __name__ == "__main__":
method = input('method: ')
filepath = Dataset().cldf_dir._path('../output/distmat_' + method +
'.csv').resolve()
with open(filepath, encoding="utf-8") as infile:
reader = csv.reader(infile)
lang_names = []
dist_matrix = []
header_row = next(reader)
for row in reader:
lang_names.append(row[0])
dist_matrix.append([float(x) for x in row[1:]])
root_node = UPGMA(dist_matrix, lang_names)
root_XML = XML_node(root_node)
outfilepath = Dataset().cldf_dir._path('../output/tree_' + method +
'.xml').resolve()
with open(outfilepath, encoding='utf-8') as outfile:
outfile.write(root_XML)
from lexibank_deepadungpalaung import Dataset
from lingpy import *
from lingpy.compare.partial import Partial
from lingpy.evaluate.acd import bcubes
columns=('concept_name', 'language_id',
'value', 'form', 'segments', 'language_glottocode', 'cogid_cognateset_id'
)
namespace=(('concept_name', 'concept'), ('language_id',
'doculect'), ('segments', 'tokens'), ('language_glottocode',
'glottolog'), ('concept_concepticon_id', 'concepticon'),
('language_latitude', 'latitude'), ('language_longitude',
'longitude'), ('cognacy', 'cognacy'),
('cogid_cognateset_id', 'cog'))
part = Partial.from_cldf(Dataset().cldf_dir.joinpath('cldf-metadata.json'),
columns=columns, namespace=namespace)
part.renumber('cog')
method = input('method: ')
# type 'cogid' or 'cog' for method to see a tree based on Deepadung et al.'s
# cognate judgements
if method == 'lexstatcogids':
part.get_partial_scorer(runs=10000)
part.partial_cluster(method='lexstat', ref="lexstatcogids", threshold=0.55)
elif method == 'lexstatcogid':
part.get_scorer(runs=10000)
from lingpy import *
from lexibank_deepadungpalaung import Dataset
from lingpy.evaluate.acd import bcubes
ds = Dataset()
wl = Wordlist.from_cldf(ds.dir.joinpath('cldf', 'cldf-metadata.json'),
columns=[
'language_id', 'concept_name', 'value', 'form',
'segments', 'cogid_cognateset_id'
],
namespace=dict([['language_id', 'doculect'],
['concept_name', 'concept'],
['value', 'value'], ['form', 'form'],
['segments', 'tokens'],
['cogid_cognateset_id', 'cog']]))
wl.renumber('cog')
lex = LexStat(wl)
lex.get_scorer(runs=10000)
for i in range(1, 20):
t = i * 0.05
ts = '{0}'.format(int(t * 100 + 0.5))
lex.cluster(method='sca',
threshold=t,
ref='sca_' + ts,
restricted_chars='')
lex.cluster(method='lexstat',
threshold=t,
ref='ls_' + ts,
restricted_chars='')