Pandas 데이터 분석 기초 실습-1

In [2]:

import pandas as pd

In [12]:

data_frame = pd.read_csv('data/friend_list.csv')
data_frame

Out[12]:

	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 [15]:

data_frame.head(2)  #앞에 두개

Out[15]:

	name	age	job
0	John	20	student
1	Jenny	30	developer

In [17]:

data_frame.tail(2)  #뒤에 두개 ,column = Series

Out[17]:

	name	age	job
6	BoBo	6	Dog
7	Sol	1	Dog

In [19]:

type(data_frame.name)   #type은 series
#Dataframe은 series의 결합체

Out[19]:

pandas.core.series.Series

In [26]:

#series 는 리스트로 만든다
list_tmp = [1,2,3]
s1 = pd.core.series.Series(list_tmp)    #첫번째 column
s2 = pd.core.series.Series(['one','two','three'])   #두번째 column

In [29]:

pd.DataFrame(data = dict(num = s1,word = s2))   #dataframe은 dict로

Out[29]:

	num	word
0	1	one
1	2	two
2	3	three

In [31]:

df = pd.read_csv('data/friend_list.csv')

In [32]:

df

Out[32]:

	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 [33]:

df.head()   #처음부터 5개까지(기본)

Out[33]:

	name	age	job
0	John	20	student
1	Jenny	30	developer
2	Nate	30	teacher
3	Julia	40	dentist
4	Brian	45	manager

In [35]:

df.tail() #뒤에서 5개까지(기본)

Out[35]:

	name	age	job
3	Julia	40	dentist
4	Brian	45	manager
5	Chris	25	intern
6	BoBo	6	Dog
7	Sol	1	Dog

In [37]:

df = pd.read_csv('data/friend_list.txt')    #콤마로 구분된 txt파일도 사용가능
df

Out[37]:

	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 [41]:

df = pd.read_csv('data/friend_list_tab.txt')    #다른 기준으로 분류 된 경우 데이터 프레임이 이상하게 나온다
df

Out[41]:

	name\tage\tjob
0	Jenny\t30\tdeveloper
1	Nate\t30\tteacher
2	Julia\t40\tdentist
3	Brian\t45\tmanager
4	Chris\t25\tintern
5	BoBo\t6\tDog
6	Sol\t1\tDog

In [42]:

df = pd.read_csv('data/friend_list_tab.txt',delimiter='\t')
#구분 기준이 다를 경우 delimeter를 줄것
df

Out[42]:

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

In [43]:

df = pd.read_csv('data/friend_list_no_head.csv',header = None)
#head 가 없는경우 header가 없음을 표시
df

Out[43]:

	0	1	2
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 [45]:

df.columns = ['name','age','job']   #column의 header를 넣기
df

Out[45]:

	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 [47]:

df = pd.read_csv('data/friend_list_no_head.csv',header=None,names = ['name','age','job'])
#1단계로 끝내기
df

Out[47]:

	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