可视化模板自定义指标过滤的实现


(iQuant) #1

很多朋友在使用平台时希望在交易时加入一些自定义的指标过滤,比如股价在120日均线之上等。在可视化模板中如何修改,以实现过滤功能呢?分为两种情况:

  • 第一种情况:
    如果只是在买卖操作中做风控系统过滤,可以通过trade模块的盘前函数进行指标定义,通过context传给主函数模块,在主函数中通过条件判断实现风险控制,这可以参考下面的案例:
克隆策略

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2012-01-01","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\nclose_0\nreturn_5/return_10","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-bdf8-104b137c8601-29","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v6","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"300","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-35","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v2","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"OutputPortsInternal":[{"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"feature_gains","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"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":"2015-03-01","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-bdf8-104b137c8601-70","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v6","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"300","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-76","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v2","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"import talib\ndef self_diy(df,close_0): \n close = [float(x) for x in df['close_0']]\n df['close_0']=(df['close_0']>talib.MA(np.array(close), timeperiod=5)).astype(int)\n return df['close_0']\n #return pd.rolling_apply(df['close_0'], 5,np.mean)\nbigquant_run = {\n 'self_diy': self_diy\n}\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-81","ModuleId":"BigQuantSpace.trade.trade-v3","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"handle_data","Value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金\n # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按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_condition=context.buy_condition\n buy_list_today=list(buy_condition[(buy_condition['date']==data.current_dt.strftime('%Y-%m-%d')) & (buy_condition.condition>0)].instrument)\n all_instruments = list(ranker_prediction.instrument)\n buy_list=[i for i in all_instruments if i in buy_list_today]\n buy_instruments=buy_list[:len(buy_cash_weights)]\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎:准备数据,只执行一次\ndef bigquant_run(context):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n \n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n stock_count = 5\n # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]\n context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.2\n context.options['hold_days'] = 5\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"def bigquant_run(context,data):\n end_date=context.end_date\n start_date=(pd.to_datetime(context.end_date) - datetime.timedelta(days=200)).strftime('%Y-%m-%d') # 多取几天的数据\n all_data = D.history_data(context.instruments, start_date=start_date , end_date=end_date, fields=['close']).reset_index()\n all_data['ma_120'] = all_data['close'].rolling(120).mean()\n all_data['self_func'] = all_data['ma_120'] < all_data['close']\n all_data['condition'] = np.where(all_data['self_func'],1,0) \n buy_condition = all_data[['date','instrument','condition']]\n #这里根据自定义条件确定一个买入条件\n context.buy_condition=buy_condition\n #通过context把计算的每日仓位数据pos_df传给handle,信号以当日价格计算,次日执行","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":1000000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"amount_integer","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":12,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"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}],"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='671,23,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-29' Position='381,188,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-35' Position='372,265,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='638,561,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='237,406,200,200'/><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='287d2cb0-f53c-4101-bdf8-104b137c8601-70' Position='1078,236,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-76' Position='1074,315,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-81' Position='1038,752,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='408,504,200,200'/><NodePosition Node='-86' Position='1069,467,200,200'/></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 [26]:
    # 本代码由可视化策略环境自动生成 2018年5月8日 12:52
    # 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
    
    
    m1 = M.instruments.v2(
        start_date='2012-01-01',
        end_date='2015-01-01',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m2 = M.advanced_auto_labeler.v2(
        instruments=m1.data,
        label_expr="""# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
    #   添加benchmark_前缀,可使用对应的benchmark数据
    # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -5) / shift(open, -1)
    
    # 极值处理:用1%和99%分位的值做clip
    clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
    
    # 将分数映射到分类,这里使用20个分类
    all_wbins(label, 20)
    
    # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
    where(shift(high, -1) == shift(low, -1), NaN, label)
    """,
        start_date='',
        end_date='',
        benchmark='000300.SHA',
        drop_na_label=True,
        cast_label_int=True
    )
    
    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
    close_0
    return_5/return_10"""
    )
    
    m4 = M.general_feature_extractor.v6(
        instruments=m1.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=300
    )
    
    m5 = M.derived_feature_extractor.v2(
        input_data=m4.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        user_functions={}
    )
    
    m7 = M.join.v3(
        data1=m2.data,
        data2=m5.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m13 = M.dropnan.v1(
        input_data=m7.data
    )
    
    m6 = M.stock_ranker_train.v5(
        training_ds=m13.data,
        features=m3.data,
        learning_algorithm='排序',
        number_of_leaves=30,
        minimum_docs_per_leaf=1000,
        number_of_trees=20,
        learning_rate=0.1,
        max_bins=1023,
        feature_fraction=1,
        m_lazy_run=False
    )
    
    m9 = M.instruments.v2(
        start_date=T.live_run_param('trading_date', '2015-01-01'),
        end_date=T.live_run_param('trading_date', '2015-03-01'),
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m10 = M.general_feature_extractor.v6(
        instruments=m9.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=300
    )
    
    import talib
    def self_diy(df,close_0): 
        close = [float(x) for x in df['close_0']]
        df['close_0']=(df['close_0']>talib.MA(np.array(close), timeperiod=5)).astype(int)
        return df['close_0']
       #return pd.rolling_apply(df['close_0'], 5,np.mean)
    m11_user_functions_bigquant_run = {
        'self_diy':  self_diy
    }
    
    m11 = M.derived_feature_extractor.v2(
        input_data=m10.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        user_functions=m11_user_functions_bigquant_run
    )
    
    m14 = M.dropnan.v1(
        input_data=m11.data
    )
    
    m8 = M.stock_ranker_predict.v5(
        model=m6.model,
        data=m14.data,
        m_lazy_run=False
    )
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m12_handle_data_bigquant_run(context, data):
        # 按日期过滤得到今日的预测数据
        ranker_prediction = context.ranker_prediction[
            context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
    
        # 1. 资金分配
        # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金
        # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)
        is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
        cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
        cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
        cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
        positions = {e.symbol: p.amount * p.last_sale_price
                     for e, p in context.perf_tracker.position_tracker.positions.items()}
    
        # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
        if not is_staging and cash_for_sell > 0:
            equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
            instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                    lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
            # print('rank order for sell %s' % instruments)
            for instrument in instruments:
                context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
                if cash_for_sell <= 0:
                    break
    
        # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票
        buy_cash_weights = context.stock_weights
        buy_condition=context.buy_condition
        buy_list_today=list(buy_condition[(buy_condition['date']==data.current_dt.strftime('%Y-%m-%d')) & (buy_condition.condition>0)].instrument)
        all_instruments = list(ranker_prediction.instrument)
        buy_list=[i for i in all_instruments if i in buy_list_today]
        buy_instruments=buy_list[:len(buy_cash_weights)]
        max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
        for i, instrument in enumerate(buy_instruments):
            cash = cash_for_buy * buy_cash_weights[i]
            if cash > max_cash_per_instrument - positions.get(instrument, 0):
                # 确保股票持仓量不会超过每次股票最大的占用资金量
                cash = max_cash_per_instrument - positions.get(instrument, 0)
            if cash > 0:
                context.order_value(context.symbol(instrument), cash)
    
    # 回测引擎:准备数据,只执行一次
    def m12_prepare_bigquant_run(context):
        pass
    
    # 回测引擎:初始化函数,只执行一次
    def m12_initialize_bigquant_run(context):
        # 加载预测数据
        context.ranker_prediction = context.options['data'].read_df()
        
        # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
        context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
        # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
        # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
        stock_count = 5
        # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]
        context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
        # 设置每只股票占用的最大资金比例
        context.max_cash_per_instrument = 0.2
        context.options['hold_days'] = 5
    
    def m12_before_trading_start_bigquant_run(context,data):
        end_date=context.end_date
        start_date=(pd.to_datetime(context.end_date) - datetime.timedelta(days=200)).strftime('%Y-%m-%d') # 多取几天的数据
        all_data = D.history_data(context.instruments, start_date=start_date , end_date=end_date, fields=['close']).reset_index()
        all_data['ma_120'] = all_data['close'].rolling(120).mean()
        all_data['self_func'] = all_data['ma_120'] < all_data['close']
        all_data['condition'] = np.where(all_data['self_func'],1,0)     
        buy_condition = all_data[['date','instrument','condition']]
        #这里根据自定义条件确定一个买入条件
        context.buy_condition=buy_condition
        #通过context把计算的每日仓位数据pos_df传给handle,信号以当日价格计算,次日执行
    m12 = M.trade.v3(
        instruments=m9.data,
        options_data=m8.predictions,
        start_date='',
        end_date='',
        handle_data=m12_handle_data_bigquant_run,
        prepare=m12_prepare_bigquant_run,
        initialize=m12_initialize_bigquant_run,
        before_trading_start=m12_before_trading_start_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy='open',
        order_price_field_sell='close',
        capital_base=1000000,
        benchmark='000300.SHA',
        auto_cancel_non_tradable_orders=True,
        data_frequency='daily',
        price_type='后复权',
        plot_charts=True,
        backtest_only=False,
        amount_integer=False
    )
    
    [2018-05-08 12:52:33.742420] INFO: bigquant: instruments.v2 开始运行..
    [2018-05-08 12:52:33.746455] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.747369] INFO: bigquant: instruments.v2 运行完成[0.004975s].
    [2018-05-08 12:52:33.756703] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
    [2018-05-08 12:52:33.758649] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.759443] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.00274s].
    [2018-05-08 12:52:33.762832] INFO: bigquant: input_features.v1 开始运行..
    [2018-05-08 12:52:33.765874] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.766651] INFO: bigquant: input_features.v1 运行完成[0.003818s].
    [2018-05-08 12:52:33.773702] INFO: bigquant: general_feature_extractor.v6 开始运行..
    [2018-05-08 12:52:33.776024] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.776789] INFO: bigquant: general_feature_extractor.v6 运行完成[0.003073s].
    [2018-05-08 12:52:33.782507] INFO: bigquant: derived_feature_extractor.v2 开始运行..
    [2018-05-08 12:52:33.784377] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.785193] INFO: bigquant: derived_feature_extractor.v2 运行完成[0.002681s].
    [2018-05-08 12:52:33.790986] INFO: bigquant: join.v3 开始运行..
    [2018-05-08 12:52:33.792886] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.793665] INFO: bigquant: join.v3 运行完成[0.002672s].
    [2018-05-08 12:52:33.799004] INFO: bigquant: dropnan.v1 开始运行..
    [2018-05-08 12:52:33.800965] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.801824] INFO: bigquant: dropnan.v1 运行完成[0.002815s].
    [2018-05-08 12:52:33.811683] INFO: bigquant: stock_ranker_train.v5 开始运行..
    [2018-05-08 12:52:33.814414] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.815223] INFO: bigquant: stock_ranker_train.v5 运行完成[0.003542s].
    [2018-05-08 12:52:33.819649] INFO: bigquant: instruments.v2 开始运行..
    [2018-05-08 12:52:33.821525] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.822657] INFO: bigquant: instruments.v2 运行完成[0.003003s].
    [2018-05-08 12:52:33.830347] INFO: bigquant: general_feature_extractor.v6 开始运行..
    [2018-05-08 12:52:33.832272] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.833283] INFO: bigquant: general_feature_extractor.v6 运行完成[0.002929s].
    [2018-05-08 12:52:33.840333] INFO: bigquant: derived_feature_extractor.v2 开始运行..
    [2018-05-08 12:52:33.842303] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.843126] INFO: bigquant: derived_feature_extractor.v2 运行完成[0.002794s].
    [2018-05-08 12:52:33.848557] INFO: bigquant: dropnan.v1 开始运行..
    [2018-05-08 12:52:33.851162] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.851984] INFO: bigquant: dropnan.v1 运行完成[0.003421s].
    [2018-05-08 12:52:33.858844] INFO: bigquant: stock_ranker_predict.v5 开始运行..
    [2018-05-08 12:52:33.864068] INFO: bigquant: 命中缓存
    [2018-05-08 12:52:33.864867] INFO: bigquant: stock_ranker_predict.v5 运行完成[0.006022s].
    [2018-05-08 12:52:33.896796] INFO: bigquant: backtest.v7 开始运行..
    [2018-05-08 12:52:33.899192] INFO: bigquant: 命中缓存
    
    • 收益率8.29%
    • 年化收益率77.46%
    • 基准收益率1.11%
    • 阿尔法0.71
    • 贝塔0.39
    • 夏普比率2.52
    • 胜率0.538
    • 盈亏比1.473
    • 收益波动率28.79%
    • 信息比率2.15
    • 最大回撤8.44%
    [2018-05-08 12:52:34.743473] INFO: bigquant: backtest.v7 运行完成[0.846679s].
    
    • 第二种情况:
      如果希望在训练中就加入过滤条件,回测也使用相同的过滤条件,则可以参考下面的框架。

    在输入特征列表中定义需要计算的因子名称,这个名称必须是个函数名(自变量)的格式,例如计算MA需要close_0因子作为自变量,那么可以定义指标因子名称为MA(close_0)。要注意自变量要填写齐全,比如计算成本均线需要用到换手率,那么指标名字就要定义成:CYC(close_o,turn_0)。
    此外,这个输入特征列表里面的自定义指标只是用作过滤使用,由于并没有传给训练模块,因此并不参与最终的模型训练,只做过滤使用。
    在衍生数据抽取模块中需要定义指标的计算公式,定义方法可以参考策略。
    由于函数名不能用过滤模块直接过滤,所以指标抽取后在自定义模块中进行数据的过滤。
    可视化流程中分为左分支训练集和右分支预测集的特征提取,新增模块应在两个分支保持一致,代码也保持一致以保证训练和测试过程的一致性。

