Pandas 기초 8 (데이터 그룹화 및 그룹데이터 생성)

In [1]:

import pandas as pd

In [2]:

student_list = [{'name': 'John', 'major': "Computer Science", 'sex': "male"},
                {'name': 'Nate', 'major': "Computer Science", 'sex': "male"},
                {'name': 'Abraham', 'major': "Physics", 'sex': "male"},
                {'name': 'Brian', 'major': "Psychology", 'sex': "male"},
                {'name': 'Janny', 'major': "Economics", 'sex': "female"},
                {'name': 'Yuna', 'major': "Economics", 'sex': "female"},
                {'name': 'Jeniffer', 'major': "Computer Science", 'sex': "female"},
                {'name': 'Edward', 'major': "Computer Science", 'sex': "male"},
                {'name': 'Zara', 'major': "Psychology", 'sex': "female"},
                {'name': 'Wendy', 'major': "Economics", 'sex': "female"},
                {'name': 'Sera', 'major': "Psychology", 'sex': "female"}
         ]
df = pd.DataFrame(student_list, columns = ['name', 'major', 'sex'])
df

Out[2]:

	name	major	sex
0	John	Computer Science	male
1	Nate	Computer Science	male
2	Abraham	Physics	male
3	Brian	Psychology	male
4	Janny	Economics	female
5	Yuna	Economics	female
6	Jeniffer	Computer Science	female
7	Edward	Computer Science	male
8	Zara	Psychology	female
9	Wendy	Economics	female
10	Sera	Psychology	female

In [3]:

# 전공으로 그룹화
groupby_major = df.groupby('major')

In [4]:

groupby_major.groups

Out[4]:

{'Computer Science': [0, 1, 6, 7], 'Economics': [4, 5, 9], 'Physics': [2], 'Psychology': [3, 8, 10]}

In [5]:

#보기좋게
for name, group in groupby_major:
    print(name + ":" + str(len(group)))
    print(group)
    print()

Computer Science:4
       name             major     sex
0      John  Computer Science    male
1      Nate  Computer Science    male
6  Jeniffer  Computer Science  female
7    Edward  Computer Science    male

Economics:3
    name      major     sex
4  Janny  Economics  female
5   Yuna  Economics  female
9  Wendy  Economics  female

Physics:1
      name    major   sex
2  Abraham  Physics  male

Psychology:3
     name       major     sex
3   Brian  Psychology    male
8    Zara  Psychology  female
10   Sera  Psychology  female

In [8]:

# 그룹지어 새로 데이터프레임 생성 .reset_index()는 인덱스정렬에 사용
df_major_cnt = pd.DataFrame({'count' : groupby_major.size()}).reset_index()
df_major_cnt

Out[8]:

	major	count
0	Computer Science	4
1	Economics	3
2	Physics	1
3	Psychology	3

In [9]:

# 성별로 그룹화
groupby_sex = df.groupby('sex')
for name, group in groupby_sex:
    print(name +":"+ str(len(group)))
    print(group)
    print()

female:6
        name             major     sex
4      Janny         Economics  female
5       Yuna         Economics  female
6   Jeniffer  Computer Science  female
8       Zara        Psychology  female
9      Wendy         Economics  female
10      Sera        Psychology  female

male:5
      name             major   sex
0     John  Computer Science  male
1     Nate  Computer Science  male
2  Abraham           Physics  male
3    Brian        Psychology  male
7   Edward  Computer Science  male

In [ ]: