In [1]:

    

import pandas as pd
import numpy as np
%matplotlib inline
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from sklearn import metrics
import seaborn; seaborn.set()


    

In [2]:

    

solarGe = pd.read_csv("Actual Generation per Production Type_201501010000-201501020000.csv", sep=",")
solarSz = pd.read_csv("Generation Forecasts - Day Ahead for Wind and Solar_201501010000-201501020000.csv", sep=",")


    

In [3]:

    

solarGe.head(2)


    

    
Out[3]:







  

    

      

      
Area
      
MTU
      
Solar  - Actual Aggregated [MW]
      
Solar  - Actual Consumption [MW]
    
  
  

    

      
0
      
Germany (DE)
      
01.01.2015 00:00 - 01.01.2015 00:15 (CET)
      
0
      
0
    
    

      
1
      
Germany (DE)
      
01.01.2015 00:15 - 01.01.2015 00:30 (CET)
      
0
      
0
    
  

In [4]:

    

solarSz.head()


    

    
Out[4]:







  

    

      

      
MTU (CET)
      
Generation - Sum [MW] (D) / Germany (DE)
      
Generation - Solar  [MW] (D) / Germany (DE)
    
  
  

    

      
0
      
01.01.2015 00:00 - 01.01.2015 00:15 (CET)
      
0
      
0
    
    

      
1
      
01.01.2015 00:15 - 01.01.2015 00:30 (CET)
      
0
      
0
    
    

      
2
      
01.01.2015 00:30 - 01.01.2015 00:45 (CET)
      
0
      
0
    
    

      
3
      
01.01.2015 00:45 - 01.01.2015 01:00 (CET)
      
0
      
0
    
    

      
4
      
01.01.2015 01:00 - 01.01.2015 01:15 (CET)
      
0
      
0
    
  

In [5]:

    

solar = pd.concat([solarGe, solarSz], axis=1)
solar.columns


    

    
Out[5]:





Index(['Area', 'MTU', 'Solar  - Actual Aggregated [MW]',
       'Solar  - Actual Consumption [MW]', 'MTU (CET)',
       'Generation - Sum [MW] (D) / Germany (DE)',
       'Generation - Solar  [MW] (D) / Germany (DE)'],
      dtype='object')

In [6]:

    

solarC = solar.drop(['Area','MTU','Solar  - Actual Consumption [MW]','Generation - Sum [MW] (D) / Germany (DE)','MTU (CET)'],axis=1)
solarC.columns = ['Gen','Szac']


    

In [7]:

    

solarC.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 96 entries, 0 to 95
Data columns (total 2 columns):
Gen     96 non-null int64
Szac    96 non-null int64
dtypes: int64(2)
memory usage: 1.6 KB

In [8]:

    

range = pd.date_range('2015-01-01 00:15:00', '2015-01-02 00:00:00', freq='15min')
solarC = solarC.set_index(range)


    

In [9]:

    

solarC.plot(figsize=(20,10), x_compat=True, title='Rzeczywista generacja energii vs szacunkowa')
plt.gca().xaxis.set_major_locator(mdates.HourLocator())
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%H : %M'));


    

In [10]:

    

solarC['error'] = np.abs(solarC['Gen'] - solarC['Szac'])


    

In [11]:

    

solarC['error'].describe()


    

    
Out[11]:





count      96.000000
mean      156.916667
std       321.652302
min         0.000000
25%         0.000000
50%         0.000000
75%       103.250000
max      1262.000000
Name: error, dtype: float64

In [12]:

    

print(np.sqrt(metrics.mean_squared_error(solarC['Gen'], solarC['Szac'])))


    

    




356.378076393