评估(分类)模块报错计算不了roc_df,不知道是啥原因

策略分享
标签: #<Tag:0x00007f4ce9742ad8>

(Pon) #1
克隆策略

GBDT多因子选股策略

本例使用GBDT算法进行模型训练和数据预测

1、新建可视化AI模板策略

2、在左侧模块导航栏“机器学习”中拖出“GBDT训练”和“GBDT预测”模块替换原有的 StockRanker 训练模块和 StockRanker 预测模块

   本例设置“GBDT训练”中的参数: 

    损失函数类型:'reg:linear',

    评价指标:'rmse',

    模型:'gbtree'

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-339:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"-339:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-346:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-353:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-360:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-391:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-353:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-370:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-12659:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-391:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"-410:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-346:input_data","SourceOutputPortId":"-339:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-346:data"},{"DestinationInputPortId":"-360:input_data","SourceOutputPortId":"-353:data"},{"DestinationInputPortId":"-12670:data2","SourceOutputPortId":"-360:data"},{"DestinationInputPortId":"-410:model","SourceOutputPortId":"-391:model"},{"DestinationInputPortId":"-370:options_data","SourceOutputPortId":"-410:predictions"},{"DestinationInputPortId":"-12693:data2","SourceOutputPortId":"-410:predictions"},{"DestinationInputPortId":"-12670:data1","SourceOutputPortId":"-12659:data"},{"DestinationInputPortId":"-12693:data1","SourceOutputPortId":"-12659:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-12670:data"},{"DestinationInputPortId":"-12699:predictions","SourceOutputPortId":"-12693:data"},{"DestinationInputPortId":"-12962:predictions","SourceOutputPortId":"-12693:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2016-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-04-30","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"Name":"label_expr","Value":"# #号开始的表示注释\n# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html\n# 添加benchmark_前缀,可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(close, -1)\nwhere(label > 1.02, 1, 0)\n# 极值处理:用1%和99%分位的值做clip\n#clip(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\n#all_wbins(label, 20)\n\n# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"# #号开始的表示注释\n# 多个特征,每行一个,可以包含基础特征和衍生特征\n#return_5\n#return_10\n#return_20\n#avg_amount_0/avg_amount_5\n#avg_amount_5/avg_amount_20\n#rank_avg_amount_0/rank_avg_amount_5\n#rank_avg_amount_5/rank_avg_amount_10\n#rank_return_0\n#rank_return_5\n#rank_return_10\n#rank_return_0/rank_return_5\n#rank_return_5/rank_return_10\n#pe_ttm_0\n#west_netprofit_ftm_0\n#shift(west_netprofit_ftm_0, 5)\n#shift(west_netprofit_ftm_0, 10)\n#shift(west_netprofit_ftm_0, 20)\n#shift(west_netprofit_ftm_0, 30)\n#shift(west_netprofit_ftm_0, 60)\n#shift(west_netprofit_ftm_0, 90)\n#shift(west_netprofit_ftm_0, 180)\n#mean(west_netprofit_ftm_0, 5)\n#mean(west_netprofit_ftm_0, 10)\n#mean(west_netprofit_ftm_0, 20)\n#mean(west_netprofit_ftm_0, 30)\n#mean(west_netprofit_ftm_0, 60)\n#mean(west_netprofit_ftm_0, 90)\n#mean(west_netprofit_ftm_0, 180)\nwest_eps_ftm_0\nshift(west_eps_ftm_0, 5)\nshift(west_eps_ftm_0, 10)\nshift(west_eps_ftm_0, 20)\nshift(west_eps_ftm_0, 30)\nshift(west_eps_ftm_0, 60)\nshift(west_eps_ftm_0, 90)\nshift(west_eps_ftm_0, 180)\n\n\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2018-05-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2019-10-01","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,"IsPartOfPartialRun":null,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"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,"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":"-339","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"200","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-339"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-339"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-339","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-346","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-346"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-346"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-346","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-353","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":"200","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-353"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-353"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-353","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-360","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":"-360"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-360"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-360","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-370","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n 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":"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":"真实价格","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-370"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-370"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-370"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-370"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-370"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-370","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-391","ModuleId":"BigQuantSpace.GBDT_train.GBDT_train-v1","ModuleParameters":[{"Name":"num_boost_round","Value":"5","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"early_stopping_rounds","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"objective","Value":"binary:logistic","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"num_class","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"eval_metric","Value":"auc","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"booster","Value":"gbtree","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"eta","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"gamma","Value":0.0001,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"_lambda","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"lambda_bias","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"alpha","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_depth","Value":6,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_leaf_nodes","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"subsample","Value":0.8,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"xgb_param","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"-391"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-391"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"-391"}],"OutputPortsInternal":[{"Name":"model","NodeId":"-391","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-410","ModuleId":"BigQuantSpace.GBDT_predict.GBDT_predict-v1","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"-410"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data","NodeId":"-410"}],"OutputPortsInternal":[{"Name":"predictions","NodeId":"-410","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-12659","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/develop/datasource/deprecated/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/develop/bigexpr/usage.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(close, -1)\nwhere(label > 1.02, 1, 0)\n# 极值处理:用1%和99%分位的值做clip\n#clip(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\n#all_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":"-12659"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12659","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-12670","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":"-12670"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-12670"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12670","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-12693","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":"-12693"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-12693"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12693","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-12699","ModuleId":"BigQuantSpace.metrics_regression.metrics_regression-v1","ModuleParameters":[{"Name":"explained_variance_score","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"mean_absolute_error","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"mean_squared_error","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"mean_squared_log_error","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"median_absolute_error","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"r2_score","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"predictions","NodeId":"-12699"}],"OutputPortsInternal":[{"Name":"report","NodeId":"-12699","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":12,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-12962","ModuleId":"BigQuantSpace.metrics_classification.metrics_classification-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"predictions","NodeId":"-12962"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12962","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='-35,-2,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='-179,168,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='328,-152,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='-2,360,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='671,-10,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='18,449,200,200'/><NodePosition Node='-86' Position='487,485,200,200'/><NodePosition Node='-339' Position='131,173,200,200'/><NodePosition Node='-346' Position='81,265,200,200'/><NodePosition Node='-353' Position='629,223,200,200'/><NodePosition Node='-360' Position='668,316,200,200'/><NodePosition Node='-370' Position='497,747,200,200'/><NodePosition Node='-391' Position='183,554,200,200'/><NodePosition Node='-410' Position='232,638,200,200'/><NodePosition Node='-12659' Position='376,276,200,200'/><NodePosition Node='-12670' Position='462,389,200,200'/><NodePosition Node='-12693' Position='-114,701,200,200'/><NodePosition Node='-12699' Position='181,790,200,200'/><NodePosition Node='-12962' Position='-122,795,200,200'/></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 [84]:
    # 本代码由可视化策略环境自动生成 2019年11月1日 14:57
    # 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
    
