-
Notifications
You must be signed in to change notification settings - Fork 2
/
ARIMA model
75 lines (67 loc) · 2.12 KB
/
ARIMA model
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
from pandas import Series
from matplotlib import pyplot
from statsmodels.tsa.arima_model import ARIMA
from statsmodels.tsa.arima_model import ARIMAResults
from sklearn.metrics import mean_squared_error
from math import sqrt
from sklearn.metrics import accuracy_score
import numpy
# create a differenced series
def difference(dataset, interval=1):
diff = list()
for i in range(interval, len(dataset)):
value = dataset[i] - dataset[i - interval]
diff.append(value)
return diff
# invert differenced value
def inverse_difference(history, yhat, interval=1):
return yhat + history[-interval]
# load and prepare datasets
dataset = Series.from_csv('dataset.csv')
X = dataset.values.astype('float32')
history = [x for x in X]
hours_in_day = 24
validation = Series.from_csv('validation.csv')
y = validation.values.astype('float32')
# load model
model_fit = ARIMAResults.load('model.pkl')
bias = numpy.load('model_bias.npy')
# make first prediction
predictions = list()
yhat = float(model_fit.forecast()[0])
yhat = bias + inverse_difference(history, yhat, hours_in_day)
predictions.append(yhat)
history.append(y[0])
print('>Predicted=%.3f, Expected=%3.f' % (yhat, y[0]))
# rolling forecasts
for i in range(1, len(y)):
# difference data
hours_in_day = 24
diff = difference(history, hours_in_day)
# predict
model = ARIMA(diff, order=(1,0,1))
model_fit = model.fit(trend='nc', disp=0)
yhat = model_fit.forecast()[0]
yhat = bias + inverse_difference(history, yhat, hours_in_day)
predictions.append(yhat)
# observation
obs = y[i]
history.append(obs)
print('>Predicted=%.3f, Expected=%3.f' % (yhat, obs))
accurac = abs((((obs - yhat) / obs)*100))
accurac = 1 - accurac
print('Accuracy: %.3f%%' % accurac)
# report performance
mse = mean_squared_error(y, predictions)
rmse = sqrt(mse)
print('RMSE: %.3f' % rmse)
#accuracy = accuracy_score(y, predictions)
#print('Accuracy: %.3f' % accuracy)
pyplot.plot(y)
pyplot.plot(predictions, color='red')
#pyplot.show()
pyplot.title('Statistical Time Forecasting Load Demand')
pyplot.ylabel('Load Demand (Megawatts)')
pyplot.xlabel('Hours')
pyplot.legend(['Expected', 'Predicted'], loc='upper left')
pyplot.show()