def main(args: argparse.Namespace):
dataset = Dataset(args.train)
model_args = {
'hidden_size': args.hidden_size,
'input_size': args.input_size,
'feature_size': len(dataset.dataframe.columns),
}
train_x, train_y = dataset(**model_args)
test_frame = dataset.load(args.test)
test = np.concatenate(
(train_x[0],
dataset.transform(
np.hstack((test_frame, np.zeros((len(test_frame), 1)))))))
model = Model.from_file(args.weight)
# Test sequences
print('Testing ...')
for index in range(len(test) - args.input_size):
test_input = np.expand_dims(test[index:index + args.input_size], 0)
pred = model.predict(test_input).squeeze()
test[index + args.input_size, -1] = pred
test_frame[dataset.dataframe.columns[-1]] = dataset.inverse_transform(
test[args.input_size:, -1])
test_frame.to_csv(str(out.joinpath('test-prediction.csv')), index=None)
prediction = test_frame[dataset.dataframe.columns[-1]]
prediction += abs(prediction.min())
label = pd.read_csv(args.label).values[:, -1]
label = MinMaxScaler().fit_transform(label.reshape(-1, 1))
prediction = MinMaxScaler().fit_transform(prediction.reshape(-1, 1))
mse = mean_squared_error(label, prediction)
mae = mean_absolute_error(label, prediction)
mape = mean_absolute_percentage_error(label, prediction, args.epsilon)
print(f'MSE: {mse:.4f}, MAE: {mae:.4f}, MAPE: {mape:.4f}')
def main(args: argparse.Namespace):
init(args.seed)
dataset = Dataset(args.train)
model_args = {
'hidden_size': args.hidden_size,
'input_size': args.input_size,
'feature_size': len(dataset.dataframe.columns),
'nested': args.nested,
'dropout': args.dropout,
}
optim_args = {
'lr': args.lr,
'beta_1': args.beta_1,
'beta_2': args.beta_2,
'decay': args.decay,
}
train_x, train_y = dataset(**model_args)
test_frame = dataset.load(args.test)
label = test_frame.values[:, -1]
test = np.concatenate((train_x[0],
dataset.transform(
np.hstack((test_frame.values[:, :-1],
np.zeros((len(test_frame), 1)))))))
if args.use_test:
test_y = test_frame.values[args.input_size:, -1]
test_x = np.empty((len(test_frame) - args.input_size, args.input_size,
len(dataset.dataframe.columns)))
for i in range(len(test_y) - args.input_size):
test_x[i] = test_frame.values[i:i + args.input_size]
train_x = np.vstack((train_x, test_x))
train_y = np.concatenate((train_y, test_y))
out = Path(args.output)
out.mkdir(exist_ok=True, parents=True)
if args.model:
print(f'Model load from {args.model} ...')
model = Model.from_file(args.model)
else:
model = Model(model_args, optim_args)
if not args.silence:
model.summary()
# Train sequences
print('Training ...')
model.fit(train_x,
train_y,
epochs=args.epoch,
shuffle=False,
batch_size=args.batch,
verbose=not args.silence,
callbacks=model.callbacks(early_stop=not args.no_stop))
model.save(str(out.joinpath('model.h5')))
# Test sequences
print('Testing ...')
for index in tqdm(range(len(test) - args.input_size)):
test_input = np.expand_dims(test[index:index + args.input_size], 0)
pred = model.predict(test_input).squeeze()
test[index + args.input_size, -1] = pred
test_frame[dataset.dataframe.columns[-1]] = test[args.input_size:, -1]
test_frame.to_csv(str(out.joinpath('prediction.csv')), index=None)
test_frame[dataset.dataframe.columns[-1]] = dataset.inverse_transform(
test[args.input_size:, -1])
test_frame.to_csv(str(out.joinpath('prediction-scaled.csv')), index=None)
if not args.no_fig:
def scaler(values: np.ndarray)\
-> np.ndarray:
min_, max_ = values.min(), values.max()
return (values - min_) / (max_ - min_)
import matplotlib
import matplotlib.pyplot as plt
matplotlib.use('Agg')
label_scale = scaler(label)
prediction = scaler(test_frame.values[:, -1])
x_range = np.arange(np.size(prediction, 0))
error = mean_absolute_percentage_error(label_scale, prediction)
plt.title(f'MAPE: {error:.4}')
plt.ylim(0, 1)
plt.plot(x_range, label_scale, c='r')
plt.plot(x_range, prediction, c='b')
plt.savefig(str(out.joinpath('figure.jpg')), dpi=400)
print(f'MAPE: {error:.4}')
