Pandas 데이터분석 기초실습 -3

데이터 프레임 파일로 저장하기¶

In [1]:

import pandas as pd

In [3]:

friends = [
    {'name':'Jone','age':20,'job':'student'},
    {'name':'Jenny','age':30,'job':None},
    {'name':'Nate','age':30,'job':'teacher'}
]
df = pd.DataFrame(friends)
df = df[['name','age','job']]
df.head()

Out[3]:

	name	age	job
0	Jone	20	student
1	Jenny	30	None
2	Nate	30	teacher

In [6]:

df.to_csv('friends.csv',index= True,header =True)
#index = True, header =True 는 default로 설정 되어 있음

In [8]:

df.to_csv('friends.csv',index = True, header = False)
#header 없이 저장

In [9]:

df.to_csv('friends.csv',index = False)
#index 없이 저장

In [11]:

df.to_csv('friends.csv',index = False, header = False,na_rep = '-')
#na replace '-'

데이터프레임 행 , 열 선택 및 필터 하기¶

In [14]:

import pandas as pd
from collections import OrderedDict

In [24]:

friend_ordered_dict =OrderedDict([ 
    ('name',['John','Jenny','Nate']),
    ('age',[20,30,30]),
    ('job',['student','developer','teacher'])
])
df = pd.DataFrame.from_dict(friend_ordered_dict)
df.head()

Out[24]:

	name	age	job
0	John	20	student
1	Jenny	30	developer
2	Nate	30	teacher

In [25]:

#Jenny와 Nate만 추출
df[1:3]

Out[25]:

	name	age	job
1	Jenny	30	developer
2	Nate	30	teacher

In [26]:

df = df[1:3]
df  #추출값 적용

Out[26]:

	name	age	job
1	Jenny	30	developer
2	Nate	30	teacher

In [28]:

friend_ordered_dict =OrderedDict([ 
    ('name',['John','Jenny','Nate']),
    ('age',[20,30,30]),
    ('job',['student','developer','teacher'])
])
df = pd.DataFrame.from_dict(friend_ordered_dict)

John과 Nate 만 원할때 loc함수¶

In [30]:

df.loc[[0,2]]

Out[30]:

	name	age	job
0	John	20	student
2	Nate	30	teacher

In [32]:

df = df.loc[[0,2]]
df

Out[32]:

	name	age	job
0	John	20	student
2	Nate	30	teacher

by column condition¶

In [34]:

friend_ordered_dict =OrderedDict([ 
    ('name',['John','Jenny','Nate']),
    ('age',[20,30,30]),
    ('job',['student','developer','teacher'])
])
df = pd.DataFrame.from_dict(friend_ordered_dict)

In [36]:

df[df.age > 25]

Out[36]:

	name	age	job
1	Jenny	30	developer
2	Nate	30	teacher

In [39]:

df.query('age>25')  #df[df.age > 25]와 같은결과

Out[39]:

	name	age	job
1	Jenny	30	developer
2	Nate	30	teacher

In [43]:

df[(df.age>25) & (df.name == 'Nate')]   #25세 이상, 이름이 Nate

Out[43]:

	name	age	job
2	Nate	30	teacher

Filter Column¶

by Index¶

In [52]:

friend_list = [
    ['John',20,'student'],
    ['Jenny',30,'developer'],
    ['Nate',30,'teacher']
]
df = pd.DataFrame.from_records(friend_list)
df

Out[52]:

	0	1	2
0	John	20	student
1	Jenny	30	developer
2	Nate	30	teacher

In [47]:

df.iloc[:,0:2]  #모든 row 의 0~1번 column

Out[47]:

	0	1
0	John	20
1	Jenny	30
2	Nate	30

In [54]:

df.iloc[0:2,0:2]

Out[54]:

	0	1
0	John	20
1	Jenny	30

by column name¶

In [57]:

df = pd.read_csv('data/friend_list_no_head.csv',header =None,names =['name','age','job'])
df

Out[57]:

	name	age	job
0	John	20	student
1	Jenny	30	developer
2	Nate	30	teacher
3	Julia	40	dentist
4	Brian	45	manager
5	Chris	25	intern
6	BoBo	6	Dog
7	Sol	1	Dog

In [60]:

#job column이 필요없을경우 ,job filter out
df_filtered  = df[['name','age']]

In [62]:

df_filtered

Out[62]:

	name	age
0	John	20
1	Jenny	30
2	Nate	30
3	Julia	40
4	Brian	45
5	Chris	25
6	BoBo	6
7	Sol	1

In [64]:

df.filter(items =['age','job']) #age와 job만 들은것 원함

Out[64]:

	age	job
0	20	student
1	30	developer
2	30	teacher
3	40	dentist
4	45	manager
5	25	intern
6	6	Dog
7	1	Dog

In [65]:

df

Out[65]:

	name	age	job
0	John	20	student
1	Jenny	30	developer
2	Nate	30	teacher
3	Julia	40	dentist
4	Brian	45	manager
5	Chris	25	intern
6	BoBo	6	Dog
7	Sol	1	Dog

In [67]:

#column name에 a 가 들어간 것만 원한다
df.filter(like = 'a',axis =1)

Out[67]:

	name	age
0	John	20
1	Jenny	30
2	Nate	30
3	Julia	40
4	Brian	45
5	Chris	25
6	BoBo	6
7	Sol	1

In [68]:

df

Out[68]:

	name	age	job
0	John	20	student
1	Jenny	30	developer
2	Nate	30	teacher
3	Julia	40	dentist
4	Brian	45	manager
5	Chris	25	intern
6	BoBo	6	Dog
7	Sol	1	Dog

In [72]:

#regex 사용(정규식)
#column name이 b로 끝나는 것만 추출
df.filter(regex = 'b$',axis = 1 )

Out[72]:

	job
0	student
1	developer
2	teacher
3	dentist
4	manager
5	intern
6	Dog
7	Dog