克隆策略
In [5]:
# 模型滚动更新次数 
len(m10.result['rollings'])
Out[5]:
4
In [14]:
# 第一次训练的开始时间和结束时间
m10.result['rollings'][0]['m1'].data.read()['start_date'],m10.result['rollings'][0]['m1'].data.read()['end_date']
Out[14]:
('2011-01-04', '2016-12-30')
In [20]:
m10.result['rollings'][0]['m4'].feature_gains.read()
Out[20]:
feature gain
0 close_0/mean(close_0,20) 501.373879
1 close_0/mean(close_0,5) 276.174358
2 close_0/open_0 141.480593
3 close_0/mean(close_0,10) 129.087628
4 open_0/mean(close_0,20) 117.782951
5 open_0/mean(close_0,5) 74.362422
6 open_0/mean(close_0,10) 42.474288

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-339:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"-339:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-346:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-355:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-362:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-213:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-2576:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-374:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-355:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-374:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-346:input_data","SourceOutputPortId":"-339:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-346:data"},{"DestinationInputPortId":"-362:input_data","SourceOutputPortId":"-355:data"},{"DestinationInputPortId":"-2580:input_data","SourceOutputPortId":"-362:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"-213:model"},{"DestinationInputPortId":"-213:training_ds","SourceOutputPortId":"-2576:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-2580:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2011-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"Name":"label_expr","Value":"# #号开始的表示注释\n# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html\n# 添加benchmark_前缀，可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_\n\n# 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)\nshift(close, -2) / shift(open, -1)\n\n# 极值处理：用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类，这里使用20个分类\nall_wbins(label, 20)\n\n# 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)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"# #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\nclose_0/mean(close_0,5)\nclose_0/mean(close_0,10)\nclose_0/mean(close_0,20)\nclose_0/open_0\nopen_0/mean(close_0,5)\nopen_0/mean(close_0,10)\nopen_0/mean(close_0,20)","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","ModuleId":"BigQuantSpace.stock_ranker_predict.stock_ranker_predict-v5","ModuleParameters":[{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"OutputPortsInternal":[{"Name":"predictions","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2020-03-06","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"IsPartOfPartialRun":null,"Comment":"预测数据，用于回测和模拟","CommentCollapsed":false},{"Id":"-339","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-339"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-339"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-339","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-346","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":"-346"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-346"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-346","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-355","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-355"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-355"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-355","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-362","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":"-362"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-362"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-362","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-374","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","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 # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 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\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)\n # 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\n context.stock_count = 1\n # 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, ..]\n #context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, context.stock_count)])\n context.stock_weights = [0.5/context.stock_count for k in range(context.stock_count)] #半仓买入，每只股票等资金分配\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.5\n #context.options['hold_days'] = 5\n\n","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 # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n \n # 当日可用资金\n cash_for_buy = context.portfolio.cash\n \n #　获取当日买入列表,每天选取context.stock_count只\n buy_list = list(ranker_prediction.instrument[:context.stock_count])\n \n #　获取当前持仓\n stock_hold_now = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()} \n\n # 需要卖出的股票:已有持仓中不在买入列表的股票\n stock_to_sell = [ i for i in stock_hold_now if i not in buy_list ]\n stock_to_buy = [ i for i in buy_list if i not in stock_hold_now ]\n \n # 卖出列表进行卖出操作\n if len(stock_to_sell)>0:\n for instrument in stock_to_sell:\n sid = context.symbol(instrument) # 将标的转化为equity格式\n cur_position = context.portfolio.positions[sid].amount # 持仓\n if cur_position > 0 and data.can_trade(sid):\n context.order_target_percent(sid, 0) # 全部卖出\n # 如果是早盘买早盘卖，卖出的资金可以用于买股票，此时应将下面的注释打开，卖出股票时更新可用现金；\n # 如果是早盘买尾盘卖，则卖出时不需更新可用现金，因为尾盘卖出股票所得现金无法使用\n #cash_for_buy += stock_hold_now[instrument]\n \n # 买入列表执行买操作\n if len(stock_to_buy)>0:\n for instrument,weight in zip(stock_to_buy,context.stock_weights):\n sid = context.symbol(instrument) # 将标的转化为equity格式\n if data.can_trade(sid):\n context.order_target_value(sid, min(cash_for_buy,context.portfolio.portfolio_value*0.5)) # 买入","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 pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","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":"股票","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":"-374"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-374"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-374"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-374"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-374"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-374","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-213","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v6","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_row_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"ndcg_discount_base","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"-213"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-213"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"-213"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"-213"}],"OutputPortsInternal":[{"Name":"model","NodeId":"-213","OutputType":null},{"Name":"feature_gains","NodeId":"-213","OutputType":null},{"Name":"m_lazy_run","NodeId":"-213","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2576","ModuleId":"BigQuantSpace.dropnan.dropnan-v2","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-2576"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-2576"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2576","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2580","ModuleId":"BigQuantSpace.dropnan.dropnan-v2","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-2580"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-2580"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2580","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-234","ModuleId":"BigQuantSpace.hyper_rolling_train.hyper_rolling_train-v1","ModuleParameters":[{"Name":"run","Value":"def bigquant_run(\n bq_graph,\n inputs,\n trading_days_market='CN', # 使用那个市场的交易日历, TODO\n train_instruments_mid='m1', # 训练数据 证券代码列表 模块id\n test_instruments_mid='m9', # 测试数据 证券代码列表 模块id\n predict_mid='m8', # 预测 模块id\n trade_mid='m19', # 回测 模块id\n start_date='2011-01-01', # 数据开始日期\n end_date=T.live_run_param('trading_date', '2020-03-06'), # 数据结束日期\n train_update_days=250, # 更新周期，按交易日计算，每多少天更新一次\n train_update_days_for_live=None, #模拟实盘模式下的更新周期，按交易日计算，每多少天更新一次。如果需要在模拟实盘阶段使用不同的模型更新周期，可以设置这个参数\n train_data_min_days=1458, # 最小数据天数，按交易日计算，所以第一个滚动的结束日期是 从开始日期到开始日期+最小数据天数\n train_data_max_days=2000, # 最大数据天数，按交易日计算，0，表示没有限制，否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期\n rolling_count_for_live=1, #实盘模式下滚动次数，模拟实盘模式下，取最后多少次滚动。一般在模拟实盘模式下，只用到最后一次滚动训练的模型，这里可以设置为1；如果你的滚动训练数据时间段很短，以至于期间可能没有训练数据，这里可以设置大一点。0表示没有限制\n):\n def merge_datasources(input_1):\n df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]\n df = pd.concat(df_list)\n instrument_data = {\n 'start_date': df['date'].min().strftime('%Y-%m-%d'),\n 'end_date': df['date'].max().strftime('%Y-%m-%d'),\n 'instruments': list(set(df['instrument'])),\n }\n return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))\n\n def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):\n # 是否实盘模式\n tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])\n is_live_run = T.live_run_param('trading_date', None) is not None\n\n if is_live_run and train_update_days_for_live:\n train_update_days = train_update_days_for_live\n\n rollings = []\n train_end_date = train_data_min_days\n while train_end_date < len(tdays):\n if train_data_max_days is not None and train_data_max_days > 0:\n train_start_date = max(train_end_date - train_data_max_days, 0)\n else:\n train_start_date = 0\n rollings.append({\n 'train_start_date': tdays[train_start_date].strftime('%Y-%m-%d'),\n 'train_end_date': tdays[train_end_date - 1].strftime('%Y-%m-%d'),\n 'test_start_date': tdays[train_end_date].strftime('%Y-%m-%d'),\n 'test_end_date': tdays[min(train_end_date + train_update_days, len(tdays)) - 1].strftime('%Y-%m-%d'),\n })\n train_end_date += train_update_days\n\n if not rollings:\n raise Exception('没有滚动需要执行，请检查配置')\n\n if is_live_run and rolling_count_for_live:\n rollings = rollings[-rolling_count_for_live:]\n\n return rollings\n\n g = bq_graph\n\n rolling_dates = gen_rolling_dates(\n trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)\n\n # 训练和预测\n results = []\n for rolling in rolling_dates:\n parameters = {}\n # 先禁用回测\n parameters[trade_mid + '.__enabled__'] = False\n parameters[train_instruments_mid + '.start_date'] = rolling['train_start_date']\n parameters[train_instruments_mid + '.end_date'] = rolling['train_end_date']\n parameters[test_instruments_mid + '.start_date'] = rolling['test_start_date']\n parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']\n # print('------ rolling_train:', parameters)\n results.append(g.run(parameters))\n\n # 合并预测结果并回测\n mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].predictions, result[test_instruments_mid].data.read_pickle()['start_date']] for result in results])\n parameters = {}\n parameters['*.__enabled__'] = False\n parameters[trade_mid + '.__enabled__'] = True\n parameters[trade_mid + '.instruments'] = mx.instrument_data\n parameters[trade_mid + '.options_data'] = mx.data\n\n trade = g.run(parameters)\n\n return {'rollings': results, 'trade': trade}\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"run_now","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bq_graph","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"bq_graph_port","NodeId":"-234"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-234"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-234"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-234"}],"OutputPortsInternal":[{"Name":"result","NodeId":"-234","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":10,"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='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='211,64,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='67,180,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='599,0,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='1039,609,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1078,136,200,200'/><NodePosition Node='-339' Position='381,185,200,200'/><NodePosition Node='-346' Position='385,280,200,200'/><NodePosition Node='-355' Position='1078,236,200,200'/><NodePosition Node='-362' Position='1081,327,200,200'/><NodePosition Node='-374' Position='709,656,200,200'/><NodePosition Node='-213' Position='640,539,200,200'/><NodePosition Node='-2576' Position='496,462,200,200'/><NodePosition Node='-2580' Position='1078,418,200,200'/><NodePosition Node='-234' Position='183,521,200,200'/></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 [1]:
    # 本代码由可视化策略环境自动生成 2021年1月28日15:36
# 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。


