AI超越传统量化选股,通过AI自动获得收益提升

人工智能
传统量化
标签: #<Tag:0x00007f4cd03ca630> #<Tag:0x00007f4cd03ca4f0>

(iQuant) #1

我们在数百个因子了测试了传统因子方法和AI方法,在80%的因子上,AI都表现出更好的收益。通过AI我们可以自动的获得一个收益提升。

  • 传统量化:通过因子排序,买入排名靠前的股票
  • AI:通过数据学习(本示例中使用201年到-2017的数据),得到一个AI模型,用此模型预测(2018年),买入预测分数靠前的股票。本文中AI使用 StockRanker

流通市值因子 rank(market_cap_float_0)

rank(ta_mom(close_0, 5))

完整代码

欢迎克隆、使用和优化,在更多因子上通过AI自动获得更多的收益:

克隆策略

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"-128:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-96:sort_by_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-103:features_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-114:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-121:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-89:instrument_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-572:instrument_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-96:input_ds","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-181:input_data","SourceOutputPortId":"-121:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-128:data"},{"DestinationInputPortId":"-128:input_data","SourceOutputPortId":"-181:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:instruments","SourceOutputPortId":"-89:data_1"},{"DestinationInputPortId":"-89:prediction_ds","SourceOutputPortId":"-96:data_1"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:options_data","SourceOutputPortId":"-96:data_1"},{"DestinationInputPortId":"-121:features","SourceOutputPortId":"-103:data"},{"DestinationInputPortId":"-107:features","SourceOutputPortId":"-103:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-107: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":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-354:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-572:prediction_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"-175:input_data","SourceOutputPortId":"-107:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-114:data"},{"DestinationInputPortId":"-114:input_data","SourceOutputPortId":"-175:data"},{"DestinationInputPortId":"-354:instruments","SourceOutputPortId":"-572:data_1"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"rank(market_cap_float_0)","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":"在这里输入因子","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2018-02-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2018-08-14","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":"287d2cb0-f53c-4101-bdf8-104b137c8601-81","ModuleId":"BigQuantSpace.trade.trade-v3","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 # 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 # 1. 资金分配\n # 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\n # 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)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","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":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n print('------------ 传统方法/升序方向 ------------')\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 stock_count = 5\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, stock_count)])\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'] = 1\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":"benchmark","Value":"000300.SHA","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":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"amount_integer","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":12,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-86","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-86"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-86","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-121","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":"30","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-121"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-121"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-121","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-128","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":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-128"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-128"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-128","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-181","ModuleId":"BigQuantSpace.filter.filter-v3","ModuleParameters":[{"Name":"expr","Value":"st_status_0==0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_left_data","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-181"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-181","OutputType":null},{"Name":"left_data","NodeId":"-181","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":26,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-89","ModuleId":"BigQuantSpace.filter_instruments_with_predictions.filter_instruments_with_predictions-v3","ModuleParameters":[{"Name":"count","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instrument_ds","NodeId":"-89"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"prediction_ds","NodeId":"-89"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-89","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-96","ModuleId":"BigQuantSpace.sort.sort-v4","ModuleParameters":[{"Name":"sort_by","Value":"--","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"group_by","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"keep_columns","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"ascending","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_ds","NodeId":"-96"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"sort_by_ds","NodeId":"-96"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-96","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"传统选股,基于规则打分,选择靠前的股票","CommentCollapsed":false},{"Id":"-103","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"st_status_0\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-103"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-103","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"用于过滤ST股票的特征","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-01-01","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":2,"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_cbins(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":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","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":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"OutputPortsInternal":[{"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"feature_gains","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"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":10,"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":11,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-107","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":"-107"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-107"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-107","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":20,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-114","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":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-114"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-114"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-114","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":21,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-175","ModuleId":"BigQuantSpace.filter.filter-v3","ModuleParameters":[{"Name":"expr","Value":"st_status_0==0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_left_data","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-175"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-175","OutputType":null},{"Name":"left_data","NodeId":"-175","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":27,"IsPartOfPartialRun":null,"Comment":"过滤掉ST股票","CommentCollapsed":false},{"Id":"-152","ModuleId":"BigQuantSpace.comments.comments-v1","ModuleParameters":[],"InputPortsInternal":[],"OutputPortsInternal":[],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"AI","CommentCollapsed":false},{"Id":"-153","ModuleId":"BigQuantSpace.comments.comments-v1","ModuleParameters":[],"InputPortsInternal":[],"OutputPortsInternal":[],"UsePreviousResults":true,"moduleIdForCode":13,"IsPartOfPartialRun":null,"Comment":"传统方法","CommentCollapsed":false},{"Id":"-354","ModuleId":"BigQuantSpace.trade.trade-v3","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 # 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 # 1. 资金分配\n # 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\n # 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)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","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":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n print('------------ AI/买入AI预测靠前的股票 ------------')\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 stock_count = 5\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, stock_count)])\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'] = 1\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":"benchmark","Value":"000300.SHA","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":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"amount_integer","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-354"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-354"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-354","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-572","ModuleId":"BigQuantSpace.filter_instruments_with_predictions.filter_instruments_with_predictions-v3","ModuleParameters":[{"Name":"count","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instrument_ds","NodeId":"-572"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"prediction_ds","NodeId":"-572"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-572","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":49,"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-bdf8-104b137c8601-24' Position='532,-196,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='994,66,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-81' Position='919,861,200,200'/><NodePosition Node='-86' Position='1022,465,200,200'/><NodePosition Node='-121' Position='1020,252,200,200'/><NodePosition Node='-128' Position='1024,393,200,200'/><NodePosition Node='-181' Position='1022,323,200,200'/><NodePosition Node='-89' Position='918,779,200,200'/><NodePosition Node='-96' Position='918,654,200,200'/><NodePosition Node='-103' Position='531,-71,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='-40,31,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='-162,161,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='64,618,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='-37,442,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='183,705,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='-33,528,200,200'/><NodePosition Node='-107' Position='158,164,200,200'/><NodePosition Node='-114' Position='165,356,200,200'/><NodePosition Node='-175' Position='165,253,200,200'/><NodePosition Node='-152' Position='-37,-103,200,200'/><NodePosition Node='-153' Position='995,-97,200,200'/><NodePosition Node='-354' Position='176,869,200,200'/><NodePosition Node='-572' Position='182,797,200,200'/></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 [2]:
    # 本代码由可视化策略环境自动生成 2018年8月18日 09:52
    # 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。
    
