常用python tips

格式化输出字符串

print('i am {0}, my age is {1}'.format('Tom',18))

i am Tom, my age is 18

转为集合类型

a = [1,2,4,2,1]
set(a)   # result: {1,2,4}

排序函数

a = [1,4,2,3,1]
sorted(a, reverse = Ture)   # result: [4,3,2,1,1]

正则表达式

\. 可以查找英文点号

\d可以查找一个数字
\d+可以查找多个数字

统计表格中内容出现的次数

# encoding=utf-8
import openpyxl
wb = openpyxl.Workbook()
wb = openpyxl.load_workbook('copy1.xlsx')       # Excel名
sh = wb['keyword']                              # sheet名
'''
换一种写法
sheet=wb.get_sheet_by_name(xl_sheet_names[0]) # 序号为0的sheet
row=sheet.max_row                             # 得到行数
'''
cons=[]  # 将所有数据append成一个list
for cases in list(sh.rows)[1:9240]: # 行数，也可以通过代码来带入
    case_D = cases[4].value         # 关键词所在的列
    cons.append(case_D)   

result_new = []
res2 = []
for con in cons:
    fenci = con.strip().split('; ') # 假定关键词是以分号隔开
    result_new.append(fenci)
new = sum(result_new,[])
res2.append(new)
#print(res2)  # res2的形式是   [['aaa','bbb','abc']]

import collections
dic = collections.Counter(res2[0])
f1 = open('关键词及次数.txt','w',encoding = 'utf-8')
# 将关键词和次数写入txt文件
# 写入Excel更好,见下一段代码
for key in dic:
    f1.write(str(key) +"\t"+ str(dic[key])+"\n")
    print(key,dic[key])
f1.close()

from openpyxl import Workbook
workbook = Workbook()
i=1
# 默认sheet
sh = workbook.active
sh.title = "count"
for key in dic:
    sh.cell(row=i, column=1, value=str(key))
    sh.cell(row=i, column=2, value=str(dic[key]))
    i+=1
workbook.save(r'name.xlsx')

接下来就是愉快的分析啦。
over is Over——Lee