y_hat_predicted = algorithm.knn_regressor(x_train, y_train, x_train, 5)
rmse, y_predicted = compare_train(x_test, y_hat_predicted)
print('RMSE KNN(5) %.3f' % (rmse))
# KNN10
y_hat_predicted = algorithm.knn_regressor(x_train, y_train, x_train, 10)
rmse, y_predicted = compare_train(x_test, y_hat_predicted)
print('RMSE KNN(10) %.3f' % (rmse))
# SGD
y_hat_predicted = algorithm.sgd_regressor(x_train, y_train, x_train)
rmse, y_predicted = compare_train(x_test, y_hat_predicted)
print('RMSE SGD %.3f' % (rmse))
# LSTM
y_hat_predicted = algorithm.lstm(x_train, y_train, x_train, batch_size=1, nb_epoch=3, neurons=1)
rmse, y_predicted = compare_train(x_test, y_hat_predicted)
print('RMSE LSTM %.3f' % (rmse))
print('------- Test --------')
# No Prediction
y_hat_predicted = y_test
rmse, y_hat_predicted = compare_test(y_test, y_hat_predicted)
print('RMSE NoPredic %.3f' % (rmse))
# Dummy
y_predicted_dummy_es = x_test[:, 0]
rmse, y_predicted_dummy = compare_test(y_test, y_predicted_dummy_es)
print('RMSE Dummy %.3f' % (rmse))
# ElasticNet
print('RMSE KNN(10) %.3f' % (rmse))
# SGD
y_predicted_sgd_sc = algorithm.sgd_regressor(x_train, y_train, x_test)
rmse, y_predicted_sgd = compare_test(y_test, y_predicted_sgd_sc)
print('RMSE SGD %.3f' % (rmse))
# Lasso
y_predicted_la_sc = algorithm.lasso(x_train, y_train, x_test, normalize=False)
rmse, y_predicted_la = compare_test(y_test, y_predicted_la_sc)
print('RMSE Lasso %.3f' % (rmse))
# LSTM
y_predicted_lstm = algorithm.lstm(x_train,
y_train,
x_test,
batch_size=1,
nb_epoch=200,
neurons=3)
rmse, y_predicted_lstm = compare_test(y_test, y_predicted_lstm)
print('RMSE LSTM %.3f' % (rmse))
# print('Y_test')
# print(y_test)
titles = ['Y', 'ElasticNet', 'KNN5', 'KNN10', 'SGD', 'Lasso']
data = [
y_test, y_predicted_en, y_predicted_knn5, y_predicted_knn10,
y_predicted_sgd, y_predicted_la
]
# titles = ['', 'Y', 'ElasticNet', 'KNN5', 'KNN10', 'SGD']
# data = [[], y_test, y_predicted_en, y_predicted_knn5, y_predicted_knn10, y_predicted_sgd]