index名重排

列序号按顺序重排

# 方法1 速度更快
# drop控制重拍index后是否将原先的index加入DataFrame，
# 为True时不加入，为False时加入，默认值为False
df.reset_index(drop=True, inplace=True)
# 方法2
df.index = range(len(df))

列序号转为DataFrame中的一列

df.reset_index(drop=False)  # 默认为False

其中一列设置为index

df.set_index(["D"], inplace=True)

多级行列标签的情况

https://blog.csdn.net/weixin_43298886/article/details/108090189
指定列名

data = pd.DataFrame({'a':[1,2,3]
                    ,'b':[2,3,4]
                    ,'c':[3,4,5]})
data.set_index([['A', 'B', 'C']],inplace=True)

多级索引情况

参数level

如果索引有多个列，仅从索引中删除由level指定的列，默认删除所有列。输入整数时表示将index的names中下标为level的索引删除；输入为字符串时表示将名字为level的索引删除

import pandas as pd
import numpy as np
index = pd.MultiIndex.from_tuples([('bird', 'falcon'), ('bird', 'parrot'), ('mammal', 'lion'), ('mammal', 'monkey')], names=['class', 'name'])
columns = pd.MultiIndex.from_tuples([('speed', 'max'), ('species', 'type')])
df = pd.DataFrame([(389.0, 'fly'), ( 24.0, 'fly'), ( 80.5, 'run'), (np.nan, 'jump')], index=index, columns=columns)
print(df)
print('\n')
df0 = df.reset_index()
print(df0)
print('\n')
df1 = df.reset_index(level=1)
print(df1)
print('\n')
df2 = df.reset_index(level='name')
print(df2)

参数col_level

import pandas as pd
import numpy as np
index = pd.MultiIndex.from_tuples([('bird', 'falcon'), ('bird', 'parrot'), ('mammal', 'lion'), ('mammal', 'monkey')], names=['class', 'name'])
columns = pd.MultiIndex.from_tuples([('speed', 'max'), ('species', 'type')])
df = pd.DataFrame([(389.0, 'fly'), ( 24.0, 'fly'), ( 80.5, 'run'), (np.nan, 'jump')], index=index, columns=columns)
print(df)
print('\n')
df1 = df.reset_index(level=0, col_level=0)
print(df1)
print('\n')
df2 = df.reset_index(level=0, col_level=1)
print(df2)
print('\n')

参数col_fill

重置索引时被删除的索引只能插入一个级别，如果列名(columns)有多个级别，那么这个列的列名的其他级别如何命名就由col_fill决定，默认不做填充，如果传入None则用被删除的索引的名字填充

import pandas as pd
import numpy as np
index = pd.MultiIndex.from_tuples([('bird', 'falcon'), ('bird', 'parrot'), ('mammal', 'lion'), ('mammal', 'monkey')], names=['class', 'name'])
columns = pd.MultiIndex.from_tuples([('speed', 'max'), ('species', 'type')])
df = pd.DataFrame([(389.0, 'fly'), ( 24.0, 'fly'), ( 80.5, 'run'), (np.nan, 'jump')], index=index, columns=columns)
print(df)
print('\n')
df0 = df.reset_index(level=0, col_level=0)
print(df0)
print('\n')
df1 = df.reset_index(level=0, col_level=0, col_fill=None)
print(df1)
print('\n')
df2 = df.reset_index(level=0, col_level=1, col_fill='species')
print(df2)
print('\n')
df3 = df.reset_index(level=0, col_level=0, col_fill='genus')
print(df3)
print('\n')