老师您好,我想把TBIL技术指标MACD红柱的信号加入选股中,通过数据过滤应该怎么去构建因子呢?

策略分享
新手专区
标签: #<Tag:0x00007fc4c3c6b3a0> #<Tag:0x00007fc4c3c6b238>

(woshisilvio) #1

https://i.bigquant.com/user/woshisilvio/lab/share/userlib%2F%E8%BF%99%E4%B8%AA%E6%98%AF%E6%88%90%E5%8A%9F%E7%9A%84%E4%BA%A4%E6%98%93%E9%80%BB%E8%BE%91%E7%BB%BC%E5%90%88%E6%A1%88%E4%BE%8B--%E7%A7%BB%E5%8A%A8%E5%8D%8A%E4%BB%93.ipynb?_t=1584708493605

Exception Traceback (most recent call last)
in ()
509 data_row_fraction=1,
510 ndcg_discount_base=1,
–> 511 m_lazy_run=False
512 )
513

Exception: 模型训练失败:可能导致错误的原因是训练数据问题,请检查训练数据, err_code=1 (975ee4a46aac11ea94200a580a80035b)

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":"-404: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-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-329:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-418:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-1918:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-224:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-8068:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-323:input_ds","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-411:input_data","SourceOutputPortId":"-404:data"},{"DestinationInputPortId":"-524:input_data","SourceOutputPortId":"-411:data"},{"DestinationInputPortId":"-425:input_data","SourceOutputPortId":"-418:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-425:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"-8068:model"},{"DestinationInputPortId":"-418:features","SourceOutputPortId":"-318:data"},{"DestinationInputPortId":"-425:features","SourceOutputPortId":"-318:data"},{"DestinationInputPortId":"-329:data2","SourceOutputPortId":"-323:data"},{"DestinationInputPortId":"-202:data1","SourceOutputPortId":"-329:data"},{"DestinationInputPortId":"-404:features","SourceOutputPortId":"-255:data"},{"DestinationInputPortId":"-411:features","SourceOutputPortId":"-255:data"},{"DestinationInputPortId":"-8068:features","SourceOutputPortId":"-255:data"},{"DestinationInputPortId":"-318:features_ds","SourceOutputPortId":"-255:data"},{"DestinationInputPortId":"-224:features","SourceOutputPortId":"-148:data"},{"DestinationInputPortId":"-202:data2","SourceOutputPortId":"-224:data"},{"DestinationInputPortId":"-490:input_ds","SourceOutputPortId":"-202:data"},{"DestinationInputPortId":"-1918:options_data","SourceOutputPortId":"-490:sorted_data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-524:data"},{"DestinationInputPortId":"-255:features_ds","SourceOutputPortId":"-1237:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2014-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2015-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"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-bdf8-104b137c8601-53","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":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2020-03-09","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":13,"Comment":"","CommentCollapsed":true},{"Id":"-86","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-86"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-86","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"Comment":"","CommentCollapsed":true},{"Id":"-404","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":"-404"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-404"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-404","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"Comment":"","CommentCollapsed":true},{"Id":"-411","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":"-411"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-411"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-411","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"Comment":"","CommentCollapsed":true},{"Id":"-418","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":"-418"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-418"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-418","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"Comment":"","CommentCollapsed":true},{"Id":"-425","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":"-425"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-425"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-425","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"Comment":"","CommentCollapsed":true},{"Id":"-1918","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n stock_count = 10\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 = 0.3\n context.options['hold_days'] = 15\n\n from zipline.finance.slippage import SlippageModel\n class FixedPriceSlippage(SlippageModel):\n def process_order(self, data, order, bar_volume=0, trigger_check_price=0):\n if order.limit is None:\n price_field = self._price_field_buy if order.amount > 0 else self._price_field_sell\n price = data.current(order.asset, price_field)\n else:\n price = data.current(order.asset, self._price_field_buy)\n # 返回希望成交的价格和数量\n return (price, order.amount)\n # 设置price_field,默认是开盘买入,收盘卖出\n context.fix_slippage = FixedPriceSlippage(price_field_buy='open', price_field_sell='close')\n context.set_slippage(us_equities=context.fix_slippage)","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 # 获取当前持仓\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.portfolio.positions.items()}\n \n today = data.current_dt.strftime('%Y-%m-%d')\n #获取当日日期\n \n stock_hold_now = [equity.symbol for equity in context.portfolio.positions ]\n #大盘风控模块,读取风控数据 \n benckmark_risk=context.benckmark_risk[today]\n context.symbol\n #当risk为1时,市场有风险,全部平仓,不再执行其它操作\n if benckmark_risk > 0:\n for instrument in stock_hold_now:\n context.order_target(symbol(instrument), 0)\n print(today,'大盘风控止损触发,全仓卖出')\n return\n#--------------------------------------大盘风控结束-------------------------- \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 == today]\n \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 \n \n # 2. 