克隆策略
{"Description":"实验创建于2018/10/16","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"-1442:instruments","SourceOutputPortId":"-25:data"},{"DestinationInputPortId":"-1483:input_1","SourceOutputPortId":"-25:data"},{"DestinationInputPortId":"-136:input_1","SourceOutputPortId":"-25:data"},{"DestinationInputPortId":"-1473:features","SourceOutputPortId":"-1468:data"},{"DestinationInputPortId":"-1632:input_data","SourceOutputPortId":"-1473:data"},{"DestinationInputPortId":"-1473:input_data","SourceOutputPortId":"-1483:data_1"},{"DestinationInputPortId":"-1442:options_data","SourceOutputPortId":"-1632:data"},{"DestinationInputPortId":"-1442:benchmark_ds","SourceOutputPortId":"-136:data_1"}],"ModuleNodes":[{"Id":"-25","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2017-11-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-05-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_FUTURE","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"RU1809.SHF","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"-25"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-25","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-1442","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"handle_data","Value":"# 回测引擎：每日数据处理函数，每天执行一次\ndef bigquant_run(context, data):\n # 获取当日指标数据\n today = data.current_dt.strftime('%Y-%m-%d') # 当前交易日期\n buy_condition=context.buy_condition[today]\n sell_condition=context.sell_condition[today]\n \n instrument = context.future_symbol(context.instruments[0]) # 交易标的\n curr_po=context.portfolio.positions[instrument] # 组合持仓\n curr_position = curr_po.amount # 持仓数量\n \n\n # 交易逻辑\n if buy_condition>0 and data.can_trade(instrument): # 开多，下单数量20手\n order_target(instrument, 20)\n print(today,'平空开多')\n \n elif sell_condition>0 and data.can_trade(instrument):# 开空，下单数量20手\n order_target(instrument, -20)\n print(today,'平多开空')","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎：准备数据，只执行一次\ndef bigquant_run(context):\n df = context.options['data'].read_df()\n df['date']=df['date'].apply(lambda x:x.strftime('%Y-%m-%d'))\n df.set_index('date',inplace=True)\n context.buy_condition=df['buy_condition']\n context.sell_condition=df['sell_condition']\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎：初始化函数，只执行一次\ndef bigquant_run(context):\n # 设置是否是结算模式\n context.set_need_settle(False)\n # 设置最大杠杆\n context.set_max_leverage(1, 'fill_amap')","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"# 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。\ndef bigquant_run(context, data):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":"1000000","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"期货","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-1442"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-1442"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-1442"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-1442"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-1442"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-1442","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-1468","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"\n# #号开始的表示注释\n# 多个特征，每行一个，可以包含基础特征和衍生特征\nbuy_condition=where((close-(mean(close,20)-2*std(close,20)))/(4*std(close,20))>=1,1,0)\nsell_condition=where((close-(mean(close,20)-2*std(close,20)))/(4*std(close,20))<=0,1,0)\n\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-1468"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1468","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-1473","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-1473"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-1473"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1473","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-1483","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# 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\ndef bigquant_run(input_1, input_2, input_3,before_days):\n # 示例代码如下。在这里编写您的代码\n start_date=(pd.to_datetime(input_1.read_pickle()['start_date']) - datetime.timedelta(days=before_days)).strftime('%Y-%m-%d')\n end_date=input_1.read_pickle()['end_date']\n instruments=input_1.read_pickle()['instruments']\n fields=['open','high','low','close']\n df = DataSource('bar1d_CN_FUTURE').read(instruments,start_date,end_date,fields)\n df['adjust_factor']=1.0\n data_1 = DataSource.write_df(df)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"post_run","Value":"# 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。