python 合并多个数据集

烈酒焚心 提交于 2019-12-22 01:44:00
#合并多个数据集
#合并: 关系型数据库中的两个表之间的连接
#table1.field1  table2.field2 select table1.field1,table2.field2 from table1,table2 where table1.field1 = table2.field2

#1. 一对一
#2. 多对一
#3.  多对多

import pandas as pd
person = pd.read_csv('./data/survey_person.csv')
site = pd.read_csv('./data/survey_site.csv')
survey = pd.read_csv('./data/survey_survey.csv')
visited = pd.read_csv('./data/survey_visited.csv')

print(person)
print(site)
print(visited)
print(survey)

#取行
visited_subset = visited.loc[[0,2,6],]
print(visited_subset)


#一对一连接
#参与连接的字段或者列名   --left_on、right_on  left_on的结果集是site   右边结果集是right_on
merge1 = site.merge(visited_subset,left_on ='name',right_on = 'site')
print(merge1)

#多对一
merge2 = site.merge(visited,left_on='name',right_on='site')
print(merge2)

#多对多
ps = person.merge(survey,left_on='ident',right_on='person')
vs = visited.merge(survey,left_on = 'ident',right_on = 'taken')
print(ps)
print(vs)
(venv) E:\py3>python py21.py
      ident   personal    family
0      dyer    William      Dyer
1        pb      Frank   Pabodie
2      lake   Anderson      Lake
3       roe  Valentina   Roerich
4  danforth      Frank  Danforth
    name    lat    long
0   DR-1 -49.85 -128.57
1   DR-3 -47.15 -126.72
2  MSK-4 -48.87 -123.40
   ident   site       dated
0    619   DR-1  1927-02-08
1    622   DR-1  1927-02-10
2    734   DR-3  1939-01-07
3    735   DR-3  1930-01-12
4    751   DR-3  1930-02-26
5    752   DR-3         NaN
6    837  MSK-4  1932-01-14
7    844   DR-1  1932-03-22
    taken person quant  reading
0     619   dyer   rad     9.82
1     619   dyer   sal     0.13
2     622   dyer   rad     7.80
3     622   dyer   sal     0.09
4     734     pb   rad     8.41
5     734   lake   sal     0.05
6     734     pb  temp   -21.50
7     735     pb   rad     7.22
8     735    NaN   sal     0.06
9     735    NaN  temp   -26.00
10    751     pb   rad     4.35
11    751     pb  temp   -18.50
12    751   lake   sal     0.10
13    752   lake   rad     2.19
14    752   lake   sal     0.09
15    752   lake  temp   -16.00
16    752    roe   sal    41.60
17    837   lake   rad     1.46
18    837   lake   sal     0.21
19    837    roe   sal    22.50
20    844    roe   rad    11.25
   ident   site       dated
0    619   DR-1  1927-02-08
2    734   DR-3  1939-01-07
6    837  MSK-4  1932-01-14
    name    lat    long  ident   site       dated
0   DR-1 -49.85 -128.57    619   DR-1  1927-02-08
1   DR-3 -47.15 -126.72    734   DR-3  1939-01-07
2  MSK-4 -48.87 -123.40    837  MSK-4  1932-01-14