根据需要加入移动止赢止损模块、固定天数卖出模块、ST或退市股卖出模块\n stock_sold = [] # 记录卖出的股票,防止多次卖出出现空单\n \n #------------------------START:止赢止损模块(含建仓期)---------------\n current_stopwin_stock = [] #------把部分冲高回落的票先锁定利润----推高止赚部分---------------当日止赢\n today = data.current_dt \n equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}\n if len(equities) > 0:\n for i in equities.keys():\n stock_market_price = data.current(context.symbol(i), 'price') # 最新市场价格\n last_sale_date = equities[i].last_sale_date # 上次交易日期\n delta_days = today - last_sale_date \n hold_days = delta_days.days # 持仓天数\n \n amount = equities[i].amount\n market_value = amount * stock_market_price \n stock_cost = equities[i].cost_basis\n #------------若处于盈利状态-------的移动止损部分\n #查看 建仓以来的最高价\n highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()\n \n if highest_price_since_buy/stock_cost - 1 <= 0.05: # 保证是冲高回落的股票\n continue\n \n \n # 确定止赢空仓位置 \n stopwin_line_zero = stock_cost + stock_cost * 0.01 # 盈利1%\n \n \n # 确定止赢半仓位置\n stopwin_line_half = highest_price_since_buy - highest_price_since_buy * 0.03 # 回撤3%\n \n \n # 如果价格下穿止损位置\n if stock_market_price < stopwin_line_half:\n context.order_target_value(context.symbol(i), market_value/2) \n current_stopwin_stock.append(i)\n print('日期:', today, '股票:', i, '出现止赢卖出一半仓位状况')\n # 如果价格下穿止损位置\n elif stock_market_price < stopwin_line_zero:\n context.order_target_value(context.symbol(i), 0) \n current_stopwin_stock.append(i)\n print('日期:', today, '股票:', i, '出现止赢卖出全部仓位状况') \n #-------处于亏损状态的--------------止损部分------如果建仓后直接亏损5%则强制止损空仓卖出 \n \n current_stopwin_stock=[]\n current_stoploss_stock = [] \n positions_cost={e.symbol:p.cost_basis for e,p in context.portfolio.positions.items()}\n if len(positions)>0:\n for instrument in positions.keys():\n stock_cost=positions_cost[instrument] \n stock_market_price=data.current(context.symbol(instrument),'price') \n # 赚15%且为可交易状态就止盈\n if stock_market_price/stock_cost-1>=0.15 and data.can_trade(context.symbol(instrument)):\n context.order_target_percent(context.symbol(instrument),0)\n cash_for_sell -= positions[instrument]\n current_stopwin_stock.append(instrument)\n # 亏5%并且为可交易状态就止损\n if stock_market_price/stock_cost-1 <= -0.05 and data.can_trade(context.symbol(instrument)): \n context.order_target_percent(context.symbol(instrument),0)\n cash_for_sell -= positions[instrument]\n current_stoploss_stock.append(instrument)\n if len(current_stopwin_stock)>0:\n print(today,'止盈股票列表',current_stopwin_stock)\n stock_sold += current_stopwin_stock\n if len(current_stoploss_stock)>0:\n print(today,'止损股票列表',current_stoploss_stock)\n stock_sold += current_stoploss_stock\n \n \n #--------------------------END: 止赢止损模块--------------------------\n \n #--------------------------START:持有固定天数卖出(不含建仓期)-----------\n current_stopdays_stock = []\n positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.portfolio.positions.items()}\n # 不是建仓期(在前hold_days属于建仓期)\n if not is_staging:\n for instrument in positions.keys():\n #如果上面的止盈止损已经卖出过了,就不要重复卖出以防止产生空单\n if instrument in stock_sold:\n continue\n # 今天和上次交易的时间相隔hold_days就全部卖出 datetime.timedelta(context.options['hold_days'])也可以换成自己需要的天数,比如datetime.timedelta(5)\n if data.current_dt - positions_lastdate[instrument]>=datetime.timedelta(5) and data.can_trade(context.symbol(instrument)):\n context.order_target_percent(context.symbol(instrument), 0)\n current_stopdays_stock.append(instrument)\n cash_for_sell -= positions[instrument]\n if len(current_stopdays_stock)>0: \n print(today,'固定天数卖出列表',current_stopdays_stock)\n stock_sold += current_stopdays_stock\n #------------------------- END:持有固定天数卖出-----------------------\n \n #-------------------------- START: ST和退市股卖出 --------------------- \n st_stock_list = []\n for instrument in positions.keys():\n try:\n instrument_name = ranker_prediction[ranker_prediction.instrument==instrument].name.values[0]\n # 如果股票状态变为了st或者退市 则卖出\n if 'ST' in instrument_name or '退' in instrument_name:\n if instrument in stock_sold:\n continue\n if data.can_trade(context.symbol(instrument)):\n context.order_target(context.symbol(instrument), 0)\n st_stock_list.append(instrument)\n cash_for_sell -= positions[instrument]\n except:\n continue\n if st_stock_list!=[]:\n print(today,'持仓出现st股/退市股',st_stock_list,'进行卖出处理') \n stock_sold += st_stock_list\n\n #-------------------------- END: ST和退市股卖出 --------------------- \n \n \n # 3. 生成轮仓卖出订单: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 instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in positions)])))\n for instrument in instruments:\n # 如果资金够了就不卖出了\n if cash_for_sell <= 0:\n break\n #防止多个止损条件同时满足,出现多次卖出产生空单\n if instrument in stock_sold:\n continue\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n stock_sold.append(instrument)\n\n # 4. 生成轮仓买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n # 计算今日跌停的股票\n dt_list = list(ranker_prediction[ranker_prediction.price_limit_status_0==1].instrument)\n # 计算今日ST/退市的股票\n st_list = list(ranker_prediction[ranker_prediction.name.str.contains('ST')|ranker_prediction.name.str.contains('退')].instrument)\n # 计算所有禁止买入的股票池\n banned_list = stock_sold+dt_list+st_list\n buy_cash_weights = context.stock_weights\n buy_instruments=[k for k in list(ranker_prediction.instrument) if k not in banned_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 \n\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 #在数据准备函数中一次性计算每日的大盘风控条件相比于在handle中每日计算风控条件可以提高回测速度\n # 多取50天的数据便于计算均值(保证回测的第一天均值不为Nan值),其中context.start_date和context.end_date是回测指定的起始时间和终止时间\n start_date= (pd.to_datetime(context.start_date) - datetime.timedelta(days=50)).strftime('%Y-%m-%d') \n df=DataSource('bar1d_index_CN_STOCK_A').read(start_date=start_date,end_date=context.end_date,fields=['close'])\n benckmark_data=df[df.instrument=='000001.HIX']\n #计算上证指数5日涨幅\n benckmark_data['ret5']=benckmark_data['close']/benckmark_data['close'].shift(5)-1\n #计算大盘风控条件,如果5日涨幅小于-4%则设置风险状态risk为1,否则为0\n benckmark_data['risk'] = np.where(benckmark_data['ret5']<-0.04,1,0)\n #如果5日涨幅大于4\n benckmark_data['risk'] = np.where(benckmark_data['ret5']<-0.04,1,0)\n #修改日期格式为字符串(便于在handle中使用字符串日期索引来查看每日的风险状态)\n benckmark_data['date']=benckmark_data['date'].apply(lambda x:x.strftime('%Y-%m-%d'))\n #设置日期为索引\n benckmark_data.set_index('date',inplace=True)\n #把风控序列输出给全局变量context.benckmark_risk\n context.benckmark_risk=benckmark_data['risk']\n\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"def bigquant_run(context, data):\n # 获取涨跌停状态数据\n df_price_limit_status = context.ranker_prediction.set_index('date')\n today=data.current_dt.strftime('%Y-%m-%d')\n # 得到当前未完成订单\n for orders in get_open_orders().values():\n # 循环,撤销订单\n for _order in orders:\n