def __init__(self,
keywords,
sentences,
corpus_file,
size,
alpha,
word_ngrams,
min_n,
max_n,
bucket,
corpus_worker,
corpus_chunksize,
case_sensitive,
window=5,
min_count=5,
max_vocab_size=None,
sample=0.001,
seed=1,
workers=3,
min_alpha=0.0001,
sg=0,
hs=0,
negative=5,
ns_exponent=0.75,
cbow_mean=1,
iter=5,
null_word=0,
trim_rule=None,
sorted_vocab=1,
batch_words=10000):
# 20181130 LIN, Y.D.: Save all sentences for training
Sec2Vec.__init__(self, sentences, corpus_file)
# 20181126 Hannah Chen, modified variable: corpus_worker
KeywordCorpusFactory.__init__(self, keywords, case_sensitive,
corpus_worker)
# 20181130 Hannah Chen
self.kc = self.create(SentenceIterator(self.sentences),
corpus_chunksize)
# 20181130 LIN, Y.D.: Save all sentences for training
# self.kc = self.create(self.sentences, corpus_chunksize)
# self.kc = self.create(sentences, corpus_chunksize)
self.kv = dict(((keyword, []) for keyword in self.kc.keys()))
self.keyword_count = dict(((keyword, 0) for keyword in self.kc.keys()))
self.corpus_chunksize = corpus_chunksize
FastText.__init__(self,
corpus_file=corpus_file,
size=size,
alpha=alpha,
word_ngrams=word_ngrams,
window=window,
min_count=min_count,
max_vocab_size=max_vocab_size,
sample=sample,
seed=seed,
workers=workers,
min_n=min_n,
max_n=max_n,
min_alpha=min_alpha,
sg=sg,
hs=hs,
bucket=bucket,
negative=negative,
ns_exponent=ns_exponent,
cbow_mean=cbow_mean,
iter=iter,
null_word=null_word,
trim_rule=trim_rule,
sorted_vocab=sorted_vocab,
batch_words=batch_words,
callbacks=[])
