pandas 对dataframe的复制

转载自：
https://www.cnblogs.com/jdwfff/p/11990552.html
https://www.it1352.com/1689965.html

• 方法一：直接df复制

data_p = pd.DataFrame(np.arange(25).reshape(5,5))
print(data_p)
pd2=pd.DataFrame()
 
for i in range(len(data_p)):
    a=data_p.loc[i]
    d=pd.DataFrame(a).T
    pd2=pd2.append([d]*24)  #每行复制24倍
print(pd2)

• 方法2：利用np

import numpy as np
import pandas as pd

arr = np.array(
    [[1,0,1,1,1,5],
     [0,0,0,0,1,3],
     [1,0,0,0,1,1],
     [1,0,0,1,1,1],
     [1,0,0,0,1,1],
     [1,1,0,0,1,1]]
    )

df = pd.DataFrame(
    np.repeat(arr, arr[:,5], axis=0),
    columns=['var1','var2','var3','var4','var5','cnt']
    )

print(df)
#     var1  var2  var3  var4  var5  cnt
# 0      1     0     1     1     1    5
# 1      1     0     1     1     1    5
# 2      1     0     1     1     1    5
# 3      1     0     1     1     1    5
# 4      1     0     1     1     1    5
# 5      0     0     0     0     1    3
# 6      0     0     0     0     1    3
# 7      0     0     0     0     1    3
# 8      1     0     0     0     1    1
# 9      1     0     0     1     1    1
# 10     1     0     0     0     1    1
# 11     1     1     0     0     1    1