\ndef bigquant_run(outputs):\n return outputs\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{'before_days':60}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-1483"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-1483"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-1483"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-1483","OutputType":null},{"Name":"data_2","NodeId":"-1483","OutputType":null},{"Name":"data_3","NodeId":"-1483","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-1632","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-1632"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1632","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-136","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# 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\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n start = input_1.read_pickle()['start_date']\n end = input_1.read_pickle()['end_date']\n bm = DataSource('bar1d_CN_FUTURE').read(instruments=['RU8888.SHF'],start_date=start,end_date=end)\n bm.index = range(len(bm)) \n data_1 = DataSource.write_df(bm)\n return Outputs(data_1=data_1)","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"post_run","Value":"# 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。\ndef bigquant_run(outputs):\n return outputs\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-136"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-136"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-136"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-136","OutputType":null},{"Name":"data_2","NodeId":"-136","OutputType":null},{"Name":"data_3","NodeId":"-136","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='-25' Position='-240,14,200,200'/><NodePosition Node='-1442' Position='210,482,200,200'/><NodePosition Node='-1468' Position='259,28,200,200'/><NodePosition Node='-1473' Position='213,237,200,200'/><NodePosition Node='-1483' Position='-17,124,200,200'/><NodePosition Node='-1632' Position='151,342,200,200'/><NodePosition Node='-136' Position='490,356,200,200'/></NodePositions><NodeGroups /></DataV1>"},"IsDraft":true,"ParentExperimentId":null,"WebService":{"IsWebServiceExperiment":false,"Inputs":[],"Outputs":[],"Parameters":[{"Name":"交易日期","Value":"","ParameterDefinition":{"Name":"交易日期","FriendlyName":"交易日期","DefaultValue":"","ParameterType":"String","HasDefaultValue":true,"IsOptional":true,"ParameterRules":[],"HasRules":false,"MarkupType":0,"CredentialDescriptor":null}}],"WebServiceGroupId":null,"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions></NodePositions><NodeGroups /></DataV1>"},"DisableNodesUpdate":false,"Category":"user","Tags":[],"IsPartialRun":true}
In [3]:
# 本代码由可视化策略环境自动生成 2019年3月9日 16:10
# 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。
# 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 m4_run_bigquant_run(input_1, input_2, input_3,before_days):
# 示例代码如下。在这里编写您的代码
start_date=(pd.to_datetime(input_1.read_pickle()['start_date']) - datetime.timedelta(days=before_days)).strftime('%Y-%m-%d')
end_date=input_1.read_pickle()['end_date']
instruments=input_1.read_pickle()['instruments']
fields=['open','high','low','close']
df = DataSource('bar1d_CN_FUTURE').read(instruments,start_date,end_date,fields)
df['adjust_factor']=1.0
data_1 = DataSource.write_df(df)
return Outputs(data_1=data_1, 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 m4_post_run_bigquant_run(outputs):
return outputs
# 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 m1_run_bigquant_run(input_1, input_2, input_3):
# 示例代码如下。在这里编写您的代码
start = input_1.read_pickle()['start_date']
end = input_1.read_pickle()['end_date']
bm = DataSource('bar1d_CN_FUTURE').read(instruments=['RU8888.SHF'],start_date=start,end_date=end)
bm.index = range(len(bm))
data_1 = DataSource.write_df(bm)
return Outputs(data_1=data_1)
# 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 m1_post_run_bigquant_run(outputs):
return outputs
# 回测引擎：每日数据处理函数，每天执行一次
def m3_handle_data_bigquant_run(context, data):
