"""将数据列表转换成一些词频count,字典dictionary 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: if word in dictionary: index = dictionary[word] else: 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
编程练习(时间序列)
猜你喜欢
转载自www.cnblogs.com/yttas/p/10513821.html
今日推荐
周排行