ins=str(_order.sid.symbol)\n try:\n #判断一下如果当日涨停,则取消卖单\n if df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status_0.ix[today]>2 and _order.amount<0:\n cancel_order(_order)\n print(today,'尾盘涨停取消卖单',ins) \n except:\n continue","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":"1000001","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-1918"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-1918"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-1918"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-1918"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-1918"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-1918","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":4,"Comment":"","CommentCollapsed":true},{"Id":"-8068","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v6","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_row_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"ndcg_discount_base","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"-8068"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-8068"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"-8068"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"-8068"}],"OutputPortsInternal":[{"Name":"model","NodeId":"-8068","OutputType":null},{"Name":"feature_gains","NodeId":"-8068","OutputType":null},{"Name":"m_lazy_run","NodeId":"-8068","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"Comment":"","CommentCollapsed":true},{"Id":"-318","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\nprice_limit_status_0\nclose_0>=mean(close_1,3)\nclose_1>=mean(close_2,3)\nvolume_0>mean(volume_1,3)\n#volume_1<mean(volume_2,3)\n#mf_net_pct_main_0>mean(mf_net_pct_main_0,3)\n#mf_net_amount_0>mean(mf_net_amount_1,3)\nmarket_cap_float_0 < 10000000000","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-318"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-318","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"Comment":"","CommentCollapsed":true},{"Id":"-323","ModuleId":"BigQuantSpace.select_columns.select_columns-v3","ModuleParameters":[{"Name":"columns","Value":"date,instrument,price_limit_status_0","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"reverse_select","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_ds","NodeId":"-323"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"columns_ds","NodeId":"-323"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-323","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"Comment":"","CommentCollapsed":true},{"Id":"-329","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":"-329"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-329"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-329","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"Comment":"","CommentCollapsed":true},{"Id":"-255","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\n\n\n\ncond1=close_0==ts_max(high_0,60)\ncond2=(mean(close_0,3)>mean(close_0,5)) & (mean(close_0,5)>mean(close_0,10))\ncond3=amount_0/shift(amount_0,1)>1.4\n\n\nrank_turn_3 #过去i个交易日的换手率 (turn_i) 排名,=从小到大排名序号/总数\nreturn_3\nreturn_10 #10日累计收益\nreturn_360 #360日累计收益\nreturn_360/market_cap_float_0 #360日累计收益与流通市值比\nwest_netprofit_ftm_0 #一致预测净利润(未来12个月)\nwest_eps_ftm_0\t#一致预测每股收益(未来12个月)\nwest_avgcps_ftm_0\t#一致预测每股现金流(未来12个月)\nlist_board_0 #所在版块\nta_sma_5_0 \nta_sma_10_0\nta_sma_20_0\ndaily_return_4#4天收益\nfs_eps_yoy_0\t#每股收益同比增长率\nrank_fs_cash_ratio_0\t#现金比率,升序百分比排名 \nfs_roe_ttm_0\t#净资产收益率 (TTM)\nfs_net_profit_yoy_0\t#归属母公司股东的净利润同比增长率\nta_macd_macd_12_26_9_0 #MACD\nswing_volatility_5_0 #波动率\nprice_limit_status_1+price_limit_status_2+price_limit_status_3+price_limit_status_4+price_limit_status_5+price_limit_status_6+price_limit_status_7+price_limit_status_8+price_limit_status_9+price_limit_status_10\navg_amount_0/avg_amount_5\nrank_avg_amount_0/rank_avg_amount_5\npe_ttm_0\nrank_avg_mf_net_amount_3\navg_mf_net_amount_3/market_cap_float_0\n# BOLL、成交量相关\n(avg_amount_10/avg_amount_5) * sum((ta_sma_20_0 + 2 * std(close_0, 20)),5) / 5\n(avg_amount_10/avg_amount_5) * sum((ta_sma_20_0 - 2 * std(close_0, 20)),5) / 5\n","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-255"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-255","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":21,"Comment":"","CommentCollapsed":true},{"Id":"-2676","ModuleId":"BigQuantSpace.hyper_rolling_train.hyper_rolling_train-v1","ModuleParameters":[{"Name":"run","Value":"def bigquant_run(\n bq_graph,\n inputs,\n trading_days_market='CN', # 使用那个市场的交易日历, TODO\n train_instruments_mid='m1', # 训练数据 证券代码列表 模块id\n test_instruments_mid='m9', # 测试数据 证券代码列表 模块id\n predict_mid='m8', # 预测 模块id\n trade_mid='m19', # 回测 模块id\n start_date='2014-01-01', # 数据开始日期\n end_date=T.live_run_param('trading_date', '2017-01-01'), # 数据结束日期\n train_update_days=125, # 更新周期,按交易日计算,每多少天更新一次\n train_update_days_for_live=None, #模拟实盘模式下的更新周期,按交易日计算,每多少天更新一次。如果需要在模拟实盘阶段使用不同的模型更新周期,可以设置这个参数\n train_data_min_days=125, # 最小数据天数,按交易日计算,所以第一个滚动的结束日期是 从开始日期到开始日期+最小数据天数\n train_data_max_days=125, # 最大数据天数,按交易日计算,0,表示没有限制,否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期\n rolling_count_for_live=1, #实盘模式下滚动次数,模拟实盘模式下,取最后多少次滚动。一般在模拟实盘模式下,只用到最后一次滚动训练的模型,这里可以设置为1;如果你的滚动训练数据时间段很短,以至于期间可能没有训练数据,这里可以设置大一点。0表示没有限制\n):\n def merge_datasources(input_1):\n df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]\n df = pd.concat(df_list)\n instrument_data = {\n 'start_date': df['date'].min().strftime('%Y-%m-%d'),\n 'end_date': df['date'].max().strftime('%Y-%m-%d'),\n 'instruments': list(set(df['instrument'])),\n }\n return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))\n\n def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):\n # 是否实盘模式\n tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])\n is_live_run = T.live_run_param('trading_date', None) is not None\n\n if is_live_run and train_update_days_for_live:\n train_update_days = train_update_days_for_live\n\n rollings = []\n train_end_date = train_data_min_days\n while train_end_date < len(tdays):\n if train_data_max_days is not None and train_data_max_days > 0:\n train_start_date = max(train_end_date - train_data_max_days, 0)\n else:\n train_start_date = 0\n rollings.append({\n 'train_start_date': tdays[train_start_date].strftime('%Y-%m-%d'),\n 'train_end_date': tdays[train_end_date - 1].strftime('%Y-%m-%d'),\n 'test_start_date': tdays[train_end_date].strftime('%Y-%m-%d'),\n 'test_end_date': tdays[min(train_end_date + train_update_days, len(tdays)) - 1].strftime('%Y-%m-%d'),\n })\n train_end_date += train_update_days\n\n if not rollings:\n raise Exception('没有滚动需要执行,请检查配置')\n\n if is_live_run and rolling_count_for_live:\n rollings = rollings[-rolling_count_for_live:]\n\n return rollings\n\n g = bq_graph\n\n rolling_dates = gen_rolling_dates(\n trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)\n\n # 训练和预测\n results = []\n for rolling in rolling_dates:\n parameters = {}\n # 先禁用回测\n parameters[trade_mid + '.