In [1]:

    

#-*- coding: utf-8 -*-
import pandas as pd
import pandas_datareader.data as web
import datetime

def get_file_path(code):
    return "../data/" + code


    

In [15]:

    

def download(code, year1, month1, day1, year2, month2, day2):
    start = datetime.datetime(year1, month1, day1)
    end = datetime.datetime(year2, month2, day2)
    df = web.DataReader("%s.KS" % code, "yahoo", start, end)
    df.to_pickle(get_file_path(code))
    
    return df


    

In [16]:

    

def load(code):
    df = pd.read_pickle(get_file_path(code))
    return df


    

In [17]:

    

df = download("005930", 2016, 1, 1, 2016, 11, 1)


    

In [18]:

    

df.describe()


    

    
Out[18]:






  

    

      

      
Open
      
High
      
Low
      
Close
      
Volume
      
Adj Close
    
  
  

    

      
count
      
2.180000e+02
      
2.180000e+02
      
2.180000e+02
      
2.180000e+02
      
2.180000e+02
      
2.180000e+02
    
    

      
mean
      
1.381495e+06
      
1.395876e+06
      
1.369876e+06
      
1.383977e+06
      
2.321674e+05
      
1.383450e+06
    
    

      
std
      
1.683836e+05
      
1.725185e+05
      
1.673190e+05
      
1.712811e+05
      
1.356109e+05
      
1.716604e+05
    
    

      
min
      
1.088000e+06
      
1.133000e+06
      
1.088000e+06
      
1.126000e+06
      
0.000000e+00
      
1.125195e+06
    
    

      
25%
      
1.257000e+06
      
1.264250e+06
      
1.246250e+06
      
1.253000e+06
      
1.669250e+05
      
1.252104e+06
    
    

      
50%
      
1.330000e+06
      
1.356500e+06
      
1.324000e+06
      
1.349000e+06
      
2.106000e+05
      
1.348036e+06
    
    

      
75%
      
1.547250e+06
      
1.568750e+06
      
1.536750e+06
      
1.547250e+06
      
2.728250e+05
      
1.547250e+06
    
    

      
max
      
1.700000e+06
      
1.716000e+06
      
1.690000e+06
      
1.706000e+06
      
1.250500e+06
      
1.706000e+06
    
  

In [19]:

    

#df.quantile([.25, .5, .75])


    

In [ ]:

    




    

In [20]:

    

import matplotlib.pyplot as plt


    

    













    




Bin : 1088000, Frequency = 11
Bin : 1149200, Frequency = 33
Bin : 1210400, Frequency = 26
Bin : 1271600, Frequency = 39
Bin : 1332800, Frequency = 7
Bin : 1394000, Frequency = 18
Bin : 1455200, Frequency = 14
Bin : 1516400, Frequency = 34
Bin : 1577600, Frequency = 27
Bin : 1638800, Frequency = 9

In [25]:

    

from pandas.tools.plotting import scatter_matrix
scatter_matrix(df[['Open', 'High', 'Low', 'Close']], alpha=0.2, figsize=(6, 6), diagonal='kde')
plt.show()


    

In [28]:

    

df[['Open', 'High', 'Low', 'Close']].plot(kind='box')
plt.show()


    

In [ ]: