在AI策略中使用滚动训练

可视化
滚动训练
滚动运行
模拟交易
标签: #<Tag:0x00007f5bfff492c0> #<Tag:0x00007f5bfff490b8> #<Tag:0x00007f5bfff48eb0> #<Tag:0x00007f5bfff48ca8>

(iQuant) #1

为了能更简单、更灵活同时在回测和实盘模拟中无缝支持滚动训练和模型自动更新,我们增加了滚动运行支持,并优化了相应模块。

如何在实验中增加滚动训练支持

使用模板新建一个策略:策略 > 新建 > 可视化策略 - AI选股策略
image

如下三步即可增加滚动训练支持:

  1. 添加滚动运行配置模块:
    image

    • 连接滚动运行模块 和 证券代码列表模块
    • 设置滚动运行的参数,可以设置训练更新周期等,默认配置对应的是每365天更新一次模型,最少要有730天的数据才开始训练
    • 清除 证券代码列表 配置的 开始时间 和 结束时间,以使用来自 滚动配置 的时间
      image
    • 模拟实盘中自动更新模型:将滚动运行配置的 结束日期 绑定到实盘日期
      image
  2. 添加滚动运行到模型训练上:

    • 如上图连接:StockRanker训练 -> 滚动运行 -> Trade(回测/模拟),注意 StockRanker训练 到 滚动运行 的连接是在 延迟运行 输出端口上
    • StockRanker配置:勾选 延迟运行,为了支持滚动运行和最小的代码改动,平台增加了对模块延迟运行的支持,可以将模块打包作为参数传入其他模块,并在其中调用。这里我们将配置好的 StockRanker训练 打包到滚动运行中,由滚动决定模块的调用方式。
      image
    • 因为使用了滚动训练,所以我们可以使用更多的回测数据了,这里可以把开始时间设置的更早一些。预测模块已经内建了对滚动训练的支持。同时对于较早的数据,而没有模型可用时,会自动跳过。
      image
  3. 添加滚动预测:

    • 如上图连接模块
    • 勾选 StockRanker预测 延迟运行

注意:我们优化了模块时间的配置,不再需要在 自动数据标注、基础特征抽取和Trade模块里重复配置时间。可视化策略开发模板已经更新。如果您的策略是以前生成的,您需要将 自动数据标注、基础特征抽取和Trade模块 的 开始日期 和 结束日期 参数设置为空

滚动训练示意图

滚动运行详解

金融数据属于时间序列数据,数据之间具有自相关性,因此不能采取经典机器学习的交叉验证的方式,对训练集进行随机划分。这里,我们建议采取滚动训练方式。滚动训练依赖于滚动运行模块,我们分别介绍不使用滚动运行和使用滚动运行,加深大家对滚动运行模块的理解。

  • 不使用滚动运行
    如果我们不使用滚动运行,回测区间为2015.1.1到2017.10.01,那么模型只会在训练集上训练模型,然后对验证集数据进行预测,这样只会有一次训练一次预测。时间较远的数据做训练来预测最近的数据可能效果不是很理想。此外,不同时期市场状况和结构也不一致,因此需要采取滚动运行。
    11

  • 使用滚动运行
    使用滚动运行,我们就可以及时更新模型,用最近的数据来预测数据,这样从策略开发逻辑和实盘交易的角度看比较合理。
    假设参数配置是这样,开始日期为2010-1-1,结束日期为2017-10-01, 其中,回测区间为2012.1.1到2017.10.1, 最小数据天数为730,最大数据天数为1095,更新天数为365。
    12

模块源代码

完整的示例策略

克隆策略

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29: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-bdf8-104b137c8601-29:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76: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":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:data"},{"DestinationInputPortId":"-107:run","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:m_lazy_run"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-113:predict","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:m_lazy_run"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:rolling_conf","SourceOutputPortId":"-578:data"},{"DestinationInputPortId":"-107:input_list","SourceOutputPortId":"-578:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"-107:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:options_data","SourceOutputPortId":"-113:predictions"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"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, -5) / shift(open, -1)\n\n# 极值处理:用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类,这里使用20个分类\nall_wbins(label, 20)\n\n# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"# #号开始的表示注释\n# 多个特征,每行一个,可以包含基础特征和衍生特征\nreturn_5\nreturn_10\nreturn_20\navg_amount_0/avg_amount_5\navg_amount_5/avg_amount_20\nrank_avg_amount_0/rank_avg_amount_5\nrank_avg_amount_5/rank_avg_amount_10\nrank_return_0\nrank_return_5\nrank_return_10\nrank_return_0/rank_return_5\nrank_return_5/rank_return_10\npe_ttm_0\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-29","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v6","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-35","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v2","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":"287d2cb0-f53c-4101-bdf8-104b137c8601-35"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"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":"True","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":6,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"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":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"OutputPortsInternal":[{"Name":"predictions","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2012-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2017-01-01","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":"287d2cb0-f53c-4101-bdf8-104b137c8601-70","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v6","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-76","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v2","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":"287d2cb0-f53c-4101-bdf8-104b137c8601-76"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"Comment":"","CommentCollapsed":true},{"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StockRanker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StockRanker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 # 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 = 0.2\n context.options['hold_days'] = 5\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":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","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,"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":13,"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,"Comment":"","CommentCollapsed":true},{"Id":"-578","ModuleId":"BigQuantSpace.rolling_conf.rolling_conf-v1","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2015-12-31","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"rolling_update_days","Value":"365","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"rolling_update_days_for_live","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"rolling_min_days","Value":730,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"rolling_max_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"rolling_count_for_live","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[],"OutputPortsInternal":[{"Name":"data","NodeId":"-578","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":15,"Comment":"","CommentCollapsed":true},{"Id":"-107","ModuleId":"BigQuantSpace.rolling_run.rolling_run-v1","ModuleParameters":[{"Name":"param_name","Value":"rolling_input","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"run","NodeId":"-107"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_list","NodeId":"-107"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-107","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"Comment":"","CommentCollapsed":true},{"Id":"-113","ModuleId":"BigQuantSpace.rolling_run_predict.rolling_run_predict-v1","ModuleParameters":[{"Name":"model_param_name","Value":"model","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_param_name","Value":"data","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"predict","NodeId":"-113"}],"OutputPortsInternal":[{"Name":"predictions","NodeId":"-113","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='211,64,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,183,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='765,21,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-29' Position='381,188,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-35' Position='385,280,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='553,545,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='732.4429321289062,701.5533447265625,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1074,127,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-70' Position='1078,237,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-76' Position='1081,327,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-81' Position='1058.837890625,847.34375,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='376,467,200,200'/><NodePosition Node='-86' Position='1078,418,200,200'/><NodePosition Node='-578' Position='308,-44,200,200'/><NodePosition Node='-107' Position='613,630.8458251953125,200,200'/><NodePosition Node='-113' Position='875.4267578125,775.1358642578125,200,200'/></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 [6]:
    # 本代码由可视化策略环境自动生成 2017年10月20日 21:26
    # 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="""# #号开始的表示注释
    # 多个特征,每行一个,可以包含基础特征和衍生特征
    return_5
    return_10
    return_20
    avg_amount_0/avg_amount_5
    avg_amount_5/avg_amount_20
    rank_avg_amount_0/rank_avg_amount_5
    rank_avg_amount_5/rank_avg_amount_10
    rank_return_0
    rank_return_5
    rank_return_10
    rank_return_0/rank_return_5
    rank_return_5/rank_return_10
    pe_ttm_0
    """
    )
    
    m9 = M.instruments.v2(
        start_date=T.live_run_param('trading_date', '2012-01-01'),
        end_date=T.live_run_param('trading_date', '2017-01-01'),
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m10 = M.general_feature_extractor.v6(
        instruments=m9.data,
        features=m3.data,
        start_date='',
        end_date=''
    )
    
    m11 = M.derived_feature_extractor.v2(
        input_data=m10.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument'
    )
    
    m14 = M.dropnan.v1(
        input_data=m11.data
    )
    
    m15 = M.rolling_conf.v1(
        start_date='2010-01-01',
        end_date=T.live_run_param('trading_date', '2015-12-31'),
        rolling_update_days=365,
        rolling_min_days=730,
        rolling_max_days=0,
        rolling_count_for_live=1
    )
    
    m1 = M.instruments.v2(
        rolling_conf=m15.data,
        start_date='',
        end_date='',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m2 = M.advanced_auto_labeler.v2(
        instruments=m1.data,
        label_expr="""# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
    #   添加benchmark_前缀,可使用对应的benchmark数据
    # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -5) / shift(open, -1)
    
