The rivertext from dccuchile

View Code? Open in Web Editor NEW

RiverText is a framework that standardizes the Incremental Word Embeddings proposed in the state-of-art. Please feel welcome to open an issue in case you have any questions or a pull request if you want to contribute to the project!

License: MIT License

Python 100.00%

rivertext's People

Contributors

Stargazers

Watchers

rivertext's Issues

IWord2Vec does not work

The following code will not work correctly
Is this project still under development and does not work?

from torch.utils.data import DataLoader
from rivertext.models.iw2v import IWord2Vec
from rivertext.utils import TweetStream
from tqdm import tqdm
ts = TweetStream("a.txt")
dataloader = DataLoader(ts, batch_size=32)
iw2v = IWord2Vec(window_size=3, vocab_size=3, emb_size=3, sg=1, neg_samples_sum=1,  device="cuda:0")
for batch in tqdm(dataloader):
   iw2v.learn_many(batch)
print(iw2v.vocab2dict())

0it [00:00, ?it/s]/home/pf/glove/rivertext/rivertext/models/iword2vec/unigram_table.py:83: RuntimeWarning: invalid value encountered in true_divide
  nums = self.max_size * counts_pow / z
0it [00:00, ?it/s]
Traceback (most recent call last):
  File "/home/pf/glove/rivertext/a.py", line 9, in <module>
    iw2v.learn_many(batch)
  File "/home/pf/glove/rivertext/rivertext/models/iw2v.py", line 267, in learn_many
    batch = self.prep(tokens)
  File "/home/pf/glove/rivertext/rivertext/models/iword2vec/preprocessing.py", line 261, in __call__
    self.update_unigram_table(token)
  File "/home/pf/glove/rivertext/rivertext/models/iword2vec/preprocessing.py", line 98, in update_unigram_table
    self.rebuild_unigram_table()
  File "/home/pf/glove/rivertext/rivertext/models/iword2vec/preprocessing.py", line 78, in rebuild_unigram_table
    self.unigram_table.build(self.vocab, self.alpha)
  File "/home/pf/glove/rivertext/rivertext/models/iword2vec/unigram_table.py", line 84, in build
    nums = np.vectorize(round_number)(nums)
  File "/home/pf/.local/lib/python3.10/site-packages/numpy/lib/function_base.py", line 2304, in __call__
    return self._vectorize_call(func=func, args=vargs)
  File "/home/pf/.local/lib/python3.10/site-packages/numpy/lib/function_base.py", line 2382, in _vectorize_call
    ufunc, otypes = self._get_ufunc_and_otypes(func=func, args=args)
  File "/home/pf/.local/lib/python3.10/site-packages/numpy/lib/function_base.py", line 2342, in _get_ufunc_and_otypes
    outputs = func(*inputs)
  File "/home/pf/glove/rivertext/rivertext/utils/rand.py", line 17, in round_number
    c = ceil(num)
ValueError: cannot convert float NaN to integer

Recommend Projects