第二步,创建字典,取频数最高的50000个单词,按照频数从高到低存到字典中,编号为1到50000,其它单词认定其为Unknow,编号为0
# Step 2: Build the dictionary and replace rare words with UNK token.
vocabulary_size = 50000
def build_dataset(words, n_words):
"""Process raw inputs into a dataset."""
count = [['UNK', -1]]
count.extend(collections.Counter(words).most_common(n_words - 1))
dictionary = dict()
for word, _ in count:
dictionary[word] = len(dictionary)
data = list()
unk_count = 0
for word in words:
index = dictionary.get(word, 0) #获取单词的编号
if index == 0: # dictionary['UNK']
unk_count += 1
data.append(index)
count[0][1] = unk_count
reversed_dictionary = dict(zip(dictionary.values(), dictionary.keys()))
return data, count, dictionary, reversed_dictionary
# Filling 4 global variables:
# data