    
    m3 = M.input_features.v1(
        features='rank(market_cap_float_0)'
    )
    
    m1 = M.input_features.v1(
        features_ds=m3.data,
        features="""st_status_0
    """
    )
    
    m9 = M.instruments.v2(
        start_date=T.live_run_param('trading_date', '2018-02-01'),
        end_date=T.live_run_param('trading_date', '2018-08-14'),
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m17 = M.general_feature_extractor.v7(
        instruments=m9.data,
        features=m1.data,
        start_date='',
        end_date='',
        before_start_days=30
    )
    
    m26 = M.filter.v3(
        input_data=m17.data,
        expr='st_status_0==0',
        output_left_data=False
    )
    
    m18 = M.derived_feature_extractor.v3(
        input_data=m26.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument'
    )
    
    m14 = M.dropnan.v1(
        input_data=m18.data
    )
    
    m7 = M.sort.v4(
        input_ds=m14.data,
        sort_by_ds=m3.data,
        sort_by='--',
        group_by='date',
        keep_columns='date,instrument',
        ascending=True
    )
    
    m6 = M.filter_instruments_with_predictions.v3(
        instrument_ds=m9.data,
        prediction_ds=m7.data_1,
        count=5
    )
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m12_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.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
        cash_avg = context.portfolio.portfolio_value / context.options['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)
        positions = {e.symbol: p.amount * p.last_sale_price
                     for e, p in context.perf_tracker.position_tracker.positions.items()}
    
        # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
        if not is_staging and cash_for_sell > 0:
            equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.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 instrument in instruments:
                context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
                if cash_for_sell <= 0:
                    break
    
        # 3. 生成买入订单:按机器学习算法预测的排序,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 - positions.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 - positions.get(instrument, 0)
            if cash > 0:
                context.order_value(context.symbol(instrument), cash)
    
