Pandas 데이터프레임 오름차순, 내림차순 정렬 .Sort_values() ,sort_index()

SORTING AND ORDERING¶

In [41]:

df = pd.DataFrame({'Employee ID':[111, 222, 333, 444], 
                   'Employee Name':['Chanel', 'Steve', 'Mitch', 'Bird'], 
                   'Salary [$/h]':[35, 29, 38, 20], 
                   'Years of Experience':[3, 4 ,9, 1]})
df

Out[41]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
0	111	Chanel	35	3
1	222	Steve	29	4
2	333	Mitch	38	9
3	444	Bird	20	1

In [42]:

# 경력을 오름차순으로 정렬하세요 

In [43]:

my_dict = {"홍길동" : 23, "김나나" : 34, "Mike" : 28, "Alice": 42}

In [44]:

my_dict

Out[44]:

{'홍길동': 23, '김나나': 34, 'Mike': 28, 'Alice': 42}

In [47]:

sorted(my_dict.values())

Out[47]:

[23, 28, 34, 42]

In [53]:

df.sort_values("Years of Experience")

Out[53]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
3	444	Bird	20	1
0	111	Chanel	35	3
1	222	Steve	29	4
2	333	Mitch	38	9

In [ ]:

# 경력 내림차순 정렬

In [52]:

df.sort_values("Years of Experience", ascending=False)

Out[52]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
2	333	Mitch	38	9
1	222	Steve	29	4
0	111	Chanel	35	3
3	444	Bird	20	1

In [54]:

# 이름과 경력으로 정렬하세요
# ( 이름으로 정렬하고, 이름이 같으면 경력으로 정렬하라는 뜻 )

In [57]:

df = pd.DataFrame({'Employee ID':[111, 222, 333, 444, 555], 
                   'Employee Name':['Chanel', 'Steve', 'Mitch', 'Bird','Chanel'], 
                   'Salary [$/h]':[35, 29, 38, 20, 35], 
                   'Years of Experience':[3, 4 ,9, 1, 6]})

In [59]:

df

Out[59]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
0	111	Chanel	35	3
1	222	Steve	29	4
2	333	Mitch	38	9
3	444	Bird	20	1
4	555	Chanel	35	6

In [60]:

df.sort_values( ['Employee Name' , 'Years of Experience' ])

Out[60]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
3	444	Bird	20	1
0	111	Chanel	35	3
4	555	Chanel	35	6
2	333	Mitch	38	9
1	222	Steve	29	4

In [61]:

# 이름과 경력으로 정렬하되,
# 이름은 오름차순이고, 경력은 내림차순으로 저열하세요.

In [64]:

df.sort_values( [ 'Employee Name' , ('Years of Experience' ,ascending=False )])

  Cell In [64], line 1
    df.sort_values( [ 'Employee Name' , ('Years of Experience' ,ascending=False )])
                                                                         ^
SyntaxError: invalid syntax

In [66]:

df.sort_values( [ 'Employee Name' , 'Years of Experience' ] , ascending= [True,False])

Out[66]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
3	444	Bird	20	1
4	555	Chanel	35	6
0	111	Chanel	35	3
2	333	Mitch	38	9
1	222	Steve	29	4

In [ ]:

# 인덱스를 내림차순으로 정렬하세요

In [67]:

df

Out[67]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
0	111	Chanel	35	3
1	222	Steve	29	4
2	333	Mitch	38	9
3	444	Bird	20	1
4	555	Chanel	35	6

In [70]:

df.sort_index(ascending=False) # ascending 디폴트값은 True

Out[70]:

	Employee ID	Employee Name	Salary [$/h]	Years of Experience
4	555	Chanel	35	6
3	444	Bird	20	1
2	333	Mitch	38	9
1	222	Steve	29	4
0	111	Chanel	35	3