__enabled__'] = False\n parameters[train_instruments_mid + '.start_date'] = rolling['train_start_date']\n parameters[train_instruments_mid + '.end_date'] = rolling['train_end_date']\n parameters[test_instruments_mid + '.start_date'] = rolling['test_start_date']\n parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']\n # print('------ rolling_train:', parameters)\n results.append(g.run(parameters))\n\n # 合并预测结果并回测\n mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].predictions, result[test_instruments_mid].data.read_pickle()['start_date']] for result in results])\n parameters = {}\n parameters['*.__enabled__'] = False\n parameters[trade_mid + '.__enabled__'] = True\n parameters[trade_mid + '.instruments'] = mx.instrument_data\n parameters[trade_mid + '.options_data'] = mx.data\n\n trade = g.run(parameters)\n\n return {'rollings': results, 'trade': trade}\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"run_now","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"bq_graph","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"bq_graph_port","NodeId":"-2676"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-2676"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-2676"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-2676"}],"OutputPortsInternal":[{"Name":"result","NodeId":"-2676","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":23,"Comment":"","CommentCollapsed":true},{"Id":"-148","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\nname","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-148"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-148","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":12,"Comment":"","CommentCollapsed":true},{"Id":"-224","ModuleId":"BigQuantSpace.use_datasource.use_datasource-v1","ModuleParameters":[{"Name":"datasource_id","Value":"instruments_CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-224"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-224"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-224","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":19,"Comment":"","CommentCollapsed":true},{"Id":"-202","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"left","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"-202"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-202"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-202","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":20,"Comment":"","CommentCollapsed":true},{"Id":"-490","ModuleId":"BigQuantSpace.sort.sort-v4","ModuleParameters":[{"Name":"sort_by","Value":"position","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"group_by","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"keep_columns","Value":"--","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"ascending","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_ds","NodeId":"-490"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"sort_by_ds","NodeId":"-490"}],"OutputPortsInternal":[{"Name":"sorted_data","NodeId":"-490","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":22,"Comment":"","CommentCollapsed":true},{"Id":"-524","ModuleId":"BigQuantSpace.filter.filter-v3","ModuleParameters":[{"Name":"expr","Value":"cond1==True and cond2==True and cond3==True ","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_left_data","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-524"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-524","OutputType":null},{"Name":"left_data","NodeId":"-524","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":25,"Comment":"","CommentCollapsed":true},{"Id":"-1237","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\nhigh_0\nopen_0\nlow_0\nclose_0\namount_0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-1237"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-1237","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"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='212.16824340820312,-30.994277954101562,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='79,197,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='293,409,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='782,629,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1113,61,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='364,477,200,200'/><NodePosition Node='-86' Position='1070,475,200,200'/><NodePosition Node='-404' Position='437.6634521484375,158.7794647216797,200,200'/><NodePosition Node='-411' Position='465.276611328125,259.66729736328125,200,200'/><NodePosition Node='-418' Position='1063,267,200,200'/><NodePosition Node='-425' Position='1067,376,200,200'/><NodePosition Node='-1918' Position='1266,954,200,200'/><NodePosition Node='-8068' Position='591,536,200,200'/><NodePosition Node='-318' Position='919,180,200,200'/><NodePosition Node='-323' Position='1109,588,200,200'/><NodePosition Node='-329' Position='1118,698,200,200'/><NodePosition Node='-255' Position='684.1102294921875,24.5047607421875,200,200'/><NodePosition Node='-2676' Position='616,743,200,200'/><NodePosition Node='-148' Position='1520,475,200,200'/><NodePosition Node='-224' Position='1462,578,200,200'/><NodePosition Node='-202' Position='1316,775,200,200'/><NodePosition Node='-490' Position='1322,856,200,200'/><NodePosition Node='-524' Position='468.33270263671875,326.723388671875,200,200'/><NodePosition Node='-1237' Position='706.1241455078125,-105.9647445678711,200,200'/></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 [40]:
    # 本代码由可视化策略环境自动生成 2020年3月20日 21:22
    # 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
    
