Last active
May 20, 2020 17:47
-
-
Save AVJdataminer/425ebc0b421c398d5e59e5254f01700b to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Make a function to find the MSE of a single ARIMA model | |
def evaluate_arima_model(data, arima_order): | |
# Needs to be an integer because it is later used as an index. | |
split=int(len(data) * 0.8) | |
train, test = data[0:split], data[split:len(data)] | |
past=[x for x in train] | |
# make predictions | |
predictions = list() | |
for i in range(len(test)):#timestep-wise comparison between test data and one-step prediction ARIMA model. | |
model = ARIMA(past, order=arima_order) | |
model_fit = model.fit(disp=0) | |
future = model_fit.forecast()[0] | |
predictions.append(future) | |
past.append(test[i]) | |
# calculate out of sample error | |
error = mean_squared_error(test, predictions) | |
return error | |
# Make a function to evaluate different ARIMA models with several different p, d, and q values. | |
def evaluate_models(dataset, p_values, d_values, q_values): | |
best_score, best_cfg = float("inf"), None | |
for p in p_values: | |
for d in d_values: | |
for q in q_values: | |
order = (p,d,q) | |
try: | |
mse = evaluate_arima_model(dataset, order) | |
if mse < best_score: | |
best_score, best_cfg = mse, order | |
print('ARIMA%s MSE=%.3f' % (order,mse)) | |
except: | |
continue | |
return print('Best ARIMA%s MSE=%.3f' % (best_cfg, best_score)) | |
# Now, we choose a couple of values to try for each parameter. | |
p_values = [x for x in range(0, 4)] | |
d_values = [x for x in range(0, 1)] | |
q_values = [x for x in range(15, 20)] | |
# Finally, we can find the optimum ARIMA model for our data. | |
# Nb. this can take a while...! | |
import warnings | |
warnings.filterwarnings("ignore") | |
y_log = np.log(y) | |
evaluate_models(y_log, p_values, d_values, q_values) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment