def parse_toloka_lrwc(lines):
skip_header(lines)
records = parse_tsv(lines)
for record in records:
hyponym, hypernym, genitive, judgement, confidence = record
judgement = parse_judgement(judgement)
confidence = parse_confidence(confidence)
yield LRWCRecord(hyponym, hypernym, genitive, judgement, confidence)
def parse_meta(file, encoding='utf8'):
lines = TextIOWrapper(file, encoding)
rows = parse_tsv(lines)
header = skip_header(rows)
for row in rows:
yield dict(zip(header, row))
def parse_ruadrect(lines):
rows = parse_tsv(lines)
skip_header(rows)
for cells in rows:
yield RuADReCTRecord(*cells)
def parse_simlex(lines):
skip_header(lines)
records = parse_tsv(lines)
for word1, word2, score in records:
score = float(score)
yield SimlexRecord(word1, word2, score)