【模板策略】超参寻优调参顺序

meetup
标签: #<Tag:0x00007ff190cc69e0>

(iQuant) #1

12月17日Meetup模板策略】:超参寻优调参顺序

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":"-2378: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":"-2378:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-2385:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-2392:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-2399:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-132:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-266:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-2409:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-2392:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-2409:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-2385:input_data","SourceOutputPortId":"-2378:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-2385:data"},{"DestinationInputPortId":"-2399:input_data","SourceOutputPortId":"-2392:data"},{"DestinationInputPortId":"-270:input_data","SourceOutputPortId":"-2399:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"-132:model"},{"DestinationInputPortId":"-132:training_ds","SourceOutputPortId":"-266:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-270:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2014-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2015-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"Name":"label_expr","Value":"# #号开始的表示注释\n# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html\n# 添加benchmark_前缀,可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -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,"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\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":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","ModuleId":"BigQuantSpace.stock_ranker_predict.stock_ranker_predict-v5","ModuleParameters":[{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"OutputPortsInternal":[{"Name":"predictions","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2015-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2016-01-01","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,"IsPartOfPartialRun":null,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"-2378","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-2378"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-2378"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2378","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2385","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":"-2385"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-2385"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2385","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2392","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-2392"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-2392"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2392","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2399","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":"-2399"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-2399"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2399","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2409","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":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-2409"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-2409"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-2409"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-2409"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-2409"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-2409","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2431","ModuleId":"BigQuantSpace.hyper_parameter_search.hyper_parameter_search-v1","ModuleParameters":[{"Name":"param_grid_builder","Value":"def bigquant_run():\n param_grid = {}\n\n # 在这里设置需要调优的参数备选\n param_grid['m4.number_of_trees'] = [5, 10, 20]\n param_grid['m19.volume_limit'] = [0.025, 0.03]\n\n return param_grid\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"scoring","Value":"def bigquant_run(result):\n score = result.get('m19').read_raw_perf()['sharpe'].tail(1)[0]\n\n return score\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"search_algorithm","Value":"随机搜索","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"search_iterations","Value":"3","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"random_state","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"workers","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"worker_distributed_run","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"worker_silent","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"run_now","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bq_graph","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"bq_graph_port","NodeId":"-2431"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-2431"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-2431"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-2431"}],"OutputPortsInternal":[{"Name":"result","NodeId":"-2431","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":20,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-132","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v6","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_row_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"ndcg_discount_base","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"-132"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-132"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"-132"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"-132"}],"OutputPortsInternal":[{"Name":"model","NodeId":"-132","OutputType":null},{"Name":"feature_gains","NodeId":"-132","OutputType":null},{"Name":"m_lazy_run","NodeId":"-132","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-266","ModuleId":"BigQuantSpace.dropnan.dropnan-v2","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-266"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-266"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-266","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-270","ModuleId":"BigQuantSpace.dropnan.dropnan-v2","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-270"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-270"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-270","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='211,64,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,183,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='765,21,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='906,647,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1074,127,200,200'/><NodePosition Node='-2378' Position='381,188,200,200'/><NodePosition Node='-2385' Position='385,280,200,200'/><NodePosition Node='-2392' Position='1078,236,200,200'/><NodePosition Node='-2399' Position='1081,327,200,200'/><NodePosition Node='-2409' Position='1035,752,200,200'/><NodePosition Node='-2431' Position='352,673,200,200'/><NodePosition Node='-132' Position='639,561,200,200'/><NodePosition Node='-266' Position='376,467,200,200'/><NodePosition Node='-270' Position='1078,418,200,200'/></NodePositions><NodeGroups /></DataV1>"},"IsDraft":true,"ParentExperimentId":null,"WebService":{"IsWebServiceExperiment":false,"Inputs":[],"Outputs":[],"Parameters":[{"Name":"交易日期","Value":"","ParameterDefinition":{"Name":"交易日期","FriendlyName":"交易日期","DefaultValue":"","ParameterType":"String","HasDefaultValue":true,"IsOptional":true,"ParameterRules":[],"HasRules":false,"MarkupType":0,"CredentialDescriptor":null}}],"WebServiceGroupId":null,"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions></NodePositions><NodeGroups /></DataV1>"},"DisableNodesUpdate":false,"Category":"user","Tags":[],"IsPartialRun":true}
    In [1]:
    # 本代码由可视化策略环境自动生成 2020年12月18日 11:23
    # 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
    