# 回测引擎：初始化函数，只执行一次
def m19_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
    context.stock_count = 1
    # 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, context.stock_count)])
    context.stock_weights = [0.5/context.stock_count for k in range(context.stock_count)]  #半仓买入，每只股票等资金分配
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.5
    #context.options['hold_days'] = 5


# 回测引擎：每日数据处理函数，每天执行一次
def m19_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')]
    
    # 当日可用资金
    cash_for_buy = context.portfolio.cash
    
    #　获取当日买入列表,每天选取context.stock_count只
    buy_list = list(ranker_prediction.instrument[:context.stock_count])
    
    #　获取当前持仓
    stock_hold_now = {e.symbol: p.amount * p.last_sale_price
                      for e, p in context.perf_tracker.position_tracker.positions.items()} 

    # 需要卖出的股票:已有持仓中不在买入列表的股票
    stock_to_sell = [ i for i in stock_hold_now if i not in buy_list ]
    stock_to_buy =  [ i for i in buy_list if i not in stock_hold_now ]
    
    # 卖出列表进行卖出操作
    if len(stock_to_sell)>0:
        for instrument in stock_to_sell:
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 持仓
            if cur_position > 0 and data.can_trade(sid):
                context.order_target_percent(sid, 0) # 全部卖出
                # 如果是早盘买早盘卖，卖出的资金可以用于买股票，此时应将下面的注释打开，卖出股票时更新可用现金；
                # 如果是早盘买尾盘卖，则卖出时不需更新可用现金，因为尾盘卖出股票所得现金无法使用
                #cash_for_buy += stock_hold_now[instrument]
    
