python pandas学习杂记（Movan python）

 pandas 的基本介绍 

 pandas更像一个字典形式的numpy。如果说numpy是一个列表的话，pandas可以说成字典。
# 因为可以给不同的行不同列重新命名。 一般是结合使用
import numpy as np
import pandas as pd
s = pd.Series([1,3,6,np.nan,44,1])
print(s)
dates = pd.date_range('20180101',periods=6)
dates
#DataFrame 类似于numpy的矩阵
df = pd.DataFrame(np.random.randn(),index=dates,columns=['a','b','c','d']) #行是index 或者是row
print(df)
df2 = pd.DataFrame(np.arange(12).reshape((3,4)))
print(df2)


#输出
0     1.0
1     3.0
2     6.0
3     NaN
4    44.0
5     1.0
dtype: float64
                   a         b         c         d
2018-01-01 -2.110566 -2.110566 -2.110566 -2.110566
2018-01-02 -2.110566 -2.110566 -2.110566 -2.110566
2018-01-03 -2.110566 -2.110566 -2.110566 -2.110566
2018-01-04 -2.110566 -2.110566 -2.110566 -2.110566
2018-01-05 -2.110566 -2.110566 -2.110566 -2.110566
2018-01-06 -2.110566 -2.110566 -2.110566 -2.110566
   0  1   2   3
0  0  1   2   3
1  4  5   6   7
2  8  9  10  11
    

#另一种方式生成DataFrame
#用字典的方式，一列代表一行数据。
df3 = pd.DataFrame({'A' : 1.,
                       'B' : pd.Timestamp('20130102'),
                        'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
                        'D' : np.array([3] * 4,dtype='int32'),
                        'E' : pd.Categorical(["test","train","test","train"]),
                        'F' : 'foo'})
print(df3)
print(df3.dtypes) #与numpy一样，d代表有多少维度的数据。 打印出每一列的数据类型
print(df3.index) # 每一行的名字
print(df3.columns) # 每一列的名字
print(df3.values) #打印值
print(df3.describe()) # 只能对数字行进行统计。
print(df3.T) #同样转置
print(df3.sort_index(axis=1,ascending=False)) #对index进行倒序排序
#除了排序index，还可以排序values
print(df3.sort_values(by='E'))

#输出
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo
A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object
Int64Index([0, 1, 2, 3], dtype='int64')
Index(['A', 'B', 'C', 'D', 'E', 'F'], dtype='object')
[[1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
 [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']
 [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'test' 'foo']
 [1.0 Timestamp('2013-01-02 00:00:00') 1.0 3 'train' 'foo']]
         A    C    D
count  4.0  4.0  4.0
mean   1.0  1.0  3.0
std    0.0  0.0  0.0
min    1.0  1.0  3.0
25%    1.0  1.0  3.0
50%    1.0  1.0  3.0
75%    1.0  1.0  3.0
max    1.0  1.0  3.0
                     0                    1                    2  \
A                    1                    1                    1   
B  2013-01-02 00:00:00  2013-01-02 00:00:00  2013-01-02 00:00:00   
C                    1                    1                    1   
D                    3                    3                    3   
E                 test                train                 test   
F                  foo                  foo                  foo   

                     3  
A                    1  
B  2013-01-02 00:00:00  
C                    1  
D                    3  
E                train  
F                  foo  
     F      E  D    C          B    A
0  foo   test  3  1.0 2013-01-02  1.0
1  foo  train  3  1.0 2013-01-02  1.0
2  foo   test  3  1.0 2013-01-02  1.0
3  foo  train  3  1.0 2013-01-02  1.0
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
2  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
3  1.0 2013-01-02  1.0  3  train  foo

 pandas选择数据

 

import numpy as np
import pandas as pd

dates = pd.date_range('20180101',periods=6)
df = pd.DataFrame(np.arange(24).reshape((6,4)),index=dates,columns=['A','B','C','D']) #行是index 或者是row
print(df)
#选择某一列
print(df['A'],df.A)
print(df[0:3]) #第0行到第3行
print(df['20180102':'20180104']) #第0行到第3行
#输出
        A   B   C   D
2018-01-01   0   1   2   3
2018-01-02   4   5   6   7
2018-01-03   8   9  10  11
2018-01-04  12  13  14  15
2018-01-05  16  17  18  19
2018-01-06  20  21  22  23
2018-01-01     0
2018-01-02     4
2018-01-03     8
2018-01-04    12
2018-01-05    16
2018-01-06    20
Freq: D, Name: A, dtype: int32 2018-01-01     0
2018-01-02     4
2018-01-03     8
2018-01-04    12
2018-01-05    16
2018-01-06    20
Freq: D, Name: A, dtype: int32
            A  B   C   D
2018-01-01  0  1   2   3
2018-01-02  4  5   6   7
2018-01-03  8  9  10  11
             A   B   C   D
2018-01-02   4   5   6   7
2018-01-03   8   9  10  11
2018-01-04  12  13  14  15

 

#select by label: loc
print(df.loc['20180101'])
print(df.loc[:,(['A','B'])])
print(df.loc['20180101',(['A','B'])])
#输出
A    0
B    1
C    2
D    3
Name: 2018-01-01 00:00:00, dtype: int32
             A   B
2018-01-01   0   1
2018-01-02   4   5
2018-01-03   8   9
2018-01-04  12  13
2018-01-05  16  17
2018-01-06  20  21
A    0
B    1
Name: 2018-01-01 00:00:00, dtype: int32

#select by position: iloc
print(df.iloc[3])
print(df.iloc[3:5,1:3])
print(df.iloc[[1,3,4],1:3])
#输出
A    12
B    13
C    14
D    15
Name: 2018-01-04 00:00:00, dtype: int32
             B   C
2018-01-04  13  14
2018-01-05  17  18
             B   C
2018-01-02   5   6
2018-01-04  13  14
2018-01-05  17  18

# select by mix position: ix
print(df.ix[:3,['A','c']])
# Boolean indexing 是或者否的删选
print(df)
print(df[df.A>8]) #筛选小于8的
#输出
            A   C
2018-01-01  0   2
2018-01-02  4   6
2018-01-03  8  10
             A   B   C   D
2018-01-01   0   1   2   3
2018-01-02   4   5   6   7
2018-01-03   8   9  10  11
2018-01-04  12  13  14  15
2018-01-05  16  17  18  19
2018-01-06  20  21  22  23
             A   B   C   D
2018-01-04  12  13  14  15
2018-01-05  16  17  18  19
2018-01-06  20  21  22  23