    
    # 回测引擎:初始化函数,只执行一次
    def m19_initialize_bigquant_run(context):
        # 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
    
    
    g = T.Graph({
    
        'm1': 'M.instruments.v2',
        'm1.start_date': '2014-01-01',
        'm1.end_date': '2015-01-01',
        'm1.market': 'CN_STOCK_A',
        'm1.instrument_list': '',
        'm1.max_count': 0,
    
        'm2': 'M.advanced_auto_labeler.v2',
        'm2.instruments': T.Graph.OutputPort('m1.data'),
        'm2.label_expr': """# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
    #   添加benchmark_前缀,可使用对应的benchmark数据
    # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -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)
    """,
        'm2.start_date': '',
        'm2.end_date': '',
        'm2.benchmark': '000300.SHA',
        'm2.drop_na_label': True,
        'm2.cast_label_int': True,
    
        'm3': 'M.input_features.v1',
        'm3.features': """# #号开始的表示注释
    # 多个特征,每行一个,可以包含基础特征和衍生特征
    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
    """,
    
        'm15': 'M.general_feature_extractor.v7',
        'm15.instruments': T.Graph.OutputPort('m1.data'),
        'm15.features': T.Graph.OutputPort('m3.data'),
        'm15.start_date': '',
        'm15.end_date': '',
        'm15.before_start_days': 0,
    
        'm16': 'M.derived_feature_extractor.v3',
        'm16.input_data': T.Graph.OutputPort('m15.data'),
        'm16.features': T.Graph.OutputPort('m3.data'),
        'm16.date_col': 'date',
        'm16.instrument_col': 'instrument',
        'm16.drop_na': False,
        'm16.remove_extra_columns': False,
    
        'm7': 'M.join.v3',
        'm7.data1': T.Graph.OutputPort('m2.data'),
        'm7.data2': T.Graph.OutputPort('m16.data'),
        'm7.on': 'date,instrument',
        'm7.how': 'inner',
        'm7.sort': False,
    
        'm5': 'M.dropnan.v2',
        'm5.input_data': T.Graph.OutputPort('m7.data'),
    
        'm4': 'M.stock_ranker_train.v6',
        'm4.training_ds': T.Graph.OutputPort('m5.data'),
        'm4.features': T.Graph.OutputPort('m3.data'),
        'm4.learning_algorithm': '排序',
        'm4.number_of_leaves': 30,
        'm4.minimum_docs_per_leaf': 1000,
        'm4.number_of_trees': 20,
        'm4.learning_rate': 0.1,
        'm4.max_bins': 1023,
        'm4.feature_fraction': 1,
        'm4.data_row_fraction': 1,
        'm4.ndcg_discount_base': 1,
        'm4.m_lazy_run': False,
    
        'm9': 'M.instruments.v2',
        'm9.start_date': T.live_run_param('trading_date', '2015-01-01'),
        'm9.end_date': T.live_run_param('trading_date', '2016-01-01'),
        'm9.market': 'CN_STOCK_A',
        'm9.instrument_list': '',
        'm9.max_count': 0,
    
        'm17': 'M.general_feature_extractor.v7',
        'm17.instruments': T.Graph.OutputPort('m9.data'),
        'm17.features': T.Graph.OutputPort('m3.data'),
        'm17.start_date': '',
        'm17.end_date': '',
        'm17.before_start_days': 0,
    
