金融统计分析与挖掘实战3.3.3-3.5

# 3.3.3 数据框
# 8.as_matrix()报错
import pandas as pd
import numpy as np
list1 = [1,2,3,4,5,6]
list2 = [2,3,4,5,6,7]
D = pd.DataFrame({"m1":list1,"m2":list2})

print(D)

   m1  m2
0   1   2
1   2   3
2   3   4
3   4   5
4   5   6
5   6   7

D1 = D.as_matrix()
print(D1)

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

AttributeError                            Traceback (most recent call last)

<ipython-input-3-63694ea5efae> in <module>
----> 1 D1 = D.as_matrix()
      2 print(D1)


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\generic.py in __getattr__(self, name)
   5463             if self._info_axis._can_hold_identifiers_and_holds_name(name):
   5464                 return self[name]
-> 5465             return object.__getattribute__(self, name)
   5466 
   5467     def __setattr__(self, name: str, value) -> None:


AttributeError: 'DataFrame' object has no attribute 'as_matrix'

#两种方法解决
#1.用values 替代as_matrix
D2 = D.values
print(D2)

[[1 2]
 [2 3]
 [3 4]
 [4 5]
 [5 6]
 [6 7]]

#2.用iloc[:,:].values替代as_matrix ,切片取所有，建议选择上一种
D3 = D.iloc[:,:].values
print(D3)

[[1 2]
 [2 3]
 [3 4]
 [4 5]
 [5 6]
 [6 7]]

# 把数据框导入到Excel文件中 to _excel()
D4 = D.to_excel("D.xlsx")
print(D4)   #文件已保存到默认路径

None

# 10 统计方法
# 求数据框的和，平均值，描述统计等统计量
R1 = D.sum()   #求各列的和
print(R1)

m1    21
m2    27
dtype: int64

R2 = D.mean()   #求各列平均
print(R2)

m1    3.5
m2    4.5
dtype: float64

R3 = D.describe()  # 对各列作描述统计
print(R3)   #包括样本数，均值，标准误，最小值，四分位数，中位数，最大值

             m1        m2
count  6.000000  6.000000
mean   3.500000  4.500000
std    1.870829  1.870829
min    1.000000  2.000000
25%    2.250000  3.250000
50%    3.500000  4.500000
75%    4.750000  5.750000
max    6.000000  7.000000

# 3.3.4 数据框切片 
#1. 利用数据框中的iloc函数切片
c1 = D.iloc[1:3,1]   # 取行索引为1,2，列索引为1的元素
print(c1)

1    3
2    4
Name: m2, dtype: int64

c2 = D.iloc[1:3,:]  #取行索引为1,2的所有列
print(c2)

   m1  m2
1   2   3
2   3   4

# 按照逻辑切片
TF = [True,False,False,True,True,False]
c3 = D.iloc[TF,[0]]
print(c3)

   m1
0   1
3   4
4   5

# 2.利用loc属性进行切片
# 主要是基于列标签进行索引
c4 = D.loc[D["m1"] == 2,:]   #把列标签m1下面取值等于2的所有列挑出
print(c4)

   m1  m2
1   2   3

# 3.4 外部文件读取
# 3.4.1 excel 文件的读取

# 将文件放到工作路径下
import os  #工作路径查询

os.getcwd()  #查询当前默认路径

'C:\\Users\\Administrator'

os.chdir("C:\\Users\\Administrator\\Desktop")  #更改工作路径，注意双\\

# 将Excel文件放入工作路径中
path = "ss.xlsx"   # 把上车人数文件名改为字母，这不是必须的，中文名也可以，可以自己杜撰一个数据进行操作，下同
data = pd.read_excel(path)
print(data)

      车次        日期  上车人数
0    D02  20150101  2143
1    D02  20150102   856
2    D02  20150106   860
3    D02  20150104  1011
4    D02  20150105   807
..   ...       ...   ...
115  D06  20150120  1342
116  D06  20150121  1389
117  D06  20150122  1467
118  D06  20150123  1516
119  D06  20150124  1888

[120 rows x 3 columns]

#如果要打开Excel其它工作簿的文件，需要写工作簿的名称
path = "ss.xlsx"
data1 = pd.read_excel(path,"Sheet2")   #Sheet2是工作簿名称
print(data1)

     车次        日期    上车人数
0   D02  20150101  2143.0
1   D02  20150102   856.0
2   D02  20150106     NaN
3   D03  20150104  1011.0
4   D02  20150105   807.0
5   D02  20150103   761.0
6   D03  20150107   803.0
7   D02  20150108   732.0
8   D02  20150109   753.0
9   D03  20150110     NaN
10  D02  20150111   694.0
11  D02  20150112   930.0
12  D03  20150113   825.0
13  D02  20150114     NaN
14  D02  20150115   802.0
15  D02  20150116   815.0

