本文整理匯總了Python中preprocess.build_save_vocab方法的典型用法代碼示例。如果您正苦於以下問題：Python preprocess.build_save_vocab方法的具體用法？Python preprocess.build_save_vocab怎麽用？Python preprocess.build_save_vocab使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類preprocess的用法示例。
在下文中一共展示了preprocess.build_save_vocab方法的4個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: dataset_build
# 需要導入模塊: import preprocess [as 別名]
# 或者: from preprocess import build_save_vocab [as 別名]
def dataset_build(self, opt):
fields = onmt.inputters.get_fields("text", 0, 0)
if hasattr(opt, 'src_vocab') and len(opt.src_vocab) > 0:
with codecs.open(opt.src_vocab, 'w', 'utf-8') as f:
f.write('a\nb\nc\nd\ne\nf\n')
if hasattr(opt, 'tgt_vocab') and len(opt.tgt_vocab) > 0:
with codecs.open(opt.tgt_vocab, 'w', 'utf-8') as f:
f.write('a\nb\nc\nd\ne\nf\n')
train_data_files = preprocess.build_save_dataset('train', fields, opt)
preprocess.build_save_vocab(train_data_files, fields, opt)
preprocess.build_save_dataset('valid', fields, opt)
# Remove the generated *pt files.
for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'):
os.remove(pt)
if hasattr(opt, 'src_vocab') and os.path.exists(opt.src_vocab):
os.remove(opt.src_vocab)
if hasattr(opt, 'tgt_vocab') and os.path.exists(opt.tgt_vocab):
os.remove(opt.tgt_vocab) 示例2: dataset_build
# 需要導入模塊: import preprocess [as 別名]
# 或者: from preprocess import build_save_vocab [as 別名]
def dataset_build(self, opt):
fields = onmt.io.get_fields("text", 0, 0)
if hasattr(opt, 'src_vocab') and len(opt.src_vocab) > 0:
with codecs.open(opt.src_vocab, 'w', 'utf-8') as f:
f.write('a\nb\nc\nd\ne\nf\n')
if hasattr(opt, 'tgt_vocab') and len(opt.tgt_vocab) > 0:
with codecs.open(opt.tgt_vocab, 'w', 'utf-8') as f:
f.write('a\nb\nc\nd\ne\nf\n')
train_data_files = preprocess.build_save_dataset('train', fields, opt)
preprocess.build_save_vocab(train_data_files, fields, opt)
preprocess.build_save_dataset('valid', fields, opt)
# Remove the generated *pt files.
for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'):
os.remove(pt)
if hasattr(opt, 'src_vocab') and os.path.exists(opt.src_vocab):
os.remove(opt.src_vocab)
if hasattr(opt, 'tgt_vocab') and os.path.exists(opt.tgt_vocab):
os.remove(opt.tgt_vocab) 示例3: dataset_build
# 需要導入模塊: import preprocess [as 別名]
# 或者: from preprocess import build_save_vocab [as 別名]
def dataset_build(self, opt):
fields = onmt.io.get_fields("text", 0, 0)
train_data_files = preprocess.build_save_dataset('train', fields, opt)
preprocess.build_save_vocab(train_data_files, fields, opt)
preprocess.build_save_dataset('valid', fields, opt)
# Remove the generated *pt files.
for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'):
os.remove(pt) 示例4: dataset_build
# 需要導入模塊: import preprocess [as 別名]
# 或者: from preprocess import build_save_vocab [as 別名]
def dataset_build(self, opt):
fields = onmt.inputters.get_fields("text", 0, 0)
if hasattr(opt, 'src_vocab') and len(opt.src_vocab) > 0:
with codecs.open(opt.src_vocab, 'w', 'utf-8') as f:
f.write('a\nb\nc\nd\ne\nf\n')
if hasattr(opt, 'tgt_vocab') and len(opt.tgt_vocab) > 0:
with codecs.open(opt.tgt_vocab, 'w', 'utf-8') as f:
f.write('a\nb\nc\nd\ne\nf\n')
src_reader = onmt.inputters.str2reader[opt.data_type].from_opt(opt)
tgt_reader = onmt.inputters.str2reader["text"].from_opt(opt)
train_data_files = preprocess.build_save_dataset(
'train', fields, src_reader, tgt_reader, opt)
preprocess.build_save_vocab(train_data_files, fields, opt)
preprocess.build_save_dataset(
'valid', fields, src_reader, tgt_reader, opt)
# Remove the generated *pt files.
for pt in glob.glob(SAVE_DATA_PREFIX + '*.pt'):
os.remove(pt)
if hasattr(opt, 'src_vocab') and os.path.exists(opt.src_vocab):
os.remove(opt.src_vocab)
if hasattr(opt, 'tgt_vocab') and os.path.exists(opt.tgt_vocab):
os.remove(opt.tgt_vocab)