    
    # 回测引擎:初始化函数,只执行一次
    def m19_initialize_bigquant_run(context):
        # 加载预测数据
        context.ranker_prediction = context.options['data'].read_df()
    
        # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
        context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
        # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
        # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
        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
    
    # 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
    
    
    m1 = M.instruments.v2(
        start_date='2016-01-01',
        end_date='2018-04-30',
        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(close, -1)
    where(label > 1.02, 1, 0)
    # 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
    )
    
    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
    #west_netprofit_ftm_0
    #shift(west_netprofit_ftm_0, 5)
    #shift(west_netprofit_ftm_0, 10)
    #shift(west_netprofit_ftm_0, 20)
    #shift(west_netprofit_ftm_0, 30)
    #shift(west_netprofit_ftm_0, 60)
    #shift(west_netprofit_ftm_0, 90)
    #shift(west_netprofit_ftm_0, 180)
    #mean(west_netprofit_ftm_0, 5)
    #mean(west_netprofit_ftm_0, 10)
    #mean(west_netprofit_ftm_0, 20)
    #mean(west_netprofit_ftm_0, 30)
    #mean(west_netprofit_ftm_0, 60)
    #mean(west_netprofit_ftm_0, 90)
    #mean(west_netprofit_ftm_0, 180)
    west_eps_ftm_0
    shift(west_eps_ftm_0, 5)
    shift(west_eps_ftm_0, 10)
    shift(west_eps_ftm_0, 20)
    shift(west_eps_ftm_0, 30)
    shift(west_eps_ftm_0, 60)
    shift(west_eps_ftm_0, 90)
    shift(west_eps_ftm_0, 180)
    
