## 策略简介
因子:样例因子(7个)
因子是否标准化:是
标注:未来5日收益(不做离散化)
算法:DNN
类型:回归问题
训练集:10-15年
测试集:16-19年
选股依据:根据预测值降序排序买入
持股数:30
持仓天数:5
模型结构
输入层 7 - 因子数量
全连接层 256 激活函数为relu
dropout 0.1
全连接层 128 激活函数为relu
全连接层 1 激活函数为linear - 预测输出
# 本代码由可视化策略环境自动生成 2021年11月25日 17:38
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
# 用户的自定义层需要写到字典中,比如
# {
# "MyLayer": MyLayer
# }
m5_custom_objects_bigquant_run = {
}
# Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端
def m24_run_bigquant_run(input_1, input_2, input_3):
# 示例代码如下。在这里编写您的代码
pred_label = input_1.read_pickle()
df = input_2.read_df()
df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})
df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])
return Outputs(data_1=DataSource.write_df(df), data_2=None, data_3=None)
# 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m24_post_run_bigquant_run(outputs):
return outputs
# 回测引擎:初始化函数,只执行一次
def m13_initialize_bigquant_run(context):
# 加载预测数据
context.ranker_prediction = context.options['data'].read_df()
# 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
# 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
# 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
stock_count = 5
# 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]
context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
# 设置每只股票占用的最大资金比例
context.max_cash_per_instrument = 0.2
context.hold_days = 5
# 回测引擎:每日数据处理函数,每天执行一次
def m13_handle_data_bigquant_run(context, data):
# 按日期过滤得到今日的预测数据
ranker_prediction = context.ranker_prediction[
context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
# 1. 资金分配
# 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金
# 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)
is_staging = context.trading_day_index < context.hold_days # 是否在建仓期间(前 hold_days 天)
cash_avg = context.portfolio.portfolio_value / context.hold_days
cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
# 通过positions对象,使用列表生成式的方法获取目前持仓的股票列表
stock_hold_now = {e.symbol: p.amount * p.last_sale_price
for e, p in context.portfolio.positions.items()}
# 所拥有的仓位情况
positions = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
#------------------------------------------止赢模块START--------------------------------------------
date = data.current_dt.strftime('%Y-%m-%d')
positions_1 = {e.symbol: p.cost_basis for e, p in context.portfolio.positions.items()}
# 新建当日止赢股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
current_stopwin_stock = []
if len(positions_1) > 0:
for i in positions.keys():
stock_cost = positions_1[i]
stock_market_price = data.current(context.symbol(i), 'price')
# 赚3元就止赢
if stock_market_price - stock_cost >= 5:
context.order_target_percent(context.symbol(i),0)
cash_for_sell -= stock_hold_now[i]
current_stopwin_stock.append(i)
print('日期:',date,'股票:',i,'出现止盈状况')
#-------------------------------------------止赢模块END---------------------------------------------
#------------------------------------------止损模块START--------------------------------------------
# 新建当日止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
current_stoploss_stock = []
if len(positions) > 0:
for i in positions.keys():
stock_market_price = data.current(context.symbol(i), 'price') # 最新市场价格
last_sale_date = positions[i].last_sale_date # 上次交易日期
delta_days = data.current_dt - last_sale_date
hold_days = delta_days.days # 持仓天数
# 建仓以来的最高价
highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
# 确定止损位置
stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.25
record('止损位置', stoploss_line)
# 如果价格下穿止损位置
if stock_market_price < stoploss_line:
context.order_target_percent(context.symbol(i),0)
cash_for_sell -= stock_hold_now[i]
current_stoploss_stock.append(i)
print('日期:', date , '股票:', i, '出现止损状况')
#-------------------------------------------止损模块END--------------------------------------------------
# 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按StockRanker预测的排序末位淘汰
stock_to_sell = []
