机器人写诗项目——数据预处理

首先来看全部代码

import collections

start_token = 'G'
end_token = 'E'

def process_poems(file_name):
    # 诗集
    poems = []
    with open(file_name, "r", encoding='utf-8', ) as f:
        for line in f.readlines():
            try:
                title, content = line.strip().split(':')
                content = content.replace(' ', '')
                if '_' in content or '(' in content or '（' in content or '《' in content or '[' in content or 
                        start_token in content or end_token in content:
                    continue
                if len(content) < 5 or len(content) > 79:
                    continue
                content = start_token + content + end_token
                poems.append(content)
            except ValueError as e:
                pass
    # 按诗的字数排序
    poems = sorted(poems, key=lambda l: len(line))

    # 统计每个字出现次数
    all_words = []
    for poem in poems:
        all_words += [word for word in poem]
    # 这里根据包含了每个字对应的频率
    counter = collections.Counter(all_words)
    count_pairs = sorted(counter.items(), key=lambda x: -x[1])
    words, _ = zip(*count_pairs)

    # 取前多少个常用字
    words = words[:len(words)] + (' ',)
    # 每个字映射为一个数字ID
    word_int_map = dict(zip(words, range(len(words))))
    poems_vector = [list(map(lambda word: word_int_map.get(word, len(words)), poem)) for poem in poems]

    return poems_vector, word_int_map, words

之后看一下数据集

最后来一点点分析

定义一个数据预处理函数：

def process_poems(file_name):

首先把处理好的结果指定成一个list：

    poems = []

打开处理模块，首先制定好一个路径，然后以读的方式打开 ，最后因为诗是中文的，所以编码方式为‘utf-8’：

    with open(file_name, "r", encoding='utf-8', ) as f:

一行一行去读

        for line in f.readlines():

用冒号将文本分割为诗的题目和内容：

                title, content = line.strip().split(':')

如果训练数据集中古诗存在问题，应该舍弃该诗：

                if '_' in content or '(' in content or '（' in content or '《' in content or '[' in content or 
                        start_token in content or end_token in content:
                    continue
                if len(content) < 5 or len(content) > 79:
                    continue

对诗的内容进行处理，加上开始和中止符号，然后才能将诗的内容传进结果的list里：

                content = start_token + content + end_token
                poems.append(content)

对得到的结果list进行排序处理：

    poems = sorted(poems, key=lambda l: len(line))

统计每个字出现的次数，两层循环，第一层是循环每一首诗，第二层是循环每首诗里的每一个字：

    all_words = []
    for poem in poems:
        all_words += [word for word in poem]

计算词频：

    counter = collections.Counter(all_words)
    count_pairs = sorted(counter.items(), key=lambda x: -x[1])
    words, _ = zip(*count_pairs)

取前多少个常用字：

    words = words[:len(words)] + (' ',)

每个字映射为一个数字ID：

    word_int_map = dict(zip(words, range(len(words))))
    poems_vector = [list(map(lambda word: word_int_map.get(word, len(words)), poem)) for poem in poems]

返回所需要的值：

    return poems_vector, word_int_map, words