pandas

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

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

0    4
1    7
2   -5
3    3
dtype: int64

obj.values

array([ 4,  7, -5,  3], dtype=int64)

obj.index

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

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

d    4
b    7
a   -5
c    3
dtype: int64

obj2.index

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

#索引取值
obj2['a']

-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

'r' in obj2

False

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

Ohio      35000
Texas     71000
Oregon    16000
Utah       5000
dtype: int64

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

California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64

#缺失值
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

#根据运算的索引标签自动对齐数据：
obj3 

Ohio      35000
Texas     71000
Oregon    16000
Utah       5000
dtype: int64

obj4

California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
dtype: float64

obj3 + obj4

California         NaN
Ohio           70000.0
Oregon         32000.0
Texas         142000.0
Utah               NaN
dtype: float64

obj4.name = 'population'
obj4.index.name = 'state'
obj4

state
California        NaN
Ohio          35000.0
Oregon        16000.0
Texas         71000.0
Name: population, dtype: float64

obj

0    4
1    7
2   -5
3    3
dtype: int64

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

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

#DdataFrame 表格型数据结构

data = data = {'state': ['Ohio', 'Ohio', 'Ohio', 'Nevada', 'Nevada', 'Nevada'],
        'year': [2000, 2001, 2002, 2001, 2002, 2003],
        'pop': [1.5, 1.7, 3.6, 2.4, 2.9, 3.2]}
frame = pd.DataFrame(data)

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
5	Nevada	2003	3.2

frame.head()  #前五行

	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

pd.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
5	2003	Nevada	3.2

frame2 = pd.DataFrame(data, columns=['year', 'state', 'pop', 'debt'],
                      index=['one', 'two', 'three', 'four', 'five', 'six'])
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
six	2003	Nevada	3.2	NaN

frame2.columns

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

frame2['state'] #返回Series

one        Ohio
two        Ohio
three      Ohio
four     Nevada
five     Nevada
six      Nevada
Name: state, dtype: object

frame2.year

one      2000
two      2001
three    2002
four     2001
five     2002
six      2003
Name: year, dtype: int64

frame2.loc['three']    #loc返回行数据

year     2002
state    Ohio
pop       3.6
debt      NaN
Name: three, dtype: object

frame2['debt'] = 16.5
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
six	2003	Nevada	3.2	16.5

frame2['debt'] = np.arange(6.)
frame2

	year	state	pop	debt
one	2000	Ohio	1.5	0.0
two	2001	Ohio	1.7	1.0
three	2002	Ohio	3.6	2.0
four	2001	Nevada	2.4	3.0
five	2002	Nevada	2.9	4.0
six	2003	Nevada	3.2	5.0

val = pd.Series([-1.2,-1.5,-1.7],index = ['two','four','five'])
frame2['debt'] = val
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
six	2003	Nevada	3.2	NaN

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
six	2003	Nevada	3.2	NaN	False

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
six	2003	Nevada	3.2	NaN

#嵌套字典
pop = {'Nevada': {2001: 2.4, 2002: 2.9},
       'Ohio': {2000: 1.5, 2001: 1.7, 2002: 3.6}}
#外层字典的键作为列，内层键则作为行索引
frame3 = pd.DataFrame(pop)
frame3

	Nevada	Ohio
2000	NaN	1.5
2001	2.4	1.7
2002	2.9	3.6

#转置
frame3.T

	2000	2001	2002
Nevada	NaN	2.4	2.9
Ohio	1.5	1.7	3.6

frame3.index.name = 'year';frame3.columns.name = 'state'
frame3

state	Nevada	Ohio
year
2000	NaN	1.5
2001	2.4	1.7
2002	2.9	3.6

frame3.values

array([[nan, 1.5],
       [2.4, 1.7],
       [2.9, 3.6]])

frame2.values

array([[2000, 'Ohio', 1.5, nan],
       [2001, 'Ohio', 1.7, -1.2],
       [2002, 'Ohio', 3.6, nan],
       [2001, 'Nevada', 2.4, -1.5],
       [2002, 'Nevada', 2.9, -1.7],
       [2003, 'Nevada', 3.2, nan]], dtype=object)

#索引对象 Index
obj = pd.Series(range(3),index=['a','b','c'])
index = obj.index
index

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

index[1:]