    克隆策略

      {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-1713:features_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:data"},{"DestinationInputPortId":"-124:input_1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70:data"},{"DestinationInputPortId":"-132:input_1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35:features","SourceOutputPortId":"-1713:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29:features","SourceOutputPortId":"-1713:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76:features","SourceOutputPortId":"-1713:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-124:data_1"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-132:data_1"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2012-01-01","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\nclose_0\nreturn_5/return_10","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":false,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-29","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v6","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":"300","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-29","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-35","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v2","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"import talib\ndef self_diy(df,close_0): \n close = [float(x) for x in df['close_0']]\n df['condition']=(df['close_0']>talib.MA(np.array(close), timeperiod=5)).astype(int)\n return df['condition']\n #rolling_apply方式也是可以考虑的 return pd.rolling_apply(df['close_0'], 5,np.mean)\nbigquant_run = {\n 'self_diy': self_diy\n}\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-35","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"OutputPortsInternal":[{"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"feature_gains","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"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":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"IsPartOfPartialRun":null,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-70","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v6","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-70","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-76","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v2","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"import talib\ndef self_diy(df,close_0): \n close = [float(x) for x in df['close_0']]\n df['close_0']=(df['close_0']>talib.MA(np.array(close), timeperiod=5)).astype(int)\n return df['close_0']\n #return pd.rolling_apply(df['close_0'], 5,np.mean)\nbigquant_run = {\n 'self_diy': self_diy\n}\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-76","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-81","ModuleId":"BigQuantSpace.trade.trade-v3","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"handle_data","Value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金\n # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎:准备数据,只执行一次\ndef bigquant_run(context):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n stock_count = 5\n # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]\n context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.2\n context.options['hold_days'] = 5\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":1000000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"amount_integer","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-81","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":12,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"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":"-1713","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"\n# #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\nself_diy(close_0)","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-1713"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1713","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-124","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n df = input_1.read_df()\n df1=df[df['self_diy(close_0)']>0]\n data_1 = DataSource.write_df(df1)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-124"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-124"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-124"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-124","OutputType":null},{"Name":"data_2","NodeId":"-124","OutputType":null},{"Name":"data_3","NodeId":"-124","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-132","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n df = input_1.read_df()\n df1=df[df['self_diy(close_0)']>0]\n data_1 = DataSource.write_df(df1)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-132"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-132"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-132"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-132","OutputType":null},{"Name":"data_2","NodeId":"-132","OutputType":null},{"Name":"data_3","NodeId":"-132","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"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='773,-3,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-29' Position='381,188,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-35' Position='372,265,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='638,561,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='239,406,200,200'/><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='287d2cb0-f53c-4101-bdf8-104b137c8601-70' Position='1078,236,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-76' Position='1074,315,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-81' Position='1037,751,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='408,504,200,200'/><NodePosition Node='-86' Position='1069,467,200,200'/><NodePosition Node='-1713' Position='585,97,200,200'/><NodePosition Node='-124' Position='385,333,200,200'/><NodePosition Node='-132' Position='1080,394,200,200'/></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 [4]:
      # 本代码由可视化策略环境自动生成 2018年5月8日 12:57
      # 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。
      
      
      m1 = M.instruments.v2(
          start_date='2012-01-01',
          end_date='2015-01-01',
          market='CN_STOCK_A',
          instrument_list='',
          max_count=0
      )
      
      m2 = M.advanced_auto_labeler.v2(
          instruments=m1.data,
          label_expr="""# #号开始的表示注释
      # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
      # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
      #   添加benchmark_前缀,可使用对应的benchmark数据
      # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
      
      # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
      shift(close, -5) / shift(open, -1)
      
      # 极值处理:用1%和99%分位的值做clip
      clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
      
      # 将分数映射到分类,这里使用20个分类
      all_wbins(label, 20)
      
      # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
      where(shift(high, -1) == shift(low, -1), NaN, label)
      """,
          start_date='',
          end_date='',
          benchmark='000300.SHA',
          drop_na_label=True,
          cast_label_int=True
      )
      
      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
      close_0
      return_5/return_10""",
          m_cached=False
      )
      
      m15 = M.input_features.v1(
          features_ds=m3.data,
          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
      self_diy(close_0)""",
          m_cached=False
      )
      
      m4 = M.general_feature_extractor.v6(
          instruments=m1.data,
          features=m15.data,
          start_date='',
          end_date='',
          before_start_days=300
      )
      
      import talib
      def self_diy(df,close_0): 
          close = [float(x) for x in df['close_0']]
          df['condition']=(df['close_0']>talib.MA(np.array(close), timeperiod=5)).astype(int)
          return df['condition']
         #rolling_apply方式也是可以考虑的 return pd.rolling_apply(df['close_0'], 5,np.mean)
      m5_user_functions_bigquant_run = {
          'self_diy':  self_diy
      }
      
      m5 = M.derived_feature_extractor.v2(
          input_data=m4.data,
          features=m15.data,
          date_col='date',
          instrument_col='instrument',
          user_functions=m5_user_functions_bigquant_run,
          m_cached=False
      )
      
      # Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端
      def m16_run_bigquant_run(input_1, input_2, input_3):
          # 示例代码如下。在这里编写您的代码
          df = input_1.read_df()
          df1=df[df['self_diy(close_0)']>0]
          data_1 = DataSource.write_df(df1)
          return Outputs(data_1=data_1, data_2=None, data_3=None)
      
      m16 = M.cached.v3(
          input_1=m5.data,
          run=m16_run_bigquant_run
      )
      
      m7 = M.join.v3(
          data1=m2.data,
          data2=m16.data_1,
          on='date,instrument',
          how='inner',
          sort=False
      )
      
      m13 = M.dropnan.v1(
          input_data=m7.data
      )
      
      m6 = M.stock_ranker_train.v5(
          training_ds=m13.data,
          features=m3.data,
          learning_algorithm='排序',
          number_of_leaves=30,
          minimum_docs_per_leaf=1000,
          number_of_trees=20,
          learning_rate=0.1,
          max_bins=1023,
          feature_fraction=1,
          m_lazy_run=False
      )
      
      m9 = M.instruments.v2(
          start_date=T.live_run_param('trading_date', '2015-01-01'),
          end_date=T.live_run_param('trading_date', '2017-01-01'),
          market='CN_STOCK_A',
          instrument_list='',
          max_count=0
      )
      
      m10 = M.general_feature_extractor.v6(
          instruments=m9.data,
          features=m3.data,
          start_date='',
          end_date='',
          before_start_days=0
      )
      
      import talib
      def self_diy(df,close_0): 
          close = [float(x) for x in df['close_0']]
          df['close_0']=(df['close_0']>talib.MA(np.array(close), timeperiod=5)).astype(int)
          return df['close_0']
         #return pd.rolling_apply(df['close_0'], 5,np.mean)
      m11_user_functions_bigquant_run = {
          'self_diy':  self_diy
      }
      
      m11 = M.derived_feature_extractor.v2(
          input_data=m10.data,
          features=m15.data,
          date_col='date',
          instrument_col='instrument',
          user_functions=m11_user_functions_bigquant_run
      )
      
      # Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端
      def m17_run_bigquant_run(input_1, input_2, input_3):
          # 示例代码如下。在这里编写您的代码
          df = input_1.read_df()
          df1=df[df['self_diy(close_0)']>0]
          data_1 = DataSource.write_df(df1)
          return Outputs(data_1=data_1, data_2=None, data_3=None)
      
      m17 = M.cached.v3(
          input_1=m11.data,
          run=m17_run_bigquant_run
      )
      
      m14 = M.dropnan.v1(
          input_data=m17.data_1
      )
      
      m8 = M.stock_ranker_predict.v5(
          model=m6.model,
          data=m14.data,
          m_lazy_run=False
      )
      
      # 回测引擎:每日数据处理函数,每天执行一次
      def m12_handle_data_bigquant_run(context, data):
          # 按日期过滤得到今日的预测数据
          ranker_prediction = context.ranker_prediction[
              context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
      
          # 1. 资金分配
          # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金
          # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)
          is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
          cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
          cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
          cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
          positions = {e.symbol: p.amount * p.last_sale_price
                       for e, p in context.perf_tracker.position_tracker.positions.items()}
      
          # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
          if not is_staging and cash_for_sell > 0:
              equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
              instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                      lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
              # print('rank order for sell %s' % instruments)
              for instrument in instruments:
                  context.order_target(context.symbol(instrument), 0)
                  cash_for_sell -= positions[instrument]
                  if cash_for_sell <= 0:
                      break
      
          # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票
          buy_cash_weights = context.stock_weights
          buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
          max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
          for i, instrument in enumerate(buy_instruments):
              cash = cash_for_buy * buy_cash_weights[i]
              if cash > max_cash_per_instrument - positions.get(instrument, 0):
                  # 确保股票持仓量不会超过每次股票最大的占用资金量
                  cash = max_cash_per_instrument - positions.get(instrument, 0)
              if cash > 0:
                  context.order_value(context.symbol(instrument), cash)
      
      # 回测引擎:准备数据,只执行一次
      def m12_prepare_bigquant_run(context):
          pass
      
      # 回测引擎:初始化函数,只执行一次
      def m12_initialize_bigquant_run(context):
          # 加载预测数据
          context.ranker_prediction = context.options['data'].read_df()
      
          # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
          context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
          # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
          # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
          stock_count = 5
          # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]
          context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
          # 设置每只股票占用的最大资金比例
          context.max_cash_per_instrument = 0.2
          context.options['hold_days'] = 5
      
      m12 = M.trade.v3(
          instruments=m9.data,
          options_data=m8.predictions,
          start_date='',
          end_date='',
          handle_data=m12_handle_data_bigquant_run,
          prepare=m12_prepare_bigquant_run,
          initialize=m12_initialize_bigquant_run,
          volume_limit=0.025,
          order_price_field_buy='open',
          order_price_field_sell='close',
          capital_base=1000000,
          benchmark='000300.SHA',
          auto_cancel_non_tradable_orders=True,
          data_frequency='daily',
          price_type='后复权',
          plot_charts=True,
          backtest_only=False,
          amount_integer=False
      )
      
      [2018-05-08 12:54:02.728637] INFO: bigquant: instruments.v2 开始运行..
      [2018-05-08 12:54:02.748097] INFO: bigquant: 命中缓存
      [2018-05-08 12:54:02.748994] INFO: bigquant: instruments.v2 运行完成[0.020392s].
      [2018-05-08 12:54:02.756544] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
      [2018-05-08 12:54:02.758726] INFO: bigquant: 命中缓存
      [2018-05-08 12:54:02.759589] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.003054s].
      [2018-05-08 12:54:02.763358] INFO: bigquant: input_features.v1 开始运行..
      [2018-05-08 12:54:02.768233] INFO: bigquant: input_features.v1 运行完成[0.004874s].
      [2018-05-08 12:54:02.771658] INFO: bigquant: input_features.v1 开始运行..
      [2018-05-08 12:54:02.775296] INFO: bigquant: input_features.v1 运行完成[0.003636s].
      [2018-05-08 12:54:02.782726] INFO: bigquant: general_feature_extractor.v6 开始运行..
      [2018-05-08 12:54:02.784914] INFO: bigquant: 命中缓存
      [2018-05-08 12:54:02.785796] INFO: bigquant: general_feature_extractor.v6 运行完成[0.003069s].
      [2018-05-08 12:54:02.791927] INFO: bigquant: derived_feature_extractor.v2 开始运行..
      [2018-05-08 12:54:04.475834] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.004s
      [2018-05-08 12:54:05.436252] INFO: derived_feature_extractor: 提取完成 self_diy(close_0), 0.959s
      [2018-05-08 12:54:06.726153] INFO: derived_feature_extractor: /y_2011, 433943
      [2018-05-08 12:54:07.389448] INFO: derived_feature_extractor: /y_2012, 565675
      [2018-05-08 12:54:07.922636] INFO: derived_feature_extractor: /y_2013, 564168
      [2018-05-08 12:54:08.267234] INFO: derived_feature_extractor: /y_2014, 569948
      [2018-05-08 12:54:08.536453] INFO: bigquant: derived_feature_extractor.v2 运行完成[5.744503s].
      [2018-05-08 12:54:08.545499] INFO: bigquant: cached.v3 开始运行..
      [2018-05-08 12:54:10.348629] INFO: bigquant: cached.v3 运行完成[1.803122s].
      [2018-05-08 12:54:10.355814] INFO: bigquant: join.v3 开始运行..
      [2018-05-08 12:54:16.794471] INFO: join: /data, 行数=873600/1071991, 耗时=4.691144s
      [2018-05-08 12:54:16.895560] INFO: join: 最终行数: 873600
      [2018-05-08 12:54:16.897280] INFO: bigquant: join.v3 运行完成[6.541459s].
      [2018-05-08 12:54:16.904302] INFO: bigquant: dropnan.v1 开始运行..
      [2018-05-08 12:54:18.295184] INFO: dropnan: /data, 872346/873600
      [2018-05-08 12:54:18.309626] INFO: dropnan: 行数: 872346/873600
      [2018-05-08 12:54:18.345607] INFO: bigquant: dropnan.v1 运行完成[1.441276s].
      [2018-05-08 12:54:18.353825] INFO: bigquant: stock_ranker_train.v5 开始运行..
      [2018-05-08 12:54:18.847275] INFO: df2bin: prepare bins ..
      [2018-05-08 12:54:18.996993] INFO: df2bin: prepare data: training ..
      [2018-05-08 12:54:19.165814] INFO: df2bin: sort ..
      [2018-05-08 12:54:27.137758] INFO: stock_ranker_train: dd63e5da 准备训练: 872346 行数
      [2018-05-08 12:54:57.150829] INFO: bigquant: stock_ranker_train.v5 运行完成[38.796994s].
      [2018-05-08 12:54:57.165348] INFO: bigquant: instruments.v2 开始运行..
      [2018-05-08 12:54:57.172124] INFO: bigquant: 命中缓存
      [2018-05-08 12:54:57.173004] INFO: bigquant: instruments.v2 运行完成[0.007653s].
      [2018-05-08 12:54:57.182010] INFO: bigquant: general_feature_extractor.v6 开始运行..
      [2018-05-08 12:54:57.184069] INFO: bigquant: 命中缓存
      [2018-05-08 12:54:57.184816] INFO: bigquant: general_feature_extractor.v6 运行完成[0.002808s].
      [2018-05-08 12:54:57.192974] INFO: bigquant: derived_feature_extractor.v2 开始运行..
      [2018-05-08 12:54:58.083216] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.003s
      [2018-05-08 12:54:58.417033] INFO: derived_feature_extractor: 提取完成 self_diy(close_0), 0.333s
      [2018-05-08 12:54:58.835263] INFO: derived_feature_extractor: /y_2015, 569698
      [2018-05-08 12:54:59.454070] INFO: derived_feature_extractor: /y_2016, 641546
      [2018-05-08 12:54:59.854522] INFO: bigquant: derived_feature_extractor.v2 运行完成[2.66152s].
      [2018-05-08 12:54:59.864075] INFO: bigquant: cached.v3 开始运行..
      [2018-05-08 12:55:00.805412] INFO: bigquant: cached.v3 运行完成[0.941296s].
      [2018-05-08 12:55:00.814346] INFO: bigquant: dropnan.v1 开始运行..
      [2018-05-08 12:55:01.350617] INFO: dropnan: /data, 647430/650591
      [2018-05-08 12:55:01.361879] INFO: dropnan: 行数: 647430/650591
      [2018-05-08 12:55:01.385075] INFO: bigquant: dropnan.v1 运行完成[0.570706s].
      [2018-05-08 12:55:01.395389] INFO: bigquant: stock_ranker_predict.v5 开始运行..
      [2018-05-08 12:55:01.697557] INFO: df2bin: prepare data: prediction ..
      [2018-05-08 12:55:07.469305] INFO: stock_ranker_predict: 准备预测: 647430 行
      [2018-05-08 12:55:11.787601] INFO: bigquant: stock_ranker_predict.v5 运行完成[10.392179s].
      [2018-05-08 12:55:11.822294] INFO: bigquant: backtest.v7 开始运行..
      [2018-05-08 12:55:11.930517] INFO: algo: set price type:backward_adjusted
      [2018-05-08 12:55:50.311871] INFO: Performance: Simulated 488 trading days out of 488.
      [2018-05-08 12:55:50.313065] INFO: Performance: first open: 2015-01-05 01:30:00+00:00
      [2018-05-08 12:55:50.313833] INFO: Performance: last close: 2016-12-30 07:00:00+00:00
      
      • 收益率90.89%
      • 年化收益率39.64%
      • 基准收益率-6.33%
      • 阿尔法0.43
      • 贝塔1.01
      • 夏普比率0.98
      • 胜率0.612
      • 盈亏比0.908
      • 收益波动率37.04%
      • 信息比率2.4
      • 最大回撤35.41%
      [2018-05-08 12:55:53.815545] INFO: bigquant: backtest.v7 运行完成[41.993244s].
      

