def execute(dataframe, file_name):
# Parameters
period_len, next_periods = 12, 12
# Generate result
forecast_result, alpha, beta, gamma, rmse = hw.multiplicative(dataframe, period_len, next_periods)
# Log result to file
out_file_name = 'data/result_' + file_name.split('.')[0] + '_holt_winter.txt'
f = open(out_file_name, 'w')
print('Full timeframe:\n{}'.format(forecast_result), file=f)
print('\n------------------------\n', file=f)
print('Partial timeframe:\n{}'.format(forecast_result[-next_periods:]), file=f)
print('\n------------------------\n', file=f)
print('Alpha = {}'.format(alpha), file=f)
print('\n------------------------\n', file=f)
print('Beta = {}'.format(beta), file=f)
print('\n------------------------\n', file=f)
print('Gamma = {}'.format(gamma), file=f)
print('\n------------------------\n', file=f)
print('RMSE = {}'.format(rmse), file=f)
f.close()
# Combine dataframe
result = pd.concat(objs=[dataframe, forecast_result], axis=1)
result.columns = ['Actual', 'Forecast']
# Plot
result.plot()
plt.show()
def holt_pred_test(steps, path, func):
index_name, my_trend = parse_csv(path)
if func == 'additive':
future, alpha, beta, gamma, rmse = additive(my_trend[-5 * 52:-steps],
52, steps)
if func == 'multi':
future, alpha, beta, gamma, rmse = multiplicative(
my_trend[-5 * 52:-steps], 52, steps)
y_pred = np.array(future)
y_true = np.array(my_trend[-steps:])
metrics_result = {
'sarima_MAE': metrics.mean_absolute_error(y_true, y_pred),
'sarima_MSE': metrics.mean_squared_error(y_true, y_pred),
'sarima_MAPE': np.mean(np.abs((y_true - y_pred) / y_true)) * 100
}
p1 = plt.plot(my_trend[-steps:], '*-')
p2 = plt.plot(future)
# p1 = plt.plot(index_name,my_trend,'r-')
# p2 = plt.plot(index_name_future,future,'g-')
plt.ylabel('Search Intensity')
plt.xlabel('Year')
plt.title('Search Prediction of ' + path.split('/')[-1][:-4])
plt.legend((p1[0], p2[0]), ["Actual", "Predicted"], loc=1)
plt.grid(True)
# print metrics_result['sarima_MAPE']
return metrics_result['sarima_MAPE']
def holt_pred_test(steps,path,func):
index_name,my_trend = parse_csv(path)
if func == 'additive':
future, alpha, beta, gamma, rmse = additive(my_trend[-5*52:-steps],52,steps)
if func == 'multi':
future, alpha, beta, gamma, rmse = multiplicative(my_trend[-5*52:-steps],52,steps)
y_pred = np.array(future)
y_true = np.array(my_trend[-steps:])
metrics_result = {'sarima_MAE':metrics.mean_absolute_error(y_true, y_pred),'sarima_MSE':metrics.mean_squared_error(y_true, y_pred),
'sarima_MAPE':np.mean(np.abs((y_true - y_pred) / y_true)) * 100}
p1 = plt.plot(my_trend[-steps:],'*-')
p2 = plt.plot(future)
# p1 = plt.plot(index_name,my_trend,'r-')
# p2 = plt.plot(index_name_future,future,'g-')
plt.ylabel('Search Intensity')
plt.xlabel('Year')
plt.title('Search Prediction of '+path.split('/')[-1][:-4])
plt.legend((p1[0], p2[0]), ["Actual","Predicted"], loc=1)
plt.grid(True)
# print metrics_result['sarima_MAPE']
return metrics_result['sarima_MAPE']
if __name__ == '__main__':
forecastCount = 12
x = np.array([i for i in range(0, len(data)+forecastCount)])
linearfc = np.zeros([1,len(data)+forecastCount])
additivefc = np.zeros([1,len(data)+forecastCount])
multiplefc = np.zeros([1,len(data)+forecastCount])
for i in range(2, len(data)):
forecast, alpha, beta, rmse = hw.linear(data[:i], 1)
linearfc[0, i:i+len(forecast)] = forecast
if i>4:
forecast, alpha, beta, gamma, rmse = hw.additive(data[:i], m=4, fc=1)
additivefc[0, i:i+len(forecast)] = forecast
forecast, alpha, beta, gamma, rmse = hw.multiplicative(data[:i], m=4, fc=1)
multiplefc[0, i:i+len(forecast)] = forecast
else:
forecast, alpha, beta, gamma, rmse = hw.additive(data[:i], m=1, fc=1)
additivefc[0, i:i+len(forecast)] = forecast