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

labels = pd.Index(np.arange(3))
labels

Int64Index([0, 1, 2], dtype='int64')

obj2 = pd.Series([1.5,-2.5,0],index=labels)
obj2

0    1.5
1   -2.5
2    0.0
dtype: float64

obj2.index is labels

True

frame3

	Nevada	Ohio
2000	NaN	1.5
2001	2.4	1.7
2002	2.9	3.6

frame3.columns

Index(['Nevada', 'Ohio'], dtype='object')

'Ohio'in frame3.columns

True

dup_labels = pd.Index(['foo','foo', 'bar', 'bar'])
dup_labels

Index(['foo', 'foo', 'bar', 'bar'], dtype='object')

#基本功能

#重新索引
obj = pd.Series([4.5, 7.2, -5.3, 3.6], index=['d', 'b', 'a', 'c'])
obj

d    4.5
b    7.2
a   -5.3
c    3.6
dtype: float64

obj2 = obj.reindex(['a', 'b', 'c', 'd', 'e'])
obj2

a   -5.3
b    7.2
c    3.6
d    4.5
e    NaN
dtype: float64

obj3 = pd.Series(['blue','purple','yellow'],index=[0,2,4])
obj3

0      blue
2    purple
4    yellow
dtype: object

obj3.reindex(range(6),method='ffill')#插值处理

0      blue
1      blue
2    purple
3    purple
4    yellow
5    yellow
dtype: object

frame = pd.DataFrame(np.arange(9).reshape((3, 3)),
                         index=['a', 'c', 'd'],
                         columns=['Ohio', 'Texas', 'California'])
frame

	Ohio	Texas	California
a	0	1	2
c	3	4	5
d	6	7	8

frame2 = frame.reindex(['a','b','c','d'])
frame2

	Ohio	Texas	California
a	0.0	1.0	2.0
b	NaN	NaN	NaN
c	3.0	4.0	5.0
d	6.0	7.0	8.0

states = ['Texas','Utah','California']
frame.reindex(columns=states)

	Texas	Utah	California
a	1	NaN	2
c	4	NaN	5
d	7	NaN	8

#丢弃指定轴上的项 drop
obj = pd.Series(np.arange(5.), index=['a', 'b', 'c', 'd', 'e'])
obj

a    0.0
b    1.0
c    2.0
d    3.0
e    4.0
dtype: float64

new_obj = obj.drop('c')
new_obj

a    0.0
b    1.0
d    3.0
e    4.0
dtype: float64

obj.drop(['d','c'])

a    0.0
b    1.0
e    4.0
dtype: float64

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
                        index=['Ohio', 'Colorado', 'Utah', 'New York'],
                        columns=['one', 'two', 'three', 'four'])

data

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

data.drop(['Colorado','Ohio'])

	one	two	three	four
Utah	8	9	10	11
New York	12	13	14	15

data.drop('two',axis=1) #axis指定行或列

	one	three	four
Ohio	0	2	3
Colorado	4	6	7
Utah	8	10	11
New York	12	14	15

data.drop(['two','four'],axis = 'columns')

	one	three
Ohio	0	2
Colorado	4	6
Utah	8	10
New York	12	14

obj

a    0.0
b    1.0
c    2.0
d    3.0
e    4.0
dtype: float64

obj.drop('c',inplace=True) #inplace销毁被删除数据
obj

a    0.0
b    1.0
d    3.0
e    4.0
dtype: float64

obj

a    0.0
b    1.0
d    3.0
e    4.0
dtype: float64

#索引，选取和过滤
obj = pd.Series(np.arange(4),index=['a', 'b', 'c', 'd'])
obj

a    0
b    1
c    2
d    3
dtype: int32

obj['b']

1

obj[1]

1

obj[2:4]

c    2
d    3
dtype: int32

obj[['b','a','d']]

b    1
a    0
d    3
dtype: int32

obj[[1,3]]

b    1
d    3
dtype: int32

obj[obj<2]

a    0
b    1
dtype: int32

#利用标签的切片运算与普通的Python切片运算不同，其末端是包含的
obj['b':'c']

b    1
c    2
dtype: int32

obj['b':'c'] = 5
obj

a    0
b    5
c    5
d    3
dtype: int32

data = pd.DataFrame(np.arange(16).reshape((4, 4)),
                      index=['Ohio', 'Colorado', 'Utah', 'New York'],
                      columns=['one', 'two', 'three', 'four'])

data

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

data['two']

Ohio         1
Colorado     5
Utah         9
New York    13
Name: two, dtype: int32

data[['three','one']]

	three	one
Ohio	2	0
Colorado	6	4
Utah	10	8
New York	14	12

data[:2]

	one	two	three	four
Ohio	0	1	2	3
Colorado	4	5	6	7

data[data['three']>5]

	one	two	three	four
Colorado	4	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

data<5

	one	two	three	four
Ohio	True	True	True	True
Colorado	True	False	False	False
Utah	False	False	False	False
New York	False	False	False	False

data[data<5] = 0
data

	one	two	three	four
Ohio	0	0	0	0
Colorado	0	5	6	7
Utah	8	9	10	11
New York	12	13	14	15

#利用loc和iloc进行选取；标签运算符
data.loc['Colorado',['two','three']]

two      5
three    6
Name: Colorado, dtype: int32

data.iloc[2,[3,0,1]]

four    11
one      8
two      9
Name: Utah, dtype: int32

data.iloc[2]

one       8
two       9
three    10
four     11
Name: Utah, dtype: int32

data.iloc[[1,2],[3,0,1]]

	four	one	two
Colorado	7	0	5
Utah	11	8	9

data.loc[:'Utah','two']

Ohio        0
Colorado    5
Utah        9
Name: two, dtype: int32

data.iloc[:,:3][data.three>5]

	one	two	three
Colorado	0	5	6
Utah	8	9	10
New York	12	13	14

#整数索引
ser = pd.Series(np.arange(3))
ser

0    0
1    1
2    2
dtype: int32

ser[-1]

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

KeyError                                  Traceback (most recent call last)

 in ()
----> 1 ser[-1]


C:\Anaconda\lib\site-packages\pandas\core\series.py in __getitem__(self, key)
    765         key = com._apply_if_callable(key, self)
    766         try:
--> 767             result = self.index.get_value(self, key)
    768 
    769             if not is_scalar(result):


C:\Anaconda\lib\site-packages\pandas\core\indexes\base.py in get_value(self, series, key)
   3116         try:
   3117             return self._engine.get_value(s, k,
-> 3118                                           tz=getattr(series.dtype, 'tz', None))
   3119         except KeyError as e1:
   3120             if len(self) > 0 and self.inferred_type in ['integer', 'boolean']:


pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_value()


pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_value()


pandas\_libs\index.pyx in pandas._libs.index.IndexEngine.get_loc()


pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()


pandas\_libs\hashtable_class_helper.pxi in pandas._libs.hashtable.Int64HashTable.get_item()


KeyError: -1

ser2 = pd.Series(np.arange(3.), index=['a', 'b', 'c']) #非整数索引
ser2[-1]

2.0

ser[:1]

0    0
dtype: int32

ser.loc[:1] #注意区别

0    0
1    1
dtype: int32

#算术运算和数据对齐
s1 = pd.Series([7.3, -2.5, 3.4, 1.5], index=['a', 'c', 'd', 'e'])
s2 = pd.Series([-2.1, 3.6, -1.5, 4, 3.1],
               index=['a', 'c', 'e', 'f', 'g'])
s1

a    7.3
c   -2.5
d    3.4
e    1.5
dtype: float64

s2

a   -2.1
c    3.6
e   -1.5
f    4.0
g    3.1
dtype: float64

s1 + s2  #对齐操作

a    5.2
c    1.1
d    NaN
e    0.0
f    NaN
g    NaN
dtype: float64

df1 = pd.DataFrame(np.arange(9.).reshape((3, 3)), columns=list('bcd'),
                    index=['Ohio', 'Texas', 'Colorado'])
df2 = pd.DataFrame(np.arange(12.).reshape((4, 3)), columns=list('bde'),
                       index=['Utah', 'Ohio', 'Texas', 'Oregon'])
df1

	b	c	d
Ohio	0.0	1.0	2.0
Texas	3.0	4.0	5.0
Colorado	6.0	7.0	8.0

df2

	b	d	e
Utah	0.0	1.0	2.0
Ohio	3.0	4.0	5.0
Texas	6.0	7.0	8.0
Oregon	9.0	10.0	11.0

df1 + df2 #DataFrame对象相加，没有共用的列或行标签，结果都会是空

	b	c	d	e
Colorado	NaN	NaN	NaN	NaN
Ohio	3.0	NaN	6.0	NaN
Oregon	NaN	NaN	NaN	NaN
Texas	9.0	NaN	12.0	NaN
Utah	NaN	NaN	NaN	NaN

#在算术方法中填充值
df1 = pd.DataFrame(np.arange(12.).reshape((3, 4)),
                    columns=list('abcd'))
df2 = pd.DataFrame(np.arange(20.).reshape((4, 5)),
                    columns=list('abcde'))  
df2.loc[1,'b'] = np.nan

df1

	a	b	c	d
0	0.0	1.0	2.0	3.0
1	4.0	5.0	6.0	7.0
2	8.0	9.0	10.0	11.0

df2

	a	b	c	d	e
0	0.0	1.0	2.0	3.0	4.0
1	5.0	NaN	7.0	8.0	9.0
2	10.0	11.0	12.0	13.0	14.0
3	15.0	16.0	17.0	18.0	19.0

df1 + df2

	a	b	c	d	e
0	0.0	2.0	4.0	6.0	NaN
1	9.0	NaN	13.0	15.0	NaN
2	18.0	20.0	22.0	24.0	NaN
3	NaN	NaN	NaN	NaN	NaN

df1.add(df2,fill_value=0)   #指定填充值

	a	b	c	d	e
0	0.0	2.0	4.0	6.0	4.0
1	9.0	5.0	13.0	15.0	9.0
2	18.0	20.0	22.0	24.0	14.0
3	15.0	16.0	17.0	18.0	19.0

#DataFrame和Series之间的运算
arr = np.arange(12).reshape(3,4)
arr

array([[ 0,  1,  2,  3],
       [ 4,  5,  6,  7],
       [ 8,  9, 10, 11]])

arr[0]

array([0, 1, 2, 3])

arr - arr[0]    #广播

array([[0, 0, 0, 0],
       [4, 4, 4, 4],
       [8, 8, 8, 8]])

frame = pd.DataFrame(np.arange(12.).reshape((4, 3)),
                      columns=list('bde'),
                      index=['Utah', 'Ohio', 'Texas', 'Oregon'])
series =frame.iloc[0]
frame

	b	d	e
Utah	0.0	1.0	2.0
Ohio	3.0	4.0	5.0
Texas	6.0	7.0	8.0
Oregon	9.0	10.0	11.0

series

b    0.0
d    1.0
e    2.0
Name: Utah, dtype: float64

frame - series

	b	d	e
Utah	0.0	0.0	0.0
Ohio	3.0	3.0	3.0
Texas	6.0	6.0	6.0
Oregon	9.0	9.0	9.0

series2 = pd.Series(range(3), index=['b', 'e', 'f'])
frame + series2

	b	d	e	f
Utah	0.0	NaN	3.0	NaN
Ohio	3.0	NaN	6.0	NaN
Texas	6.0	NaN	9.0	NaN
Oregon	9.0	NaN	12.0	NaN

series3 = frame['d']
frame

	b	d	e
Utah	0.0	1.0	2.0
Ohio	3.0	4.0	5.0
Texas	6.0	7.0	8.0
Oregon	9.0	10.0	11.0

series3

Utah       1.0
Ohio       4.0
Texas      7.0
Oregon    10.0
Name: d, dtype: float64

frame.sub(series3,axis='index')

	b	d	e
Utah	-1.0	0.0	1.0
Ohio	-1.0	0.0	1.0
Texas	-1.0	0.0	1.0
Oregon	-1.0	0.0	1.0

#函数应用和映射 ufuncs（元素级数组方法）

frame = pd.DataFrame(np.random.randn(4, 3), columns=list('bde'),
                      index=['Utah', 'Ohio', 'Texas', 'Oregon'])
frame

	b	d	e
Utah	-0.951265	-0.498273	-0.388690
Ohio	1.988546	0.370789	-0.488038
Texas	0.692938	-0.160944	0.654771
Oregon	-1.314237	1.163286	-1.687210

np.abs(frame)

	b	d	e
Utah	0.951265	0.498273	0.388690
Ohio	1.988546	0.370789	0.488038
Texas	0.692938	0.160944	0.654771
Oregon	1.314237	1.163286	1.687210

f = lambda x:x.max()-x.min()
frame.apply(f)  #默认列执行f

b    3.302783
d    1.661559
e    2.341980
dtype: float64

frame.apply(f,axis='columns')#行执行f

Utah      0.562574
Ohio      2.476585
Texas     0.853882
Oregon    2.850495
dtype: float64

