In [10]: result = pd.concat([df1, df4], axis=1, join='inner')
join='inner' 只会选择index相同的进行展示。
如果合并之后，我们只想保存原来frame的index相关的数据，那么可以使用reindex：
In [11]: result = pd.concat([df1, df4], axis=1).reindex(df1.index)
或者这样：
In [12]: pd.concat([df1, df4.reindex(df1.index)], axis=1)
Out[12]:
A B C D B D F
0 A0 B0 C0 D0 NaN NaN NaN
1 A1 B1 C1 D1 NaN NaN NaN
2 A2 B2 C2 D2 B2 D2 F2
3 A3 B3 C3 D3 B3 D3 F3
看下结果：
可以合并DF和Series：
In [18]: s1 = pd.Series(['X0', 'X1', 'X2', 'X3'], name='X')
In [19]: result = pd.concat([df1, s1], axis=1)
如果是多个Series，使用concat可以指定列名：
In [23]: s3 = pd.Series([0, 1, 2, 3], name='foo')
In [24]: s4 = pd.Series([0, 1, 2, 3])
In [25]: s5 = pd.Series([0, 1, 4, 5])
In [27]: pd.concat([s3, s4, s5], axis=1, keys=['red', 'blue', 'yellow'])
Out[27]:
red blue yellow
0 0 0 0
1 1 1 1
2 2 2 4
3 3 3 5
使用append
append可以看做是concat的简化版本，它沿着axis=0 进行concat：
In [13]: result = df1.append(df2)
如果append的两个 DF的列是不一样的会自动补全NaN：
In [14]: result = df1.append(df4, sort=False)
如果设置ignore_index=True，可以忽略原来的index，并重写分配index：
In [17]: result = df1.append(df4, ignore_index=True, sort=False)
向DF append一个Series：
In [35]: s2 = pd.Series(['X0', 'X1', 'X2', 'X3'], index=['A', 'B', 'C', 'D'])
In [36]: result = df1.append(s2, ignore_index=True)
In [45]: result = pd.merge(left, right, how='left', on=['key1', 'key2'])
指定indicator=True ，可以表示具体行的连接方式：
In [60]: df1 = pd.DataFrame({'col1': [0, 1], 'col_left': ['a', 'b']})
In [61]: df2 = pd.DataFrame({'col1': [1, 2, 2], 'col_right': [2, 2, 2]})
In [62]: pd.merge(df1, df2, on='col1', how='outer', indicator=True)
Out[62]:
col1 col_left col_right _merge
0 0 a NaN left_only
1 1 b 2.0 both
2 2 NaN 2.0 right_only
3 2 NaN 2.0 right_only
如果传入字符串给indicator，会重命名indicator这一列的名字：
In [63]: pd.merge(df1, df2, on='col1', how='outer', indicator='indicator_column')
Out[63]:
col1 col_left col_right indicator_column
0 0 a NaN left_only
1 1 b 2.0 both
2 2 NaN 2.0 right_only
3 2 NaN 2.0 right_only
多个index进行合并：
In [112]: leftindex = pd.MultiIndex.from_tuples([('K0', 'X0'), ('K0', 'X1'),
.....: ('K1', 'X2')],
.....: names=['key', 'X'])
.....:
In [113]: left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
.....: 'B': ['B0', 'B1', 'B2']},
.....: index=leftindex)
.....:
In [114]: rightindex = pd.MultiIndex.from_tuples([('K0', 'Y0'), ('K1', 'Y1'),
.....: ('K2', 'Y2'), ('K2', 'Y3')],
.....: names=['key', 'Y'])
.....:
In [115]: right = pd.DataFrame({'C': ['C0', 'C1', 'C2', 'C3'],
.....: 'D': ['D0', 'D1', 'D2', 'D3']},
.....: index=rightindex)
.....:
In [116]: result = pd.merge(left.reset_index(), right.reset_index(),
.....: on=['key'], how='inner').set_index(['key', 'X', 'Y'])
支持多个列的合并：
In [117]: left_index = pd.Index(['K0', 'K0', 'K1', 'K2'], name='key1')
In [118]: left = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
.....: 'B': ['B0', 'B1', 'B2', 'B3'],
.....: 'key2': ['K0', 'K1', 'K0', 'K1']},
.....: index=left_index)
.....:
In [119]: right_index = pd.Index(['K0', 'K1', 'K2', 'K2'], name='key1')
In [120]: right = pd.DataFrame({'C': ['C0', 'C1', 'C2', 'C3'],
.....: 'D': ['D0', 'D1', 'D2', 'D3'],
.....: 'key2': ['K0', 'K0', 'K0', 'K1']},
.....: index=right_index)
.....:
In [121]: result = left.merge(right, on=['key1', 'key2'])
使用join
join将两个不同index的DF合并成一个。可以看做是merge的简写。
In [84]: left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
....: 'B': ['B0', 'B1', 'B2']},
....: index=['K0', 'K1', 'K2'])
....:
In [85]: right = pd.DataFrame({'C': ['C0', 'C2', 'C3'],
....: 'D': ['D0', 'D2', 'D3']},
....: index=['K0', 'K2', 'K3'])
....:
In [86]: result = left.join(right)
可以指定how来指定连接方式：
In [87]: result = left.join(right, how='outer')
默认join是按index来进行连接。
还可以按照列来进行连接：
In [91]: left = pd.DataFrame({'A': ['A0', 'A1', 'A2', 'A3'],
....: 'B': ['B0', 'B1', 'B2', 'B3'],
....: 'key': ['K0', 'K1', 'K0', 'K1']})
....:
In [92]: right = pd.DataFrame({'C': ['C0', 'C1'],
....: 'D': ['D0', 'D1']},
....: index=['K0', 'K1'])
....:
In [93]: result = left.join(right, on='key')
单个index和多个index进行join：
In [100]: left = pd.DataFrame({'A': ['A0', 'A1', 'A2'],
.....: 'B': ['B0', 'B1', 'B2']},
.....: index=pd.Index(['K0', 'K1', 'K2'], name='key'))
.....:
In [101]: index = pd.MultiIndex.from_tuples([('K0', 'Y0'), ('K1', 'Y1'),
.....: ('K2', 'Y2'), ('K2', 'Y3')],
.....: names=['key', 'Y'])
.....:
In [102]: right = pd.DataFrame({'C': ['C0', 'C1', 'C2', 'C3'],
.....: 'D': ['D0', 'D1', 'D2', 'D3']},
.....: index=index)
.....:
In [103]: result = left.join(right, how='inner')
列名重复的情况：
In [122]: left = pd.DataFrame({'k': ['K0', 'K1', 'K2'], 'v': [1, 2, 3]})
In [123]: right = pd.DataFrame({'k': ['K0', 'K0', 'K3'], 'v': [4, 5, 6]})
In [124]: result = pd.merge(left, right, on='k')
可以自定义重复列名的命名规则：
In [125]: result = pd.merge(left, right, on='k', suffixes=('_l', '_r'))
