def main(config):
logger = load_logger(config)
try:
np.random.seed(config.random_seed) # 设置随机种子
data_gainer = Data(config)
if config.do_train:
train_X, valid_X, train_Y, valid_Y = data_gainer.get_train_and_valid_data(
)
train(config, logger, [train_X, train_Y, valid_X, valid_Y])
if config.do_predict:
test_X, test_Y, test_date = data_gainer.get_test_data(
return_label_data=True)
pred_result = predict(config, test_X)
pred_result = [np.argwhere(i == max(i)) for i in pred_result]
pred_result = np.squeeze(pred_result)
test_Y = np.squeeze(test_Y)
draw(config, data_gainer, logger, pred_result, test_Y, test_date)
#save_predict(config,pred_result,test_date)
if config.do_predict_all:
test_X, test_date = data_gainer.get_test_data(
return_label_data=False, predict_all=True)
pred_result = predict(config, test_X)
pred_result = [np.argwhere(i == max(i)) for i in pred_result]
pred_result = np.squeeze(pred_result)
#draw(config, data_gainer, logger, pred_result, test_Y,test_date)
save_predict(config, pred_result, test_date)
except Exception:
logger.error("Run Error", exc_info=True)
def main(config):
logger = load_logger(config)
try:
np.random.seed(config.random_seed) # 设置随机种子，保证可复现
data_gainer = Data(config)
if config.do_train:
train_X, valid_X, train_Y, valid_Y = data_gainer.get_train_and_valid_data(
)
train(config, logger, [train_X, train_Y, valid_X, valid_Y])
if config.do_predict:
test_X, test_Y = data_gainer.get_test_data()
pred_ys, real_ys, pred_ys_no_flat = predict(
config, [test_X, test_Y])
target_names = ['class flat', 'class down',
'class rise'] # label: 0:平 1:跌 2:涨
print('Classification table for test set:')
print(
classification_report(real_ys,
pred_ys,
target_names=target_names))
# draw(config, data_gainer, logger, pred_result)
except Exception:
logger.error("Run Error", exc_info=True)
def main(config):
np.random.seed(config.random_seed)
data_gainer = Data(config)
if config.do_train:
train_X, valid_X, train_Y, valid_Y = data_gainer.get_train_and_valid_data(
)
train(config, train_X, train_Y, valid_X, valid_Y)
if config.do_predict:
test_X, test_Y = data_gainer.get_test_data(return_label_data=True)
pred_result = predict(config, test_X)
draw(config, data_gainer, pred_result)
def main(config):
logger = load_logger(config)
try:
np.random.seed(config.random_seed) # 设置随机种子，保证可复现
data_gainer = Data(config)
if config.do_train:
train_X, valid_X, train_Y, valid_Y = data_gainer.get_train_and_valid_data()
train(config, logger, [train_X, train_Y, valid_X, valid_Y])
if config.do_predict:
test_X, test_Y = data_gainer.get_test_data(return_label_data=True)
pred_result = predict(config, test_X) # 这里输出的是未还原的归一化预测数据
draw(config, data_gainer, logger, pred_result)
except Exception:
logger.error("Run Error", exc_info=True)
def main(config):
logger = load_logger(config)
try:
np.random.seed(config.random_seed)
data_gainer = Data(config)
if config.do_train:
train_X, train_Y = data_gainer.get_dataset('train')
valid_X, valid_Y = data_gainer.get_dataset('val')
train(config, logger, [train_X, train_Y, valid_X, valid_Y])
if config.do_predict:
test_X, test_Y = data_gainer.get_test_data(return_label_data=True)
pred_result = predict(config, test_X)
# TODO:save prediction result into csv file
save_prediction_data(config, data_gainer, pred_result)
#draw(config, data_gainer, logger, pred_result)
except Exception:
logger.error("Run Error", exc_info=True)