        'm18': 'M.derived_feature_extractor.v3',
        'm18.input_data': T.Graph.OutputPort('m17.data'),
        'm18.features': T.Graph.OutputPort('m3.data'),
        'm18.date_col': 'date',
        'm18.instrument_col': 'instrument',
        'm18.drop_na': False,
        'm18.remove_extra_columns': False,
    
        'm6': 'M.dropnan.v2',
        'm6.input_data': T.Graph.OutputPort('m18.data'),
    
        'm8': 'M.stock_ranker_predict.v5',
        'm8.model': T.Graph.OutputPort('m4.model'),
        'm8.data': T.Graph.OutputPort('m6.data'),
        'm8.m_lazy_run': False,
    
        'm19': 'M.trade.v4',
        'm19.instruments': T.Graph.OutputPort('m9.data'),
        'm19.options_data': T.Graph.OutputPort('m8.predictions'),
        'm19.start_date': '',
        'm19.end_date': '',
        'm19.initialize': m19_initialize_bigquant_run,
        'm19.handle_data': m19_handle_data_bigquant_run,
        'm19.prepare': m19_prepare_bigquant_run,
        'm19.volume_limit': 0.025,
        'm19.order_price_field_buy': 'open',
        'm19.order_price_field_sell': 'close',
        'm19.capital_base': 1000000,
        'm19.auto_cancel_non_tradable_orders': True,
        'm19.data_frequency': 'daily',
        'm19.price_type': '后复权',
        'm19.product_type': '股票',
        'm19.plot_charts': True,
        'm19.backtest_only': False,
        'm19.benchmark': '',
    })
    
    # g.run({})
    
    
    def m20_param_grid_builder_bigquant_run():
        param_grid = {}
    
        # 在这里设置需要调优的参数备选
        param_grid['m4.number_of_trees'] = [5, 10, 20]
        param_grid['m19.volume_limit'] = [0.025, 0.03]
    
        return param_grid
    
    def m20_scoring_bigquant_run(result):
        score = result.get('m19').read_raw_perf()['sharpe'].tail(1)[0]
    
        return score
    
    
    m20 = M.hyper_parameter_search.v1(
        param_grid_builder=m20_param_grid_builder_bigquant_run,
        scoring=m20_scoring_bigquant_run,
        search_algorithm='随机搜索',
        search_iterations=3,
        workers=1,
        worker_distributed_run=True,
        worker_silent=True,
        run_now=True,
        bq_graph=g
    )
    
    Fitting 1 folds for each of 3 candidates, totalling 3 fits
    [Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
    [CV] m4.number_of_trees=20, m19.volume_limit=0.03 ....................
    
    [CV]  m4.number_of_trees=20, m19.volume_limit=0.03, score=2.003586847712331, total= 4.2min
    [Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:  4.2min remaining:    0.0s
    [CV] m4.number_of_trees=5, m19.volume_limit=0.03 .....................
    
    [CV]  m4.number_of_trees=5, m19.volume_limit=0.03, score=2.190739457599399, total= 2.2min
    [Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:  6.4min remaining:    0.0s
    [CV] m4.number_of_trees=10, m19.volume_limit=0.03 ....................
    
    [CV]  m4.number_of_trees=10, m19.volume_limit=0.03, score=2.5869865310906515, total= 1.5min
    [Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed:  7.9min remaining:    0.0s
    [Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed:  7.9min finished
    