    
    # 回测引擎:初始化函数,只执行一次
    def m4_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 = 10
        # 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 = 0.3
        context.options['hold_days'] = 15
    
        from zipline.finance.slippage import SlippageModel
        class FixedPriceSlippage(SlippageModel):
            def process_order(self, data, order, bar_volume=0, trigger_check_price=0):
                if order.limit is None:
                    price_field = self._price_field_buy if order.amount > 0 else self._price_field_sell
                    price = data.current(order.asset, price_field)
                else:
                    price = data.current(order.asset, self._price_field_buy)
                # 返回希望成交的价格和数量
                return (price, order.amount)
        # 设置price_field,默认是开盘买入,收盘卖出
        context.fix_slippage = FixedPriceSlippage(price_field_buy='open', price_field_sell='close')
        context.set_slippage(us_equities=context.fix_slippage)
    # 回测引擎:每日数据处理函数,每天执行一次
    def m4_handle_data_bigquant_run(context, data):
        # 获取当前持仓
        positions = {e.symbol: p.amount * p.last_sale_price
                     for e, p in context.portfolio.positions.items()}
        
        today = data.current_dt.strftime('%Y-%m-%d')
        #获取当日日期
       
        stock_hold_now = [equity.symbol for equity in context.portfolio.positions ]
        #大盘风控模块,读取风控数据    
        benckmark_risk=context.benckmark_risk[today]
        context.symbol
        #当risk为1时,市场有风险,全部平仓,不再执行其它操作
        if benckmark_risk > 0:
            for instrument in stock_hold_now:
                context.order_target(symbol(instrument), 0)
            print(today,'大盘风控止损触发,全仓卖出')
            return
    #--------------------------------------大盘风控结束--------------------------    
           # 按日期过滤得到今日的预测数据
        ranker_prediction = context.ranker_prediction[
            context.ranker_prediction.date == today]
        
        
        # 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)
       
        
        # 2. 根据需要加入移动止赢止损模块、固定天数卖出模块、ST或退市股卖出模块
        stock_sold = [] # 记录卖出的股票,防止多次卖出出现空单
        
        #------------------------START:止赢止损模块(含建仓期)---------------
        current_stopwin_stock = [] #------把部分冲高回落的票先锁定利润----推高止赚部分---------------当日止赢
        today = data.current_dt  
        equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
        if len(equities) > 0:
            for i in equities.keys():
                stock_market_price = data.current(context.symbol(i), 'price')  # 最新市场价格
                last_sale_date = equities[i].last_sale_date   # 上次交易日期
                delta_days = today - last_sale_date   
                hold_days = delta_days.days # 持仓天数
                
                amount = equities[i].amount
                market_value = amount * stock_market_price 
                stock_cost =  equities[i].cost_basis
         #------------若处于盈利状态-------的移动止损部分
                #查看 建仓以来的最高价
                highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
                
                if highest_price_since_buy/stock_cost - 1 <= 0.05:   # 保证是冲高回落的股票
                    continue
                
                
                 # 确定止赢空仓位置 
                stopwin_line_zero = stock_cost  +  stock_cost  * 0.01  # 盈利1%
                
                
                 # 确定止赢半仓位置
                stopwin_line_half = highest_price_since_buy - highest_price_since_buy * 0.03  # 回撤3%
               
                
                 # 如果价格下穿止损位置
                if stock_market_price < stopwin_line_half:
                    context.order_target_value(context.symbol(i), market_value/2)     
                    current_stopwin_stock.append(i)
                    print('日期:', today, '股票:', i, '出现止赢卖出一半仓位状况')
                # 如果价格下穿止损位置
                elif stock_market_price < stopwin_line_zero:
                    context.order_target_value(context.symbol(i), 0)     
                    current_stopwin_stock.append(i)
                    print('日期:', today, '股票:', i, '出现止赢卖出全部仓位状况')        
        #-------处于亏损状态的--------------止损部分------如果建仓后直接亏损5%则强制止损空仓卖出        
        
        current_stopwin_stock=[]
        current_stoploss_stock = []   
        positions_cost={e.symbol:p.cost_basis for e,p in context.portfolio.positions.items()}
        if len(positions)>0:
            for instrument in positions.keys():
                stock_cost=positions_cost[instrument]  
                stock_market_price=data.current(context.symbol(instrument),'price')  
                # 赚15%且为可交易状态就止盈
                if stock_market_price/stock_cost-1>=0.15 and data.can_trade(context.symbol(instrument)):
                    context.order_target_percent(context.symbol(instrument),0)
                    cash_for_sell -= positions[instrument]
                    current_stopwin_stock.append(instrument)
                # 亏5%并且为可交易状态就止损
                if stock_market_price/stock_cost-1 <= -0.05 and data.can_trade(context.symbol(instrument)):   
                    context.order_target_percent(context.symbol(instrument),0)
                    cash_for_sell -= positions[instrument]
                    current_stoploss_stock.append(instrument)
            if len(current_stopwin_stock)>0:
                print(today,'止盈股票列表',current_stopwin_stock)
                stock_sold += current_stopwin_stock
            if len(current_stoploss_stock)>0:
                print(today,'止损股票列表',current_stoploss_stock)
                stock_sold += current_stoploss_stock
               
               
        #--------------------------END: 止赢止损模块--------------------------
        
        #--------------------------START:持有固定天数卖出(不含建仓期)-----------
        current_stopdays_stock = []
        positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.portfolio.positions.items()}
        # 不是建仓期(在前hold_days属于建仓期)
        if not is_staging:
            for instrument in positions.keys():
                #如果上面的止盈止损已经卖出过了,就不要重复卖出以防止产生空单
                if instrument in stock_sold:
                    continue
                # 今天和上次交易的时间相隔hold_days就全部卖出 datetime.timedelta(context.options['hold_days'])也可以换成自己需要的天数,比如datetime.timedelta(5)
                if data.current_dt - positions_lastdate[instrument]>=datetime.timedelta(5) and data.can_trade(context.symbol(instrument)):
                    context.order_target_percent(context.symbol(instrument), 0)
                    current_stopdays_stock.append(instrument)
                    cash_for_sell -= positions[instrument]
            if len(current_stopdays_stock)>0:        
                print(today,'固定天数卖出列表',current_stopdays_stock)
                stock_sold += current_stopdays_stock
        #-------------------------  END:持有固定天数卖出-----------------------
        
