import struct
import pandas as pd
import numpy as np
# import os
# import xlsxwriter
# os.chdir("C:/Users/Xpeng/Desktop") #设置当前环境
# #导入xlsx文件
# df= pd.read_excel('E38test.xlsx',header=0) #header=0显示列名,1不显示
# print(df)
#用pandas创建数据表
df = pd.DataFrame(
{
"id":[1001,1002,1003,1004,1005,1006],
"date":pd.date_range('20130102', periods=6),
"city":['Beijing ', 'SH', ' guangzhou ', 'Shenzhen', 'shanghai', 'BEIJING '],
"age":[23,44,54,32,34,32],
"category":['100-A','100-B','110-A','110-C','210-A','130-F'],
"price":[1200,np.nan,2133,5433,np.nan,4432]
},
columns =['id','date','city','category','age','price'])
print(df)
#维度
print(df.shape)
#数据表基本信息
print(df.info)
#每一列的数据格式
print(df.dtypes)
#某一列的格式
print(df['age'].dtype)
#某一列的唯一值
print(df['age'].unique())
print('**********')
print(df.head()) #默认前5行
print(df.tail()) #默认后5行
print('用均值填充')
#使用列price的均值对NA进行填充
df['price']=df['price'].fillna(df['price'].mean())
print(df)
df['city']=df['city'].map(str.strip)
print(df)
python pandas
最新推荐文章于 2024-07-30 17:23:09 发布