      最后在两种情况下,都需要注意抽取基础因子时尽量向前多取一些天数,以保证指标值或条件值不为Nan


      如何以年线以上的票为股票池
      如何以年线以上的票为股票池
      如何过滤60天内没有涨停的股票
      (baifx) #2

      @iQuant :我做了一个自定义指标过滤,用到close_0 和 low_0,
      用上面克隆后修改。
      特征列表:
      close_0
      low_0
      return_5

      函数名定义为: self_diy(close_0, low_0)
      自定义指标计算处:

      import talib
      def self_diy(df,close_0,low_0): 
          close = [float(x) for x in df['close_0']] 
          df['condition']=(df['close_0']>talib.MA(np.array(close), timeperiod=10) and df['low_0'] < talib.MA(np.array(close), timeperiod=10)).astype(int)
          return df['condition']
      bigquant_run = {
          'self_diy':  self_diy
      }
      

      自定义指标过滤处:

       def bigquant_run(input_1, input_2, input_3):
          # 示例代码如下。在这里编写您的代码
          df = input_1.read_df()
          df1=df[df['self_diy(close_0,low_0)']>0]
         。。。。。。
      

      现在报错:

      2018-05-25 15:45:46.879323 INFO: derived_feature_extractor: 提取失败 self_diy(close_0,low_0): The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().
      ---------------------------------------------------------------------------_
      KeyError Traceback (most recent call last)_
      in ()_
      89 instrument_col=‘instrument’,_
      90 user_functions=m5_user_functions_bigquant_run,_
      —> 91 m_cached=False_
      92 )_
      93 _
      KeyError: “[‘self_diy(close_0,low_0)’] not in index”_

      请问什么原因?


      (baifx) #3

      抱歉, 找到原因了,是我pandas 出错,
      逻辑运算 and 改为 & 即可。

      def self_diy(df,close_0,low_0): 
          close = [float(x) for x in df['close_0']] 
          df['condition']=(df['close_0']>talib.MA(np.array(close), timeperiod=10) & df['low_0'] < talib.MA(np.array(close), timeperiod=10)).astype(int)
          return df['condition']
      bigquant_run = {
          'self_diy':  self_diy
      }
      

      (smallsnow) #5

      “可视化流程中分为左分支训练集和右分支预测集的特征提取,新增模块应在两个分支保持一致,代码也保持一致以保证训练和测试过程的一致性。”,我定义的一个选股函数,左右两个一样的,但是发现左边对训练集有效(m13.data),右边的选出来结果(m14.data)乱七八糟的,导致最终回测的股票的时间点全是不符合我筛选策略的。不知道什么原因


      (smallsnow) #6

      补充一下我的疑问,右侧分支的自定义函数,好像其计算结果并没有按照单个股票计算,而是多只股票混合计算了,是不是哪里 需要用groupby(‘instrument’)?
      当我只对单个股票进行测试,回测的自定义函数结果是正确的,但是多个股票就股票之间干扰了


      (iQuant) #7

      收到您的提问,我们已提交给策略工程师,会尽快给您回复。


      (达达) #8

      试一下这个吧

      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":"-132:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-169:features_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-140:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-148:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-140:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-124:data_1"},{"DestinationInputPortId":"-161:input_data","SourceOutputPortId":"-132:data"},{"DestinationInputPortId":"-155:input_data","SourceOutputPortId":"-148:data"},{"DestinationInputPortId":"-177:input_1","SourceOutputPortId":"-155:data"},{"DestinationInputPortId":"-124:input_1","SourceOutputPortId":"-161:data"},{"DestinationInputPortId":"-132:features","SourceOutputPortId":"-169:data"},{"DestinationInputPortId":"-161:features","SourceOutputPortId":"-169:data"},{"DestinationInputPortId":"-148:features","SourceOutputPortId":"-169:data"},{"DestinationInputPortId":"-155:features","SourceOutputPortId":"-169:data"},{"DestinationInputPortId":"-185:input_data","SourceOutputPortId":"-177:data_1"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-185:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2012-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2012-05-01","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,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"Name":"label_expr","Value":"# #号开始的表示注释\n# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html\n# 添加benchmark_前缀,可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(open, -1)\n\n# 极值处理:用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类,这里使用20个分类\nall_wbins(label, 20)\n\n# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"# #号开始的表示注释\n# 多个特征,每行一个,可以包含基础特征和衍生特征\nclose_0\nreturn_5/return_10","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":false,"moduleIdForCode":3,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"OutputPortsInternal":[{"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"feature_gains","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","ModuleId":"BigQuantSpace.stock_ranker_predict.stock_ranker_predict-v5","ModuleParameters":[{"Name":"m_lazy_run","Value":"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,"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":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","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":"-124","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n input_df = input_1.read_df().reset_index(drop=True)\n \n def cal(df):\n # 将价格数据转化成float类型\n close = [float(x) for x in df['close_0']]\n # 通过talib计算移动平均值(方法2)\n df['MA10'] = talib.MA(np.array(close), timeperiod=10)\n df['cond'] = (df['close_0']>df['MA10']).astype(int)\n df.drop('MA10',axis=1)\n return df\n # 计算指标条件\n result = input_df.groupby('instrument').apply(cal)\n # 过滤\n filter_result = result[result['cond']>0]\n # 输出\n data_1 = DataSource.write_df(filter_result)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"post_run","Value":"# 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。\ndef bigquant_run(outputs):\n return outputs\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-124"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-124"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-124"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-124","OutputType":null},{"Name":"data_2","NodeId":"-124","OutputType":null},{"Name":"data_3","NodeId":"-124","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"Comment":"","CommentCollapsed":true},{"Id":"-132","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":"300","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-132"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-132"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-132","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"Comment":"","CommentCollapsed":true},{"Id":"-148","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":"-148"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-148"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-148","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":20,"Comment":"","CommentCollapsed":true},{"Id":"-155","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":"-155"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-155"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-155","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":21,"Comment":"","CommentCollapsed":true},{"Id":"-140","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"handle_data","Value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金\n # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))\n # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎:准备数据,只执行一次\ndef bigquant_run(context):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n stock_count = 5\n # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]\n context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.2\n context.options['hold_days'] = 5\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":1000000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-140"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-140"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-140"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-140"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-140"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-140","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":5,"Comment":"","CommentCollapsed":true},{"Id":"-161","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":"-161"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-161"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-161","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"Comment":"","CommentCollapsed":true},{"Id":"-169","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"\n# #号开始的表示注释,注释需单独一行\n# 多个特征,每行一个,可以包含基础特征和衍生特征,特征须为本平台特征\nclose_0\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-169"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-169","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"Comment":"","CommentCollapsed":true},{"Id":"-177","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n input_df = input_1.read_df().reset_index(drop=True)\n \n def cal(df):\n # 将价格数据转化成float类型\n close = [float(x) for x in df['close_0']]\n # 通过talib计算移动平均值(方法2)\n df['MA10'] = talib.MA(np.array(close), timeperiod=10)\n df['cond'] = (df['close_0']>df['MA10']).astype(int)\n df.drop('MA10',axis=1)\n return df\n # 计算指标条件\n result = input_df.groupby('instrument').apply(cal)\n # 过滤\n filter_result = result[result['cond']>0]\n # 输出\n data_1 = DataSource.write_df(filter_result)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"post_run","Value":"# 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。\ndef bigquant_run(outputs):\n return outputs\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-177"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-177"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-177"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-177","OutputType":null},{"Name":"data_2","NodeId":"-177","OutputType":null},{"Name":"data_3","NodeId":"-177","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"Comment":"","CommentCollapsed":true},{"Id":"-185","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-185"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-185","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"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='844,-43,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='638,561,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='253,404,200,200'/><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='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='401,485,200,200'/><NodePosition Node='-124' Position='452,309,200,200'/><NodePosition Node='-132' Position='457,152,200,200'/><NodePosition Node='-148' Position='1078,236,200,200'/><NodePosition Node='-155' Position='1074,315,200,200'/><NodePosition Node='-140' Position='1037,751,200,200'/><NodePosition Node='-161' Position='458,229,200,200'/><NodePosition Node='-169' Position='756,50,200,200'/><NodePosition Node='-177' Position='1058,409,200,200'/><NodePosition Node='-185' Position='1039,522,200,200'/></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 [173]:
        # 本代码由可视化策略环境自动生成 2019年1月30日 11:42
        # 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。
        