    # 回测引擎:准备数据,只执行一次
    def m12_prepare_bigquant_run(context):
        pass
    
    # 回测引擎:初始化函数,只执行一次
    def m12_initialize_bigquant_run(context):
        print('------------ 传统方法/升序方向 ------------')
        # 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 = 0.5
        context.options['hold_days'] = 1
    
    m12 = M.trade.v3(
        instruments=m6.data_1,
        options_data=m7.data_1,
        start_date='',
        end_date='',
        handle_data=m12_handle_data_bigquant_run,
        prepare=m12_prepare_bigquant_run,
        initialize=m12_initialize_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy='open',
        order_price_field_sell='close',
        capital_base=1000000,
        benchmark='000300.SHA',
        auto_cancel_non_tradable_orders=True,
        data_frequency='daily',
        price_type='后复权',
        plot_charts=True,
        backtest_only=False,
        amount_integer=False
    )
    
    m2 = M.instruments.v2(
        start_date='2010-01-01',
        end_date='2018-01-01',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m4 = M.advanced_auto_labeler.v2(
        instruments=m2.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, -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_cbins(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)
    """,
        start_date='',
        end_date='',
        benchmark='000300.SHA',
        drop_na_label=True,
        cast_label_int=True
    )
    
    m20 = M.general_feature_extractor.v7(
        instruments=m2.data,
        features=m1.data,
        start_date='',
        end_date='',
        before_start_days=0
    )
    
    m27 = M.filter.v3(
        input_data=m20.data,
        expr='st_status_0==0',
        output_left_data=False
    )
    
    m21 = M.derived_feature_extractor.v3(
        input_data=m27.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument'
    )
    
    m10 = M.join.v3(
        data1=m4.data,
        data2=m21.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m16 = M.dropnan.v1(
        input_data=m10.data
    )
    
    m8 = M.stock_ranker_train.v5(
        training_ds=m16.data,
        features=m3.data,
        learning_algorithm='排序',
        number_of_leaves=30,
        minimum_docs_per_leaf=1000,
        number_of_trees=20,
        learning_rate=0.1,
        max_bins=1023,
        feature_fraction=1,
        m_lazy_run=False
    )
    
    m11 = M.stock_ranker_predict.v5(
        model=m8.model,
        data=m14.data,
        m_lazy_run=False
    )
    
    m49 = M.filter_instruments_with_predictions.v3(
        instrument_ds=m9.data,
        prediction_ds=m11.predictions,
        count=5
    )
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m15_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.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
        cash_avg = context.portfolio.portfolio_value / context.options['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)
        positions = {e.symbol: p.amount * p.last_sale_price
                     for e, p in context.perf_tracker.position_tracker.positions.items()}
    
        # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
        if not is_staging and cash_for_sell > 0:
            equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.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 instrument in instruments:
                context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
                if cash_for_sell <= 0:
                    break
    
        # 3. 生成买入订单:按机器学习算法预测的排序,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 - positions.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 - positions.get(instrument, 0)
            if cash > 0:
                context.order_value(context.symbol(instrument), cash)
    
    # 回测引擎:准备数据,只执行一次
    def m15_prepare_bigquant_run(context):
        pass
    
    # 回测引擎:初始化函数,只执行一次
    def m15_initialize_bigquant_run(context):
        print('------------ AI/买入AI预测靠前的股票 ------------')
        # 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 = 0.5
        context.options['hold_days'] = 1
    
    m15 = M.trade.v3(
        instruments=m49.data_1,
        options_data=m11.predictions,
        start_date='',
        end_date='',
        handle_data=m15_handle_data_bigquant_run,
        prepare=m15_prepare_bigquant_run,
        initialize=m15_initialize_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy='open',
        order_price_field_sell='close',
        capital_base=1000000,
        benchmark='000300.SHA',
        auto_cancel_non_tradable_orders=True,
        data_frequency='daily',
        price_type='后复权',
        plot_charts=True,
        backtest_only=False,
        amount_integer=False
    )
    
    m5 = M.comments.v1(
    
    )
    
    m13 = M.comments.v1(
    
    )
    