    
    """
    )
    
    m15 = M.general_feature_extractor.v7(
        instruments=m1.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=200
    )
    
    m16 = M.derived_feature_extractor.v3(
        input_data=m15.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m7 = M.join.v3(
        data1=m2.data,
        data2=m16.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m13 = M.dropnan.v1(
        input_data=m7.data
    )
    
    m6 = M.GBDT_train.v1(
        training_ds=m13.data,
        features=m3.data,
        num_boost_round=5,
        objective='binary:logistic',
        eval_metric='auc',
        booster='gbtree',
        eta=0.1,
        gamma=0.0001,
        _lambda=0,
        lambda_bias=0,
        alpha=0,
        max_depth=6,
        max_leaf_nodes=30,
        subsample=0.8,
        xgb_param={}
    )
    
    m9 = M.instruments.v2(
        start_date=T.live_run_param('trading_date', '2018-05-01'),
        end_date=T.live_run_param('trading_date', '2019-10-01'),
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m17 = M.general_feature_extractor.v7(
        instruments=m9.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=200
    )
    
    m18 = M.derived_feature_extractor.v3(
        input_data=m17.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m5 = M.advanced_auto_labeler.v2(
        instruments=m9.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/develop/datasource/deprecated/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/develop/bigexpr/usage.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(close, -1)
    where(label > 1.02, 1, 0)
    # 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,
        user_functions={}
    )
    
    m10 = M.join.v3(
        data1=m5.data,
        data2=m18.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m14 = M.dropnan.v1(
        input_data=m10.data
    )
    
    m8 = M.GBDT_predict.v1(
        model=m6.model,
        data=m14.data,
        date_col='date',
        instrument_col='instrument',
        sort=True
    )
    
    m19 = M.trade.v4(
        instruments=m9.data,
        options_data=m8.predictions,
        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='真实价格',
        product_type='股票',
        plot_charts=True,
        backtest_only=False,
        benchmark=''
    )
    
    m11 = M.join.v3(
        data1=m5.data,
        data2=m8.predictions,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m12 = M.metrics_regression.v1(
        predictions=m11.data,
        explained_variance_score=True,
        mean_absolute_error=True,
        mean_squared_error=True,
        mean_squared_log_error=True,
        median_absolute_error=True,
        r2_score=True
    )
    
    m4 = M.metrics_classification.v1(
        predictions=m11.data
    )
    

    分类-评估(metrics_classification)使用错误,你可以:

    1.一键查看文档

    2.一键搜索答案

    ---------------------------------------------------------------------------
    UnboundLocalError                         Traceback (most recent call last)
    <ipython-input-84-3544b0c6ad29> in <module>()
        211 
        212 m4 = M.metrics_classification.v1(
    --> 213     predictions=m11.data
        214 )
    
    UnboundLocalError: local variable 'roc_df' referenced before assignment

    (Pon) #2

    [2019-11-01 14:16:07.449372] WARNING: metrics_classification: 模型中无分类概率,无法绘制ROC曲线图及精准率-召回率图

    [2019-11-01 14:16:07.456801] ERROR: bigquant: module name: metrics_classification, module version: v1, trackeback: Traceback (most recent call last): UnboundLocalError: local variable ‘roc_df’ referenced before assignment


    (达达) #3

    用新的模块

    克隆策略

    GBDT多因子选股策略

    本例使用GBDT算法进行模型训练和数据预测

    1、新建可视化AI模板策略

    2、在左侧模块导航栏“机器学习”中拖出“GBDT训练”和“GBDT预测”模块替换原有的 StockRanker 训练模块和 StockRanker 预测模块

       本例设置“GBDT训练”中的参数: 
    
        损失函数类型:'reg:linear',
    
        评价指标:'rmse',
    
        模型:'gbtree'

