复制链接
克隆策略
移动止损功能¶
版本v1.0
在开发策略时，经常使用个股的固定点位/百分比止盈止损功能。
本策略以买入后最高价下跌10%止损为例，介绍移动止损功能的实现步骤：
1、新建AI可视化模板策略
2、在回测/模拟模块m19的属性栏中进入“主函数”代码框，在函数体最前面插入移动止损的相关代码，详见策略
初始化变量stoploss_stock用来记录移动止损卖出的股票，
针对持仓的股票计算买入以来的最高价，并计算最新价相比最高价的回撤百分比，如果下跌超过10%就止损卖出，同时将股票添加到stoploss_stock变量：
3、在回测/模拟模块m19的属性栏中进入“主函数”代码框，在函数体中找到“# 2. 生成卖出订单”位置，
在上方初始化 sell_stock 列表用来记录轮仓卖出的股票；
在下方轮仓卖出代码 context.order_target(context.symbol(instrument), 0) 前加入判断语句：
#如果已经移动止损卖出过则不再轮仓卖出,以防止出现空头持仓 if instrument in stoploss_stock:
continue
4、在回测/模拟模块m19的属性栏中进入“主函数”代码框，在函数体中找到“# 3. 生成买入订单”位置，将原有的buy_instruments一行代码改为如下：
# 获取所有排序结果股票列表
buy_list = list(ranker_prediction.instrument)
# 不再买入已经移动止损和轮仓卖出的股票,以防止出现空头持仓
buy_instruments = [i for i in buy_list if i not in sell_stock + stoploss_stock][:len(buy_cash_weights)]
{"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-2744:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"to_node_id":"-2744:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-2751:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-2758:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-2765:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-1260:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-149:input_1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-2775:options_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"to_node_id":"-2758:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-2775:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-2751:input_data","from_node_id":"-2744:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-2751:data"},{"to_node_id":"-2765:input_data","from_node_id":"-2758:data"},{"to_node_id":"-495:input_1","from_node_id":"-2765:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","from_node_id":"-1260:model"},{"to_node_id":"-1260:training_ds","from_node_id":"-1274:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","from_node_id":"-1278:data"},{"to_node_id":"-136:input_1","from_node_id":"-149:data_1"},{"to_node_id":"-1274:input_data","from_node_id":"-136:data_1"},{"to_node_id":"-498:input_1","from_node_id":"-495:data_1"},{"to_node_id":"-1278:input_data","from_node_id":"-498:data_1"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2022-04-15","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"cacheable":true,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","module_id":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","parameters":[{"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","type":"Literal","bound_global_parameter":null},{"name":"start_date","value":"2020-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2022-04-15","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.SHA","type":"Literal","bound_global_parameter":null},{"name":"drop_na_label","value":"True","type":"Literal","bound_global_parameter":null},{"name":"cast_label_int","value":"True","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"cacheable":true,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"# #号开始的表示注释\n# 多个特征，每行一个，可以包含基础特征和衍生特征\nreturn_5\nreturn_10\nreturn_20\navg_amount_0/avg_amount_5\navg_amount_5/avg_amount_20\nrank_avg_amount_0/rank_avg_amount_5\nrank_avg_amount_5/rank_avg_amount_10\nrank_return_0\nrank_return_5\nrank_return_10\nrank_return_0/rank_return_5\nrank_return_5/rank_return_10\npe_ttm_0\n","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"cacheable":true,"seq_num":3,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","module_id":"BigQuantSpace.join.join-v3","parameters":[{"name":"on","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"how","value":"inner","type":"Literal","bound_global_parameter":null},{"name":"sort","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"data1","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"name":"data2","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","module_id":"BigQuantSpace.stock_ranker_predict.stock_ranker_predict-v5","parameters":[{"name":"m_lazy_run","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"model","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"output_ports":[{"name":"predictions","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"name":"m_lazy_run","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"cacheable":true,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2022-04-15","type":"Literal","bound_global_parameter":"交易日期"},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"cacheable":true,"seq_num":9,"comment":"预测数据，用于回测和模拟","comment_collapsed":false},{"node_id":"-2744","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2022-04-15","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-2744"},{"name":"features","node_id":"-2744"}],"output_ports":[{"name":"data","node_id":"-2744"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-2751","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-2751"},{"name":"features","node_id":"-2751"}],"output_ports":[{"name":"data","node_id":"-2751"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