    [2018-08-18 09:05:16.603373] INFO: bigquant: input_features.v1 开始运行..
    [2018-08-18 09:05:16.607342] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.608150] INFO: bigquant: input_features.v1 运行完成[0.004797s].
    [2018-08-18 09:05:16.610320] INFO: bigquant: input_features.v1 开始运行..
    [2018-08-18 09:05:16.613182] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.614000] INFO: bigquant: input_features.v1 运行完成[0.003669s].
    [2018-08-18 09:05:16.616684] INFO: bigquant: instruments.v2 开始运行..
    [2018-08-18 09:05:16.619547] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.620356] INFO: bigquant: instruments.v2 运行完成[0.003684s].
    [2018-08-18 09:05:16.625310] INFO: bigquant: general_feature_extractor.v7 开始运行..
    [2018-08-18 09:05:16.628436] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.629149] INFO: bigquant: general_feature_extractor.v7 运行完成[0.003836s].
    [2018-08-18 09:05:16.631811] INFO: bigquant: filter.v3 开始运行..
    [2018-08-18 09:05:16.634619] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.635287] INFO: bigquant: filter.v3 运行完成[0.003468s].
    [2018-08-18 09:05:16.637829] INFO: bigquant: derived_feature_extractor.v3 开始运行..
    [2018-08-18 09:05:16.640883] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.642009] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.004166s].
    [2018-08-18 09:05:16.644784] INFO: bigquant: dropnan.v1 开始运行..
    [2018-08-18 09:05:16.647914] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.648620] INFO: bigquant: dropnan.v1 运行完成[0.003817s].
    [2018-08-18 09:05:16.652281] INFO: bigquant: sort.v4 开始运行..
    [2018-08-18 09:05:16.655135] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.655853] INFO: bigquant: sort.v4 运行完成[0.003565s].
    [2018-08-18 09:05:16.659129] INFO: bigquant: filter_instruments_with_predictions.v3 开始运行..
    [2018-08-18 09:05:16.662064] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:16.662744] INFO: bigquant: filter_instruments_with_predictions.v3 运行完成[0.003603s].
    [2018-08-18 09:05:16.674731] INFO: bigquant: backtest.v7 开始运行..
    [2018-08-18 09:05:16.677836] INFO: bigquant: 命中缓存
    
    • 收益率4.35%
    • 年化收益率8.66%
    • 基准收益率-21.12%
    • 阿尔法0.64
    • 贝塔1.09
    • 夏普比率0.33
    • 胜率0.56
    • 盈亏比0.87
    • 收益波动率38.61%
    • 信息比率0.12
    • 最大回撤27.81%
    [2018-08-18 09:05:17.177321] INFO: bigquant: backtest.v7 运行完成[0.502575s].
    [2018-08-18 09:05:17.180280] INFO: bigquant: instruments.v2 开始运行..
    [2018-08-18 09:05:17.183751] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:17.184421] INFO: bigquant: instruments.v2 运行完成[0.004149s].
    [2018-08-18 09:05:17.186463] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
    [2018-08-18 09:05:21.412237] INFO: 自动数据标注: 加载历史数据: 4597290 行
    [2018-08-18 09:05:21.413659] INFO: 自动数据标注: 开始标注 ..
    [2018-08-18 09:05:31.345561] INFO: bigquant: advanced_auto_labeler.v2 运行完成[14.159053s].
    [2018-08-18 09:05:31.351402] INFO: bigquant: general_feature_extractor.v7 开始运行..
    [2018-08-18 09:05:31.354284] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:31.355067] INFO: bigquant: general_feature_extractor.v7 运行完成[0.003673s].
    [2018-08-18 09:05:31.357211] INFO: bigquant: filter.v3 开始运行..
    [2018-08-18 09:05:31.359868] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:31.360594] INFO: bigquant: filter.v3 运行完成[0.003362s].
    [2018-08-18 09:05:31.363115] INFO: bigquant: derived_feature_extractor.v3 开始运行..
    [2018-08-18 09:05:31.365649] INFO: bigquant: 命中缓存
    [2018-08-18 09:05:31.366350] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.003227s].
    [2018-08-18 09:05:31.368756] INFO: bigquant: join.v3 开始运行..
    [2018-08-18 09:05:36.458952] INFO: join: /y_2010, 行数=401484/401771, 耗时=2.780119s
    [2018-08-18 09:05:39.163242] INFO: join: /y_2011, 行数=481991/482231, 耗时=2.690166s
    [2018-08-18 09:05:42.875143] INFO: join: /y_2012, 行数=540663/541178, 耗时=3.692548s
    [2018-08-18 09:05:45.794414] INFO: join: /y_2013, 行数=550043/550859, 耗时=2.901657s
    [2018-08-18 09:05:49.692830] INFO: join: /y_2014, 行数=559268/561221, 耗时=3.844545s
    [2018-08-18 09:05:53.368372] INFO: join: /y_2015, 行数=552436/561179, 耗时=3.6205s
    [2018-08-18 09:05:57.670126] INFO: join: /y_2016, 行数=626771/630635, 耗时=4.28288s
    [2018-08-18 09:06:02.656327] INFO: join: /y_2017, 行数=719368/730744, 耗时=4.96295s
    [2018-08-18 09:06:03.145801] INFO: join: 最终行数: 4432024
    [2018-08-18 09:06:03.148193] INFO: bigquant: join.v3 运行完成[31.779402s].
    [2018-08-18 09:06:03.151441] INFO: bigquant: dropnan.v1 开始运行..
    [2018-08-18 09:06:03.902235] INFO: dropnan: /y_2010, 401484/401484
    [2018-08-18 09:06:04.761064] INFO: dropnan: /y_2011, 481991/481991
    [2018-08-18 09:06:05.782604] INFO: dropnan: /y_2012, 540663/540663
    [2018-08-18 09:06:06.694642] INFO: dropnan: /y_2013, 550043/550043
    [2018-08-18 09:06:07.667095] INFO: dropnan: /y_2014, 559268/559268
    [2018-08-18 09:06:08.566541] INFO: dropnan: /y_2015, 552436/552436
    [2018-08-18 09:06:09.570448] INFO: dropnan: /y_2016, 626771/626771
    [2018-08-18 09:06:10.866780] INFO: dropnan: /y_2017, 719368/719368
    [2018-08-18 09:06:10.899375] INFO: dropnan: 行数: 4432024/4432024
    [2018-08-18 09:06:11.063541] INFO: bigquant: dropnan.v1 运行完成[7.912023s].
    [2018-08-18 09:06:11.066778] INFO: bigquant: stock_ranker_train.v5 开始运行..
    [2018-08-18 09:06:14.980379] INFO: df2bin: prepare bins ..
    [2018-08-18 09:06:15.779307] INFO: df2bin: prepare data: training ..
    [2018-08-18 09:06:16.795156] INFO: df2bin: sort ..
    [2018-08-18 09:07:16.650264] INFO: stock_ranker_train: e54dd434 准备训练: 4432024 行数
    [2018-08-18 09:11:44.472124] INFO: bigquant: stock_ranker_train.v5 运行完成[333.405352s].
    [2018-08-18 09:11:44.474702] INFO: bigquant: stock_ranker_predict.v5 开始运行..
    [2018-08-18 09:11:44.488181] INFO: stock_ranker_predict: 准备预测: 486608 行
    [2018-08-18 09:11:49.280338] INFO: bigquant: stock_ranker_predict.v5 运行完成[4.805613s].
    [2018-08-18 09:11:49.283653] INFO: bigquant: filter_instruments_with_predictions.v3 开始运行..
    73/3541
    [2018-08-18 09:11:49.497716] INFO: bigquant: filter_instruments_with_predictions.v3 运行完成[0.214022s].
    [2018-08-18 09:11:49.511177] INFO: bigquant: backtest.v7 开始运行..
    [2018-08-18 09:11:49.513904] INFO: bigquant: biglearning backtest:V7.1.2
    [2018-08-18 09:11:54.441494] INFO: algo: TradingAlgorithm V1.2.5
    ------------ AI/买入AI预测靠前的股票 ------------
    [2018-08-18 09:11:57.537577] INFO: Performance: Simulated 129 trading days out of 129.
    [2018-08-18 09:11:57.538486] INFO: Performance: first open: 2018-02-01 09:30:00+00:00
    [2018-08-18 09:11:57.539127] INFO: Performance: last close: 2018-08-14 15:00:00+00:00
    