stock_to_sell = current_stopwin_stock + current_stoploss_stock
if not is_staging and cash_for_sell > 0:
if len(positions) > 0:
for instrument in positions.keys():
last_sale_date = positions[instrument].last_sale_date #上次交易日期
delta_days = data.current_dt - last_sale_date
hold_days = delta_days.days #持仓天数
# 股票实行t+1制度,必须使持仓天数大于0
if hold_days > 0:
equities = {e.symbol: e for e, p in context.portfolio.positions.items()}
instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
# print('rank order for sell %s' % instruments)
for instrument1 in instruments:
context.order_target(context.symbol(instrument1), 0)
cash_for_sell -= positions_1[instrument1]
if cash_for_sell <= 0:
break
# 3. 生成买入订单:按StockRanker预测的排序,买入前面的stock_count只股票
buy_cash_weights = context.stock_weights
buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
for i, instrument in enumerate(buy_instruments):
cash = cash_for_buy * buy_cash_weights[i]
if cash > max_cash_per_instrument - stock_hold_now.get(instrument, 0):
# 确保股票持仓量不会超过每次股票最大的占用资金量
cash = max_cash_per_instrument - stock_hold_now.get(instrument, 0)
if cash > 0:
# 获取今天和过去两天的成交量
volume_since_buy = data.history(context.symbol(instrument), 'volume', 3, '1d')
close_price = data.current(context.symbol(instrument), 'close') #当收盘价
high_price = data.current(context.symbol(instrument), 'high') #当天最高价
# 冲高回落的股票不能买
if ((volume_since_buy[2]/volume_since_buy[1] < 2.5) or (high_price/close_price<1.05)) and volume_since_buy[2]/volume_since_buy[0] > 1:
current_price = data.current(context.symbol(instrument), 'price')
amount = math.floor(cash / current_price - cash / current_price % 100)
context.order(context.symbol(instrument), amount)
return
# 回测引擎:准备数据,只执行一次
def m13_prepare_bigquant_run(context):
pass
# 回测引擎:每个单位时间开始前调用一次,即每日开盘前调用一次。
def m13_before_trading_start_bigquant_run(context, data):
pass
m1 = M.instruments.v2(
start_date='2015-01-01',
end_date='2019-12-31',
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m2 = M.advanced_auto_labeler.v2(
instruments=m1.data,
label_expr="""# #号开始的表示注释
# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
# 添加benchmark_前缀,可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)-1
# 极值处理:用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
start_date='',
end_date='',
benchmark='000300.SHA',
drop_na_label=True,
cast_label_int=False
)
m33 = M.standardlize.v9(
input_1=m2.data,
standard_func='ZScoreNorm',
columns_input='label'
)
m3 = M.input_features.v1(
features="""close_0/mean(close_0,5)
close_0/mean(close_0,10)
close_0/mean(close_0,20)
close_0/open_0
open_0/mean(close_0,5)
open_0/mean(close_0,10)
open_0/mean(close_0,20)
return_5
return_10
avg_amount_0/avg_amount_5
rank_avg_amount_0/rank_avg_amount_5
rank_return_0
rank_return_5
rank_return_0/rank_return_5
pe_ttm_0
""",
m_cached=False
)
m12 = M.input_features.v1(
features_ds=m3.data,
features="""# #号开始的表示注释
# 多个特征,每行一个,可以包含基础特征和衍生特征
close_0
high_1
open_0
low_0
st_status_0"""
)
m15 = M.general_feature_extractor.v7(
instruments=m1.data,
features=m12.data,
start_date='',
end_date='',
before_start_days=0
)
m16 = M.derived_feature_extractor.v3(
input_data=m15.data,
features=m12.data,
date_col='date',
instrument_col='instrument',
drop_na=True,
remove_extra_columns=False
)
m31 = M.standardlize.v9(
input_1=m16.data,
input_2=m3.data,
standard_func='ZScoreNorm',
columns_input='[]'
)
m7 = M.join.v3(
data1=m33.data,
data2=m31.data,
on='date,instrument',
how='inner',
sort=False
)
m19 = M.filter.v3(
input_data=m7.data,
expr='st_status_0==0 and low_0>high_1 and close_0>open_0',
output_left_data=False
)
m26 = M.dl_convert_to_bin.v2(
input_data=m19.data,
features=m12.data,
window_size=1,
feature_clip=5,
flatten=True,
window_along_col='instrument'
)
m9 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2020-01-01'),
end_date=T.live_run_param('trading_date', '2021-11-19'),
