기초, Series, DataFrame 사용법, Sublime Text 사용법

[참조] http://pinkwink.kr/734, http://pinkwink.kr/735

1) pandas 설치

cd Python35

cd script

pip3 install pandas

2) 에디터로 sublime text 를 사용해본다.

- 우측하단에 Plain Text 를 Python 으로 변경

- https://packagecontrol.io/installation 에 접속해서 import urlib....어쩌고하는 문구를 복사한뒤,

sublime 에서 Ctrl + ` 을 눌러서 붙여넣는다.

- sublime text 를 재시작한다.

- Preferences > Package Control  혹은 SHIFT + CTRL + P

  Package Conotrol: Add Repository 검색후, 하단 URL에 https://github.com/wuub/SublimeREPL 을 

  붙여넣는다.

[ Series ]

3) 

from pandas import Series, DataFrame

import pandas as pd

import numpy as np

obj = Series([4,7,-5,3])

print(obj.index)

print(obj.values)

print(obj)

obj.index = ['Bob','steve','Jeff','Ryan']

print(obj)

-------------------

RangeIndex(start=0, stop=4, step=1)

[ 4  7 -5  3]

0    4

1    7

2   -5

3    3

dtype: int64

Bob      4

steve    7

Jeff    -5

Ryan     3

dtype: int64

4)

obj2 = Series([4,7,-5,3], index=['b','b','a','c'])

print(obj2)

print(obj2['a'])

print(obj2['b'])

print(np.exp(obj2))

print(obj2 * 2)

----------------------------

b    4

b    7

a   -5

c    3

dtype: int64

-5

b    4

b    7

dtype: int64

b      54.598150

b    1096.633158

a       0.006738

c      20.085537

dtype: float64

b     8

b    14

a   -10

c     6

dtype: int64

5)

sdata = {'Ohio':35000,'Texas':71000,'Oregon':16000,'Utah':5000}

obj3 = Series(sdata)

print(obj3)

states=['California', 'Ohio', 'Oregon', 'Texas']

obj4 = Series(sdata, index=states)

print(obj4)

pd.isnull(obj4)

------------------------------

Ohio      35000

Texas     71000

Oregon    16000

Utah       5000

dtype: int64

California        NaN

Ohio          35000.0

Oregon        16000.0

Texas         71000.0

dtype: float64

California     True

Ohio          False

Oregon        False

Texas         False

dtype: bool

6)

pd.notnull(obj4)

California     True

Ohio          False

Oregon        False

Texas         False

dtype: bool

7)

obj4.isnull()

California     True

Ohio          False

Oregon        False

Texas         False

dtype: bool

8)

print(obj3 + obj4)

California         NaN

Ohio           70000.0

Oregon         32000.0

Texas         142000.0

Utah               NaN

dtype: float64

9)

obj4.name = "population"

obj4.index.name="state"

print(obj4)

state

California        NaN

Ohio          35000.0

Oregon        16000.0

Texas         71000.0

Name: population, dtype: float64

[ DataFrame ]

1)

from pandas import Series, DataFrame

import pandas as pd

import numpy as np

data = {'state':['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada'],

        'year':[2000,2001,2002,2001,2002],

        'pop':[1.5,1.7,3.6,2.4,2.9]}

frame = DataFrame(data)

print(frame)

    state  year  pop

0    Ohio  2000  1.5

1    Ohio  2001  1.7

2    Ohio  2002  3.6

3  Nevada  2001  2.4

4  Nevada  2002  2.9

2)

frame2 = DataFrame(data, columns=['year','state','pop','debt'], index=['one','two','three','four','five'])

print(frame2)

print(frame2.loc['three'])

frame2.debt = 3.14

print(frame2)

       year   state  pop debt

one    2000    Ohio  1.5  NaN

two    2001    Ohio  1.7  NaN

three  2002    Ohio  3.6  NaN

four   2001  Nevada  2.4  NaN

five   2002  Nevada  2.9  NaN

year     2002

state    Ohio

pop       3.6

debt      NaN

Name: three, dtype: object

       year   state  pop  debt

one    2000    Ohio  1.5  3.14

two    2001    Ohio  1.7  3.14

three  2002    Ohio  3.6  3.14

four   2001  Nevada  2.4  3.14

five   2002  Nevada  2.9  3.14

3)

frame2.debt = np.arange(5)

print(frame2)

val = Series([-1.2, -1.5, -1.7], index=['two', 'four','five'])

frame2.debt = val

frame2

       year   state  pop  debt

one    2000    Ohio  1.5     0

two    2001    Ohio  1.7     1

three  2002    Ohio  3.6     2

four   2001  Nevada  2.4     3

five   2002  Nevada  2.9     4

year state pop debt

one 2000 Ohio 1.5 NaN

two 2001 Ohio 1.7 -1.2

three 2002 Ohio 3.6 NaN

four 2001 Nevada 2.4 -1.5

five 2002 Nevada 2.9 -1.7

4)

frame2['eastern'] = frame2.state== 'Ohio'

frame2

  year state pop debt eastern

one 2000 Ohio 1.5 NaN True

two 2001 Ohio 1.7 -1.2 True

three 2002 Ohio 3.6 NaN True

four 2001 Nevada 2.4 -1.5 False

five 2002 Nevada 2.9 -1.7 False

5)

del frame2['eastern']

frame2

  year state pop debt

one 2000 Ohio 1.5 NaN

two 2001 Ohio 1.7 -1.2

three 2002 Ohio 3.6 NaN

four 2001 Nevada 2.4 -1.5

five 2002 Nevada 2.9 -1.7

6)

pop = {'Nevada':{2001:2.4, 2002:2.9}, 'Ohio':{2000:1.5, 2001:1.7, 2002:3.6}}

frame3 = DataFrame(pop)

frame3

  Nevada Ohio

2000 NaN 1.5

2001 2.4 1.7

2002 2.9 3.6

7)

frame3.T

  2000 2001 2002

Nevada NaN 2.4 2.9

Ohio 1.5 1.7 3.6