    • 收益率10.62%
    • 年化收益率21.79%
    • 基准收益率-21.12%
    • 阿尔法0.77
    • 贝塔1.12
    • 夏普比率0.63
    • 胜率0.55
    • 盈亏比0.95
    • 收益波动率38.75%
    • 信息比率0.14
    • 最大回撤17.17%
    [2018-08-18 09:11:58.357839] INFO: bigquant: backtest.v7 运行完成[8.846666s].
    [2018-08-18 09:11:58.360555] INFO: bigquant: comments.v1 开始运行..
    [2018-08-18 09:11:58.362575] INFO: bigquant: 命中缓存
    [2018-08-18 09:11:58.363576] INFO: bigquant: comments.v1 运行完成[0.003019s].
    [2018-08-18 09:11:58.366189] INFO: bigquant: comments.v1 开始运行..
    [2018-08-18 09:11:58.367470] INFO: bigquant: 命中缓存
    [2018-08-18 09:11:58.368052] INFO: bigquant: comments.v1 运行完成[0.001866s].
    

    最近的市场不太好,这边还真是平静
    (gligl) #2

    试了几个因子,确实效果很好 👍


    (hooou) #3

    这个策略跑不起来,能看一下吗


    (达达) #4

    模块升级,有的连线断了

    克隆策略

      {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"-128:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-96:sort_by_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-103:features_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-114:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-121:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-89:instrument_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-572:instrument_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-96:input_ds","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-181:input_data","SourceOutputPortId":"-121:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-128:data"},{"DestinationInputPortId":"-128:input_data","SourceOutputPortId":"-181:data"},{"DestinationInputPortId":"-161:instruments","SourceOutputPortId":"-89:data_1"},{"DestinationInputPortId":"-89:prediction_ds","SourceOutputPortId":"-96:sorted_data"},{"DestinationInputPortId":"-161:options_data","SourceOutputPortId":"-96:sorted_data"},{"DestinationInputPortId":"-121:features","SourceOutputPortId":"-103:data"},{"DestinationInputPortId":"-107:features","SourceOutputPortId":"-103:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-107: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":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-572:prediction_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-185:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"-175:input_data","SourceOutputPortId":"-107:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-114:data"},{"DestinationInputPortId":"-114:input_data","SourceOutputPortId":"-175:data"},{"DestinationInputPortId":"-185:instruments","SourceOutputPortId":"-572:data_1"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"rank(market_cap_float_0)","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,"Comment":"在这里输入因子","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2018-02-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2018-08-14","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,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"-86","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-86"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-86","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"Comment":"","CommentCollapsed":true},{"Id":"-121","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":"30","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-121"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-121"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-121","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"Comment":"","CommentCollapsed":true},{"Id":"-128","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":"-128"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-128"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-128","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"Comment":"","CommentCollapsed":true},{"Id":"-181","ModuleId":"BigQuantSpace.filter.filter-v3","ModuleParameters":[{"Name":"expr","Value":"st_status_0==0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_left_data","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-181"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-181","OutputType":null},{"Name":"left_data","NodeId":"-181","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":26,"Comment":"","CommentCollapsed":true},{"Id":"-89","ModuleId":"BigQuantSpace.filter_instruments_with_predictions.filter_instruments_with_predictions-v3","ModuleParameters":[{"Name":"count","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instrument_ds","NodeId":"-89"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"prediction_ds","NodeId":"-89"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-89","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"Comment":"","CommentCollapsed":true},{"Id":"-96","ModuleId":"BigQuantSpace.sort.sort-v4","ModuleParameters":[{"Name":"sort_by","Value":"--","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"group_by","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"keep_columns","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"ascending","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_ds","NodeId":"-96"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"sort_by_ds","NodeId":"-96"}],"OutputPortsInternal":[{"Name":"sorted_data","NodeId":"-96","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"Comment":"传统选股,基于规则打分,选择靠前的股票","CommentCollapsed":false},{"Id":"-103","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"st_status_0\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-103"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-103","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"Comment":"用于过滤ST股票的特征","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-01-01","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":2,"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_cbins(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":4,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","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":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"OutputPortsInternal":[{"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"feature_gains","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"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":10,"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":11,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"Comment":"","CommentCollapsed":true},{"Id":"-107","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":"-107"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-107"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-107","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":20,"Comment":"","CommentCollapsed":true},{"Id":"-114","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":"-114"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-114"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-114","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":21,"Comment":"","CommentCollapsed":true},{"Id":"-175","ModuleId":"BigQuantSpace.filter.filter-v3","ModuleParameters":[{"Name":"expr","Value":"st_status_0==0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_left_data","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-175"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-175","OutputType":null},{"Name":"left_data","NodeId":"-175","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":27,"Comment":"过滤掉ST股票","CommentCollapsed":false},{"Id":"-152","ModuleId":"BigQuantSpace.comments.comments-v1","ModuleParameters":[],"InputPortsInternal":[],"OutputPortsInternal":[],"UsePreviousResults":true,"moduleIdForCode":5,"Comment":"AI","CommentCollapsed":false},{"Id":"-153","ModuleId":"BigQuantSpace.comments.comments-v1","ModuleParameters":[],"InputPortsInternal":[],"OutputPortsInternal":[],"UsePreviousResults":true,"moduleIdForCode":13,"Comment":"传统方法","CommentCollapsed":false},{"Id":"-572","ModuleId":"BigQuantSpace.filter_instruments_with_predictions.filter_instruments_with_predictions-v3","ModuleParameters":[{"Name":"count","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instrument_ds","NodeId":"-572"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"prediction_ds","NodeId":"-572"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-572","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":49,"Comment":"","CommentCollapsed":true},{"Id":"-161","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 print('------------ 传统方法/升序方向 ------------')\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 stock_count = 5\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, stock_count)])\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'] = 1\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 # 1. 资金分配\n # 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\n # 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)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","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":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-161"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-161"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-161"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-161"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-161"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-161","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"Comment":"","CommentCollapsed":true},{"Id":"-185","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 print('------------ AI/买入AI预测靠前的股票 ------------')\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 stock_count = 5\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, stock_count)])\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'] = 1\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 # 1. 资金分配\n # 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\n # 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)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","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":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-185"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-185"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-185"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-185"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-185"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-185","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":22,"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-bdf8-104b137c8601-24' Position='532,-196,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='994,66,200,200'/><NodePosition Node='-86' Position='1022,465,200,200'/><NodePosition Node='-121' Position='1020,252,200,200'/><NodePosition Node='-128' Position='1024,393,200,200'/><NodePosition Node='-181' Position='1022,323,200,200'/><NodePosition Node='-89' Position='935.529052734375,763.2239379882812,200,200'/><NodePosition Node='-96' Position='1016.1624755859375,617.1890869140625,200,200'/><NodePosition Node='-103' Position='531,-71,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='-40,31,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='-162,161,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='64,618,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='-37,442,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='202.28189086914062,696.2354736328125,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='-33,528,200,200'/><NodePosition Node='-107' Position='158,164,200,200'/><NodePosition Node='-114' Position='165,356,200,200'/><NodePosition Node='-175' Position='165,253,200,200'/><NodePosition Node='-152' Position='-37,-103,200,200'/><NodePosition Node='-153' Position='995,-97,200,200'/><NodePosition Node='-572' Position='182,797,200,200'/><NodePosition Node='-161' Position='919,862.7529296875,200,200'/><NodePosition Node='-185' Position='176,869,200,200'/></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 [9]:
      # 本代码由可视化策略环境自动生成 2019年9月18日 17:23
      # 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):
          print('------------ 传统方法/升序方向 ------------')
          # 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 = 0.5
          context.options['hold_days'] = 1
      