    # 极值处理:用1%和99%分位的值做clip
    clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
    
    # 将分数映射到分类,这里使用20个分类
    all_wbins(label, 20)
    
    # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
    where(shift(high, -1) == shift(low, -1), NaN, label)
    """,
        start_date='',
        end_date='',
        benchmark='000300.SHA',
        drop_na_label=True,
        cast_label_int=True
    )
    
    m4 = M.general_feature_extractor.v6(
        instruments=m1.data,
        features=m3.data,
        start_date='',
        end_date=''
    )
    
    m5 = M.derived_feature_extractor.v2(
        input_data=m4.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument'
    )
    
    m7 = M.join.v3(
        data1=m2.data,
        data2=m5.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m13 = M.dropnan.v1(
        input_data=m7.data
    )
    
    m6 = M.stock_ranker_train.v5(
        training_ds=m13.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=True
    )
    
    m16 = M.rolling_run.v1(
        run=m6.m_lazy_run,
        input_list=m15.data,
        param_name='rolling_input'
    )
    
    m8 = M.stock_ranker_predict.v5(
        model=m16.data,
        data=m14.data,
        m_lazy_run=True
    )
    
    m17 = M.rolling_run_predict.v1(
        predict=m8.m_lazy_run,
        model_param_name='model',
        data_param_name='data'
    )
    
    # 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StockRanker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StockRanker预测的排序,买入前面的stock_count只股票
        buy_cash_weights = context.stock_weights
        buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
        max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
        for i, instrument in enumerate(buy_instruments):
            cash = cash_for_buy * buy_cash_weights[i]
            if cash > max_cash_per_instrument - 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):
        # 加载预测数据
        context.ranker_prediction = context.options['data'].read_df()
    
        # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
        context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
        # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
        # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
        stock_count = 5
        # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]
        context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
        # 设置每只股票占用的最大资金比例
        context.max_cash_per_instrument = 0.2
        context.options['hold_days'] = 5
    
    m12 = M.trade.v3(
        instruments=m9.data,
        options_data=m17.predictions,
        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',
        plot_charts=True,
        backtest_only=False
    )
    
    [2017-10-20 21:23:00.948864] INFO: bigquant: input_features.v1 开始运行..
    [2017-10-20 21:23:00.952132] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:00.953017] INFO: bigquant: input_features.v1 运行完成[0.004196s].
    [2017-10-20 21:23:00.956800] INFO: bigquant: instruments.v2 开始运行..
    [2017-10-20 21:23:00.958579] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:00.959305] INFO: bigquant: instruments.v2 运行完成[0.002505s].
    [2017-10-20 21:23:00.965403] INFO: bigquant: general_feature_extractor.v6 开始运行..
    [2017-10-20 21:23:00.967222] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:00.967922] INFO: bigquant: general_feature_extractor.v6 运行完成[0.00252s].
    [2017-10-20 21:23:00.972751] INFO: bigquant: derived_feature_extractor.v2 开始运行..
    [2017-10-20 21:23:00.974405] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:00.975097] INFO: bigquant: derived_feature_extractor.v2 运行完成[0.002347s].
    [2017-10-20 21:23:00.979849] INFO: bigquant: dropnan.v1 开始运行..
    [2017-10-20 21:23:00.981792] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:00.982555] INFO: bigquant: dropnan.v1 运行完成[0.002721s].
    [2017-10-20 21:23:00.987324] INFO: 滚动运行配置: 生成了 5 次滚动,第一次 {'end_date': '2011-12-31', 'start_date': '2010-01-01'},最后一次 {'end_date': '2015-12-30', 'start_date': '2010-01-01'}
    [2017-10-20 21:23:00.997503] INFO: bigquant: instruments.v2 开始运行..
    [2017-10-20 21:23:00.999232] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.000081] INFO: bigquant: instruments.v2 运行完成[0.002561s].
    [2017-10-20 21:23:01.006614] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
    [2017-10-20 21:23:01.008366] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.009142] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.00253s].
    [2017-10-20 21:23:01.015016] INFO: bigquant: general_feature_extractor.v6 开始运行..
    [2017-10-20 21:23:01.016728] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.017473] INFO: bigquant: general_feature_extractor.v6 运行完成[0.00245s].
    [2017-10-20 21:23:01.022882] INFO: bigquant: derived_feature_extractor.v2 开始运行..
    [2017-10-20 21:23:01.024728] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.025480] INFO: bigquant: derived_feature_extractor.v2 运行完成[0.002594s].
    [2017-10-20 21:23:01.031597] INFO: bigquant: join.v3 开始运行..
    [2017-10-20 21:23:01.033292] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.034000] INFO: bigquant: join.v3 运行完成[0.002406s].
    [2017-10-20 21:23:01.039198] INFO: bigquant: dropnan.v1 开始运行..
    [2017-10-20 21:23:01.040924] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.041643] INFO: bigquant: dropnan.v1 运行完成[0.002444s].
    [2017-10-20 21:23:01.050254] INFO: bigquant: 延迟运行 stock_ranker_train.v5
    [2017-10-20 21:23:01.055494] INFO: bigquant: rolling_run.v1 开始运行..
    [2017-10-20 21:23:01.057264] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.058057] INFO: bigquant: rolling_run.v1 运行完成[0.002558s].
    [2017-10-20 21:23:01.065179] INFO: bigquant: 延迟运行 stock_ranker_predict.v5
    [2017-10-20 21:23:01.070487] INFO: bigquant: rolling_run_predict.v1 开始运行..
    [2017-10-20 21:23:01.094552] INFO: bigquant: 命中缓存
    [2017-10-20 21:23:01.095407] INFO: bigquant: rolling_run_predict.v1 运行完成[0.024911s].
    [2017-10-20 21:23:01.219971] INFO: bigquant: backtest.v7 开始运行..
    [2017-10-20 21:24:09.449538] INFO: Performance: Simulated 1214 trading days out of 1214.
    [2017-10-20 21:24:09.450669] INFO: Performance: first open: 2012-01-04 14:30:00+00:00
    [2017-10-20 21:24:09.451652] INFO: Performance: last close: 2016-12-30 20:00:00+00:00
    [注意] 有 221 笔卖出是在多天内完成的。当日卖出股票超过了当日股票交易的2.5%会出现这种情况。
    