        
        # Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端
        def m16_run_bigquant_run(input_1, input_2, input_3):
            # 示例代码如下。在这里编写您的代码
            input_df = input_1.read_df().reset_index(drop=True)
            
            def cal(df):
                # 将价格数据转化成float类型
                close = [float(x) for x in df['close_0']]
                # 通过talib计算移动平均值(方法2)
                df['MA10'] = talib.MA(np.array(close), timeperiod=10)
                df['cond'] = (df['close_0']>df['MA10']).astype(int)
                df.drop('MA10',axis=1)
                return df
            # 计算指标条件
            result = input_df.groupby('instrument').apply(cal)
            # 过滤
            filter_result = result[result['cond']>0]
            # 输出
            data_1 = DataSource.write_df(filter_result)
            return Outputs(data_1=data_1, data_2=None, data_3=None)
        
        # 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。
        def m16_post_run_bigquant_run(outputs):
            return outputs
        
        # Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端
        def m14_run_bigquant_run(input_1, input_2, input_3):
            # 示例代码如下。在这里编写您的代码
            input_df = input_1.read_df().reset_index(drop=True)
            
            def cal(df):
                # 将价格数据转化成float类型
                close = [float(x) for x in df['close_0']]
                # 通过talib计算移动平均值(方法2)
                df['MA10'] = talib.MA(np.array(close), timeperiod=10)
                df['cond'] = (df['close_0']>df['MA10']).astype(int)
                df.drop('MA10',axis=1)
                return df
            # 计算指标条件
            result = input_df.groupby('instrument').apply(cal)
            # 过滤
            filter_result = result[result['cond']>0]
            # 输出
            data_1 = DataSource.write_df(filter_result)
            return Outputs(data_1=data_1, data_2=None, data_3=None)
        
        # 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。
        def m14_post_run_bigquant_run(outputs):
            return outputs
        
        # 回测引擎:每日数据处理函数,每天执行一次
        def m5_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 m5_prepare_bigquant_run(context):
            pass
        
        # 回测引擎:初始化函数,只执行一次
        def m5_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
        
        
        m1 = M.instruments.v2(
            start_date='2012-01-01',
            end_date='2012-05-01',
            market='CN_STOCK_A',
            instrument_list='',
            max_count=0
        )
        
        m2 = M.advanced_auto_labeler.v2(
            instruments=m1.data,
            label_expr="""# #号开始的表示注释
        # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
        # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
        #   添加benchmark_前缀,可使用对应的benchmark数据
        # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
        
        # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
        shift(close, -5) / shift(open, -1)
        
        # 极值处理:用1%和99%分位的值做clip
        clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
        
        # 将分数映射到分类,这里使用20个分类
        all_wbins(label, 20)
        
        # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
        where(shift(high, -1) == shift(low, -1), NaN, label)
        """,
            start_date='',
            end_date='',
            benchmark='000300.SHA',
            drop_na_label=True,
            cast_label_int=True
        )
        
        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
        close_0
        return_5/return_10""",
            m_cached=False
        )
        
        m4 = M.input_features.v1(
            features_ds=m3.data,
            features="""
        # #号开始的表示注释,注释需单独一行
        # 多个特征,每行一个,可以包含基础特征和衍生特征,特征须为本平台特征
        close_0
        """
        )
        
        m18 = M.general_feature_extractor.v7(
            instruments=m1.data,
            features=m4.data,
            start_date='',
            end_date='',
            before_start_days=300
        )
        
        m10 = M.derived_feature_extractor.v3(
            input_data=m18.data,
            features=m4.data,
            date_col='date',
            instrument_col='instrument',
            drop_na=False,
            remove_extra_columns=False,
            user_functions={}
        )
        
        m16 = M.cached.v3(
            input_1=m10.data,
            run=m16_run_bigquant_run,
            post_run=m16_post_run_bigquant_run,
            input_ports='',
            params='{}',
            output_ports=''
        )
        
        m7 = M.join.v3(
            data1=m2.data,
            data2=m16.data_1,
            on='date,instrument',
            how='inner',
            sort=False
        )
        
        m13 = M.dropnan.v1(
            input_data=m7.data
        )
        
        m6 = M.stock_ranker_train.v5(
            training_ds=m13.data,
            features=m3.data,
            learning_algorithm='排序',
            number_of_leaves=30,
            minimum_docs_per_leaf=1000,
            number_of_trees=20,
            learning_rate=0.1,
            max_bins=1023,
            feature_fraction=1,
            m_lazy_run=False
        )
        
        m9 = M.instruments.v2(
            start_date=T.live_run_param('trading_date', '2015-01-01'),
            end_date=T.live_run_param('trading_date', '2017-01-01'),
            market='CN_STOCK_A',
            instrument_list='',
            max_count=0
        )
        
        m20 = M.general_feature_extractor.v7(
            instruments=m9.data,
            features=m4.data,
            start_date='',
            end_date='',
            before_start_days=0
        )
        
        m21 = M.derived_feature_extractor.v3(
            input_data=m20.data,
            features=m4.data,
            date_col='date',
            instrument_col='instrument',
            drop_na=False,
            remove_extra_columns=False,
            user_functions={}
        )
        
        m14 = M.cached.v3(
            input_1=m21.data,
            run=m14_run_bigquant_run,
            post_run=m14_post_run_bigquant_run,
            input_ports='',
            params='{}',
            output_ports=''
        )
        
        m15 = M.dropnan.v1(
            input_data=m14.data_1
        )
        
        m8 = M.stock_ranker_predict.v5(
            model=m6.model,
            data=m15.data,
            m_lazy_run=False
        )
        
        m5 = M.trade.v4(
            instruments=m9.data,
            options_data=m8.predictions,
            start_date='',
            end_date='',
            handle_data=m5_handle_data_bigquant_run,
            prepare=m5_prepare_bigquant_run,
            initialize=m5_initialize_bigquant_run,
            volume_limit=0.025,
            order_price_field_buy='open',
            order_price_field_sell='close',
            capital_base=1000000,
            auto_cancel_non_tradable_orders=True,
            data_frequency='daily',
            price_type='后复权',
            product_type='股票',
            plot_charts=True,
            backtest_only=False,
            benchmark='000300.SHA'
        )
        
