import jieba
from collections import Counter
import matplotlib.pyplot as plt
import numpy as np


class HlmNameCount():
    def showNameBar(self,name_list_sort,name_list_count):
        x = np.arange(len(name_list_sort))
        plt.rcParams['font.sans-serif'] = ['SimHei']
        bars = plt.bar(x,name_list_count)
        plt.xticks(x,name_list_sort)
        i = 0
        for bar in bars:
            plt.text((bar.get_x() + bar.get_width() / 2), bar.get_height(), '%d' % name_list_count[i], ha='center', va='bottom')
            i += 1
        plt.show()

    def showNamePie(self, name_list_sort, name_list_fracs):
        plt.rcParams['font.sans-serif'] = ['SimHei']
        plt.pie(name_list_fracs, labels=name_list_sort, autopct='%1.2f%%', shadow=True)
        plt.show()

    def getNameTimesSort(self,name_list,txt_path):
        for k in name_list:
            jieba.add_word(k)
        file_obj = open(txt_path, 'rb').read()
        jieba_cut = jieba.cut(file_obj)
        book_counter = Counter(jieba_cut)
        name_dict ={}
        name_total_count = 0
        for k in name_list:
            if k == '熙凤':
                name_dict['凤姐'] += book_counter[k]
            else:
                name_dict[k] = book_counter[k]
            name_total_count += book_counter[k]
        name_counter = Counter(name_dict)
        name_list_sort = []
        name_list_fracs = []
        name_list_count = []
        for k,v in name_counter.most_common():
            name_list_sort.append(k)
            name_list_fracs.append(round(v/name_total_count,2)*100)
            name_list_count.append(v)
        self.showNameBar(name_list_sort, name_list_count)
        self.showNamePie(name_list_sort,name_list_fracs)
        

if __name__ == '__main__':
    name_list = ['宝玉', '黛玉', '宝钗', '元春', '探春', '湘云', '妙玉', '迎春', '惜春', '凤姐', '熙凤', '巧姐', '李纨', '可卿', '贾母', '贾珍', '贾蓉', '贾赦', '贾政', '王夫人', '贾琏', '薛蟠', '香菱', '宝琴', '袭人', '晴雯', '平儿', '紫鹃', '莺儿']
    txt_path = 'D:/123.txt'
    hnc = HlmNameCount()
    hnc.getNameTimesSort(name_list,txt_path)