forecast, alpha, beta, gamma, rmse = hw.multiplicative(data[:i], m=1, fc=1)
multiplefc[0, i:i+len(forecast)] = forecast
# Linear
forecast, alpha, beta, rmse = hw.linear(data, forecastCount)
linearfc[0,-forecastCount:] = forecast
# Additive
forecast, alpha, beta, gamma, rmse = hw.additive(data, m=4, fc=forecastCount)
# ----------------------------------------------------------
# Period 1: Jan 1994 to Mar 2016 with forecast to Mar 2017
# ----------------------------------------------------------
fig = plt.figure()
fig = plt.figure(figsize=(10,6))
plt.plot(car_sales)
plt.title("Figure HW1. Number of Car sales in Australia from January 1994 to March 2017")
plt.xlabel("Months")
plt.ylabel("Number of Sales")
plt.show(block=False)
fc1 = 12 # 12 months forecasting
h1 = 12 # Number of seasons
y_smoothed_mult1, y_forecast_vals1, alpha1, beta1, gamma1, rmse1 = hw.multiplicative(y1_list,fc=fc1,m=h1)
plt.plot(x1full_list,y1full_list,label = 'Observed')
plt.plot(x1full_list,y_smoothed_mult1[:-1], '-r',color= "red",label ='Multiplicative' + 'rmse = '+str(np.round(rmse1,2)))
plt.title('Figure HW2. Number of Car Sales, Holt-Winters Multiplicative Method, January 1994 -March 2017: alpha = '+str(np.round(alpha1,2)) +' ,beta = '+ str(np.round(beta1,2))+',gamma = '+ str(np.round(gamma1,2)))
plt.xlabel('Year')
plt.legend(loc="lower right")
plt.ylabel('Number of Sales')
fig = plt.figure()
fig = plt.figure(figsize=(10,6))
plt.plot(y_forecast_vals1)
plt.title('Figure HW3. Estimated Seasonal Components')
plt.xlabel("Months")
plt.ylabel("Number of Sales")
def Multiplicative(df):
x_smoothed, Y, s, alpha, beta, gamma, rmse = multiplicative(
list(df.values), 12, 6)
return Y
train = y[:-12]
test = y[-12:]
x1 = x[:-12]
#the additive method forecasting
y_smoothed_additive, y_forecast_vals_additive, alpha, beta, gamma,rmse = hw.additive(train.tolist(), fc=fc, m=h)
plt.plot(np.hstack((x1,xp)),y_smoothed_additive[:-1], c = 'red',label="Additive forecasts")
plt.plot(xp,test,c = 'green',label='test set')
plt.legend()
print(alpha,beta,gamma)
#the multiplicative method forecasting
plt.figure(figsize = (12,8))
plt.plot(x,y,label='train set')
plt.xlabel('time span')
plt.ylabel('house price')
plt.title('Multiplicative Holt winters forecasts')
y_smoothed_mult, y_forecast_vals_Multi, alpha, beta, gamma,rmse = hw.multiplicative(train.tolist(), fc=fc, m=h)
plt.plot(np.hstack((x1,xp)),y_smoothed_mult[:-1], c = 'red',label="Multiplicitive forecasts")
plt.plot(xp,test,c = 'green',label='test set')
plt.legend()
print(alpha,beta,gamma)
print(rmse)
# model accuracy for the testing set
yf1 = y_forecast_vals_additive
yf2 = y_forecast_vals_Multi
def mae(yf1, test):
return np.average(np.abs(yf1-test))
def mae(yf2, test):
return np.average(np.abs(yf2-test))
def rmse(yf1,test):
return np.sqrt(np.average(np.power(yf1-test,2)))
def rmse(yf2,test):
x = np.array([i for i in range(0, len(data) + forecastCount)])
linearfc = np.zeros([1, len(data) + forecastCount])
additivefc = np.zeros([1, len(data) + forecastCount])
multiplefc = np.zeros([1, len(data) + forecastCount])
for i in range(2, len(data)):
forecast, alpha, beta, rmse = hw.linear(data[:i], 1)
linearfc[0, i:i + len(forecast)] = forecast
if i > 4:
forecast, alpha, beta, gamma, rmse = hw.additive(data[:i],
m=4,
fc=1)
additivefc[0, i:i + len(forecast)] = forecast
forecast, alpha, beta, gamma, rmse = hw.multiplicative(data[:i],
m=4,
fc=1)
multiplefc[0, i:i + len(forecast)] = forecast
else:
forecast, alpha, beta, gamma, rmse = hw.additive(data[:i],
m=1,
fc=1)
additivefc[0, i:i + len(forecast)] = forecast
forecast, alpha, beta, gamma, rmse = hw.multiplicative(data[:i],
m=1,
fc=1)
multiplefc[0, i:i + len(forecast)] = forecast
# Linear
forecast, alpha, beta, rmse = hw.linear(data, forecastCount)