    # 买入列表执行买操作
    if len(stock_to_buy)>0:
        for instrument,weight in zip(stock_to_buy,context.stock_weights):
            sid = context.symbol(instrument) # 将标的转化为equity格式
            if data.can_trade(sid):
                context.order_target_value(sid, min(cash_for_buy,context.portfolio.portfolio_value*0.5)) # 买入
# 回测引擎：准备数据，只执行一次
def m19_prepare_bigquant_run(context):
    pass


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2011-01-01',
    'm1.end_date': '2017-01-01',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.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, -2) / shift(open, -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))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 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)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.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/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)""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 0,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m3.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': False,
    'm16.remove_extra_columns': False,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m2.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm5': 'M.dropnan.v2',
    'm5.input_data': T.Graph.OutputPort('m7.data'),

    'm4': 'M.stock_ranker_train.v6',
    'm4.training_ds': T.Graph.OutputPort('m5.data'),
    'm4.features': T.Graph.OutputPort('m3.data'),
    'm4.learning_algorithm': '排序',
    'm4.number_of_leaves': 30,
    'm4.minimum_docs_per_leaf': 1000,
    'm4.number_of_trees': 20,
    'm4.learning_rate': 0.1,
    'm4.max_bins': 1023,
    'm4.feature_fraction': 1,
    'm4.data_row_fraction': 1,
    'm4.ndcg_discount_base': 1,
    'm4.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2017-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2020-03-06'),
    'm9.market': 'CN_STOCK_A',
    'm9.instrument_list': '',
    'm9.max_count': 0,

    'm17': 'M.general_feature_extractor.v7',
    'm17.instruments': T.Graph.OutputPort('m9.data'),
    'm17.features': T.Graph.OutputPort('m3.data'),
    'm17.start_date': '',
    'm17.end_date': '',
    'm17.before_start_days': 0,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m17.data'),
    'm18.features': T.Graph.OutputPort('m3.data'),
    'm18.date_col': 'date',
    'm18.instrument_col': 'instrument',
    'm18.drop_na': False,
    'm18.remove_extra_columns': False,

    'm6': 'M.dropnan.v2',
    'm6.input_data': T.Graph.OutputPort('m18.data'),

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m4.model'),
    'm8.data': T.Graph.OutputPort('m6.data'),
    'm8.m_lazy_run': False,

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m8.predictions'),
    'm19.start_date': '',
    'm19.end_date': '',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.prepare': m19_prepare_bigquant_run,
    'm19.volume_limit': 0.025,
    'm19.order_price_field_buy': 'open',
    'm19.order_price_field_sell': 'close',
    'm19.capital_base': 1000000,
    'm19.auto_cancel_non_tradable_orders': True,
    'm19.data_frequency': 'daily',
    'm19.price_type': '后复权',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '',
})

# g.run({})


def m10_run_bigquant_run(
    bq_graph,
    inputs,
    trading_days_market='CN', # 使用那个市场的交易日历, TODO
    train_instruments_mid='m1', # 训练数据 证券代码列表 模块id
    test_instruments_mid='m9', # 测试数据 证券代码列表 模块id
    predict_mid='m8', # 预测 模块id
    trade_mid='m19', # 回测 模块id
    start_date='2011-01-01', # 数据开始日期
    end_date=T.live_run_param('trading_date', '2020-03-06'), # 数据结束日期
    train_update_days=250, # 更新周期，按交易日计算，每多少天更新一次
    train_update_days_for_live=None, #模拟实盘模式下的更新周期，按交易日计算，每多少天更新一次。如果需要在模拟实盘阶段使用不同的模型更新周期，可以设置这个参数
    train_data_min_days=1458, # 最小数据天数，按交易日计算，所以第一个滚动的结束日期是 从开始日期到开始日期+最小数据天数
    train_data_max_days=2000, # 最大数据天数，按交易日计算，0，表示没有限制，否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期
    rolling_count_for_live=1, #实盘模式下滚动次数，模拟实盘模式下，取最后多少次滚动。一般在模拟实盘模式下，只用到最后一次滚动训练的模型，这里可以设置为1；如果你的滚动训练数据时间段很短，以至于期间可能没有训练数据，这里可以设置大一点。0表示没有限制
):
    def merge_datasources(input_1):
        df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]
        df = pd.concat(df_list)
        instrument_data = {
            'start_date': df['date'].min().strftime('%Y-%m-%d'),
            'end_date': df['date'].max().strftime('%Y-%m-%d'),
            'instruments': list(set(df['instrument'])),
        }
        return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))

    def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):
        # 是否实盘模式
        tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])
        is_live_run = T.live_run_param('trading_date', None) is not None

        if is_live_run and train_update_days_for_live:
            train_update_days = train_update_days_for_live

        rollings = []
        train_end_date = train_data_min_days
        while train_end_date < len(tdays):
            if train_data_max_days is not None and train_data_max_days > 0:
                train_start_date = max(train_end_date - train_data_max_days, 0)
            else:
                train_start_date = 0
            rollings.append({
                'train_start_date': tdays[train_start_date].strftime('%Y-%m-%d'),
                'train_end_date': tdays[train_end_date - 1].strftime('%Y-%m-%d'),
                'test_start_date': tdays[train_end_date].strftime('%Y-%m-%d'),
                'test_end_date': tdays[min(train_end_date + train_update_days, len(tdays)) - 1].strftime('%Y-%m-%d'),
            })
            train_end_date += train_update_days

        if not rollings:
            raise Exception('没有滚动需要执行，请检查配置')

        if is_live_run and rolling_count_for_live:
            rollings = rollings[-rolling_count_for_live:]

        return rollings

    g = bq_graph

    rolling_dates = gen_rolling_dates(
        trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)

    # 训练和预测
    results = []
    for rolling in rolling_dates:
        parameters = {}
        # 先禁用回测
        parameters[trade_mid + '.__enabled__'] = False
        parameters[train_instruments_mid + '.start_date'] = rolling['train_start_date']
        parameters[train_instruments_mid + '.end_date'] = rolling['train_end_date']
        parameters[test_instruments_mid + '.start_date'] = rolling['test_start_date']
        parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']
        # print('------ rolling_train:', parameters)
        results.append(g.run(parameters))

    # 合并预测结果并回测
    mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].predictions, result[test_instruments_mid].data.read_pickle()['start_date']] for result in results])
    parameters = {}
    parameters['*.__enabled__'] = False
    parameters[trade_mid + '.__enabled__'] = True
    parameters[trade_mid + '.instruments'] = mx.instrument_data
    parameters[trade_mid + '.options_data'] = mx.data

    trade = g.run(parameters)

    return {'rollings': results, 'trade': trade}


m10 = M.hyper_rolling_train.v1(
    run=m10_run_bigquant_run,
    run_now=True,
    bq_graph=g
)
    设置评估测试数据集，查看训练曲线
    [视频教程]StockRanker训练曲线
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-2a597ecd72af4feca177e4879405d5fc"}/bigcharts-data-end
    设置评估测试数据集，查看训练曲线
    [视频教程]StockRanker训练曲线
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-ed4cdb1df5404e9e97ca084f2be2229c"}/bigcharts-data-end
    设置评估测试数据集，查看训练曲线
    [视频教程]StockRanker训练曲线
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-c0c13e62734d4b6fab719db080726e5a"}/bigcharts-data-end
    设置评估测试数据集，查看训练曲线
    [视频教程]StockRanker训练曲线
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9f9d08a6dde24cfbb90a754a812d3274"}/bigcharts-data-end
    • 收益率130.01%
    • 年化收益率32.15%
    • 基准收益率23.01%
    • 阿尔法0.28
    • 贝塔0.45
    • 夏普比率0.9
    • 胜率0.53
    • 盈亏比1.16
    • 收益波动率34.24%
    • 信息比率0.05
    • 最大回撤26.93%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-f25181b400fd49f885d425613b6bd38c"}/bigcharts-data-end