Pandas中DataFrame的基本操作之重新索引讲解_python_

import pandas as pd data=[[1,1,1,1],[2,2,2,2],[3,3,3,3],[4,4,4,4]] df = pd.DataFrame(data,index=['d','b','c','a']) print(df)

df=df.reindex(['a','b','c','d','e']) print(df)

df=df.reindex(columns=[2,1,3,4,0]) print(df)

import pandas as pd data=[[1,1,1,1],[2,2,2,2],[3,3,3,3]] df = pd.DataFrame(data,index=range(3)) print(df) df=df.reindex([0,1,2,3,4,5],method='ffill') print('--------------') print(df)

import pandas as pd import numpy as np a=pd.DataFrame(np.random.randint(1,10,20).reshape(4,5)) print(a) 0 1 2 3 4 0 1 3 2 7 6 1 8 2 2 7 2 2 2 6 6 2 5 3 4 1 6 8 9 b=a.sort_values(by=4) print(b) 0 1 2 3 4 1 8 2 2 7 2 2 2 6 6 2 5 0 1 3 2 7 6 3 4 1 6 8 9 ### 重置索引:方法1 c=a.sort_values(by=4,ignore_index=True) print(c) 0 1 2 3 4 0 8 2 2 7 2 1 2 6 6 2 5 2 1 3 2 7 6 3 4 1 6 8 9 ### 重置索引：方法2 d=b.reset_index(drop=True) print(d) 0 1 2 3 4 0 8 2 2 7 2 1 2 6 6 2 5 2 1 3 2 7 6 3 4 1 6 8 9