        #-------------------------- START: ST和退市股卖出 ---------------------  
        st_stock_list = []
        for instrument in positions.keys():
            try:
                instrument_name = ranker_prediction[ranker_prediction.instrument==instrument].name.values[0]
                # 如果股票状态变为了st或者退市 则卖出
                if 'ST' in instrument_name or '退' in instrument_name:
                    if instrument in stock_sold:
                        continue
                    if data.can_trade(context.symbol(instrument)):
                        context.order_target(context.symbol(instrument), 0)
                        st_stock_list.append(instrument)
                        cash_for_sell -= positions[instrument]
            except:
                continue
        if st_stock_list!=[]:
            print(today,'持仓出现st股/退市股',st_stock_list,'进行卖出处理')    
            stock_sold += st_stock_list
    
        #-------------------------- END: ST和退市股卖出 --------------------- 
        
        
        # 3. 生成轮仓卖出订单: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:
            instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                    lambda x: x in positions)])))
            for instrument in instruments:
                # 如果资金够了就不卖出了
                if cash_for_sell <= 0:
                    break
                #防止多个止损条件同时满足,出现多次卖出产生空单
                if instrument in stock_sold:
                    continue
                context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
                stock_sold.append(instrument)
    
        # 4. 生成轮仓买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票
        # 计算今日跌停的股票
        dt_list = list(ranker_prediction[ranker_prediction.price_limit_status_0==1].instrument)
        # 计算今日ST/退市的股票
        st_list = list(ranker_prediction[ranker_prediction.name.str.contains('ST')|ranker_prediction.name.str.contains('退')].instrument)
        # 计算所有禁止买入的股票池
        banned_list = stock_sold+dt_list+st_list
        buy_cash_weights = context.stock_weights
        buy_instruments=[k for k in list(ranker_prediction.instrument) if k not in banned_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 m4_prepare_bigquant_run(context):
        #在数据准备函数中一次性计算每日的大盘风控条件相比于在handle中每日计算风控条件可以提高回测速度
        # 多取50天的数据便于计算均值(保证回测的第一天均值不为Nan值),其中context.start_date和context.end_date是回测指定的起始时间和终止时间
        start_date= (pd.to_datetime(context.start_date) - datetime.timedelta(days=50)).strftime('%Y-%m-%d') 
        df=DataSource('bar1d_index_CN_STOCK_A').read(start_date=start_date,end_date=context.end_date,fields=['close'])
        benckmark_data=df[df.instrument=='000001.HIX']
        #计算上证指数5日涨幅
        benckmark_data['ret5']=benckmark_data['close']/benckmark_data['close'].shift(5)-1
        #计算大盘风控条件,如果5日涨幅小于-4%则设置风险状态risk为1,否则为0
        benckmark_data['risk'] = np.where(benckmark_data['ret5']<-0.04,1,0)
        #如果5日涨幅大于4
        benckmark_data['risk'] = np.where(benckmark_data['ret5']<-0.04,1,0)
        #修改日期格式为字符串(便于在handle中使用字符串日期索引来查看每日的风险状态)
        benckmark_data['date']=benckmark_data['date'].apply(lambda x:x.strftime('%Y-%m-%d'))
        #设置日期为索引
        benckmark_data.set_index('date',inplace=True)
        #把风控序列输出给全局变量context.benckmark_risk
        context.benckmark_risk=benckmark_data['risk']
    
    
    def m4_before_trading_start_bigquant_run(context, data):
        # 获取涨跌停状态数据
        df_price_limit_status = context.ranker_prediction.set_index('date')
        today=data.current_dt.strftime('%Y-%m-%d')
        # 得到当前未完成订单
        for orders in get_open_orders().values():
            # 循环,撤销订单
            for _order in orders:
                ins=str(_order.sid.symbol)
                try:
                    #判断一下如果当日涨停,则取消卖单
                    if  df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status_0.ix[today]>2 and _order.amount<0:
                        cancel_order(_order)
                        print(today,'尾盘涨停取消卖单',ins) 
                except:
                    continue
    
    g = T.Graph({
    
        'm1': 'M.instruments.v2',
        'm1.start_date': '2014-01-01',
        'm1.end_date': '2015-01-01',
        'm1.market': 'CN_STOCK_A',
        'm1.instrument_list': '',
        'm1.max_count': 0,
    
        'm2': 'M.advanced_auto_labeler.v2',
        'm2.instruments': T.Graph.OutputPort('m1.data'),
        'm2.label_expr': """# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
    #   添加benchmark_前缀,可使用对应的benchmark数据
    # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -5) / shift(open, -1)
    
    # 极值处理:用1%和99%分位的值做clip
    clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
    
    # 将分数映射到分类,这里使用20个分类
    all_wbins(label, 20)
    
    # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
    where(shift(high, -1) == shift(low, -1), NaN, label)
    """,
        'm2.start_date': '',
        'm2.end_date': '',
        'm2.benchmark': '000300.SHA',
        'm2.drop_na_label': True,
        'm2.cast_label_int': True,
    
        'm9': 'M.instruments.v2',
        'm9.start_date': T.live_run_param('trading_date', '2017-01-01'),
        'm9.end_date': T.live_run_param('trading_date', '2020-03-09'),
        'm9.market': 'CN_STOCK_A',
        'm9.instrument_list': '',
        'm9.max_count': 0,
    
        'm12': 'M.input_features.v1',
        'm12.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
    name""",
    
        'm19': 'M.use_datasource.v1',
        'm19.instruments': T.Graph.OutputPort('m9.data'),
        'm19.features': T.Graph.OutputPort('m12.data'),
        'm19.datasource_id': 'instruments_CN_STOCK_A',
        'm19.start_date': '',
        'm19.end_date': '',
    
        'm3': 'M.input_features.v1',
        'm3.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
    high_0
    open_0
    low_0
    close_0
    amount_0""",
    
        'm21': 'M.input_features.v1',
        'm21.features_ds': T.Graph.OutputPort('m3.data'),
        'm21.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
    
