Python数据分析_第05课：Pandas基础及数据读写_笔记

GitHub: https://github.com/RealEmperor/Python-for-Data-Analysis

pandas

Series

import numpy as np
import pandas as pd
import sys
from pandas import Series, DataFrame


obj = Series([4, 7, -5, 3])
print(obj)
print(obj.values)
print(obj.index)

0    4
1    7
2   -5
3    3
dtype: int64
[ 4  7 -5  3]
RangeIndex(start=0, stop=4, step=1)

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

d    4
b    7
a   -5
c    3
dtype: int64
Index(['d', 'b', 'a', 'c'], dtype='object')
-5

obj2['d'] = 6
obj2[['c', 'a', 'd']]

c    3
a   -5
d    6
dtype: int64

obj2[obj2 > 0]

d    6
b    7
c    3
dtype: int64

obj2 * 2

d    12
b    14
a   -10
c     6
dtype: int64

np.exp(obj2)

d     403.428793
b    1096.633158
a       0.006738
c      20.085537
dtype: float64

'b' in obj2

True

'e' in obj2

False

sdata = {
   'Ohio': 35000, 'Texas': 71000, 'Oregon': 16000, 'Utah': 5000}
obj3 = Series(sdata)
print(obj3)

Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64

states = ['California', 'Ohio', 'Oregon', 'Texas']
obj4 = Series(sdata, index=states)
print(obj4)

California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64

pd.isnull(obj4)

California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool

pd.notnull(obj4)

California    False
Ohio           True
Oregon         True
Texas          True
dtype: bool

obj4.isnull()

California     True
Ohio          False
Oregon        False
Texas         False
dtype: bool

print(obj3)
print(obj4)
print(obj3 + obj4)

Ohio      35000
Oregon    16000
Texas     71000
Utah       5000
dtype: int64
California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64
California         NaN
Ohio           70000.0
Oregon         32000.0
Texas         142000.0
Utah               NaN
dtype: float64

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

obj.index = ['Bob', 'Steve', 'Jeff', 'Ryan']
print(obj)

Bob      4
Steve    7
Jeff    -5
Ryan     3
dtype: int64

dataframe

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)

   pop   state  year
0  1.5    Ohio  2000
1  1.7    Ohio  2001
2  3.6    Ohio  2002
3  2.4  Nevada  2001
4  2.9  Nevada  2002

DataFrame(data, columns=['year', 'state', 'pop'])

	year	state	pop
0	2000	Ohio	1.5
1	2001	Ohio	1.7
2	2002	Ohio	3.6
3	2001	Nevada	2.4
4	2002	Nevada	2.9

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

       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
Index(['year', 'state', 'pop', 'debt'], dtype='object')

print(frame2['state'])
print(frame2.year)
print(frame2.loc['three'])

one        Ohio
two        Ohio
three      Ohio
four     Nevada
five     Nevada
Name: state, dtype: object
one      2000
two      2001
three    2002
four     2001
five     2002
Name: year, dtype: int64
year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object

frame2['debt'] = 16.5
print(frame2)

       year   state  pop  debt
one    2000    Ohio  1.5  16.5
two    2001    Ohio  1.7  16.5
three  2002    Ohio  3.6  16.5
four   2001  Nevada  2.4  16.5
five   2002  Nevada  2.9  16.5

frame2['debt'] = np.arange(5.)