Pandas中Concat与Append的实现与区别小结

# Series合并
ser1 = pd.Series(['A', 'B', 'C'], index=[1, 2, 3])
ser2 = pd.Series(['D', 'E', 'F'], index=[4, 5, 6])
pd.concat([ser1,ser2])
Out：
 1 A 
 2 B 
 3 C 
 4 D 
 5 E 
 6 F 
 dtype: object
 
# DataFrame合并，将concat的axis参数设置为1即可横向合并
df1 = pd.DataFrame([["A1","B1"],["A2","B2"]],index=[1,2],columns=["A","B"])
df2 = pd.DataFrame([["A3","B3"],["A4","B4"]],index=[3,4],columns=["A","B"])
pd.concat([df1,df2])
Out：
    A  B
 1 A1 B1 
 2 A2 B2 
 3 A3 B3 
 4 A4 B4

df3 = pd.DataFrame([["A1","B1"],["A2","B2"]],index=[1,2],columns=["A","B"])
df4 = pd.DataFrame([["A1","B1"],["A2","B2"]],index=[1,2],columns=["A","B"])
pd.concat([df3,df4])
Out：
    A  B
 1 A1 B1 
 2 A2 B2 
 1 A3 B3 
 2 A4 B4

try: 
 pd.concat([df3, df4], verify_integrity=True) 
except ValueError as e: 
 print("ValueError:", e)
Out：
ValueError: Indexes have overlapping values: [0, 1]

pd.concat([df3,df4],ignore_index=True)
Out：
   A B 
0 A0 B0 
1 A1 B1 
2 A2 B2 
3 A3 B3

pd.concat([df3, df4], keys=['x', 'y'])
Out：
     A B 
x 0 A0 B0 
  1 A1 B1 
y 0 A2 B2 
  1 A3 B3

df5 = pd.DataFrame([["A1","B1","C1"],["A2","B2","C2"]],index=[1,2],columns=["A","B","C"])
df6 = pd.DataFrame([["B3","C3","D3"],["B4","C4","D4"]],index=[3,4],columns=["B","C","D"])
pd.concat([df5,df6])
Out：
    A  B  C  D
 1 A1  B1 C1 NaN
 2 A2  B2 C2 NaN
 3 NaN B3 C3 D3
 4 NaN B4 C4 D4

pd.concat([df5,df6],join="inner") # 合并取交集
Out：
    B C 
 1 B1 C1 
 2 B2 C2 
 3 B3 C3 
 4 B4 C4
# join_axes的参数需为一个列表索引对象
pd.concat([df5,df6],join_axes=[pd.Index(["B","C"])])
Out：
    B C 
 1 B1 C1 
 2 B2 C2 
 3 B3 C3 
 4 B4 C4