

In [15]:

    
import pandas as pd
import numpy as np
from numpy import *
from pandas import Series, DataFrame, Panel,



In [8]:

    
file_location = 'D:/GitHub/Spot-Price-Analysis/clean-data/Price.csv'
col_names = ['region','az','time','instance','category','spotprice','demandprice','compute','memory','hdd','ssd','storage']
prices_df = pd.read_csv(file_location, names=col_names, header=None)



In [12]:

    
prices_df.head()









    Out[12]:






  
    
      
      region
      az
      time
      instance
      category
      spotprice
      demandprice
      compute
      memory
      hdd
      ssd
      storage
    
  
  
    
      0
       us-east-1
       us-east-1c
       2014-08-11 17:23:20.000
       r3.8xlarge
       High Memory
       0.78
       2.8
       104
       244
       0
       640
       640
    
    
      1
        us-east-1
       us-east-1c
       2014-08-11 17:51:49.000
       r3.8xlarge
       High Memory
       0.78
       2.8
       104
       244
       0
       640
       640
    
    
      2
        us-east-1
       us-east-1c
       2014-08-11 18:20:38.000
       r3.8xlarge
       High Memory
       0.78
       2.8
       104
       244
       0
       640
       640
    
    
      3
        us-east-1
       us-east-1c
       2014-08-12 13:50:58.000
       r3.8xlarge
       High Memory
       0.78
       2.8
       104
       244
       0
       640
       640
    
    
      4
        us-east-1
       us-east-1c
       2014-08-27 18:47:22.000
       r3.8xlarge
       High Memory
       0.78
       2.8
       104
       244
       0
       640
       640
    
  

5 rows × 12 columns



In [18]:

    
# Do datatype conversions
prices_df.time = pd.to_datetime(prices_df.time)
prices_df_useast = prices_df[prices_df.region.isin('us-east-1')]
# http://pandas.pydata.org/pandas-docs/stable/10min.html#selection

# Convert to a time series
prices_s = Series(

# Time series analysis http://earthpy.org/pandas-basics.html http://earthpy.org/time_series_analysis_with_pandas_part_2.html http://stackoverflow.com/questions/4809577/correlation-of-two-variables-in-a-time-series-in-python http://stackoverflow.com/questions/25320773/time-series-correlation-and-lag-time



In [ ]:

	region	az	time	instance	category	spotprice	demandprice	compute	memory	ssd	storage
0	us-east-1	us-east-1c	2014-08-11 17:23:20.000	r3.8xlarge	High Memory	0.78	2.8	104	244	640	640
1	us-east-1	us-east-1c	2014-08-11 17:51:49.000	r3.8xlarge	High Memory	0.78	2.8	104	244	640	640
2	us-east-1	us-east-1c	2014-08-11 18:20:38.000	r3.8xlarge	High Memory	0.78	2.8	104	244	640	640
3	us-east-1	us-east-1c	2014-08-12 13:50:58.000	r3.8xlarge	High Memory	0.78	2.8	104	244	640	640
4	us-east-1	us-east-1c	2014-08-27 18:47:22.000	r3.8xlarge	High Memory	0.78	2.8	104	244	640	640