def f(x):
    return pd.Series([x.min(), x.max()], index=['min', 'max'])
frame.apply(f)     #接受多值的series函数

	b	d	e
min	-1.314237	-0.498273	-1.687210
max	1.988546	1.163286	0.654771

format = lambda x: '%.2f' % x
frame.applymap(format)      #元素级函数

	b	d	e
Utah	-0.95	-0.50	-0.39
Ohio	1.99	0.37	-0.49
Texas	0.69	-0.16	0.65
Oregon	-1.31	1.16	-1.69

frame['e'].map(format)     #区分map与applymap

Utah      -0.39
Ohio      -0.49
Texas      0.65
Oregon    -1.69
Name: e, dtype: object

# 排序和排名

obj = pd.Series(range(4), index=['d', 'a', 'b', 'c'])
obj.sort_index()

a    1
b    2
c    3
d    0
dtype: int64

frame = pd.DataFrame(np.arange(8).reshape((2, 4)),
                       index=['three', 'one'],
                       columns=['d', 'a', 'b', 'c'])
frame.sort_index()

	d	a	b	c
one	4	5	6	7
three	0	1	2	3

frame.sort_index(axis=1,ascending=False)

	d	c	b	a
three	0	3	2	1
one	4	7	6	5

obj = pd.Series([4,7,-3,2])
obj.sort_values()

2   -3
3    2
0    4
1    7
dtype: int64

obj = pd.Series([4, np.nan, 7, np.nan, -3, 2])
obj.sort_values()

4   -3.0
5    2.0
0    4.0
2    7.0
1    NaN
3    NaN
dtype: float64

frame = pd.DataFrame({'b': [4, 7, -3, 2], 'a': [0, 1, 0, 1]})
frame

	b	a
0	4	0
1	7	1
2	-3	0
3	2	1

frame.sort_values(by='b')

	b	a
2	-3	0
3	2	1
0	4	0
1	7	1

frame.sort_values(by=['a','b'])

	b	a
2	-3	0
0	4	0
3	2	1
1	7	1

obj=pd.Series([7, -5, 7, 4, 2, 0, 4])#rank是通过“为各组分配一个平均排名”的方式破坏平级关系的
obj.rank()

0    6.5
1    1.0
2    6.5
3    4.5
4    3.0
5    2.0
6    4.5
dtype: float64

obj.rank(method='first')

0    6.0
1    1.0
2    7.0
3    4.0
4    3.0
5    2.0
6    5.0
dtype: float64

obj.rank(ascending=False, method='max')

0    2.0
1    7.0
2    2.0
3    4.0
4    5.0
5    6.0
6    4.0
dtype: float64

frame = pd.DataFrame({'b': [4.3, 7, -3, 2], 'a': [0, 1, 0, 1],
                      'c': [-2, 5, 8, -2.5]})
frame

	b	a	c
0	4.3	0	-2.0
1	7.0	1	5.0
2	-3.0	0	8.0
3	2.0	1	-2.5

frame.rank(axis='columns')

	b	a	c
0	3.0	2.0	1.0
1	3.0	1.0	2.0
2	1.0	2.0	3.0
3	3.0	2.0	1.0

#带有重复标签的轴索引
obj = pd.Series(range(5),index=['a','a','b','b','c'])
obj

a    0
a    1
b    2
b    3
c    4
dtype: int64

obj.index.is_unique

False

obj['a']

a    0
a    1
dtype: int64

obj['b']

b    2
b    3
dtype: int64

df = pd.DataFrame(np.random.randn(4,3),index= ['a','a','b','b'])
df

	0	1	2
a	1.265240	0.407293	-0.652129
a	0.268019	-1.423912	1.297783
b	0.797760	-0.353663	1.323543
b	0.961888	0.227132	1.843558

df.loc['b']

	0	1	2
b	0.797760	-0.353663	1.323543
b	0.961888	0.227132	1.843558

#汇总和计算描绘统计
df = pd.DataFrame([[1.4, np.nan], [7.1, -4.5],
                   [np.nan, np.nan], [0.75, -1.3]],
                   index=['a', 'b', 'c', 'd'],
                   columns=['one', 'two'])
df

	one	two
a	1.40	NaN
b	7.10	-4.5
c	NaN	NaN
d	0.75	-1.3

df.sum()   #列和

one    9.25
two   -5.80
dtype: float64

df.sum(axis=1)

a    1.40
b    2.60
c    0.00
d   -0.55
dtype: float64

df.mean(axis='columns',skipna=False)   #不忽略Nan

a      NaN
b    1.300
c      NaN
d   -0.275
dtype: float64

df.idxmax()  #达到最大的索引

one    b
two    d
dtype: object

df.cumsum()

	one	two
a	1.40	NaN
b	8.50	-4.5
c	NaN	NaN
d	9.25	-5.8

df.describe()

	one	two
count	3.000000	2.000000
mean	3.083333	-2.900000
std	3.493685	2.262742
min	0.750000	-4.500000
25%	1.075000	-3.700000
50%	1.400000	-2.900000
75%	4.250000	-2.100000
max	7.100000	-1.300000

obj = pd.Series(['a', 'a', 'b', 'c'] * 4)#非数值型
obj.describe()

count     16
unique     3
top        a
freq       8
dtype: object

#相关系数与协方差
import pandas_datareader.data as web
all_data = {ticker:web.get_data_yahoo(ticker)
           for ticker in ['AAPL', 'IBM', 'MSFT', 'GOOG']}
price = pd.DataFrame({ticker: data['Adj Close']
                     for ticker, data in all_data.items()})
volume = pd.DataFrame({ticker: data['Volume']
                      for ticker, data in all_data.items()})
returns = price.pct_change()
returns.tail()
                          

	AAPL	IBM	MSFT	GOOG
Date
2018-10-18	-0.023374	-0.026110	-0.019962	-0.024846
2018-10-19	0.015230	-0.011107	0.001475	0.007804
2018-10-22	0.006110	0.007126	0.008927	0.004287
2018-10-23	0.009427	0.009152	-0.013956	0.002297
2018-10-24	-0.034302	-0.030486	-0.053469	-0.048003

returns['MSFT'].corr(returns['IBM']) #相关系数

0.4746674318628231

returns["MSFT"].cov(returns["IBM"])#协方差

8.150193655338736e-05

returns.MSFT.corr(returns.IBM)

0.4746674318628231

returns.corr()   #相关系数矩阵

	AAPL	IBM	MSFT	GOOG
AAPL	1.000000	0.364434	0.421984	0.438015
IBM	0.364434	1.000000	0.474667	0.398449
MSFT	0.421984	0.474667	1.000000	0.516364
GOOG	0.438015	0.398449	0.516364	1.000000

returns.cov()  #协方差矩阵

	AAPL	IBM	MSFT	GOOG
AAPL	0.000252	0.000070	0.000095	0.000106
IBM	0.000070	0.000146	0.000082	0.000073
MSFT	0.000095	0.000082	0.000202	0.000112
GOOG	0.000106	0.000073	0.000112	0.000232

returns.corrwith(returns.IBM)#与某一列或行的相关系数

AAPL    0.364434
IBM     1.000000
MSFT    0.474667
GOOG    0.398449
dtype: float64

returns.corrwith(volume)#传入一个DataFrame则会计算按列名配对的相关系数

AAPL   -0.065065
IBM    -0.173822
MSFT   -0.088563
GOOG   -0.016396
dtype: float64

#唯一值，值记述以及成员资格
obj = pd.Series(['c', 'a', 'd', 'a', 'a', 'b', 'b', 'c', 'c'])
uniques = obj.unique()
uniques

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

obj.value_counts()#计算出现频率

c    3
a    3
b    2
d    1
dtype: int64

obj

0    c
1    a
2    d
3    a
4    a
5    b
6    b
7    c
8    c
dtype: object

mask = obj.isin(['b','c'])#用于判断矢量化集合的成员资格
mask

0     True
1    False
2    False
3    False
4    False
5     True
6     True
7     True
8     True
dtype: bool

obj[mask]

0    c
5    b
6    b
7    c
8    c
dtype: object

to_match = pd.Series(['c', 'a', 'b', 'b', 'c', 'a'])
unique_values = pd.Series(['c','b','a'])
pd.Index(unique_values).get_indexer(to_match)
#与isin类似的是Index.get_indexer方法，它可以给你一个索引数组，从可能包含重复值的数组到另一个不同值的数组

array([0, 2, 1, 1, 0, 2], dtype=int64)