        [2019-01-30 11:40:39.936887] INFO: bigquant: instruments.v2 开始运行..
        [2019-01-30 11:40:39.953899] INFO: bigquant: 命中缓存
        [2019-01-30 11:40:39.954995] INFO: bigquant: instruments.v2 运行完成[0.01814s].
        [2019-01-30 11:40:39.968514] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
        [2019-01-30 11:40:40.812736] INFO: 自动标注(股票): 加载历史数据: 167908 行
        [2019-01-30 11:40:40.814256] INFO: 自动标注(股票): 开始标注 ..
        [2019-01-30 11:40:41.492252] INFO: bigquant: advanced_auto_labeler.v2 运行完成[1.523717s].
        [2019-01-30 11:40:41.495075] INFO: bigquant: input_features.v1 开始运行..
        [2019-01-30 11:40:41.501408] INFO: bigquant: input_features.v1 运行完成[0.00635s].
        [2019-01-30 11:40:41.504246] INFO: bigquant: input_features.v1 开始运行..
        [2019-01-30 11:40:41.513398] INFO: bigquant: input_features.v1 运行完成[0.009162s].
        [2019-01-30 11:40:41.518358] INFO: bigquant: general_feature_extractor.v7 开始运行..
        [2019-01-30 11:40:41.522616] INFO: bigquant: 命中缓存
        [2019-01-30 11:40:41.523493] INFO: bigquant: general_feature_extractor.v7 运行完成[0.005138s].
        [2019-01-30 11:40:41.526128] INFO: bigquant: derived_feature_extractor.v3 开始运行..
        [2019-01-30 11:40:41.714487] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.002s
        [2019-01-30 11:40:41.833959] INFO: derived_feature_extractor: /y_2011, 433943
        [2019-01-30 11:40:42.085119] INFO: derived_feature_extractor: /y_2012, 167908
        [2019-01-30 11:40:42.172416] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.646251s].
        [2019-01-30 11:40:42.176959] INFO: bigquant: cached.v3 开始运行..
        [2019-01-30 11:40:49.572819] INFO: bigquant: cached.v3 运行完成[7.395832s].
        [2019-01-30 11:40:49.580235] INFO: bigquant: join.v3 开始运行..
        [2019-01-30 11:40:49.876540] INFO: join: /data, 行数=94941/262505, 耗时=0.236813s
        [2019-01-30 11:40:49.901880] INFO: join: 最终行数: 94941
        [2019-01-30 11:40:49.904987] INFO: bigquant: join.v3 运行完成[0.324732s].
        [2019-01-30 11:40:49.912251] INFO: bigquant: dropnan.v1 开始运行..
        [2019-01-30 11:40:50.035313] INFO: dropnan: /data, 94903/94941
        [2019-01-30 11:40:50.043490] INFO: dropnan: 行数: 94903/94941
        [2019-01-30 11:40:50.049388] INFO: bigquant: dropnan.v1 运行完成[0.137095s].
        [2019-01-30 11:40:50.064952] INFO: bigquant: stock_ranker_train.v5 开始运行..
        [2019-01-30 11:40:50.288947] INFO: StockRanker: 特征预处理 ..
        [2019-01-30 11:40:50.313967] INFO: StockRanker: prepare data: training ..
        [2019-01-30 11:40:50.831755] INFO: StockRanker: sort ..
        [2019-01-30 11:40:52.255937] INFO: StockRanker训练: d623e5b2 准备训练: 94903 行数
        [2019-01-30 11:40:52.292947] INFO: StockRanker训练: 正在训练 ..
        [2019-01-30 11:41:32.938479] INFO: bigquant: stock_ranker_train.v5 运行完成[42.873528s].
        [2019-01-30 11:41:32.941665] INFO: bigquant: instruments.v2 开始运行..
        [2019-01-30 11:41:32.947906] INFO: bigquant: 命中缓存
        [2019-01-30 11:41:32.950211] INFO: bigquant: instruments.v2 运行完成[0.008529s].
        [2019-01-30 11:41:32.958838] INFO: bigquant: general_feature_extractor.v7 开始运行..
        [2019-01-30 11:41:32.967819] INFO: bigquant: 命中缓存
        [2019-01-30 11:41:32.970125] INFO: bigquant: general_feature_extractor.v7 运行完成[0.011311s].
        [2019-01-30 11:41:32.972817] INFO: bigquant: derived_feature_extractor.v3 开始运行..
        [2019-01-30 11:41:36.076638] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.003s
        [2019-01-30 11:41:36.244169] INFO: derived_feature_extractor: /y_2015, 569698
        [2019-01-30 11:41:36.753444] INFO: derived_feature_extractor: /y_2016, 641546
        [2019-01-30 11:41:37.116121] INFO: bigquant: derived_feature_extractor.v3 运行完成[4.14326s].
        [2019-01-30 11:41:37.120300] INFO: bigquant: cached.v3 开始运行..
        [2019-01-30 11:41:47.274580] INFO: bigquant: cached.v3 运行完成[10.154254s].
        [2019-01-30 11:41:47.277994] INFO: bigquant: dropnan.v1 开始运行..
        [2019-01-30 11:41:47.903562] INFO: dropnan: /data, 647443/648271
        [2019-01-30 11:41:47.920599] INFO: dropnan: 行数: 647443/648271
        [2019-01-30 11:41:47.945222] INFO: bigquant: dropnan.v1 运行完成[0.667158s].
        [2019-01-30 11:41:47.957907] INFO: bigquant: stock_ranker_predict.v5 开始运行..
        [2019-01-30 11:41:48.214814] INFO: StockRanker: prepare data: prediction ..
        [2019-01-30 11:41:54.224949] INFO: stock_ranker_predict: 准备预测: 647443 行
        [2019-01-30 11:41:54.226144] INFO: stock_ranker_predict: 正在预测 ..
        [2019-01-30 11:42:14.534931] INFO: bigquant: stock_ranker_predict.v5 运行完成[26.57702s].
        [2019-01-30 11:42:14.587458] INFO: bigquant: backtest.v8 开始运行..
        [2019-01-30 11:42:14.592176] INFO: bigquant: biglearning backtest:V8.1.8
        [2019-01-30 11:42:14.593339] INFO: bigquant: product_type:stock by specified
        [2019-01-30 11:42:28.861344] INFO: bigquant: 读取股票行情完成:1990277
        [2019-01-30 11:42:49.385377] INFO: algo: TradingAlgorithm V1.4.5
        [2019-01-30 11:43:00.350450] INFO: algo: trading transform...
        [2019-01-30 11:43:11.387039] INFO: Performance: Simulated 488 trading days out of 488.
        [2019-01-30 11:43:11.388383] INFO: Performance: first open: 2015-01-05 09:30:00+00:00
        [2019-01-30 11:43:11.389252] INFO: Performance: last close: 2016-12-30 15:00:00+00:00
        
        • 收益率173.24%
        • 年化收益率68.05%
        • 基准收益率-6.33%
        • 阿尔法0.59
        • 贝塔1.1
        • 夏普比率1.38
        • 胜率0.62
        • 盈亏比0.93
        • 收益波动率42.06%
        • 信息比率0.16
        • 最大回撤48.68%
        [2019-01-30 11:43:15.222149] INFO: bigquant: backtest.v8 运行完成[60.634679s].
        

