def train(self, sentences, total_examples=None, total_words=None,
epochs=None, start_alpha=None, end_alpha=None,
word_count=0, queue_factor=2, report_delay=1.0):
self.neg_labels = []
if self.negative > 0:
# precompute negative labels optimization for pure-python training
self.neg_labels = zeros(self.negative + 1)
self.neg_labels[0] = 1.
Word2Vec.train(self, sentences, total_examples=self.corpus_count, epochs=self.iter,
start_alpha=self.alpha, end_alpha=self.min_alpha)
self.get_vocab_word_vecs()
def train(self,
sentences,
total_examples=None,
total_words=None,
epochs=None,
start_alpha=None,
end_alpha=None,
word_count=0,
queue_factor=2,
report_delay=1.0):
self.neg_labels = []
if self.negative > 0:
# precompute negative labels optimization for pure-python training
self.neg_labels = zeros(self.negative + 1)
self.neg_labels[0] = 1.
Word2Vec.train(self,
sentences,
total_examples=self.corpus_count,
epochs=self.iter,
start_alpha=self.alpha,
end_alpha=self.min_alpha)
self.get_vocab_word_vecs()
def train(self,
sentences,
total_examples=None,
total_words=None,
epochs=None,
start_alpha=None,
end_alpha=None,
word_count=0,
queue_factor=2,
report_delay=1.0):
"""Update the model's neural weights from a sequence of sentences (can be a once-only generator stream).
For FastText, each sentence must be a list of unicode strings. (Subclasses may accept other examples.)
To support linear learning-rate decay from (initial) alpha to min_alpha, and accurate
progress-percentage logging, either total_examples (count of sentences) or total_words (count of
raw words in sentences) **MUST** be provided (if the corpus is the same as was provided to
:meth:`~gensim.models.fasttext.FastText.build_vocab()`, the count of examples in that corpus
will be available in the model's :attr:`corpus_count` property).
To avoid common mistakes around the model's ability to do multiple training passes itself, an
explicit `epochs` argument **MUST** be provided. In the common and recommended case,
where :meth:`~gensim.models.fasttext.FastText.train()` is only called once,
the model's cached `iter` value should be supplied as `epochs` value.
Parameters
----------
sentences : iterable of iterables
The `sentences` iterable can be simply a list of lists of tokens, but for larger corpora,
consider an iterable that streams the sentences directly from disk/network.
See :class:`~gensim.models.word2vec.BrownCorpus`, :class:`~gensim.models.word2vec.Text8Corpus`
or :class:`~gensim.models.word2vec.LineSentence` in :mod:`~gensim.models.word2vec` module for such examples.
total_examples : int
Count of sentences.
total_words : int
Count of raw words in sentences.
epochs : int
Number of iterations (epochs) over the corpus.
start_alpha : float
Initial learning rate.
end_alpha : float
Final learning rate. Drops linearly from `start_alpha`.
word_count : int
Count of words already trained. Set this to 0 for the usual
case of training on all words in sentences.
queue_factor : int
Multiplier for size of queue (number of workers * queue_factor).
report_delay : float
Seconds to wait before reporting progress.
Examples
--------
>>> from gensim.models import FastText
>>> sentences = [["cat", "say", "meow"], ["dog", "say", "woof"]]
>>>
>>> model = FastText(min_count=1)
>>> model.build_vocab(sentences)
>>> model.train(sentences, total_examples=model.corpus_count, epochs=model.iter)
"""
self.neg_labels = []
if self.negative > 0:
# precompute negative labels optimization for pure-python training
self.neg_labels = zeros(self.negative + 1)
self.neg_labels[0] = 1.
Word2Vec.train(self,
sentences,
total_examples=self.corpus_count,
epochs=self.iter,
start_alpha=self.alpha,
end_alpha=self.min_alpha)
self.get_vocab_word_vecs()