(venv) E:\py3>python py21.py
      ident   personal    family
0      dyer    William      Dyer
1        pb      Frank   Pabodie
2      lake   Anderson      Lake
3       roe  Valentina   Roerich
4  danforth      Frank  Danforth
    name    lat    long
0   DR-1 -49.85 -128.57
1   DR-3 -47.15 -126.72
2  MSK-4 -48.87 -123.40
   ident   site       dated
0    619   DR-1  1927-02-08
1    622   DR-1  1927-02-10
2    734   DR-3  1939-01-07
3    735   DR-3  1930-01-12
4    751   DR-3  1930-02-26
5    752   DR-3         NaN
6    837  MSK-4  1932-01-14
7    844   DR-1  1932-03-22
    taken person quant  reading
0     619   dyer   rad     9.82
1     619   dyer   sal     0.13
2     622   dyer   rad     7.80
3     622   dyer   sal     0.09
4     734     pb   rad     8.41
5     734   lake   sal     0.05
6     734     pb  temp   -21.50
7     735     pb   rad     7.22
8     735    NaN   sal     0.06
9     735    NaN  temp   -26.00
10    751     pb   rad     4.35
11    751     pb  temp   -18.50
12    751   lake   sal     0.10
13    752   lake   rad     2.19
14    752   lake   sal     0.09
15    752   lake  temp   -16.00
16    752    roe   sal    41.60
17    837   lake   rad     1.46
18    837   lake   sal     0.21
19    837    roe   sal    22.50
20    844    roe   rad    11.25
   ident   site       dated
0    619   DR-1  1927-02-08
2    734   DR-3  1939-01-07
6    837  MSK-4  1932-01-14
    name    lat    long  ident   site       dated
0   DR-1 -49.85 -128.57    619   DR-1  1927-02-08
1   DR-3 -47.15 -126.72    734   DR-3  1939-01-07
2  MSK-4 -48.87 -123.40    837  MSK-4  1932-01-14
    name    lat    long  ident   site       dated
0   DR-1 -49.85 -128.57    619   DR-1  1927-02-08
1   DR-1 -49.85 -128.57    622   DR-1  1927-02-10
2   DR-1 -49.85 -128.57    844   DR-1  1932-03-22
3   DR-3 -47.15 -126.72    734   DR-3  1939-01-07
4   DR-3 -47.15 -126.72    735   DR-3  1930-01-12
5   DR-3 -47.15 -126.72    751   DR-3  1930-02-26
6   DR-3 -47.15 -126.72    752   DR-3         NaN
7  MSK-4 -48.87 -123.40    837  MSK-4  1932-01-14
   ident   personal   family  taken person quant  reading
0   dyer    William     Dyer    619   dyer   rad     9.82
1   dyer    William     Dyer    619   dyer   sal     0.13
2   dyer    William     Dyer    622   dyer   rad     7.80
3   dyer    William     Dyer    622   dyer   sal     0.09
4     pb      Frank  Pabodie    734     pb   rad     8.41
5     pb      Frank  Pabodie    734     pb  temp   -21.50
6     pb      Frank  Pabodie    735     pb   rad     7.22
7     pb      Frank  Pabodie    751     pb   rad     4.35
8     pb      Frank  Pabodie    751     pb  temp   -18.50
9   lake   Anderson     Lake    734   lake   sal     0.05
10  lake   Anderson     Lake    751   lake   sal     0.10
11  lake   Anderson     Lake    752   lake   rad     2.19
12  lake   Anderson     Lake    752   lake   sal     0.09
13  lake   Anderson     Lake    752   lake  temp   -16.00
14  lake   Anderson     Lake    837   lake   rad     1.46
15  lake   Anderson     Lake    837   lake   sal     0.21
16   roe  Valentina  Roerich    752    roe   sal    41.60
17   roe  Valentina  Roerich    837    roe   sal    22.50
18   roe  Valentina  Roerich    844    roe   rad    11.25
    ident   site       dated  taken person quant  reading
0     619   DR-1  1927-02-08    619   dyer   rad     9.82
1     619   DR-1  1927-02-08    619   dyer   sal     0.13
2     622   DR-1  1927-02-10    622   dyer   rad     7.80
3     622   DR-1  1927-02-10    622   dyer   sal     0.09
4     734   DR-3  1939-01-07    734     pb   rad     8.41
5     734   DR-3  1939-01-07    734   lake   sal     0.05
6     734   DR-3  1939-01-07    734     pb  temp   -21.50
7     735   DR-3  1930-01-12    735     pb   rad     7.22
8     735   DR-3  1930-01-12    735    NaN   sal     0.06
9     735   DR-3  1930-01-12    735    NaN  temp   -26.00
10    751   DR-3  1930-02-26    751     pb   rad     4.35
11    751   DR-3  1930-02-26    751     pb  temp   -18.50
12    751   DR-3  1930-02-26    751   lake   sal     0.10
13    752   DR-3         NaN    752   lake   rad     2.19
14    752   DR-3         NaN    752   lake   sal     0.09
15    752   DR-3         NaN    752   lake  temp   -16.00
16    752   DR-3         NaN    752    roe   sal    41.60
17    837  MSK-4  1932-01-14    837   lake   rad     1.46
18    837  MSK-4  1932-01-14    837   lake   sal     0.21
19    837  MSK-4  1932-01-14    837    roe   sal    22.50
20    844   DR-1  1932-03-22    844    roe   rad    11.25

标签
易学教程内所有资源均来自网络或用户发布的内容,如有违反法律规定的内容欢迎反馈
该文章没有解决你所遇到的问题?点击提问,说说你的问题,让更多的人一起探讨吧!