Pandas--表连接的几种方式

import pandas as pd

raw_data_1 = {
        'subject_id': ['1', '2', '3', '4', '5'],
        'first_name': ['Alex', 'Amy', 'Allen', 'Alice', 'Ayoung'], 
        'last_name': ['Anderson', 'Ackerman', 'Ali', 'Aoni', 'Atiches']}

raw_data_2 = {
        'subject_id': ['4', '5', '6', '7', '8'],
        'first_name': ['Billy', 'Brian', 'Bran', 'Bryce', 'Betty'], 
        'last_name': ['Bonder', 'Black', 'Balwner', 'Brice', 'Btisan']}

raw_data_3 = {
        'subject_id': ['1', '2', '3', '4', '5', '7', '8', '9', '10', '11'],
        'test_id': [51, 15, 15, 61, 16, 14, 15, 1, 61, 16]}

df1 = pd.DataFrame(raw_data_1, columns = ['subject_id', 'first_name', 'last_name'])
df2 = pd.DataFrame(raw_data_2, columns = ['subject_id', 'first_name', 'last_name'])
df3 = pd.DataFrame(raw_data_3, columns = ['subject_id','test_id'])

df1

	subject_id	first_name	last_name
0	1	Alex	Anderson
1	2	Amy	Ackerman
2	3	Allen	Ali
3	4	Alice	Aoni
4	5	Ayoung	Atiches

df2

	subject_id	first_name	last_name
0	4	Billy	Bonder
1	5	Brian	Black
2	6	Bran	Balwner
3	7	Bryce	Brice
4	8	Betty	Btisan

df3

	subject_id	test_id
0	1	51
1	2	15
2	3	15
3	4	61
4	5	16
5	7	14
6	8	15
7	9	1
8	10	61
9	11	16

append

# ignore_index=True 充值索引
df1.append(df2, ignore_index=True)

	subject_id	first_name	last_name
0	1	Alex	Anderson
1	2	Amy	Ackerman
2	3	Allen	Ali
3	4	Alice	Aoni
4	5	Ayoung	Atiches
5	4	Billy	Bonder
6	5	Brian	Black
7	6	Bran	Balwner
8	7	Bryce	Brice
9	8	Betty	Btisan

# # verify_intergrity=True 若存在重复索引则报错
# df1.append(df2, verify_integrity=True)

# 数据框维度不同时
df1.append(df3)

	subject_id	first_name	last_name	test_id
0	1	Alex	Anderson	NaN
1	2	Amy	Ackerman	NaN
2	3	Allen	Ali	NaN
3	4	Alice	Aoni	NaN
4	5	Ayoung	Atiches	NaN
0	1	NaN	NaN	51.0
1	2	NaN	NaN	15.0
2	3	NaN	NaN	15.0
3	4	NaN	NaN	61.0
4	5	NaN	NaN	16.0
5	7	NaN	NaN	14.0
6	8	NaN	NaN	15.0
7	9	NaN	NaN	1.0
8	10	NaN	NaN	61.0
9	11	NaN	NaN	16.0

join

df = pd.DataFrame({'key': ['K0', 'K1', 'K2', 'K3', 'K4', 'K5'],
                   'A': ['A0', 'A1', 'A2', 'A3', 'A4', 'A5']})
df

	key	A
0	K0	A0
1	K1	A1
2	K2	A2
3	K3	A3
4	K4	A4
5	K5	A5

other = pd.DataFrame({'key': ['K0', 'K1', 'K2'],
                      'B': ['B0', 'B1', 'B2']})
other

	key	B
0	K0	B0
1	K1	B1
2	K2	B2

# 默认按照index左连接
# 当表中有重复列且不被作为连接依据时需要指定后缀
df.join(other, lsuffix='_caller', rsuffix='_other')

	key_caller	A	key_other	B
0	K0	A0	K0	B0
1	K1	A1	K1	B1
2	K2	A2	K2	B2
3	K3	A3	NaN	NaN
4	K4	A4	NaN	NaN
5	K5	A5	NaN	NaN

df.join(other.set_index('key'), on='key')

	key	A	B
0	K0	A0	B0
1	K1	A1	B1
2	K2	A2	B2
3	K3	A3	NaN
4	K4	A4	NaN
5	K5	A5	NaN

df.set_index('key').join(other.set_index('key'))

	A	B
key
K0	A0	B0
K1	A1	B1
K2	A2	B2
K3	A3	NaN
K4	A4	NaN
K5	A5	NaN

pandas.DataFrame.merge

# 默认内连接
df1.merge(df2, on='subject_id')

	subject_id	first_name_x	last_name_x	first_name_y	last_name_y
0	4	Alice	Aoni	Billy	Bonder
1	5	Ayoung	Atiches	Brian	Black

df2.subject_id = df2['subject_id'].astype(int)

# 指定连接基准为：左表的index，右表的subject_id列
df1.merge(df2, left_index=True, right_on='subject_id')

	subject_id	subject_id_x	first_name_x	last_name_x	subject_id_y	first_name_y	last_name_y
0	4	5	Ayoung	Atiches	4	Billy	Bonder

pd.concat

pd.concat([df1,df2])

	subject_id	first_name	last_name
0	1	Alex	Anderson
1	2	Amy	Ackerman
2	3	Allen	Ali
3	4	Alice	Aoni
4	5	Ayoung	Atiches
0	4	Billy	Bonder
1	5	Brian	Black
2	6	Bran	Balwner
3	7	Bryce	Brice
4	8	Betty	Btisan

pd.concat([df1,df3])

	subject_id	first_name	last_name	test_id
0	1	Alex	Anderson	NaN
1	2	Amy	Ackerman	NaN
2	3	Allen	Ali	NaN
3	4	Alice	Aoni	NaN
4	5	Ayoung	Atiches	NaN
0	1	NaN	NaN	51.0
1	2	NaN	NaN	15.0
2	3	NaN	NaN	15.0
3	4	NaN	NaN	61.0
4	5	NaN	NaN	16.0
5	7	NaN	NaN	14.0
6	8	NaN	NaN	15.0
7	9	NaN	NaN	1.0
8	10	NaN	NaN	61.0
9	11	NaN	NaN	16.0

pd.concat([df1,df3], axis=1, join='inner')

	subject_id	first_name	last_name	subject_id	test_id
0	1	Alex	Anderson	1	51
1	2	Amy	Ackerman	2	15
2	3	Allen	Ali	3	15
3	4	Alice	Aoni	4	61
4	5	Ayoung	Atiches	5	16