      # 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')]
      
          # 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.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
          cash_avg = context.portfolio.portfolio_value / context.options['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)
          positions = {e.symbol: p.amount * p.last_sale_price
                       for e, p in context.perf_tracker.position_tracker.positions.items()}
      
          # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
          if not is_staging and cash_for_sell > 0:
              equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.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 instrument in instruments:
                  context.order_target(context.symbol(instrument), 0)
                  cash_for_sell -= positions[instrument]
                  if cash_for_sell <= 0:
                      break
      
          # 3. 生成买入订单:按机器学习算法预测的排序,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 - positions.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 - positions.get(instrument, 0)
              if cash > 0:
                  context.order_value(context.symbol(instrument), cash)
      
      # 回测引擎:准备数据,只执行一次
      def m19_prepare_bigquant_run(context):
          pass
      
      # 回测引擎:初始化函数,只执行一次
      def m22_initialize_bigquant_run(context):
          print('------------ AI/买入AI预测靠前的股票 ------------')
          # 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 = 0.5
          context.options['hold_days'] = 1
      
      # 回测引擎:每日数据处理函数,每天执行一次
      def m22_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.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
          cash_avg = context.portfolio.portfolio_value / context.options['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)
          positions = {e.symbol: p.amount * p.last_sale_price
                       for e, p in context.perf_tracker.position_tracker.positions.items()}
      
          # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
          if not is_staging and cash_for_sell > 0:
              equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.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 instrument in instruments:
                  context.order_target(context.symbol(instrument), 0)
                  cash_for_sell -= positions[instrument]
                  if cash_for_sell <= 0:
                      break
      
          # 3. 生成买入订单:按机器学习算法预测的排序,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 - positions.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 - positions.get(instrument, 0)
              if cash > 0:
                  context.order_value(context.symbol(instrument), cash)
      
      # 回测引擎:准备数据,只执行一次
      def m22_prepare_bigquant_run(context):
          pass
      
      
      m3 = M.input_features.v1(
          features='rank(market_cap_float_0)'
      )
      
      m1 = M.input_features.v1(
          features_ds=m3.data,
          features="""st_status_0
      """
      )
      
      m9 = M.instruments.v2(
          start_date=T.live_run_param('trading_date', '2018-02-01'),
          end_date=T.live_run_param('trading_date', '2018-08-14'),
          market='CN_STOCK_A',
          instrument_list='',
          max_count=0
      )
      
      m17 = M.general_feature_extractor.v7(
          instruments=m9.data,
          features=m1.data,
          start_date='',
          end_date='',
          before_start_days=30
      )
      
      m26 = M.filter.v3(
          input_data=m17.data,
          expr='st_status_0==0',
          output_left_data=False
      )
      