# 获取当日指标数据
today = data.current_dt.strftime('%Y-%m-%d') # 当前交易日期
buy_condition=context.buy_condition[today]
sell_condition=context.sell_condition[today]
instrument = context.future_symbol(context.instruments[0]) # 交易标的
curr_po=context.portfolio.positions[instrument] # 组合持仓
curr_position = curr_po.amount # 持仓数量
# 交易逻辑
if buy_condition>0 and data.can_trade(instrument): # 开多，下单数量20手
order_target(instrument, 20)
print(today,'平空开多')
elif sell_condition>0 and data.can_trade(instrument):# 开空，下单数量20手
order_target(instrument, -20)
print(today,'平多开空')
# 回测引擎：准备数据，只执行一次
def m3_prepare_bigquant_run(context):
df = context.options['data'].read_df()
df['date']=df['date'].apply(lambda x:x.strftime('%Y-%m-%d'))
df.set_index('date',inplace=True)
context.buy_condition=df['buy_condition']
context.sell_condition=df['sell_condition']
# 回测引擎：初始化函数，只执行一次
def m3_initialize_bigquant_run(context):
# 设置是否是结算模式
context.set_need_settle(False)
# 设置最大杠杆
context.set_max_leverage(1, 'fill_amap')
# 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 m3_before_trading_start_bigquant_run(context, data):
pass
m2 = M.instruments.v2(
start_date='2017-11-01',
end_date='2018-05-01',
market='CN_FUTURE',
instrument_list='RU1809.SHF',
max_count=0
)
m4 = M.cached.v3(
input_1=m2.data,
run=m4_run_bigquant_run,
post_run=m4_post_run_bigquant_run,
input_ports='',
params='{\'before_days\':60}',
output_ports=''
)
m1 = M.cached.v3(
input_1=m2.data,
run=m1_run_bigquant_run,
post_run=m1_post_run_bigquant_run,
input_ports='',
params='{}',
output_ports=''
)
m5 = M.input_features.v1(
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
buy_condition=where((close-(mean(close,20)-2*std(close,20)))/(4*std(close,20))>=1,1,0)
sell_condition=where((close-(mean(close,20)-2*std(close,20)))/(4*std(close,20))<=0,1,0)
"""
)
m6 = M.derived_feature_extractor.v3(
input_data=m4.data_1,
features=m5.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False,
user_functions={}
)
m7 = M.dropnan.v1(
input_data=m6.data
)
m3 = M.trade.v4(
instruments=m2.data,
options_data=m7.data,
benchmark_ds=m1.data_1,
start_date='',
end_date='',
handle_data=m3_handle_data_bigquant_run,
prepare=m3_prepare_bigquant_run,
initialize=m3_initialize_bigquant_run,
before_trading_start=m3_before_trading_start_bigquant_run,
volume_limit=0,
order_price_field_buy='open',
order_price_field_sell='open',
capital_base=1000000,
auto_cancel_non_tradable_orders=True,
data_frequency='daily',
price_type='后复权',
product_type='期货',
plot_charts=True,
backtest_only=False,
benchmark=''
)
日志 27 条，错误日志
0 条
2019-03-09 16:06:02.222671 INFO: bigquant: instruments.v2 开始运行.
2019-03-09 16:06:02.229560 INFO: bigquant: 命中缓
2019-03-09 16:06:02.231405 INFO: bigquant: instruments.v2 运行完成[0.008732s]
2019-03-09 16:06:02.236410 INFO: bigquant: cached.v3 开始运行.
2019-03-09 16:06:02.241849 INFO: bigquant: 命中缓
2019-03-09 16:06:02.243259 INFO: bigquant: cached.v3 运行完成[0.006846s]
2019-03-09 16:06:02.246818 INFO: bigquant: cached.v3 开始运行.
2019-03-09 16:06:02.477100 INFO: bigquant: cached.v3 运行完成[0.23027s]
2019-03-09 16:06:02.480137 INFO: bigquant: input_features.v1 开始运行.
2019-03-09 16:06:02.484523 INFO: bigquant: 命中缓
2019-03-09 16:06:02.485871 INFO: bigquant: input_features.v1 运行完成[0.005728s]
2019-03-09 16:06:02.488940 INFO: bigquant: derived_feature_extractor.v3 开始运行.
2019-03-09 16:06:02.493502 INFO: bigquant: 命中缓
2019-03-09 16:06:02.494877 INFO: bigquant: derived_feature_extractor.v3 运行完成[0.005952s]
2019-03-09 16:06:02.497337 INFO: bigquant: dropnan.v1 开始运行.
2019-03-09 16:06:02.501807 INFO: bigquant: 命中缓
2019-03-09 16:06:02.503071 INFO: bigquant: dropnan.v1 运行完成[0.005721s]
2019-03-09 16:06:02.515925 INFO: bigquant: backtest.v8 开始运行.
2019-03-09 16:06:02.519219 INFO: bigquant: biglearning backtest:V8.1.1
2019-03-09 16:06:02.549881 INFO: bigquant: product_type:future by specifie
2019-03-09 16:06:03.085132 INFO: bigquant: 读取期货行情完成:14
2019-03-09 16:06:03.093608 INFO: algo: TradingAlgorithm V1.4.
2019-03-09 16:06:03.172198 INFO: algo: trading transform..
2019-03-09 16:06:03.567635 INFO: Performance: Simulated 120 trading days out of 120
2019-03-09 16:06:03.570212 INFO: Performance: first open: 2017-10-31 21:00:00+00:0
2019-03-09 16:06:03.571665 INFO: Performance: last close: 2018-04-27 15:00:00+00:0
2019-03-09 16:06:04.163973 INFO: bigquant: backtest.v8 运行完成[1.648038s]