      {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-339:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"-339:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-346:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-353:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-360:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-153:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-353:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-12659:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-153:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"-153:predict_ds","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-346:input_data","SourceOutputPortId":"-339:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-346:data"},{"DestinationInputPortId":"-360:input_data","SourceOutputPortId":"-353:data"},{"DestinationInputPortId":"-12670:data2","SourceOutputPortId":"-360:data"},{"DestinationInputPortId":"-12670:data1","SourceOutputPortId":"-12659:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-12670:data"},{"DestinationInputPortId":"-12962:predictions","SourceOutputPortId":"-153:predictions"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2016-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-04-30","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(close, -1)\nwhere(label > 1.02, 1, 0)\n# 极值处理:用1%和99%分位的值做clip\n#clip(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\n#all_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\n#return_5\n#return_10\n#return_20\n#avg_amount_0/avg_amount_5\n#avg_amount_5/avg_amount_20\n#rank_avg_amount_0/rank_avg_amount_5\n#rank_avg_amount_5/rank_avg_amount_10\n#rank_return_0\n#rank_return_5\n#rank_return_10\n#rank_return_0/rank_return_5\n#rank_return_5/rank_return_10\n#pe_ttm_0\n#west_netprofit_ftm_0\n#shift(west_netprofit_ftm_0, 5)\n#shift(west_netprofit_ftm_0, 10)\n#shift(west_netprofit_ftm_0, 20)\n#shift(west_netprofit_ftm_0, 30)\n#shift(west_netprofit_ftm_0, 60)\n#shift(west_netprofit_ftm_0, 90)\n#shift(west_netprofit_ftm_0, 180)\n#mean(west_netprofit_ftm_0, 5)\n#mean(west_netprofit_ftm_0, 10)\n#mean(west_netprofit_ftm_0, 20)\n#mean(west_netprofit_ftm_0, 30)\n#mean(west_netprofit_ftm_0, 60)\n#mean(west_netprofit_ftm_0, 90)\n#mean(west_netprofit_ftm_0, 180)\nwest_eps_ftm_0\nshift(west_eps_ftm_0, 5)\nshift(west_eps_ftm_0, 10)\nshift(west_eps_ftm_0, 20)\nshift(west_eps_ftm_0, 30)\nshift(west_eps_ftm_0, 60)\nshift(west_eps_ftm_0, 90)\nshift(west_eps_ftm_0, 180)\n\n\n","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":"","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-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2018-05-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2019-10-01","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-bdf8-104b137c8601-84","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":"-339","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"200","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-339"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-339"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-339","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"Comment":"","CommentCollapsed":true},{"Id":"-346","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-346"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-346"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-346","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"Comment":"","CommentCollapsed":true},{"Id":"-353","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":"200","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-353"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-353"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-353","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"Comment":"","CommentCollapsed":true},{"Id":"-360","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":"-360"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-360"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-360","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"Comment":"","CommentCollapsed":true},{"Id":"-12659","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/develop/datasource/deprecated/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/develop/bigexpr/usage.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(close, -1)\nwhere(label > 1.02, 1, 0)\n# 极值处理:用1%和99%分位的值做clip\n#clip(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\n#all_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":"-12659"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12659","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"Comment":"","CommentCollapsed":true},{"Id":"-12670","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":"-12670"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-12670"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12670","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"Comment":"","CommentCollapsed":true},{"Id":"-12962","ModuleId":"BigQuantSpace.metrics_classification.metrics_classification-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"predictions","NodeId":"-12962"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-12962","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"Comment":"","CommentCollapsed":true},{"Id":"-153","ModuleId":"BigQuantSpace.random_forest_classifier.random_forest_classifier-v1","ModuleParameters":[{"Name":"iterations","Value":10,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_depth","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"min_samples_per_leaf","Value":200,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"key_cols","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"workers","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"other_train_parameters","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"-153"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-153"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"-153"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"predict_ds","NodeId":"-153"}],"OutputPortsInternal":[{"Name":"output_model","NodeId":"-153","OutputType":null},{"Name":"predictions","NodeId":"-153","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":20,"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='-35,-2,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='-179,168,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='269.8034362792969,-49.18606758117676,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='-2,360,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='562.9541625976562,42.09351348876953,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='18,449,200,200'/><NodePosition Node='-86' Position='487,485,200,200'/><NodePosition Node='-339' Position='131,173,200,200'/><NodePosition Node='-346' Position='81,265,200,200'/><NodePosition Node='-353' Position='644.4351196289062,159.33013916015625,200,200'/><NodePosition Node='-360' Position='679.5762939453125,256.1889343261719,200,200'/><NodePosition Node='-12659' Position='379.8587646484375,243.20037841796875,200,200'/><NodePosition Node='-12670' Position='462,389,200,200'/><NodePosition Node='-12962' Position='326.1135444641113,690.2462158203125,200,200'/><NodePosition Node='-153' Position='110.93968486785889,592.2371215820312,200,200'/></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 [7]:
      # 本代码由可视化策略环境自动生成 2019年11月1日 15:14
      # 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。
      
      
      m1 = M.instruments.v2(
          start_date='2016-01-01',
          end_date='2018-04-30',
          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(close, -1)
      where(label > 1.02, 1, 0)
      # 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
      )
      
