def iter_XY(config):
(embeddingconfig, gramconfig, runconfig) = config
embedding = WordEmbedding(embeddingpath(embeddingconfig))
unknown_embedding = None
if not runconfig.filter_unknown:
unknown_embedding = zeros(embedding.values.shape[1])
def embed(gram):
return embedding.embed(gram, unknown_embedding)
with gzip.open(grampath(gramconfig), mode='rt') as f:
for line in f:
line = line.split()
if len(line) == gramconfig.gram_size:
gram = line
lbl = word_to_label(gramconfig.skipwords, '')
elif len(line) != gramconfig.gram_size + 1:
print('Skip length > 1 not supported. Dropping Gram:', *line, file=stderr)
continue
else:
gram = line[ : gramconfig.skippos] + line[gramconfig.skippos + 1 : ]
skip = line[gramconfig.skippos]
lbl = word_to_label(gramconfig.skipwords, skip)
try:
gramvec = embed(gram)
yield gramvec, lbl
except KeyError:
pass
def create_grams(gramconfig):
makedirs('data/grams', exist_ok=True)
corpuspath = config.corpuspath(gramconfig.corpus)
grampath = config.grampath(gramconfig)
if path.isfile(grampath):
return
uncompressed_grampath = str(Path(grampath).parent / Path(grampath).stem)
with gzip.open(corpuspath, mode='rt') as inf:
with open(uncompressed_grampath, mode='wt') as outf: # may overwrite
for line in inf:
c = gramconfig
for gram, skip in iter_grams(line, c.gram_size, c.skipwords, c.skippos, c.filter_skips):
completegram = ' '.join(chain(gram[ : c.skippos], skip, gram[c.skippos : ]))
print(completegram, file=outf)
subprocess.run(['/usr/bin/shuf', '-o', uncompressed_grampath, uncompressed_grampath])
compress(uncompressed_grampath)
