def get_negatives(all_contexts, corpus, K):
counter = d2l.count_corpus(corpus)
sampling_weights = [counter[i]**0.75 for i in range(len(counter))]
all_negatives, generator = [], RandomGenerator(sampling_weights)
for contexts in all_contexts:
negatives = []
while len(negatives) < len(contexts) * K:
neg = generator.draw()
if neg not in contexts:
negatives.append(neg)
all_negatives.append(negatives)
return all_negatives
def subsampling(sentences, vocab):
# Map low frequency words into <unk>
sentences = [[vocab.idx_to_token[vocab[tk]] for tk in line]
for line in sentences]
# Count the frequency for each word
counter = d2l.count_corpus(sentences)
num_tokens = sum(counter.values())
def keep(token):
return (random.uniform(0, 1) < math.sqrt(
1e-4 / counter[token] * num_tokens))
return [[tk for tk in line if keep(tk)] for line in sentences]