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m17 = M.general_feature_extractor.v7(
instruments=m9.data,
features=m12.data,
start_date='',
end_date='',
before_start_days=0
)
m18 = M.derived_feature_extractor.v3(
input_data=m17.data,
features=m12.data,
date_col='date',
instrument_col='instrument',
drop_na=True,
remove_extra_columns=False
)
m34 = M.standardlize.v9(
input_1=m18.data,
input_2=m3.data,
standard_func='ZScoreNorm',
columns_input='[]'
)
m28 = M.filter.v3(
input_data=m34.data,
expr='st_status_0==0 and low_0>high_1+0.02 and close_0>open_0',
output_left_data=False
)
m27 = M.dl_convert_to_bin.v2(
input_data=m28.data,
features=m12.data,
window_size=1,
feature_clip=5,
flatten=True,
window_along_col='instrument'
)
m6 = M.dl_layer_input.v1(
shape='20',
batch_shape='',
dtype='float32',
sparse=False,
name=''
)
m8 = M.dl_layer_dense.v1(
inputs=m6.data,
units=256,
activation='relu',
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='Zeros',
kernel_regularizer='None',
kernel_regularizer_l1=0,
kernel_regularizer_l2=0,
bias_regularizer='None',
bias_regularizer_l1=0,
bias_regularizer_l2=0,
activity_regularizer='None',
activity_regularizer_l1=0,
activity_regularizer_l2=0,
kernel_constraint='None',
bias_constraint='None',
name=''
)
m21 = M.dl_layer_dropout.v1(
inputs=m8.data,
rate=0.1,
noise_shape='',
name=''
)
m20 = M.dl_layer_dense.v1(
inputs=m21.data,
units=128,
activation='relu',
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='Zeros',
kernel_regularizer='None',
kernel_regularizer_l1=0,
kernel_regularizer_l2=0,
bias_regularizer='None',
bias_regularizer_l1=0,
bias_regularizer_l2=0,
activity_regularizer='None',
activity_regularizer_l1=0,
activity_regularizer_l2=0,
kernel_constraint='None',
bias_constraint='None',
name=''
)
m22 = M.dl_layer_dropout.v1(
inputs=m20.data,
rate=0.1,
noise_shape='',
name=''
)
m23 = M.dl_layer_dense.v1(
inputs=m22.data,
units=1,
activation='linear',
use_bias=True,
kernel_initializer='glorot_uniform',
bias_initializer='Zeros',
kernel_regularizer='None',
kernel_regularizer_l1=0,
kernel_regularizer_l2=0,
bias_regularizer='None',
bias_regularizer_l1=0,
bias_regularizer_l2=0,
activity_regularizer='None',
activity_regularizer_l1=0,
activity_regularizer_l2=0,
kernel_constraint='None',
bias_constraint='None',
name=''
)
m4 = M.dl_model_init.v1(
inputs=m6.data,
outputs=m23.data
)
m5 = M.dl_model_train.v1(
input_model=m4.data,
training_data=m26.data,
optimizer='Adam',
loss='mean_squared_error',
metrics='mse',
batch_size=1024,
epochs=20,
custom_objects=m5_custom_objects_bigquant_run,
n_gpus=0,
verbose='2:每个epoch输出一行记录',
m_cached=False
)
m11 = M.dl_model_predict.v1(
trained_model=m5.data,
input_data=m27.data,
batch_size=1024,
n_gpus=0,
verbose='2:每个epoch输出一行记录'
)
m24 = M.cached.v3(
input_1=m11.data,
input_2=m28.data,
run=m24_run_bigquant_run,
post_run=m24_post_run_bigquant_run,
input_ports='',
params='{}',
output_ports=''
)
m13 = M.trade.v4(
instruments=m9.data,
options_data=m24.data_1,
start_date='',
end_date='',
initialize=m13_initialize_bigquant_run,
handle_data=m13_handle_data_bigquant_run,
prepare=m13_prepare_bigquant_run,
before_trading_start=m13_before_trading_start_bigquant_run,
volume_limit=0.025,
order_price_field_buy='open',
order_price_field_sell='close',
capital_base=1000000,
auto_cancel_non_tradable_orders=True,
data_frequency='daily',
price_type='后复权',
product_type='股票',
plot_charts=True,
backtest_only=False,
benchmark=''
)
[2021-11-25 13:41:59.841234] INFO: moduleinvoker: instruments.v2 开始运行..
[2021-11-25 13:41:59.865630] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:41:59.868011] INFO: moduleinvoker: instruments.v2 运行完成[0.026811s].
[2021-11-25 13:41:59.880626] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..
[2021-11-25 13:41:59.888882] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:41:59.892172] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.011546s].