      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
      #west_netprofit_ftm_0
      #shift(west_netprofit_ftm_0, 5)
      #shift(west_netprofit_ftm_0, 10)
      #shift(west_netprofit_ftm_0, 20)
      #shift(west_netprofit_ftm_0, 30)
      #shift(west_netprofit_ftm_0, 60)
      #shift(west_netprofit_ftm_0, 90)
      #shift(west_netprofit_ftm_0, 180)
      #mean(west_netprofit_ftm_0, 5)
      #mean(west_netprofit_ftm_0, 10)
      #mean(west_netprofit_ftm_0, 20)
      #mean(west_netprofit_ftm_0, 30)
      #mean(west_netprofit_ftm_0, 60)
      #mean(west_netprofit_ftm_0, 90)
      #mean(west_netprofit_ftm_0, 180)
      west_eps_ftm_0
      shift(west_eps_ftm_0, 5)
      shift(west_eps_ftm_0, 10)
      shift(west_eps_ftm_0, 20)
      shift(west_eps_ftm_0, 30)
      shift(west_eps_ftm_0, 60)
      shift(west_eps_ftm_0, 90)
      shift(west_eps_ftm_0, 180)
      
      
      """
      )
      
      m15 = M.general_feature_extractor.v7(
          instruments=m1.data,
          features=m3.data,
          start_date='',
          end_date='',
          before_start_days=200
      )
      
      m16 = M.derived_feature_extractor.v3(
          input_data=m15.data,
          features=m3.data,
          date_col='date',
          instrument_col='instrument',
          drop_na=False,
          remove_extra_columns=False
      )
      
      m7 = M.join.v3(
          data1=m2.data,
          data2=m16.data,
          on='date,instrument',
          how='inner',
          sort=False
      )
      
      m13 = M.dropnan.v1(
          input_data=m7.data
      )
      
      m9 = M.instruments.v2(
          start_date=T.live_run_param('trading_date', '2018-05-01'),
          end_date=T.live_run_param('trading_date', '2019-10-01'),
          market='CN_STOCK_A',
          instrument_list='',
          max_count=0
      )
      
      m17 = M.general_feature_extractor.v7(
          instruments=m9.data,
          features=m3.data,
          start_date='',
          end_date='',
          before_start_days=200
      )
      
      m18 = M.derived_feature_extractor.v3(
          input_data=m17.data,
          features=m3.data,
          date_col='date',
          instrument_col='instrument',
          drop_na=False,
          remove_extra_columns=False
      )
      
      m5 = M.advanced_auto_labeler.v2(
          instruments=m9.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/develop/datasource/deprecated/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/develop/bigexpr/usage.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(close, -1)
      where(label > 1.02, 1, 0)
      # 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,
          user_functions={}
      )
      
      m10 = M.join.v3(
          data1=m5.data,
          data2=m18.data,
          on='date,instrument',
          how='inner',
          sort=False
      )
      
      m14 = M.dropnan.v1(
          input_data=m10.data
      )
      
      m20 = M.random_forest_classifier.v1(
          training_ds=m13.data,
          features=m3.data,
          predict_ds=m14.data,
          iterations=10,
          feature_fraction=1,
          max_depth=30,
          min_samples_per_leaf=200,
          key_cols='date,instrument',
          workers=1,
          other_train_parameters={}
      )
      
      m4 = M.metrics_classification.v1(
          predictions=m20.predictions
      )
      
      bigcharts-data-start/{"__id":"bigchart-6192b9930fb24805a85da92d63261a02","__type":"tabs"}/bigcharts-data-end

      评估(分类)模块无法绘制roc_df然后报错(WARNING: metrics_classification: 模型中无分类概率,无法绘制ROC曲线图及精准率-召回率图)