Some basic calculations.
P = dict()
P['Benzene'] = 1431
P['Toluene'] = 1290
P
{'Benzene': 1431, 'Toluene': 1290}
import pandas
prices = pandas.read_csv('TolBenNGPrices.csv', index_col = 0)
prices
Benzene | Toluene Blend | Natural Gas | |
---|---|---|---|
Prices | |||
11-Feb | 4.2866 | 2.9730 | 5.77 |
11-Mar | 4.0488 | 3.3708 | 5.21 |
11-Apr | 4.1338 | 4.2003 | 5.34 |
11-May | 4.1219 | 3.6000 | 5.21 |
11-Jun | 3.7910 | 3.5714 | 5.21 |
11-Jul | 3.9963 | 4.0194 | 5.05 |
11-Aug | 4.0838 | 3.6853 | 5.21 |
11-Sep | 3.7060 | 3.3577 | 4.84 |
11-Oct | 3.1713 | 3.3020 | 4.71 |
11-Nov | 3.1056 | 3.0904 | 4.64 |
11-Dec | 3.3738 | 3.2395 | 4.59 |
12-Jan | 4.0450 | 3.6006 | 4.59 |
12-Feb | 4.1650 | 3.7538 | 4.19 |
12-Mar | 4.1575 | 3.9608 | 3.71 |
12-Apr | 4.1425 | 4.3428 | 3.21 |
12-May | 4.0600 | 4.2330 | 3.02 |
12-Jun | 4.1463 | 3.9933 | 3.34 |
12-Jul | 4.6675 | 4.2367 | 3.60 |
12-Aug | 4.3400 | 4.2641 | 3.83 |
12-Sep | 4.3456 | 4.3466 | 3.56 |
12-Oct | 4.7313 | 3.8967 | 3.95 |
12-Nov | 4.8745 | 3.1773 | 4.46 |
12-Dec | 5.1258 | 3.2948 | 4.72 |
13-Jan | 4.9331 | 3.8594 | 4.60 |
24 rows × 3 columns
prices.plot()
<matplotlib.axes.AxesSubplot at 0x1096df850>
returns = dict()
for c in list(prices.columns):
returns[c] = log(prices[:][c]) - log(prices[:][c].shift(1))
returns = pandas.DataFrame(returns)
returns
Benzene | Natural Gas | Toluene Blend | |
---|---|---|---|
Prices | |||
11-Feb | NaN | NaN | NaN |
11-Mar | -0.057073 | -0.102092 | 0.125579 |
11-Apr | 0.020777 | 0.024646 | 0.220006 |
11-May | -0.002883 | -0.024646 | -0.154222 |
11-Jun | -0.083684 | 0.000000 | -0.007976 |
11-Jul | 0.052739 | -0.031192 | 0.118175 |
11-Aug | 0.021659 | 0.031192 | -0.086781 |
11-Sep | -0.097075 | -0.073665 | -0.093096 |
11-Oct | -0.155812 | -0.027227 | -0.016728 |
11-Nov | -0.020935 | -0.014974 | -0.066228 |
11-Dec | 0.082833 | -0.010834 | 0.047118 |
12-Jan | 0.181442 | 0.000000 | 0.105682 |
12-Feb | 0.029235 | -0.091179 | 0.041668 |
12-Mar | -0.001802 | -0.121669 | 0.053677 |
12-Apr | -0.003614 | -0.144761 | 0.092073 |
12-May | -0.020116 | -0.061014 | -0.025608 |
12-Jun | 0.021033 | 0.100714 | -0.058293 |
12-Jul | 0.118407 | 0.074963 | 0.059167 |
12-Aug | -0.072749 | 0.061931 | 0.006446 |
12-Sep | 0.001289 | -0.073104 | 0.019163 |
12-Oct | 0.085036 | 0.103955 | -0.109264 |
12-Nov | 0.029818 | 0.121433 | -0.204098 |
12-Dec | 0.050269 | 0.056660 | 0.036314 |
13-Jan | -0.038319 | -0.025752 | 0.158166 |
24 rows × 3 columns
returns?
returns.mean()
Benzene 0.006108 Natural Gas -0.009853 Toluene Blend 0.011345 dtype: float64
returns.std()
Benzene 0.073905 Natural Gas 0.073862 Toluene Blend 0.103191 dtype: float64
s = returns[1:23]['Benzene']
pandas.tools.plotting.autocorrelation_plot(s)
<matplotlib.axes.AxesSubplot at 0x10a4ecb10>
type(s)
pandas.core.series.Series
size(returns)
72
len(s)
24