pandas索引(分组运算，数据聚合，时间重采样，数据可视化，股票数据分析，时间事件日志)

pandas索引

1、创建s序列

import pandas as pd
import numpy as np
s = pd.Series(np.random.randn(5),index = list('abcde'))
s
'''
a   -0.206894
b    1.042893
c   -0.495746
d   -0.178118
e    0.531067
dtype: float64
'''

2、s序列的索引

s.index
'''Index(['a', 'b', 'c', 'd', 'e'], dtype='object')'''
s.index.name = 'alpha'
s
'''
alpha
a   -0.206894
b    1.042893
c   -0.495746
d   -0.178118
e    0.531067
dtype: float64
'''

3、创建df的DataFrame

df = pd.DataFrame(np.random.randn(4,3),columns = ['one','two','three'])
df

4、df的行索引，列索引，以及命名

df.index
'''
RangeIndex(start=0, stop=4, step=1)
'''
df.columns
'''
Index(['one', 'two', 'three'], dtype='object')
'''
df.index.name = 'row'
df.columns.name = 'col'
print(df)
'''
col  a  b    c  d
row              
0    0  7  one  0
1    1  6  one  1
2    2  5  one  2
3    3  4  two  0
4    4  3  two  1
5    5  2  two  2
6    6  1  two  3
'''

5、创建多级索引

a  =[['a','a','a','b','b','c','c'],[1,2,3,1,2,2,3]]
t = list(zip(*a))
t
'''
[('a', 1), ('a', 2), ('a', 3), ('b', 1), ('b', 2), ('c', 2), ('c', 3)]
'''
index = pd.MultiIndex.from_tuples(t,names = ['level1','level2'])
index
'''
MultiIndex(levels=[['a', 'b', 'c'], [1, 2, 3]],
           codes=[[0, 0, 0, 1, 1, 2, 2], [0, 1, 2, 0, 1, 1, 2]],
           names=['level1', 'level2'])
'''
s = pd.Series(np.random.rand(7),index = index)
s
'''
level1  level2
a       1         0.561636
        2         0.907344
        3         0.782276
b       1         0.674353
        2         0.203832
c       2         0.591604
        3         0.615422
dtype: float64
'''
df = pd.DataFrame(np.random.randint(1,10,(4,3)),
                 index = [['a','a','b','b'],[1,2,1,2]],
                 columns = [['one','one','two'],['blue','red','blue']])
df.index.names = ['row-1','row-2']
df.columns.names = ['col-1','col-2']
df
'''
col-1        one      two
col-2       blue red blue
row-1 row-2              
a     1        1   1    3
      2        4   4    7
b     1        6   4    9
      2        2   7    3
'''
type(df.loc['a'])
'''
pandas.core.frame.DataFrame
'''
df.loc['a',1]
'''
col-1  col-2
one    blue     1
       red      1
two    blue     3
Name: (a, 1), dtype: int32
'''
#交换
df2 = df.swaplevel('row-1','row-2')
print(df2)
'''
col-1        one      two
col-2       blue red blue
row-2 row-1              
1     a        1   1    3
2     a        4   4    7
1     b        6   4    9
2     b        2   7    3
'''
#排序
df2.sort_index(1)
'''
col-1        one      two
col-2       blue red blue
row-2 row-1              
1     a        1   1    3
2     a        4   4    7
1     b        6   4    9
2     b        2   7    3
'''
#求和
print(df.sum(level = 0))
'''
col-1  one      two
col-2 blue red blue
row-1              
a        5   5   10
b        8  11   12
'''
df = pd.DataFrame({
   
                  'a':range(7),
                  'b':range (7,0,-1),
                  'c':['one','one','one','two','two','two','two'],
                  'd':[0,1,2,0,1,2,3]})
df 
'''
  a  b    c  d
0  0  7  one  0
1  1  6  one  1
2  2  5  one  2
3  3  4  two  0
4  4  3  two  1
5  5  2  two  2
6  6  1  two  3
'''
print(df2.reset_index().sort_index('columns'))
'''
col-1  one     row-1 row-2  two
col-2 blue red             blue
0        1   1     a     1    3
1        4   4     a     2    7
2        6   4     b     1    9
3        2   7     b     2    3
'''

pandas分组运算

1、分组计算三部曲：
拆分、应用、合并
拆分：根据什么进行分组
应用：每个分组进行什么样的计算
合并：把每个分组的计算结果合并起来。

2、对Series,DataFrame的分组

import pandas as pd
import numpy as np
df = pd.DataFrame({
   'key1':['a','a','b','b','a'],
                   'key2':['one','two','one','two','one'],
                   'data1':np.random.randint(1,10,5),
                   'data2':np.random.randint(1,10,5)})
print(df)
'''
  key1 key2  data1  data2
0    a  one      9      3
1    a  two      3      8
2    b  one      2      5
3    b  two      3      4
4    a  one      9      7
'''

对Series的分组

df['data1'].groupby(df['key1']).mean()
'''
key1
a    7.0
b    2.5
'''
#自己创建key
key = [1,2,1,1,2]
df['data1'].groupby(key).mean()
'''
1    4.666667
2    6.000000
'''
#自己创建的key可为多层列表(求和)
df['data1'].groupby([df['key1'],df['key2']]).sum()
'''
key1  key2
a     one     18
      two      3
b     one      2
      two      3
'''
#求个数
df['data1'].groupby([df['key1'],df['key2']]).size()
key1  key2
a     one     2
      two     1
b     one     1
      two     1
Name: data1, dtype: int64
#key1，key2分组求和转化成DataFrame
mean = df.groupby(['key1','key2']).sum()['data1']
mean
'''
key1  key2
a     one     18
      two      3
b     one      2
      two      3
'''
print(mean.unstack())
'''
key2  one  two
key1          
a      18    3
b       2    3
'''
#for迭代
for name,group in df.groupby('key1'):
    print (name)
    print (group)
'''
a
  key1 key2  data1  data2
0    a  one      9      3
1    a  two      3      8
4    a  one      9      7
b
  key1 key2  data1  data2
2    b  one      2      5
3    b  two      3      4
'''
#转化成字典
dict(list(df.groupby('key1')))
'''
{'a':   key1 key2  data1  data2
 0    a  one      9      3
 1    a  two      3      8
 4    a  one      9      7, 'b':   key1 key2  data1  data2
 2    b  one      2      5
 3    b  two      3      4}
'''
#每一列的数据类型
df.dtypes
'''
key1     object
key2     object
data1     int32
data2     int32
'''
#根据dtypes按列分组
df.groupby(df.dtypes,axis = 1).sum()
'''
   int32
0     27
1     19
2     26
3     24
4     24
'''

3、通过函数进行分组

df = pd.DataFrame(np.random.randint(1,10,(5,5)),
                  columns = ['a','b','c','d','e'],
                  index = ['Alice','Bob','Candy','Dark','Emily'])
df.ix[1,1:3] = np