作业需求：
分析两本类型不同的现代小说的词性分布，如武侠或侦探小说等.用一个类读入整本小说。用自然语言处理工具。初始化过程分析内容。分解词语并获取词性(如动词.形容词等).类对象取索引返回词和词性两项主要信息在调用类对象的函数中，实现词性的统计。用饼状图可视化个主要词性频率，对比两本小说的饼状
编辑
全部代码：
import jieba import jieba.posseg import matplotlib.pyplot as plt import matplotlib from pylab import mpl mpl.rcParams['font.sans-serif'] = ['SimHei'] # 字体更改 matplotlib.rcParams.update({'font.size': 15}) # 字体大小 fig = plt.figure(figsize=(8, 8), dpi=80) word_type = ["a", "d", "n", "p", "r", "u", "v", "y"] word_type_chin = ["形容词", "副词", "名词", "介词", "代词", "助词", "动词", "语气词"] class Text(): def init(self): with open("yitian.txt", mode="r", encoding="utf8") as txt1: a = txt1.read() with open("baiyexing.txt", mode="r", encoding="gbk") as txt2: b = txt2.read() self.txt = [a, b] self.output = [[], []] self.flag = [[], []] self.word = [[], []] self.identify(self) return self.output[0], self.output[1] def identify(self): for x in range(0, 2): self.txt[x] = jieba.posseg.cut(self.txt[x]) for text in self.txt[x]: self.output[x].append([text.word, text.flag]) self.flag[x].append(text.flag) for t in range(0, 8): print(f"{word_type_chin[t]}: {self.flag[x].count(word_type[t])}") self.word[x].append(self.flag[x].count(word_type[t])) def pie(self): for x in range(0, 2): fig.add_subplot(1, 2, x + 1) plt.pie(self.word[x], labels=word_type_chin, # 设置饼图标签 # radius=1.2, autopct="%d%%", ) if x == 0: text_type = "武侠" elif x == 1: text_type = "侦探" plt.title(f"{text_type}小说的词性分布") fig.show() text_1, text_2 = Text.init(Text) print(f"武侠小说:\n{text_1}") print(f"\n侦探小说：\n{text_2}") Text.pie(Text) input(" >>> ENTER以继续 <<< ")
编辑
数据+代码：