    
    
    cond1=close_0==ts_max(high_0,60)
    cond2=(mean(close_0,3)>mean(close_0,5)) & (mean(close_0,5)>mean(close_0,10))
    cond3=amount_0/shift(amount_0,1)>1.4
    
    
    rank_turn_3 #过去i个交易日的换手率 (turn_i) 排名,=从小到大排名序号/总数
    return_3
    return_10 #10日累计收益
    return_360 #360日累计收益
    return_360/market_cap_float_0 #360日累计收益与流通市值比
    west_netprofit_ftm_0 #一致预测净利润(未来12个月)
    west_eps_ftm_0	#一致预测每股收益(未来12个月)
    west_avgcps_ftm_0	#一致预测每股现金流(未来12个月)
    list_board_0 #所在版块
    ta_sma_5_0 
    ta_sma_10_0
    ta_sma_20_0
    daily_return_4#4天收益
    fs_eps_yoy_0	#每股收益同比增长率
    rank_fs_cash_ratio_0	#现金比率,升序百分比排名 
    fs_roe_ttm_0	#净资产收益率 (TTM)
    fs_net_profit_yoy_0	#归属母公司股东的净利润同比增长率
    ta_macd_macd_12_26_9_0 #MACD
    swing_volatility_5_0 #波动率
    price_limit_status_1+price_limit_status_2+price_limit_status_3+price_limit_status_4+price_limit_status_5+price_limit_status_6+price_limit_status_7+price_limit_status_8+price_limit_status_9+price_limit_status_10
    avg_amount_0/avg_amount_5
    rank_avg_amount_0/rank_avg_amount_5
    pe_ttm_0
    rank_avg_mf_net_amount_3
    avg_mf_net_amount_3/market_cap_float_0
    # BOLL、成交量相关
    (avg_amount_10/avg_amount_5) * sum((ta_sma_20_0 + 2 * std(close_0, 20)),5) / 5
    (avg_amount_10/avg_amount_5) * sum((ta_sma_20_0 - 2 * std(close_0, 20)),5) / 5
    """,
    
        'm15': 'M.general_feature_extractor.v7',
        'm15.instruments': T.Graph.OutputPort('m1.data'),
        'm15.features': T.Graph.OutputPort('m21.data'),
        'm15.start_date': '',
        'm15.end_date': '',
        'm15.before_start_days': 0,
    
        'm16': 'M.derived_feature_extractor.v3',
        'm16.input_data': T.Graph.OutputPort('m15.data'),
        'm16.features': T.Graph.OutputPort('m21.data'),
        'm16.date_col': 'date',
        'm16.instrument_col': 'instrument',
        'm16.drop_na': False,
        'm16.remove_extra_columns': False,
    
        'm25': 'M.filter.v3',
        'm25.input_data': T.Graph.OutputPort('m16.data'),
        'm25.expr': 'cond1==True and cond2==True and cond3==True ',
        'm25.output_left_data': False,
    
        'm7': 'M.join.v3',
        'm7.data1': T.Graph.OutputPort('m2.data'),
        'm7.data2': T.Graph.OutputPort('m25.data'),
        'm7.on': 'date,instrument',
        'm7.how': 'inner',
        'm7.sort': False,
    
        'm13': 'M.dropnan.v1',
        'm13.input_data': T.Graph.OutputPort('m7.data'),
    
        'm5': 'M.stock_ranker_train.v6',
        'm5.training_ds': T.Graph.OutputPort('m13.data'),
        'm5.features': T.Graph.OutputPort('m21.data'),
        'm5.learning_algorithm': '排序',
        'm5.number_of_leaves': 30,
        'm5.minimum_docs_per_leaf': 1000,
        'm5.number_of_trees': 20,
        'm5.learning_rate': 0.1,
        'm5.max_bins': 1023,
        'm5.feature_fraction': 1,
        'm5.data_row_fraction': 1,
        'm5.ndcg_discount_base': 1,
        'm5.m_lazy_run': False,
    
        'm6': 'M.input_features.v1',
        'm6.features_ds': T.Graph.OutputPort('m21.data'),
        'm6.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
    price_limit_status_0
    close_0>=mean(close_1,3)
    close_1>=mean(close_2,3)
    volume_0>mean(volume_1,3)
    #volume_1<mean(volume_2,3)
    #mf_net_pct_main_0>mean(mf_net_pct_main_0,3)
    #mf_net_amount_0>mean(mf_net_amount_1,3)
    market_cap_float_0 < 10000000000""",
    
        'm17': 'M.general_feature_extractor.v7',
        'm17.instruments': T.Graph.OutputPort('m9.data'),
        'm17.features': T.Graph.OutputPort('m6.data'),
        'm17.start_date': '',
        'm17.end_date': '',
        'm17.before_start_days': 0,
    
        'm18': 'M.derived_feature_extractor.v3',
        'm18.input_data': T.Graph.OutputPort('m17.data'),
        'm18.features': T.Graph.OutputPort('m6.data'),
        'm18.date_col': 'date',
        'm18.instrument_col': 'instrument',
        'm18.drop_na': False,
        'm18.remove_extra_columns': False,
    
        'm14': 'M.dropnan.v1',
        'm14.input_data': T.Graph.OutputPort('m18.data'),
    
        'm8': 'M.stock_ranker_predict.v5',
        'm8.model': T.Graph.OutputPort('m5.model'),
        'm8.data': T.Graph.OutputPort('m14.data'),
        'm8.m_lazy_run': False,
    
        'm10': 'M.select_columns.v3',
        'm10.input_ds': T.Graph.OutputPort('m14.data'),
        'm10.columns': 'date,instrument,price_limit_status_0',
        'm10.reverse_select': False,
    
        'm11': 'M.join.v3',
        'm11.data1': T.Graph.OutputPort('m8.predictions'),
        'm11.data2': T.Graph.OutputPort('m10.data'),
        'm11.on': 'date,instrument',
        'm11.how': 'inner',
        'm11.sort': False,
    
        'm20': 'M.join.v3',
        'm20.data1': T.Graph.OutputPort('m11.data'),
        'm20.data2': T.Graph.OutputPort('m19.data'),
        'm20.on': 'date,instrument',
        'm20.how': 'left',
        'm20.sort': True,
    