# 3.4.2 txt文件读取
# Tab键分割符的文本文档
data2 = pd.read_table("txt1.txt",header = None) #分割默认Tab键，本数据设置无表头
print(data2)

        0      1      2      3      4      5     6      7
0    8.35  23.53   7.51   8.62  17.42  10.00  1.04  11.21
1    9.25  23.75   6.61   9.19  17.77  10.48  1.72  10.51
2    8.19  30.50   4.72   9.78  16.28   7.60  2.52  10.32
3    7.73  29.20   5.42   9.43  19.29   8.49  2.52  10.00
4    9.42  27.93   8.20   8.14  16.17   9.42  1.55   9.76
5    9.16  27.98   9.01   9.32  15.99   9.10  1.82  11.35
6   10.06  28.64  10.52  10.05  16.18   8.39  1.96  10.81
7    9.09  28.12   7.40   9.62  17.26  11.12  2.49  12.65
8    9.41  28.20   5.77  10.80  16.36  11.56  1.53  12.17
9    8.70  28.12   7.21  10.53  19.45  13.30  1.66  11.96
10   6.93  29.85   4.54   9.49  16.62  10.65  1.88  13.61
11   8.67  36.05   7.31   7.75  16.67  11.68  2.38  12.88
12   9.98  37.69   7.01   8.94  16.15  11.08  0.83  11.67
13   6.77  38.69   6.01   8.82  14.79  11.44  1.74  13.23
14   8.14  37.75   9.61   8.49  13.15   9.76  1.28  11.28
15   7.67  35.71   8.04   8.31  15.13   7.76  1.41  13.25
16   7.90  39.77   8.49  12.94  19.27  11.05  2.04  13.29
17   7.18  40.91   7.32   8.94  17.60  12.75  1.14  14.80
18   8.82  33.70   7.59  10.98  18.82  14.73  1.78  10.10
19   6.25  35.02   4.72   6.28  10.03   7.15  1.93  10.39
20  10.60  52.41   7.70   9.98  12.53  11.70  2.31  14.69
21   7.27  52.65   3.84   9.16  13.03  15.26  1.98  14.57
22  13.45  55.85   5.50   7.45   9.55   9.52  2.21  16.30
23  10.85  44.68   7.32  14.51  17.13  12.08  1.26  11.57
24   7.21  45.79   7.66  10.36  16.56  12.86  2.25  11.69
25   7.68  50.37  11.35  13.30  19.25  14.59  2.75  14.87
26   7.78  48.44   8.00  20.51  22.12  15.73  1.15  16.61
27   7.94  39.65  20.97  20.82  22.52  12.41  1.75   7.90
28   8.28  64.34   8.00  22.22  20.06  15.12  0.72  22.89
29  12.47  76.39   5.52  11.24  14.52  22.00  5.46  25.50

# 空格分隔符的文本文档读取
data3 = pd.read_table("txt2.txt",sep ="\s+") # sep = “\s+”表示分割符为空格
print(data3)    # 没有设置header 表示默认第一行为变量名

    a   b   c   d   e
0   1   2   3   4   5
1   6   7   8   9  10
2  11  12  13  14  15

# 逗号分割符的文本文档读取
data4 = pd.read_table("txt3.txt",sep = "," ,header = None) # 第一行不是变量名
print(data4)

    0   1   2   3   4
0   2   3   4   5   6
1   7   8   9  10  11
2  12  13  14  15  16

# 3.5 滚动计算函数
sss = pd.Series([1,2,3,4,5,6,7,8,9,10,11])
avgs = pd.rolling_mean(sss,3)     #新版pandas里面变化了module 'pandas' has no attribute 'rolling_mean'

print(avgs)  #报错

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

AttributeError                            Traceback (most recent call last)

<ipython-input-38-480887a633ac> in <module>
      1 # 3.5 滚动计算函数
      2 sss = pd.Series([1,2,3,4,5,6,7,8,9,10,11])
----> 3 avgs = pd.rolling_mean(sss,3)     #新版pandas里面变化了module 'pandas' has no attribute 'rolling_mean'
      4 
      5 print(avgs)


C:\ProgramData\Anaconda3\lib\site-packages\pandas\__init__.py in __getattr__(name)
    242         return _SparseArray
    243 
--> 244     raise AttributeError(f"module 'pandas' has no attribute '{name}'")
    245 
    246 


AttributeError: module 'pandas' has no attribute 'rolling_mean'

#新版本采用rolling().mean()
sss = pd.Series([1,2,3,4,5,6,7,8,9,10,11])
avgs = sss.rolling(3).mean()     #新版pandas里面变化了module 'pandas' has no attribute 'rolling_mean'
print(avgs)

0      NaN
1      NaN
2      2.0
3      3.0
4      4.0
5      5.0
6      6.0
7      7.0
8      8.0
9      9.0
10    10.0
dtype: float64

# 3项移动求和
sum_sss = sss.rolling(3).sum()
print(sum_sss)

0      NaN
1      NaN
2      6.0
3      9.0
4     12.0
5     15.0
6     18.0
7     21.0
8     24.0
9     27.0
10    30.0
dtype: float64

# 3项移动求最大
max_sss = sss.rolling(3).max()
print(max_sss)

0      NaN
1      NaN
2      3.0
3      4.0
4      5.0
5      6.0
6      7.0
7      8.0
8      9.0
9     10.0
10    11.0
dtype: float64