pandas文件IO(导入导出)

pandas文件IO(导入导出)

# 1. 导入相关库
import pandas as pd
import numpy as np

# 2. read_csv读取
df = pd.read_csv('data/ex1.csv')

# 3. 文件有间隔符
df = pd.read_csv('data/ex1.csv', sep=',')

# 4. 列名缺失
pd.read_csv('data/ex2.csv', header=None)

# 5. 自定义列名
pd.read_csv('data/ex2.csv', header=None, names=['a', 'b', 'c', 'd', 'msg'])

# 6. 指定行索引
pd.read_csv('data/ex2.csv', header=None, names=['a', 'b', 'c', 'd', 'msg'], index_col='msg')

# 7. 多层行索引
pd.read_csv('data/ex2.csv', header=None, names=['a', 'b', 'c', 'd', 'msg'], index_col=['msg', 'a'])

# 8. 处理不规格分隔符(正则表达式)
pd.read_table('data/ex3.csv', sep='\s+')

# 9. 缺失值处理,将某值作为nan
pd.read_csv('data/ex5.csv', na_values=['NA', 'NULL', 'foo'])

# 10. 缺失值,对某列进行缺失值读取
pd.read_csv('data/ex5.csv', na_values={'message': ['foo', 'NA'], 'something': ['two']})

# 11. 逐块读取数据,前几行
pd.read_csv('data/ex6.csv', nrows=10)

# 12. 保存到磁盘
df.to_csv('data/ex5_out.csv')

# 13. 不写索引及列名称
df.to_csv('data/ex5_out.csv', index=False, header=None)

# 14. # 指定分隔符保存
df.to_csv('data/ex5_out.csv', index=False, sep='|')

# 15  只写出一部分列
df.to_csv('data/ex5_out.csv', index=False, columns=['a', 'b', 'message'])

# 16.二进制保存
pd.to_pickle(df, 'data/ex1_pickle.bin')

# 17. 二进制读取
pd.read_pickle('data/ex1_pickle.bin')