使用jieba库进行中文分词

发表于 | 更新于: | 分类于
字数统计: 304 | 阅读时长 ≈ 1 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
# coding=utf-8
import xlwt  # 写入excel库
import jieba.analyse
import jieba
import xlrd
import numpy as np

# 将文本编码转换为utf-8格式
import sys
reload(sys)
sys.setdefaultencoding('utf-8')


# excel转变为文本
def excel2txt(file_path):
    data = xlrd.open_workbook(
        file_path, encoding_override='utf-8')  # 打开Excel文件读取数据
    sh = data.sheet_by_name("Sheet1")  # 通过工作簿名称获取
    n = 0
    i = 0
    file = open("temp.txt", "w")
    for n in range(sh.nrows):
        for i in range(sh.ncols):
            text = sh.cell_value(n, i).encode('utf-8')
            file.write(text)
            file.write('\n')

# 结巴词频分析
def jieba_analyse():
    if __name__ == "__main__":
        wbk = xlwt.Workbook(encoding='ascii')
        sheet = wbk.add_sheet("wordCount")  # Excel单元格名字
        word_lst = []
        key_list = []
        for line in open('temp.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
            # print item
            tags = jieba.analyse.extract_tags(item[0])  # jieba分词
            for t in tags:
                word_lst.append(t)

        word_dict = {}
        with open("wordCount.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]:
                        # 写入txt文档
                        wf2.write(key + ' ' + str(word_dict[key]) + '\n')
                        key_list.append(key)
                        word_dict[key] = 0

        for i in range(len(key_list)):
            sheet.write(i, 1, label=orderList[i])
            sheet.write(i, 0, label=key_list[i])
        wbk.save('wordCount.xls')  # 保存为 wordCount.xls文件

# 要分析的xlsx表
def analyse_word(file_path):
    excel2txt(file_path)
    jieba_analyse()


analyse_word('data2.xlsx')
0%