数据处理-pandas列名的修改

生成一个 dataframe

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.rand(2, 4))
print(df)

#
#              0         1         2         3
#    0  0.714730  0.566612  0.764352  0.728862
#    1  0.823414  0.662657  0.800281  0.711702

定义列名

df.columns = ['beijing', 'shanghai', 'guangzhou', 'shenzhou']
print(df)

#
#        beijing  shanghai  guangzhou  shenzhou
#    0  0.714730  0.566612   0.764352  0.728862
#    1  0.823414  0.662657   0.800281  0.711702

重命名列

df.rename({'beijing':'A', 'shanghai':'B', 'guangzhou':'C', 'shenzhou':'D'}, axis='columns', inplace=True)
print(df)

#
#              A         B         C         D
#    0  0.714730  0.566612  0.764352  0.728862
#    1  0.823414  0.662657  0.800281  0.711702

重命名列2

df.rename(columns={'A':'A_1', 'B':'B_1', 'C':'C_1', 'D':'D_1'}, inplace=True)
print(df)

#
#            A_1       B_1       C_1       D_1
#    0  0.714730  0.566612  0.764352  0.728862
#    1  0.823414  0.662657  0.800281  0.711702

替换特定的字符或前缀/后缀

df.columns = df.columns.str.replace('_', '')
print(df)

#
#             A1        B1        C1        D1
#    0  0.714730  0.566612  0.764352  0.728862
#    1  0.823414  0.662657  0.800281  0.711702