-2758","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2022-04-15","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":"60","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-2758"},{"name":"features","node_id":"-2758"}],"output_ports":[{"name":"data","node_id":"-2758"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-2765","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-2765"},{"name":"features","node_id":"-2765"}],"output_ports":[{"name":"data","node_id":"-2765"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-2775","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2022-04-15","type":"Literal","bound_global_parameter":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=0.00012, sell_cost=0.00112, 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 = 0.1\n context.options['hold_days'] = 5\n","type":"Literal","bound_global_parameter":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 \n today = data.current_dt.strftime('%Y-%m-%d')\n \n #------------------------------------------止损模块START--------------------------------------------\n equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}\n \n # 新建当日止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断\n stoploss_stock = [] \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 = data.current_dt - last_sale_date \n hold_days = delta_days.days # 持仓天数\n # 建仓以来的最高价\n highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()\n # 确定止损位置\n stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.1\n #record('止损位置', stoploss_line)\n # 如果价格下穿止损位置\n if stock_market_price < stoploss_line:\n context.order_target_percent(context.symbol(i), 0) \n stoploss_stock.append(i)\n if len(stoploss_stock)>0:\n print('日期：', today, '股票：', stoploss_stock, '出现跟踪止损状况')\n #-------------------------------------------止损模块END--------------------------------------------- \n \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 sell_stock = []\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 for instrument in instruments:\n # 如果已经移动止损卖出过则不再轮仓卖出,以防止出现空头持仓\n if instrument in stoploss_stock:\n continue\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n # 记录轮仓卖出的股票\n sell_stock.append(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_list = list(ranker_prediction.instrument)\n # 不再买入已经轮仓卖出和移动止损的股票,以防止出现空头持仓\n buy_instruments = [i for i in buy_list if i not in sell_stock + stoploss_stock][: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","type":"Literal","bound_global_parameter":null},{"name":"prepare","value":"# 回测引擎：准备数据，只执行一次\ndef bigquant_run(context):\n pass\n","type":"Literal","bound_global_parameter":null},{"name":"before_trading_start","value":"","type":"Literal","bound_global_parameter":null},{"name":"volume_limit","value":0.025,"type":"Literal","bound_global_parameter":null},{"name":"order_price_field_buy","value":"twap_1","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"twap_8","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":1000000,"type":"Literal","bound_global_parameter":null},{"name":"auto_cancel_non_tradable_orders","value":"True","type":"Literal","bound_global_parameter":null},{"name":"data_frequency","value":"daily","type":"Literal","bound_global_parameter":null},{"name":"price_type","value":"真实价格","type":"Literal","bound_global_parameter":null},{"name":"product_type","value":"股票","type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"backtest_only","value":"False","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.HIX","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-2775"},{"name":"options_data","node_id":"-2775"},{"name":"history_ds","node_id":"-2775"},{"name":"benchmark_ds","node_id":"-2775"},{"name":"trading_calendar","node_id":"-2775"}],"output_ports":[{"name":"raw_perf","node_id":"-2775"}],"cacheable":false,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-1260","module_id":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v6","parameters":[{"name":"learning_algorithm","value":"排序","type":"Literal","bound_global_parameter":null},{"name":"number_of_leaves","value":30,"type":"Literal","bound_global_parameter":null},{"name":"minimum_docs_per_leaf","value":1000,"type":"Literal","bound_global_parameter":null},{"name":"number_of_trees","value":20,"type":"Literal","bound_global_parameter":null},{"name":"learning_rate","value":0.1,"type":"Literal","bound_global_parameter":null},{"name":"max_bins","value":1023,"type":"Literal","bound_global_parameter":null},{"name":"feature_fraction","value":1,"type":"Literal","bound_global_parameter":null},{"name":"data_row_fraction","value":1,"type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"ndcg_discount_base","value":1,"type":"Literal","bound_global_parameter":null},{"name":"m_lazy_run","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"training_ds","node_id":"-1260"},{"name":"features","node_id":"-1260"},{"name":"test_ds","node_id":"-1260"},{"name":"base_model","node_id":"-1260"}],