jieba库的应用

#!/usr/bin/python
# -*- coding:utf-8 -*-

import imp,sys

imp.reload(sys)
from matplotlib.font_manager import FontProperties
import jieba.analyse
import matplotlib.pyplot as plt
if __name__ == "__main__":

word_lst = []
key_list = []
for line in open('D://jieba_new.txt'): # 1.txt是需要分词统计的文档

item = line.strip('\n\r').split('\t') # 制表格切分
tags = jieba.analyse.extract_tags(item[0]) # jieba分词
for t in tags:
word_lst.append(t)

word_dict = {}
with open("D://word.txt", 'w') as wf2: # 打开文件

for item in word_lst:
if item not in word_dict: # 统计数量
word_dict[item] = 1
else:
word_dict[item] += 1

orderList = list(word_dict.values())
orderList.sort(reverse=True)
# print orderList
for i in range(len(orderList)):
for key in word_dict:
if word_dict[key] == orderList[i]:
if word_dict[key] > 1:
wf2.write(key + ' ' + str(word_dict[key]) + '\n') # 写入txt文档
tmp = open('D://word.txt').readlines() # 把内容一次性全部读取出来 是一个列表
set(tmp)
A = []
B = []
file = open('D:\\word1.txt')
for r in file:
imporkey = r.split(' ')[0]
sumnumber = r.split(' ')[1]
int_imporkey = str(imporkey)
int_sumnumber = str(sumnumber)
A.append(int_imporkey)
B.append(int_sumnumber)
fig = plt.figure()
plt.pie(B,labels=A,autopct='%1.2f%%') #画饼图（数据，数据对应的标签，百分数保留两位小数点）
plt.title("Pie chart")
plt.show()