1.1数据分析之------pandas

import  pandas  as pd

a=[1,4,7,9]
s=pd.Series(a)
s

0    1
1    4
2    7
3    9
dtype: int64

s.dtypes

dtype('int64')

s.values

array([1, 4, 7, 9], dtype=int64)

#修改索引
a=[1,4,7,9]
index=['a','b','c','d']
s=pd.Series(a,index)
s

a    1
b    4
c    7
d    9
dtype: int64

s.index

Index(['a', 'b', 'c', 'd'], dtype='object')

s

a    1
b    4
c    7
d    9
dtype: int64

a=[1,4,7,9]
index=list('rtyu')
s=pd.Series(a,index)
s

r    1
t    4
y    7
u    9
dtype: int64

s[s>5]

y    7
u    9
dtype: int64

dic = {
   'beijing':35000,'shanghai':71000,'guangzhou':16000,'shenzhen':5000}
s1=pd.Series(dic)
s1

beijing      35000
shanghai     71000
guangzhou    16000
shenzhen      5000
dtype: int64

s1['beijing']

35000

s1.keys()

Index(['beijing', 'shanghai', 'guangzhou', 'shenzhen'], dtype='object')

list(s1.items())

[('beijing', 35000),
 ('shanghai', 71000),
 ('guangzhou', 16000),
 ('shenzhen', 5000)]

s1.notnull()

beijing      True
shanghai     True
guangzhou    True
shenzhen     True
dtype: bool

pd.notnull(s1)

beijing      True
shanghai     True
guangzhou    True
shenzhen     True
dtype: bool

s1.name='xxxxxxx'
s1

beijing      35000
shanghai     71000
guangzhou    16000
shenzhen      5000
Name: xxxxxxx, dtype: int64

s1.index.name='qqqqqqqqqqq'
s1

qqqqqqqqqqq
beijing      35000
shanghai     71000
guangzhou    16000
shenzhen      5000
Name: xxxxxxx, dtype: int64

data = {
   'city':['beijing','beijing','beijing','shanghai','shanghai','shanghai'],
        'year':[2000,2001,2002,2001,2002,2003],
        'pop':[1.5, 1.7,3.6,2.4,2.9,3.2
    ]}
data

{'city': ['beijing', 'beijing', 'beijing', 'shanghai', 'shanghai', 'shanghai'],
 'year': [2000, 2001, 2002, 2001, 2002, 2003],
 'pop': [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}

df=pd.DataFrame(data)
df

	city	year	pop
0	beijing	2000	1.5
1	beijing	2001	1.7
2	beijing	2002	3.6
3	shanghai	2001	2.4
4	shanghai	2002	2.9
5	shanghai	2003	3.2

df.index

RangeIndex(start=0, stop=6, step=1)

df.columns

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

df.dtypes

city     object
year      int64
pop     float64
dtype: object

df.values

array([['beijing', 2000, 1.5],
       ['beijing', 2001, 1.7],
       ['beijing', 2002, 3.6],
       ['shanghai', 2001, 2.4],
       ['shanghai', 2002, 2.9],
       ['shanghai', 2003, 3.2]], dtype=object)

df.head(1)
df.tail(2)

	city	year	pop
4	shanghai	2002	2.9
5	shanghai	2003	3.2

df.columns

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

df1=pd.DataFrame(data,columns=['year', 'city', 'pop'])

df1

	year	city	pop
0	2000	beijing	1.5
1	2001	beijing	1.7
2	2002	beijing	3.6
3	2001	shanghai	2.4
4	2002	shanghai	2.9
5	2003	shanghai	3.2

df2 = pd.DataFrame(data,index=['a','b'