def build_vocab(data: tp.List[tp.List[str]]) -> Dictionary:
d = Dictionary()
for s in data:
for token in s:
d.add_symbol(token)
d.finalize()
return d
def test_finalize(self):
txt = [
"A B C D",
"B C D",
"C D",
"D",
]
ref_ids1 = list(
map(
torch.IntTensor,
[
[4, 5, 6, 7, 2],
[5, 6, 7, 2],
[6, 7, 2],
[7, 2],
],
))
ref_ids2 = list(
map(
torch.IntTensor,
[
[7, 6, 5, 4, 2],
[6, 5, 4, 2],
[5, 4, 2],
[4, 2],
],
))
# build dictionary
d = Dictionary()
for line in txt:
d.encode_line(line, add_if_not_exist=True)
def get_ids(dictionary):
ids = []
for line in txt:
ids.append(dictionary.encode_line(line,
add_if_not_exist=False))
return ids
def assertMatch(ids, ref_ids):
for toks, ref_toks in zip(ids, ref_ids):
self.assertEqual(toks.size(), ref_toks.size())
self.assertEqual(0, (toks != ref_toks).sum().item())
ids = get_ids(d)
assertMatch(ids, ref_ids1)
# check finalized dictionary
d.finalize()
finalized_ids = get_ids(d)
assertMatch(finalized_ids, ref_ids2)
# write to disk and reload
with tempfile.NamedTemporaryFile(mode="w") as tmp_dict:
d.save(tmp_dict.name)
d = Dictionary.load(tmp_dict.name)
reload_ids = get_ids(d)
assertMatch(reload_ids, ref_ids2)
assertMatch(finalized_ids, reload_ids)
def dummy_dictionary(vocab_size, prefix="token_"):
d = Dictionary()
for i in range(vocab_size):
token = prefix + str(i)
d.add_symbol(token)
d.finalize(padding_factor=1) # don't add extra padding symbols
return d
def test_huffman_compresses(self):
data = make_data()
builder = make_code_builder(data)
coder = builder.build_code()
with TemporaryDirectory() as dirname:
prefix = os.path.join(dirname, "huffman")
build_dataset(prefix, data, coder)
prefix_mmap = os.path.join(dirname, "mmap")
mmap_builder = indexed_dataset.make_builder(
indexed_dataset.data_file_path(prefix_mmap),
"mmap",
vocab_size=len(POPULATION),
)
dictionary = Dictionary()
for c in POPULATION:
dictionary.add_symbol(c)
dictionary.finalize()
for sentence in data:
mmap_builder.add_item(dictionary.encode_line(" ".join(sentence)))
mmap_builder.finalize(indexed_dataset.index_file_path(prefix_mmap))
huff_size = os.stat(indexed_dataset.data_file_path(prefix)).st_size
mmap_size = os.stat(indexed_dataset.data_file_path(prefix_mmap)).st_size
self.assertLess(huff_size, mmap_size)
def build_dictionary(cls,
filenames,
workers=1,
threshold=-1,
nwords=-1,
padding_factor=8):
"""Build the dictionary
Args:
filenames (list): list of filenames
workers (int): number of concurrent workers
threshold (int): defines the minimum word count
nwords (int): defines the total number of words in the final dictionary,
including special symbols
padding_factor (int): can be used to pad the dictionary size to be a
multiple of 8, which is important on some hardware (e.g., Nvidia
Tensor Cores).
"""
d = Dictionary()
for filename in filenames:
Dictionary.add_file_to_dictionary(filename, d,
tokenizer.tokenize_line, workers)
d.finalize(threshold=threshold,
nwords=nwords,
padding_factor=padding_factor)
return d
def dummy_dictionary(vocab_size, prefix='token_'):
d = Dictionary()
for i in range(vocab_size):
token = prefix + str(i)
d.add_symbol(token)
d.finalize(padding_factor=1) # don't add extra padding symbols
return d
def main() -> None:
parser = argparse.ArgumentParser(
description="Build vocabulary from corpus data.")
parser.add_argument(
"--corpus-data",
type=str,
required=True,
help=
"The path pattern (glob) to all tokenized corpus files (train, test, val)."
)
parser.add_argument("--langs",
type=str,
required=True,
help="The pre-trained model languages.")
parser.add_argument("--output",
type=str,
required=True,
help="The vocabulary file.")