"output_ports":[{"name":"model","node_id":"-1260"},{"name":"feature_gains","node_id":"-1260"},{"name":"m_lazy_run","node_id":"-1260"}],"cacheable":true,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-1274","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-1274"},{"name":"features","node_id":"-1274"}],"output_ports":[{"name":"data","node_id":"-1274"}],"cacheable":true,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-1278","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-1278"},{"name":"features","node_id":"-1278"}],"output_ports":[{"name":"data","node_id":"-1278"}],"cacheable":true,"seq_num":10,"comment":"","comment_collapsed":true},{"node_id":"-149","module_id":"BigQuantSpace.filtet_st_stock.filtet_st_stock-v2","parameters":[],"input_ports":[{"name":"input_1","node_id":"-149"}],"output_ports":[{"name":"data_1","node_id":"-149"}],"cacheable":true,"seq_num":6,"comment":"","comment_collapsed":true},{"node_id":"-136","module_id":"BigQuantSpace.filter_delist_stock.filter_delist_stock-v4","parameters":[],"input_ports":[{"name":"input_1","node_id":"-136"}],"output_ports":[{"name":"data_1","node_id":"-136"}],"cacheable":true,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-495","module_id":"BigQuantSpace.filtet_st_stock.filtet_st_stock-v2","parameters":[],"input_ports":[{"name":"input_1","node_id":"-495"}],"output_ports":[{"name":"data_1","node_id":"-495"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-498","module_id":"BigQuantSpace.filter_delist_stock.filter_delist_stock-v4","parameters":[],"input_ports":[{"name":"input_1","node_id":"-498"}],"output_ports":[{"name":"data_1","node_id":"-498"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='208,66,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,183,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='765,21,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='846,744,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1074,127,200,200'/><node_position Node='-2744' Position='381,188,200,200'/><node_position Node='-2751' Position='385,280,200,200'/><node_position Node='-2758' Position='1078,236,200,200'/><node_position Node='-2765' Position='1081,327,200,200'/><node_position Node='-2775' Position='875,908,200,200'/><node_position Node='-1260' Position='553,630,200,200'/><node_position Node='-1274' Position='349,560,200,200'/><node_position Node='-1278' Position='1133,534,200,200'/><node_position Node='-149' Position='59,458,200,200'/><node_position Node='-136' Position='55,545,200,200'/><node_position Node='-495' Position='847,402,200,200'/><node_position Node='-498' Position='845,479,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
In [2]:
# 本代码由可视化策略环境自动生成 2022年4月18日 15:58
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。
# 回测引擎：初始化函数，只执行一次
def m19_initialize_bigquant_run(context):
# 加载预测数据
context.ranker_prediction = context.options['data'].read_df()
# 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
context.set_commission(PerOrder(buy_cost=0.00012, sell_cost=0.00112, 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 = 0.1
context.options['hold_days'] = 5
# 回测引擎：每日数据处理函数，每天执行一次
def m19_handle_data_bigquant_run(context, data):
today = data.current_dt.strftime('%Y-%m-%d')
#------------------------------------------止损模块START--------------------------------------------
equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
# 新建当日止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
stoploss_stock = []
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 = data.current_dt - last_sale_date
hold_days = delta_days.days # 持仓天数
# 建仓以来的最高价
highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
# 确定止损位置
stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.1
#record('止损位置', stoploss_line)
# 如果价格下穿止损位置
if stock_market_price < stoploss_line:
context.order_target_percent(context.symbol(i), 0)
stoploss_stock.append(i)
if len(stoploss_stock)>0:
print('日期：', today, '股票：', stoploss_stock, '出现跟踪止损状况')
#-------------------------------------------止损模块END---------------------------------------------
# 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()}
sell_stock = []
# 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]))])))
for instrument in instruments:
# 如果已经移动止损卖出过则不再轮仓卖出,以防止出现空头持仓
if instrument in stoploss_stock:
continue
context.order_target(context.symbol(instrument), 0)
cash_for_sell -= positions[instrument]
# 记录轮仓卖出的股票
sell_stock.append(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_list = list(ranker_prediction.instrument)
# 不再买入已经轮仓卖出和移动止损的股票,以防止出现空头持仓
buy_instruments = [i for i in buy_list if i not in sell_stock + stoploss_stock][:len(buy_cash_weights)]
max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
for i, instrument in enumerate(buy_instruments):
cash = cash_for_buy * buy_cash_weights[i]
if cash > max_cash_per_instrument - positions.get(instrument, 0):
# 确保股票持仓量不会超过每次股票最大的占用资金量
cash = max_cash_per_instrument - positions.get(instrument, 0)