[2021-11-25 13:41:59.900328] INFO: moduleinvoker: standardlize.v9 开始运行..
[2021-11-25 13:41:59.911186] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:41:59.913670] INFO: moduleinvoker: standardlize.v9 运行完成[0.013335s].
[2021-11-25 13:41:59.924906] INFO: moduleinvoker: input_features.v1 开始运行..
[2021-11-25 13:41:59.965431] INFO: moduleinvoker: input_features.v1 运行完成[0.040542s].
[2021-11-25 13:41:59.971328] INFO: moduleinvoker: input_features.v1 开始运行..
[2021-11-25 13:42:00.024512] INFO: moduleinvoker: input_features.v1 运行完成[0.053137s].
[2021-11-25 13:42:00.055457] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2021-11-25 13:42:00.071330] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:42:00.074059] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.018652s].
[2021-11-25 13:42:00.085053] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2021-11-25 13:42:09.790864] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.011s
[2021-11-25 13:42:13.216332] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 3.424s
[2021-11-25 13:42:16.472203] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,20), 3.253s
[2021-11-25 13:42:19.750830] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 3.277s
[2021-11-25 13:42:19.758042] INFO: derived_feature_extractor: 提取完成 close_0/open_0, 0.006s
[2021-11-25 13:42:23.020184] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,10), 3.261s
[2021-11-25 13:42:26.290998] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,20), 3.265s
[2021-11-25 13:42:29.755232] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,5), 3.462s
[2021-11-25 13:42:29.765019] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.007s
[2021-11-25 13:42:29.772630] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.006s
[2021-11-25 13:42:32.055470] INFO: derived_feature_extractor: /y_2015, 569698
[2021-11-25 13:42:34.180510] INFO: derived_feature_extractor: /y_2016, 641546
[2021-11-25 13:42:36.678758] INFO: derived_feature_extractor: /y_2017, 743233
[2021-11-25 13:42:39.901945] INFO: derived_feature_extractor: /y_2018, 816987
[2021-11-25 13:42:43.096575] INFO: derived_feature_extractor: /y_2019, 884867
[2021-11-25 13:42:48.200663] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[48.115604s].
[2021-11-25 13:42:48.209175] INFO: moduleinvoker: standardlize.v9 开始运行..
[2021-11-25 13:44:40.541793] INFO: moduleinvoker: standardlize.v9 运行完成[112.332575s].
[2021-11-25 13:44:40.563941] INFO: moduleinvoker: join.v3 开始运行..
[2021-11-25 13:45:04.171326] INFO: join: /data, 行数=3551812/3584516, 耗时=16.655225s
[2021-11-25 13:45:04.289567] INFO: join: 最终行数: 3551812
[2021-11-25 13:45:04.331244] INFO: moduleinvoker: join.v3 运行完成[23.767289s].
[2021-11-25 13:45:04.347264] INFO: moduleinvoker: filter.v3 开始运行..
[2021-11-25 13:45:04.398510] INFO: filter: 使用表达式 st_status_0==0 and low_0>high_1 and close_0>open_0 过滤
[2021-11-25 13:45:08.827461] INFO: filter: 过滤 /data, 49201/0/3551812
[2021-11-25 13:45:08.879691] INFO: moduleinvoker: filter.v3 运行完成[4.53242s].
[2021-11-25 13:45:08.905054] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..
[2021-11-25 13:45:09.069417] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.164364s].
[2021-11-25 13:45:09.079322] INFO: moduleinvoker: instruments.v2 开始运行..
[2021-11-25 13:45:09.088761] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:45:09.090422] INFO: moduleinvoker: instruments.v2 运行完成[0.011119s].
[2021-11-25 13:45:09.102805] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2021-11-25 13:45:09.109532] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:45:09.111415] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.008625s].
[2021-11-25 13:45:09.119241] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2021-11-25 13:45:13.210817] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.005s
[2021-11-25 13:45:14.709968] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 1.498s
[2021-11-25 13:45:16.178875] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,20), 1.467s
[2021-11-25 13:45:17.620264] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 1.440s
[2021-11-25 13:45:17.628641] INFO: derived_feature_extractor: 提取完成 close_0/open_0, 0.005s
[2021-11-25 13:45:19.083020] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,10), 1.451s
[2021-11-25 13:45:20.460220] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,20), 1.376s
[2021-11-25 13:45:21.878354] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,5), 1.417s
[2021-11-25 13:45:21.883251] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.003s
[2021-11-25 13:45:21.888161] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s
[2021-11-25 13:45:24.437994] INFO: derived_feature_extractor: /y_2020, 945961
[2021-11-25 13:45:27.394383] INFO: derived_feature_extractor: /y_2021, 922284
[2021-11-25 13:45:28.639390] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[19.520128s].
