python数据处理常用方法

1、读取指定sheet和指定列的内容

data = pd.read_excel("data.xlsx",sheet_name="Sheet1",usecols=["year","code1","code2","name","keywords","type",'new'])

 

2、遍历数据，对两列数据相似度比较

for i in range(0,75065):
    if data.loc[i]['code2']!=0:
        if data.loc[i]['code1'][:5]==data.loc[i]['code2'][:5]:
            data.loc[i,'inter']=0
        elif data.loc[i]['code1'][:3]==data.loc[i]['code2'][:3]:
            data.loc[i,'inter']=1
        elif data.loc[i]['code1'][:1]==data.loc[i]['code2'][:1]:
            data.loc[i,'inter']=2
        else:
            data.loc[i,'inter']=3

3、遍历数据，统计每类分类变量的数量

list= ['fund','year','inter','age','degree','title','institute','economy','gender','type']
for i in range(0,10):
    print(data[list[i]].value_counts())

4、遍历数据，删除某列为特定值的数据

df_clear = data.drop(data[data['discipline']=="H"].index)

5、正则去掉字符串左边或者右边的内容

import re
template = "DF','17340','http://www.zgglkx.com','2021','205')"

delete_left = template.lstrip('"DF')
print(delete_left)

delete_right = template.rstrip('205\')')
print(delete_right)