def finalize(filename=None):
dataset = Series.from_csv('Krakow_data.csv')
X = dataset.values.astype('float32')
history = [x for x in X]
months_in_year = 12
diff = difference.difference(X, months_in_year)
model = ARIMA(diff, order=(6, 0, 2))
model_fit = model.fit(trend='nc', disp=0)
model_fit.save('model.pkl')
np.save('model_bias.npy', [0.237574])
validation = Series.from_csv('Krakow_validation.csv')
y = validation.values.astype('float32')
model_fit = ARIMAResults.load('model.pkl')
bias = np.load('model_bias.npy')
predictions = list()
yhat = float(model_fit.forecast()[0])
yhat = bias + difference.inverse_difference(history, yhat, months_in_year)
predictions.append(yhat)
history.append(y[0])
label_for_x = [
'2017-06', '2017-07', '2017-08', '2017-09', '2017-10', '2017-11',
'2017-12', '2018-01', '2018-02', '2018-03', '2018-04', '2018-05',
'2018-06', '2018-07', '2018-08'
]
print('For month: {} Predicted= {} , Expected= {}'.format(
label_for_x[0], str(yhat), str(y[0])))
for i in range(1, len(y)):
months_in_year = 12
diff = difference.difference(history, months_in_year)
model = ARIMA(diff, order=(6, 0, 2))
model_fit = model.fit(trend='nc', disp=0)
yhat = model_fit.forecast()[0]
yhat = bias + difference.inverse_difference(history, yhat,
months_in_year)
predictions.append(yhat)
obs = y[i]
history.append(obs)
print('For month: {} Predicted= {} , Expected= {}'.format(
label_for_x[i], str(yhat), str(obs)))
mse = mean_squared_error(y, predictions)
rmse = sqrt(mse)
print('RMSE: {:0.3f}'.format(rmse))
plt.figure(figsize=(10, 7))
plt.title('Forecast for temperature in Kraków')
plt.xlabel('Data')
plt.ylabel('Temperature')
plt.xticks(list(range(0, 15)), label_for_x)
plt.xticks(rotation=45)
plt.grid()
plt.plot(y, label="Observational values")
plt.plot(predictions, color='red', label="Foreseen values")
plt.legend()
plt.savefig(filename)
return rmse
def differences(query):
import difference as dif
ans = "<NA>"
getAns= dif.difference(query)
if getAns:
ans = [{"differences":getAns}]
else:
ans =[{}]
return ans
def forecast(series, filename):
X = series.values
months_in_year = 12
differenced = np.array(difference.difference(
X, months_in_year)) #compare current value with last year value
# fit model
model = ARIMA(differenced, order=(6, 0, 2)) #adjust model to dataset
model_fit = model.fit(disp=0)
# multi-step out-of-sample forecast
forecast = model_fit.forecast(steps=12)[0]
# invert the differenced forecast to something usable
history = [x for x in X]
#generate monthly data
times = list(pd.date_range('2018-09-01', periods=12, freq='MS'))
month = 1
for yhat in forecast:
inverted = difference.inverse_difference(history, yhat, months_in_year)
print('Month {:%Y-%m} Predicted temperature: {:.2f}'.format(
times[month - 1], inverted))
history.append(inverted)
month += 1
#plotting
plt.clf()
plt.figure(figsize=(10, 7))
plt.grid()
plt.title(
'Multi-step out-of-sample forecast for Kraków within 12 upcoming months'
)
plt.xlabel('Date')
plt.ylabel('Temperature [°C]')
plt.plot(times, history[len(X):], label='Average temperature'
) #we want to plot only the last 12 predicted values
plt.legend()
RMSE = 3.114
plt.fill_between(times, [(item - RMSE) for item in history[len(X):]],
[(item + RMSE) for item in history[len(X):]],
color='k',
alpha=.15)
plt.xticks(rotation=45)
plt.yticks([item for item in range(-6, 26, 2)])
plt.savefig(filename)
def Dickey_Fuller_test(series, filename_csv, filename_plot):
X = series.values
X = X.astype('float32')
months_in_year = 12
stationary = Series(difference.difference(X, months_in_year))
stationary.index = series.index[months_in_year:]
result = adfuller(stationary)
print('ADF Statistic: %f' % result[0])
print('p-value: %f' % result[1])
print('Critical Values:')
for key, value in result[4].items():
print('\t%s: %.3f' % (key, value))
stationary.to_csv(filename_csv)
plt.clf()
plt.figure(figsize=(10, 7))
stationary.plot()
plt.grid()
plt.title('Seasonal differenced temperature line plot')
plt.ylabel('Temperature [°C]')
plt.savefig(filename_plot)
import shlex, sys, difference
if __name__ == '__main__':
ab = shlex.split(file(sys.argv[1]).read())
sys.stdout.write(str(difference.difference(ab[0], ab[1])))
import shlex, sys, difference
if __name__ == "__main__":
ab = shlex.split(file(sys.argv[1]).read())
sys.stdout.write(str(difference.difference(ab[0], ab[1])))