args = parser.parse_args()
langs = args.langs.split(",")
ft_dict = Dictionary()
for data_path in glob(args.corpus_data):
Dictionary.add_file_to_dictionary(data_path, ft_dict, tokenize_line, 4)
ft_dict.finalize(padding_factor=0)
pad_dict(ft_dict, len(langs) + 1)
ft_dict.save(args.output)
def build_word_dict(word_embed_path):
word_dict = Dictionary()
with open(word_embed_path, 'r') as f:
for line in f:
word = line.split(' ', 1)[0]
word_dict.add_symbol(word)
word_dict.finalize(padding_factor=1)
return word_dict
def build_dict(cls, filenames, word_level=False, workers=1, threshold=-1, nwords=-1, padding_factor=8):
d = Dictionary()
for filename in filenames:
Dictionary.add_file_to_dictionary(filename,
d,
tokenize_line_word if word_level else tokenize_line_char,
workers)
d.finalize(threshold=threshold, nwords=nwords, padding_factor=padding_factor)
return d
def build_sememe_dict(datapath):
sememe_dict = Dictionary()
with open(os.path.join(datapath, 'HowNet.edge'), 'r') as f:
for line in f:
sememes = line.strip().split('\t')[1]
for s in sememes.split():
sememe_dict.add_symbol(s)
sememe_dict.finalize(threshold=5, padding_factor=1)
return sememe_dict
def to_dictionary(self) -> Dictionary:
dictionary = Dictionary(bos=self.bos,
unk=self.unk,
pad=self.pad,
eos=self.eos)
for n in self:
dictionary.add_symbol(n.symbol, n=n.count)
dictionary.finalize()
return dictionary
def get_bnids_dictionary(cls) -> Dictionary:
if cls._bnids_dictionary is None:
src_dictionary = cls.get_offsets_dictionary()
tgt_dictionary = Dictionary()
string_map = cls.get_offset_to_bnids_map()
for idx, wn in enumerate(src_dictionary.symbols):
if wn.startswith('wn:'):
tgt_dictionary.add_symbol(string_map[wn])
tgt_dictionary.finalize()
cls._bnids_dictionary = tgt_dictionary
return cls._bnids_dictionary
def test_finalize(self):
txt = [
'A B C D',
'B C D',
'C D',
'D',
]
ref_ids1 = list(map(torch.IntTensor, [
[4, 5, 6, 7, 2],
[5, 6, 7, 2],
[6, 7, 2],
[7, 2],
]))
ref_ids2 = list(map(torch.IntTensor, [
[7, 6, 5, 4, 2],
[6, 5, 4, 2],
[5, 4, 2],
[4, 2],
]))
# build dictionary
d = Dictionary()
for line in txt:
Tokenizer.tokenize(line, d, add_if_not_exist=True)
def get_ids(dictionary):
ids = []
for line in txt:
ids.append(Tokenizer.tokenize(line, dictionary, add_if_not_exist=False))
return ids
def assertMatch(ids, ref_ids):
for toks, ref_toks in zip(ids, ref_ids):
self.assertEqual(toks.size(), ref_toks.size())
self.assertEqual(0, (toks != ref_toks).sum().item())
ids = get_ids(d)
assertMatch(ids, ref_ids1)
# check finalized dictionary
d.finalize()
finalized_ids = get_ids(d)
assertMatch(finalized_ids, ref_ids2)
# write to disk and reload
with tempfile.NamedTemporaryFile(mode='w') as tmp_dict:
d.save(tmp_dict.name)
d = Dictionary.load(tmp_dict.name)
reload_ids = get_ids(d)
assertMatch(reload_ids, ref_ids2)
assertMatch(finalized_ids, reload_ids)
def build_dictionary(filenames, src=False, tgt=False):
assert src ^ tgt
workers = args.workers
threshold = args.thresholdsrc if src else args.thresholdtgt
nwords = args.nwordssrc if src else args.nwordstgt
padding_factor = args.padding_factor
d = Dictionary()
for filename in filenames:
Dictionary.add_file_to_dictionary(filename, d,
tokenizer.tokenize_line, workers,
args.L)
d.finalize(threshold=threshold,
nwords=nwords,
padding_factor=padding_factor)
return d
def build_dictionary(cls,
filenames,
workers=1,
threshold=-1,
nwords=-1,
padding_factor=8):
"""Build the dictionary
Args:
filenames (list): 文件名列表
workers (int): 并发的线程数
threshold (int): 定义最小出现的次数
nwords (int): 定义最终词典中的单词总数，包括特殊符号
padding_factor (int): 可用于将字典大小填充为8的倍数，这在某些硬件上很重要 (e.g., Nvidia Tensor Cores).
"""
d = Dictionary()
for filename in filenames:
Dictionary.add_file_to_dictionary(filename, d,
tokenizer.tokenize_line, workers)
d.finalize(threshold=threshold,
nwords=nwords,
padding_factor=padding_factor)
return d
def build_dictionary(cls, filenames, workers=1, threshold=-1, nwords=-1,
padding_factor=8):
"""Build the dictionary from edit-labeled raw text inputs.
Each file contains tokenized sentences along with their token labels:
```text
My teacher is going to move to change his job .
0 0 0 0 0 0 0 0 0 0 0
And he took in my favorite subject like soccer .
0 0 0 0 0 0 1 0 0 0
...
```
A dictionary is built using only the tokens and not token labels.
Args:
filenames (list): list of filenames
workers (int): number of concurrent workers
threshold (int): defines the minimum word count
nwords (int): defines the total number of words in the final dictionary,
including special symbols
padding_factor (int): can be used to pad the dictionary size to be a
multiple of 8, which is important on some hardware (e.g., Nvidia
Tensor Cores).
"""
d = Dictionary()
for filename in filenames:
# Write only tokens to a separate file.
with open(filename) as f_in, \
open(f"{filename}.tokens", "w") as f_out:
f_out.writelines(line for i, line in enumerate(f_in)
if i % 2 == 0)
# Add tokens to dictionary with multiprocessing.
Dictionary.add_file_to_dictionary(f"{filename}.tokens", d,
tokenizer.tokenize_line, workers)
d.finalize(threshold=threshold, nwords=nwords,
padding_factor=padding_factor)
return d
def test_add_file_to_dict(self):
counts = {}
num_lines = 100
per_line = 10
with tempfile.TemporaryDirectory("test_sampling") as data_dir:
filename = os.path.join(data_dir, "dummy.txt")
with open(filename, "w", encoding="utf-8") as data:
for c in string.ascii_letters:
line = f"{c} " * per_line
for _ in range(num_lines):
data.write(f"{line}\n")
counts[c] = per_line * num_lines
per_line += 5
dict = Dictionary()
Dictionary.add_file_to_dictionary(filename, dict,
tokenizer.tokenize_line, 10)
dict.finalize(threshold=0, nwords=-1, padding_factor=8)
for c in string.ascii_letters:
count = dict.get_count(dict.index(c))
self.assertEqual(
counts[c], count,
f"{c} count is {count} but should be {counts[c]}")