[2021-11-25 13:45:28.646433] INFO: moduleinvoker: standardlize.v9 开始运行..
[2021-11-25 13:46:11.268497] INFO: moduleinvoker: standardlize.v9 运行完成[42.62205s].
[2021-11-25 13:46:11.277192] INFO: moduleinvoker: filter.v3 开始运行..
[2021-11-25 13:46:11.297546] INFO: filter: 使用表达式 st_status_0==0 and low_0>high_1+0.02 and close_0>open_0 过滤
[2021-11-25 13:46:13.137062] INFO: filter: 过滤 /data, 20118/0/1779515
[2021-11-25 13:46:13.179736] INFO: moduleinvoker: filter.v3 运行完成[1.902536s].
[2021-11-25 13:46:13.197713] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..
[2021-11-25 13:46:13.324766] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.127042s].
[2021-11-25 13:46:16.554084] INFO: moduleinvoker: dl_layer_input.v1 运行完成[3.215744s].
[2021-11-25 13:46:16.610593] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.048333s].
[2021-11-25 13:46:16.633323] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.008265s].
[2021-11-25 13:46:16.660713] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.019982s].
[2021-11-25 13:46:16.674634] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.006356s].
[2021-11-25 13:46:16.697648] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.015599s].
[2021-11-25 13:46:16.751490] INFO: moduleinvoker: cached.v3 开始运行..
[2021-11-25 13:46:16.762313] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:46:16.764667] INFO: moduleinvoker: cached.v3 运行完成[0.013216s].
[2021-11-25 13:46:16.768032] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.062626s].
[2021-11-25 13:46:16.777625] INFO: moduleinvoker: dl_model_train.v1 开始运行..
[2021-11-25 13:46:16.929941] INFO: dl_model_train: 准备训练,训练样本个数:49201,迭代次数:20
[2021-11-25 13:46:35.325890] INFO: dl_model_train: 训练结束,耗时:18.39s
[2021-11-25 13:46:35.356952] INFO: moduleinvoker: dl_model_train.v1 运行完成[18.57933s].
[2021-11-25 13:46:35.362859] INFO: moduleinvoker: dl_model_predict.v1 开始运行..
[2021-11-25 13:46:35.746596] INFO: moduleinvoker: dl_model_predict.v1 运行完成[0.383755s].
[2021-11-25 13:46:35.771854] INFO: moduleinvoker: cached.v3 开始运行..
[2021-11-25 13:46:35.988538] INFO: moduleinvoker: cached.v3 运行完成[0.216696s].
[2021-11-25 13:46:37.913939] INFO: moduleinvoker: backtest.v8 开始运行..
[2021-11-25 13:46:37.919622] INFO: backtest: biglearning backtest:V8.6.0
[2021-11-25 13:46:37.921187] INFO: backtest: product_type:stock by specified
[2021-11-25 13:46:38.043308] INFO: moduleinvoker: cached.v2 开始运行..
[2021-11-25 13:46:38.052767] INFO: moduleinvoker: 命中缓存
[2021-11-25 13:46:38.054358] INFO: moduleinvoker: cached.v2 运行完成[0.011094s].
[2021-11-25 13:46:41.013484] INFO: algo: TradingAlgorithm V1.8.5
[2021-11-25 13:46:42.113314] INFO: algo: trading transform...
[2021-11-25 13:47:31.927159] INFO: Performance: Simulated 456 trading days out of 456.
[2021-11-25 13:47:31.928746] INFO: Performance: first open: 2020-01-02 09:30:00+00:00
[2021-11-25 13:47:31.929901] INFO: Performance: last close: 2021-11-19 15:00:00+00:00
[2021-11-25 13:47:38.914002] INFO: moduleinvoker: backtest.v8 运行完成[61.000068s].
[2021-11-25 13:47:38.915815] INFO: moduleinvoker: trade.v4 运行完成[62.915567s].