    • 收益率2765.38%
    • 年化收益率100.67%
    • 基准收益率41.11%
    • 阿尔法0.93
    • 贝塔0.95
    • 夏普比率2.72
    • 收益波动率35.76%
    • 信息比率3.59
    • 最大回撤52.76%
    [2017-10-20 21:24:14.003618] INFO: bigquant: backtest.v7 运行完成[72.783625s].
    

    如何进行较高频率的滚动回测
    能否给一个可视化策略-StockRanker滚动版算法的示例?
    5条线连出一个价值选股策略
    StockRanker滚动训练报错,帮忙看下~
    【宽客学院】StockRanker结果解读
    回答一个忠实用户的几个问题
    试用滚动机器学习失败
    策略研究常用功能
    社区干货与精选整理(持续更新中...)
    (qci133) #2

    非常赞。另外,也鼓励一下大宽在逐步开源自己的东西。希望有朝一日大宽能将更多核心内容开放,便于第三方开发者加入一同改进。


    (qci133) #3

    我有个疑问,如果训练时间段、回测时间段、滚动频率等时间参数设置不合理的话,会不会出现使用未来数据的情况?这几个时间参数之间有什么设置的原则吗?


    (1899) #4

    你好,请问有没有滚动训练的介绍啊,不太了解啊,或者你简单的几句话描述一下吧 /苦笑


    (1899) #5

    意思是不是这样的:假如1-100用于训练,100-120用于预测。假设我设置滚动训练单位为5,那么我就会先用1-100去预测101-105,待随着时间进行,101-105的真实数值出来后,再利用1-105去训练106-110,一直训练到120为止


    (iQuant) #6

    @RainFall1994
    是的,基本思想是这样的。因为量化数据是时间序列的,不便于做随机切分的交叉验证,使用滚动训练的方式可以在更多数据上看效果。


    (iQuant) #7

    不会出现过拟合的情况,预测模块对于预测数据会选择用对应时间之前的数据训练的模型。稍后我们把滚动预测这个代码也剥离出来做成通用的,并开源出来。


    (amparoj) #8

    请问在模拟盘中,是否也会滚动的训练?还是只有在回测中才会进行滚动?


    (PAYNE) #10

    滚动训练的效果应该好于单次训练的

    有没有方法测试 两者偏差,和方差的?


    (神龙斗士) #11

    使用这个模板,在模拟的时候也会自动更新模型


    (神龙斗士) #12

    通过滚动训练,可以测试方差。比如看不同的更新参数下的方差,您可以自行试一试


    (SerJamie) #13

    你好,我完全采取了帖子的方法。
    为何会出现以下的情况?



    (iQuant) #14

    您是直接克隆策略吗?我们刚才进行了复现,没有发现您提到的这个问题。


    (SerJamie) #15

    我只是把特征改了下,就出现这个情况了


    (ypf007) #16

    image

    我也是有错误,不知道哪有错


    (iQuant) #17

    那这样,你能说一下你的特征吗?或者你可以把你的策略分享在社区这样方便我们查看。


    (iQuant) #18

    这个错误好像与特征有关,你用的是什么特征呢?我们复现一下


    (ypf007) #19

    image