def main():
epla_path = "../../tests/inputs/EPLA_example_1.csv"
load_cases = [0, 1, 2, 3, 4]
model = Model()
start = time.time()
model.load_epla(epla_path)
model.build()
build_time = time.time() - start
model.print_tree()
start = time.time()
root_powers = model.solve(load_cases)
solve_time = time.time() - start
cables = model.export_cables()
print(cables)
for cable in cables:
print_cable_size(cable)
model.export_tree(show_cables=True)
model.export_tree(show_cables=False)
for case in load_cases:
print("Load Case " + str(case) + ": " +
format_power(root_powers.pop()))
print('\n')
components = model.export_components()
for comp in components:
print_component_info(comp)
print("Model Evaluation Times")
print("Build Time: " + str("%.0f" % (build_time * 1000)) + " ms")
print("Solve Time: " + str("%.0f" % (solve_time * 1000)) + " ms")
from matplotlib import pyplot as plt
from core.model import Model
from core.data_processor import DataProcessor
# 数据预处理
dp = DataProcessor('./data/AAPL_080112_200112.csv', (85, 0, 15),
['Adj Close', 'Volume'])
data_x, data_y = dp.get_data(50, 'train')
test_x, test_y = dp.get_data(50, 'test')
# 训练模型
model = Model()
model.build()
model.train(data_x, data_y, epochs=10, batch_size=32, save_dir='./saved_model')
# 预测
predicted = model.predict_sequence_multiple(test_x,
window_size=50,
prediction_len=50)
plt.plot(test_y, label='True Data')
for i, data in enumerate(predicted):
padding = [None for p in range(i * 50)]
plt.plot(padding + data, label='Prediction')
plt.legend()
plt.show()