      m18 = M.derived_feature_extractor.v3(
          input_data=m26.data,
          features=m3.data,
          date_col='date',
          instrument_col='instrument',
          drop_na=False,
          remove_extra_columns=False
      )
      
      m14 = M.dropnan.v1(
          input_data=m18.data
      )
      
      m7 = M.sort.v4(
          input_ds=m14.data,
          sort_by_ds=m3.data,
          sort_by='--',
          group_by='date',
          keep_columns='date,instrument',
          ascending=True
      )
      
      m6 = M.filter_instruments_with_predictions.v3(
          instrument_ds=m9.data,
          prediction_ds=m7.sorted_data,
          count=5
      )
      
      m19 = M.trade.v4(
          instruments=m6.data_1,
          options_data=m7.sorted_data,
          start_date='',
          end_date='',
          initialize=m19_initialize_bigquant_run,
          handle_data=m19_handle_data_bigquant_run,
          prepare=m19_prepare_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='000300.SHA'
      )
      
      m2 = M.instruments.v2(
          start_date='2010-01-01',
          end_date='2018-01-01',
          market='CN_STOCK_A',
          instrument_list='',
          max_count=0
      )
      
      m4 = M.advanced_auto_labeler.v2(
          instruments=m2.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, -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_cbins(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)
      """,
          start_date='',
          end_date='',
          benchmark='000300.SHA',
          drop_na_label=True,
          cast_label_int=True
      )
      
      m20 = M.general_feature_extractor.v7(
          instruments=m2.data,
          features=m1.data,
          start_date='',
          end_date='',
          before_start_days=0
      )
      
      m27 = M.filter.v3(
          input_data=m20.data,
          expr='st_status_0==0',
          output_left_data=False
      )
      
      m21 = M.derived_feature_extractor.v3(
          input_data=m27.data,
          features=m3.data,
          date_col='date',
          instrument_col='instrument',
          drop_na=False,
          remove_extra_columns=False
      )
      
      m10 = M.join.v3(
          data1=m4.data,
          data2=m21.data,
          on='date,instrument',
          how='inner',
          sort=False
      )
      
      m16 = M.dropnan.v1(
          input_data=m10.data
      )
      
      m8 = M.stock_ranker_train.v5(
          training_ds=m16.data,
          features=m3.data,
          learning_algorithm='排序',
          number_of_leaves=30,
          minimum_docs_per_leaf=1000,
          number_of_trees=20,
          learning_rate=0.1,
          max_bins=1023,
          feature_fraction=1,
          m_lazy_run=False
      )
      
      m11 = M.stock_ranker_predict.v5(
          model=m8.model,
          data=m14.data,
          m_lazy_run=False
      )
      
      m49 = M.filter_instruments_with_predictions.v3(
          instrument_ds=m9.data,
          prediction_ds=m11.predictions,
          count=5
      )
      
      m22 = M.trade.v4(
          instruments=m49.data_1,
          options_data=m11.predictions,
          start_date='',
          end_date='',
          initialize=m22_initialize_bigquant_run,
          handle_data=m22_handle_data_bigquant_run,
          prepare=m22_prepare_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='000300.SHA'
      )
      
      m5 = M.comments.v1(
      
      )
      
      m13 = M.comments.v1(
      
      )
      
      • 收益率5.62%
      • 年化收益率11.27%
      • 基准收益率-21.12%
      • 阿尔法0.67
      • 贝塔1.09
      • 夏普比率0.39
      • 胜率0.56
      • 盈亏比0.89
      • 收益波动率38.63%
      • 信息比率0.12
      • 最大回撤27.89%
      bigcharts-data-start/{"__type":"tabs","__id":"bigchart-6c7da87edec346b9a399b12a73b74bbf"}/bigcharts-data-end
      设置测试数据集,查看训练迭代过程的NDCG
      bigcharts-data-start/{"__type":"tabs","__id":"bigchart-df3041efafcb42998e771f019411a216"}/bigcharts-data-end
      • 收益率14.17%
      • 年化收益率29.54%
      • 基准收益率-21.12%
      • 阿尔法0.83
      • 贝塔1.11
      • 夏普比率0.79
      • 胜率0.55
      • 盈亏比1.01
      • 收益波动率38.57%
      • 信息比率0.16
      • 最大回撤18.48%
      bigcharts-data-start/{"__type":"tabs","__id":"bigchart-bbf3cfdd0bc54824a84483fa87b22f4d"}/bigcharts-data-end