        (smallsnow) #9

        谢谢技术指导,可以了!通过这个例子学会了一些东西


        (smallsnow) #10

        我把这个例子和模板(普通策略)结合起来,在前面输入TALIB公式的股票筛选,在特征列表里输入buy_condition 和sell_condition买卖条件,不知道为什么,buyconditon生效,但是sell_condition条件不起作用,导致买入的股票无法卖掉,不知道哪里错了,请帮忙看看,谢谢!
        代码如下:
        import talib
        def m10_run_bigquant_run(input_1, input_2, input_3):
        # 示例代码如下。在这里编写您的代码
        df = input_1.read_df().reset_index(drop=True)
        def cal(df):
        # 将价格数据转化成float类型
        close = [float(x) for x in df[‘close_0’]]

            df['RSI6'] = talib.RSI( np.array(close),timeperiod=6)
            df['RSI6_1'] = df['RSI6'].shift(1)
            df['RSI12']= talib.RSI( np.array(close),timeperiod=12)
            df['RSI12_1'] = df['RSI12'].shift(1)
            df['RSI24']= talib.RSI( np.array(close),timeperiod=24)
            df['RSI24_1'] = df['RSI24'].shift(1)
            df['cond']=((df['RSI6']<50) & (df['RSI6_1']<df['RSI12_1'])  & (df['RSI6_1']<df['RSI24_1']) & (df['RSI6']>df['RSI12']) & (df['RSI6']>df['RSI24']) ).astype(int)
            return df
        
        # 计算指标条件
        result = df.groupby('instrument').apply(cal)
        # 过滤
        filter_result = result[result['cond']>0]
        # 输出
        data_1 = DataSource.write_df(filter_result)
        return Outputs(data_1=data_1, data_2=None, data_3=None)
        

        后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。

        def m10_post_run_bigquant_run(outputs):
        return outputs

        回测引擎:每日数据处理函数,每天执行一次

        def m9_handle_data_bigquant_run(context, data):
        # 回测引擎:每日数据处理函数,每天执行一次
        today = data.current_dt.strftime(’%Y-%m-%d’) # 日期
        # 通过positions对象,使用列表生成式的方法获取目前持仓的股票列表和对应的最新市值
        stock_hold_now = {e.symbol: p.amount * p.last_sale_price
        for e, p in context.perf_tracker.position_tracker.positions.items()}

        # 记录用于买入股票的可用现金
        cash_for_buy = context.portfolio.cash
        
        # 获取当日符合买入/卖出条件的股票列表
        try:
            buy_stock = context.daily_stock_buy[today][:3]  # 当日符合买入条件的股票,限定3股
        except:
            buy_stock=[]
        try:
            sell_stock = context.daily_stock_sell[today]  # 当日符合卖出条件的股票
        except:
            sell_stock = []
        
        # 需要卖出的股票:已有持仓中符合卖出条件的股票
        stock_to_sell = [i for i in stock_hold_now if i in sell_stock]
        # 需要买入的股票:没有持仓且符合买入条件的股票
        stock_to_buy = [i for i in buy_stock if i not in stock_hold_now]
        # 卖出
        for instrument in stock_to_sell:
            # 如果该股票停牌,则没法成交。因此需要用can_trade方法检查下该股票的状态
            # 如果返回真值,则可以正常下单,否则会出错
            # 因为stock是字符串格式,我们用symbol方法将其转化成平台可以接受的形式:Equity格式
            if data.can_trade(context.symbol(instrument)):
                # order_target_percent是平台的一个下单接口,表明下单使得该股票的权重为0,即卖出全部股票,可参考回测文档
                context.order_target_percent(context.symbol(instrument), 0)
                # 由于是收盘卖出且开盘买入,因此买入时无需更新当日可用现金,如果是收盘买入开盘卖出则需更新可用现金
                # cash_for_buy += stock_hold_now[instrument]
        # 如果当天没有买入的股票,就返回
        if len(stock_to_buy) == 0:
            return
        
        # 买入
        for instrument in stock_to_buy:
            # 针对当日可用现金使用等资金比例下单买入,整百股数下单
            cash = cash_for_buy / len(stock_to_buy)
            if data.can_trade(context.symbol(instrument)):
                current_price = data.current(context.symbol(instrument), 'price')
                amount = math.floor(cash / current_price / 100) * 100
                context.order(context.symbol(instrument), amount)
        

        回测引擎:准备数据,只执行一次

        def m9_prepare_bigquant_run(context):
        # 加载预测数据
        df = context.options[‘data’].read_df()

        # 函数:求满足开仓条件的股票列表
        def open_pos_con(df):
            return list(df[df['buy_condition']>0].instrument)
        
        # 函数:求满足平仓条件的股票列表
        def close_pos_con(df):
            return list(df[df['sell_condition']>0].instrument)
        
        # 每日买入股票的数据框
        context.daily_stock_buy= df.groupby('date').apply(open_pos_con)
        # 每日卖出股票的数据框
        context.daily_stock_sell= df.groupby('date').apply(close_pos_con)
        

        回测引擎:初始化函数,只执行一次

        def m9_initialize_bigquant_run(context):

        # 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))
        

        m1 = 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

        high_0
        low_0
        close_0
        “”"
        )

        m2 = M.instruments.v2(
        start_date=T.live_run_param(‘trading_date’, ‘2018-01-01’),
        end_date=T.live_run_param(‘trading_date’, ‘2019-01-25’),
        market=‘CN_STOCK_A’,
        instrument_list=""“000021.SZA
        000025.SZA”"",
        max_count=0
        )

        m7 = M.general_feature_extractor.v7(
        instruments=m2.data,
        features=m1.data,
        start_date=’’,
        end_date=’’,
        before_start_days=100
        )

        m10 = M.cached.v3(
        input_1=m7.data,
        run=m10_run_bigquant_run,
        post_run=m10_post_run_bigquant_run,
        input_ports=’’,
        params=’{}’,
        output_ports=’’
        )

        m11 = 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

        buy_condition =where((RSI6<50) & (RSI6>RSI12) & (RSI6>RSI24) & (RSI6_1<RSI12_1) & (RSI6_1<RSI24_1) ,1,0)
        sell_condition=where((RSI6>70) ,1,0)
        “”"
        )

        m8 = M.derived_feature_extractor.v3(
        input_data=m10.data_1,
        features=m11.data,
        date_col=‘date’,
        instrument_col=‘instrument’,
        drop_na=False,
        remove_extra_columns=False
        )

        m6 = M.dropnan.v1(
        input_data=m8.data
        )

        m9 = M.trade.v4(
        instruments=m2.data,
        options_data=m6.data,
        start_date=’’,
        end_date=’’,
        handle_data=m9_handle_data_bigquant_run,
        prepare=m9_prepare_bigquant_run,
        initialize=m9_initialize_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy=‘open’,
        order_price_field_sell=‘close’,
        capital_base=1000000,
        auto_cancel_non_tradable_orders=True,
        data_frequency=‘daily’,
        price_type=‘后复权’,
        product_type=‘股票’,
        plot_charts=True,
        backtest_only=False,
        benchmark=’’
        )


        (smallsnow) #11

        不好意思原因找到了,是被我自己的语句 filter_result = result[result[‘cond’]>0]过滤掉了卖出条件作用的对象集合。