    In [2]:
    m20.result.cv_results_
    
    Out[2]:
    {'mean_fit_time': array([251.45409727, 130.55868173,  90.51740813]),
     'mean_score_time': array([0.2287631 , 0.07436848, 0.22406101]),
     'mean_test_score': array([2.00358685, 2.19073946, 2.58698653]),
     'mean_train_score': array([2.00358685, 2.19073946, 2.58698653]),
     'param_m19.volume_limit': masked_array(data=[0.03, 0.03, 0.03],
                  mask=[False, False, False],
            fill_value='?',
                 dtype=object),
     'param_m4.number_of_trees': masked_array(data=[20, 5, 10],
                  mask=[False, False, False],
            fill_value='?',
                 dtype=object),
     'params': [{'m19.volume_limit': 0.03, 'm4.number_of_trees': 20},
      {'m19.volume_limit': 0.03, 'm4.number_of_trees': 5},
      {'m19.volume_limit': 0.03, 'm4.number_of_trees': 10}],
     'rank_test_score': array([3, 2, 1], dtype=int32),
     'split0_test_score': array([2.00358685, 2.19073946, 2.58698653]),
     'split0_train_score': array([2.00358685, 2.19073946, 2.58698653]),
     'std_fit_time': array([0., 0., 0.]),
     'std_score_time': array([0., 0., 0.]),
     'std_test_score': array([0., 0., 0.]),
     'std_train_score': array([0., 0., 0.])}
    In [3]:
    m20.result
    
    Out[3]:
    RandomizedSearchCV(cv=ShuffleSplit(n_splits=1, random_state=None, test_size=0.1, train_size=None),
              error_score='raise-deprecating',
              estimator=<biglearning.module2.modules.hyper_parameter_search.v1.graphestimator.GraphEstimator object at 0x7fedd9836e48>,
              fit_params=None, iid='warn', n_iter=3, n_jobs=1,
              param_distributions={'m4.number_of_trees': [5, 10, 20], 'm19.volume_limit': [0.025, 0.03]},
              pre_dispatch='2*n_jobs', random_state=None, refit=True,
              return_train_score='warn', scoring=None, verbose=100)
    In [7]:
    m20.result.best_params_
    
    Out[7]:
    {'m19.volume_limit': 0.03, 'm4.number_of_trees': 10}
    In [8]:
    m20.result.cv_results_
    
    Out[8]:
    {'mean_fit_time': array([251.45409727, 130.55868173,  90.51740813]),
     'mean_score_time': array([0.2287631 , 0.07436848, 0.22406101]),
     'mean_test_score': array([2.00358685, 2.19073946, 2.58698653]),
     'mean_train_score': array([2.00358685, 2.19073946, 2.58698653]),
     'param_m19.volume_limit': masked_array(data=[0.03, 0.03, 0.03],
                  mask=[False, False, False],
            fill_value='?',
                 dtype=object),
     'param_m4.number_of_trees': masked_array(data=[20, 5, 10],
                  mask=[False, False, False],
            fill_value='?',
                 dtype=object),
     'params': [{'m19.volume_limit': 0.03, 'm4.number_of_trees': 20},
      {'m19.volume_limit': 0.03, 'm4.number_of_trees': 5},
      {'m19.volume_limit': 0.03, 'm4.number_of_trees': 10}],
     'rank_test_score': array([3, 2, 1], dtype=int32),
     'split0_test_score': array([2.00358685, 2.19073946, 2.58698653]),
     'split0_train_score': array([2.00358685, 2.19073946, 2.58698653]),
     'std_fit_time': array([0., 0., 0.]),
     'std_score_time': array([0., 0., 0.]),
     'std_test_score': array([0., 0., 0.]),
     'std_train_score': array([0., 0., 0.])}
    In [9]:
    # 方法一,DataSource 方式
    DataSource.write_pickle(m20.result.cv_results_)
    
    Out[9]:
    DataSource(7a2ec6401cba427fab214b3824d943b3T, v3)
    In [10]:
    DataSource("8296958e777e43358e18ae1df9d954bfT").read()
    
    8296958e777e43358e18ae1df9d954bfT not found.
    
    In [11]:
    # 方法二,csv文件方式
    df = pd.DataFrame(m20.result.cv_results_)
    df.to_csv("results.csv")
    

    BigQuant AI量化专家Meetup(更新至12月17日)
    (fudingyu) #2

    新策略要支持一下~~~!