        'm22': 'M.sort.v4',
        'm22.input_ds': T.Graph.OutputPort('m20.data'),
        'm22.sort_by': 'position',
        'm22.group_by': 'date',
        'm22.keep_columns': '--',
        'm22.ascending': True,
    
        'm4': 'M.trade.v4',
        'm4.instruments': T.Graph.OutputPort('m9.data'),
        'm4.options_data': T.Graph.OutputPort('m22.sorted_data'),
        'm4.start_date': '',
        'm4.end_date': '',
        'm4.initialize': m4_initialize_bigquant_run,
        'm4.handle_data': m4_handle_data_bigquant_run,
        'm4.prepare': m4_prepare_bigquant_run,
        'm4.before_trading_start': m4_before_trading_start_bigquant_run,
        'm4.volume_limit': 0.025,
        'm4.order_price_field_buy': 'open',
        'm4.order_price_field_sell': 'close',
        'm4.capital_base': 1000001,
        'm4.auto_cancel_non_tradable_orders': True,
        'm4.data_frequency': 'daily',
        'm4.price_type': '后复权',
        'm4.product_type': '股票',
        'm4.plot_charts': True,
        'm4.backtest_only': False,
        'm4.benchmark': '',
    })
    
    # g.run({})
    
    
    def m23_run_bigquant_run(
        bq_graph,
        inputs,
        trading_days_market='CN', # 使用那个市场的交易日历, TODO
        train_instruments_mid='m1', # 训练数据 证券代码列表 模块id
        test_instruments_mid='m9', # 测试数据 证券代码列表 模块id
        predict_mid='m8', # 预测 模块id
        trade_mid='m19', # 回测 模块id
        start_date='2014-01-01', # 数据开始日期
        end_date=T.live_run_param('trading_date', '2017-01-01'), # 数据结束日期
        train_update_days=125, # 更新周期,按交易日计算,每多少天更新一次
        train_update_days_for_live=None, #模拟实盘模式下的更新周期,按交易日计算,每多少天更新一次。如果需要在模拟实盘阶段使用不同的模型更新周期,可以设置这个参数
        train_data_min_days=125, # 最小数据天数,按交易日计算,所以第一个滚动的结束日期是 从开始日期到开始日期+最小数据天数
        train_data_max_days=125, # 最大数据天数,按交易日计算,0,表示没有限制,否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期
        rolling_count_for_live=1, #实盘模式下滚动次数,模拟实盘模式下,取最后多少次滚动。一般在模拟实盘模式下,只用到最后一次滚动训练的模型,这里可以设置为1;如果你的滚动训练数据时间段很短,以至于期间可能没有训练数据,这里可以设置大一点。0表示没有限制
    ):
        def merge_datasources(input_1):
            df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]
            df = pd.concat(df_list)
            instrument_data = {
                'start_date': df['date'].min().strftime('%Y-%m-%d'),
                'end_date': df['date'].max().strftime('%Y-%m-%d'),
                'instruments': list(set(df['instrument'])),
            }
            return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))
    
        def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):
            # 是否实盘模式
            tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])
            is_live_run = T.live_run_param('trading_date', None) is not None
    
            if is_live_run and train_update_days_for_live:
                train_update_days = train_update_days_for_live
    
            rollings = []
            train_end_date = train_data_min_days
            while train_end_date < len(tdays):
                if train_data_max_days is not None and train_data_max_days > 0:
                    train_start_date = max(train_end_date - train_data_max_days, 0)
                else:
                    train_start_date = 0
                rollings.append({
                    'train_start_date': tdays[train_start_date].strftime('%Y-%m-%d'),
                    'train_end_date': tdays[train_end_date - 1].strftime('%Y-%m-%d'),
                    'test_start_date': tdays[train_end_date].strftime('%Y-%m-%d'),
                    'test_end_date': tdays[min(train_end_date + train_update_days, len(tdays)) - 1].strftime('%Y-%m-%d'),
                })
                train_end_date += train_update_days
    
            if not rollings:
                raise Exception('没有滚动需要执行,请检查配置')
    
            if is_live_run and rolling_count_for_live:
                rollings = rollings[-rolling_count_for_live:]
    
            return rollings
    
        g = bq_graph
    
        rolling_dates = gen_rolling_dates(
            trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)
    
        # 训练和预测
        results = []
        for rolling in rolling_dates:
            parameters = {}
            # 先禁用回测
            parameters[trade_mid + '.__enabled__'] = False
            parameters[train_instruments_mid + '.start_date'] = rolling['train_start_date']
            parameters[train_instruments_mid + '.end_date'] = rolling['train_end_date']
            parameters[test_instruments_mid + '.start_date'] = rolling['test_start_date']
            parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']
            # print('------ rolling_train:', parameters)
            results.append(g.run(parameters))
    
        # 合并预测结果并回测
        mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].predictions, result[test_instruments_mid].data.read_pickle()['start_date']] for result in results])
        parameters = {}
        parameters['*.__enabled__'] = False
        parameters[trade_mid + '.__enabled__'] = True
        parameters[trade_mid + '.instruments'] = mx.instrument_data
        parameters[trade_mid + '.options_data'] = mx.data
    
        trade = g.run(parameters)
    
        return {'rollings': results, 'trade': trade}
    
    
    m23 = M.hyper_rolling_train.v1(
        run=m23_run_bigquant_run,
        run_now=True,
        bq_graph=g
    )
    

    StockRanker训练(GBDT)(stock_ranker_train)使用错误,你可以:

    1.一键查看文档

    2.一键搜索答案

    ---------------------------------------------------------------------------
    Exception                                 Traceback (most recent call last)
    <ipython-input-40-51a83a608633> in <module>()
        140     data_row_fraction=1,
        141     ndcg_discount_base=1,
    --> 142     m_lazy_run=False
        143 )
    
    Exception: 模型训练失败:可能导致错误的原因是训练数据问题,请检查训练数据, err_code=1 (c36137fe6aad11ea94200a580a80035b)

    (dujianmin1974) #2

    我把你的训练时间修改了一下 可以运行了 但是不明白 为啥你的训练数据和预测数据的模型的特征因子为啥不一样。可能我理解的有误差吧