if cash > 0:
context.order_value(context.symbol(instrument), cash)
# 回测引擎：准备数据，只执行一次
def m19_prepare_bigquant_run(context):
pass
m1 = M.instruments.v2(
start_date='2021-01-01',
end_date='2022-04-15',
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='2020-01-01',
end_date='2022-04-15',
benchmark='000300.SHA',
drop_na_label=True,
cast_label_int=True
)
m3 = M.input_features.v1(
features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
return_5
return_10
return_20
avg_amount_0/avg_amount_5
avg_amount_5/avg_amount_20
rank_avg_amount_0/rank_avg_amount_5
rank_avg_amount_5/rank_avg_amount_10
rank_return_0
rank_return_5
rank_return_10
rank_return_0/rank_return_5
rank_return_5/rank_return_10
pe_ttm_0
"""
)
m15 = M.general_feature_extractor.v7(
instruments=m1.data,
features=m3.data,
start_date='2021-01-01',
end_date='2022-04-15',
before_start_days=0
)
m16 = M.derived_feature_extractor.v3(
input_data=m15.data,
features=m3.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m7 = M.join.v3(
data1=m2.data,
data2=m16.data,
on='date,instrument',
how='inner',
sort=False
)
m6 = M.filtet_st_stock.v2(
input_1=m7.data
)
m11 = M.filter_delist_stock.v4(
input_1=m6.data_1
)
m5 = M.dropnan.v2(
input_data=m11.data_1
)
m4 = M.stock_ranker_train.v6(
training_ds=m5.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,
data_row_fraction=1,
plot_charts=True,
ndcg_discount_base=1,
m_lazy_run=False
)
m9 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2021-01-01'),
end_date=T.live_run_param('trading_date', '2022-04-15'),
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m17 = M.general_feature_extractor.v7(
instruments=m9.data,
features=m3.data,
start_date='2021-01-01',
end_date='2022-04-15',
before_start_days=60
)
m18 = M.derived_feature_extractor.v3(
input_data=m17.data,
features=m3.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m12 = M.filtet_st_stock.v2(
input_1=m18.data
)
m13 = M.filter_delist_stock.v4(
input_1=m12.data_1
)
m10 = M.dropnan.v2(
input_data=m13.data_1
)
m8 = M.stock_ranker_predict.v5(
model=m4.model,
data=m10.data,
m_lazy_run=False
)
m19 = M.trade.v4(
instruments=m9.data,
options_data=m8.predictions,
start_date='2021-01-01',
end_date='2022-04-15',
initialize=m19_initialize_bigquant_run,
handle_data=m19_handle_data_bigquant_run,
prepare=m19_prepare_bigquant_run,
volume_limit=0.025,
order_price_field_buy='twap_1',
order_price_field_sell='twap_8',
capital_base=1000000,
auto_cancel_non_tradable_orders=True,
data_frequency='daily',
price_type='真实价格',
product_type='股票',
plot_charts=True,
backtest_only=False,
benchmark='000300.HIX'
)
日志 109 条，错误日志
2 条
[2022-04-18 15:47:53.195418] INFO: moduleinvoker: instruments.v2 开始运行..
[2022-04-18 15:47:53.377555] INFO: moduleinvoker: 命中缓存
[2022-04-18 15:47:53.379484] INFO: moduleinvoker: instruments.v2 运行完成[0.184097s].
[2022-04-18 15:47:53.390203] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..
[2022-04-18 15:47:55.452809] INFO: 自动标注(股票): 加载历史数据: 2322561 行
[2022-04-18 15:47:55.454415] INFO: 自动标注(股票): 开始标注 ..
[2022-04-18 15:47:58.099070] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[4.708863s].
[2022-04-18 15:47:58.104956] INFO: moduleinvoker: input_features.v1 开始运行..
[2022-04-18 15:47:58.112256] INFO: moduleinvoker: 命中缓存
[2022-04-18 15:47:58.113925] INFO: moduleinvoker: input_features.v1 运行完成[0.008983s].
[2022-04-18 15:47:58.131602] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2022-04-18 15:47:58.142188] INFO: moduleinvoker: 命中缓存
[2022-04-18 15:47:58.143980] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012397s].
[2022-04-18 15:47:58.159083] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2022-04-18 15:47:58.169843] INFO: moduleinvoker: 命中缓存
[2022-04-18 15:47:58.171637] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.012567s].
[2022-04-18 15:47:58.182990] INFO: moduleinvoker: join.v3 开始运行..
[2022-04-18 15:48:06.547195] INFO: join: /y_2021, 行数=1058571/1061527, 耗时=4.529054s
[2022-04-18 15:48:08.246080] INFO: join: /y_2022, 行数=291666/316265, 耗时=1.690485s
[2022-04-18 15:48:08.359442] INFO: join: 最终行数: 1350237
[2022-04-18 15:48:08.378302] INFO: moduleinvoker: join.v3 运行完成[10.195302s].
[2022-04-18 15:48:08.400974] INFO: moduleinvoker: filtet_st_stock.v2 开始运行..
[2022-04-18 15:48:14.384238] INFO: moduleinvoker: filtet_st_stock.v2 运行完成[5.983204s].
[2022-04-18 15:48:14.420560] INFO: moduleinvoker: filter_delist_stock.v4 开始运行..
[2022-04-18 15:48:20.490596] INFO: moduleinvoker: filter_delist_stock.v4 运行完成[6.070059s].
[2022-04-18 15:48:20.503482] INFO: moduleinvoker: dropnan.v2 开始运行..
[2022-04-18 15:48:23.861353] INFO: dropnan: /data, 1281741/1295066
[2022-04-18 15:48:23.954944] INFO: dropnan: 行数: 1281741/1295066
[2022-04-18 15:48:23.982335] INFO: moduleinvoker: dropnan.v2 运行完成[3.478843s].
[2022-04-18 15:48:23.995547] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..
[2022-04-18 15:48:25.861691] INFO: StockRanker: 特征预处理 ..
[2022-04-18 15:48:27.984751] INFO: StockRanker: prepare data: training ..
[2022-04-18 15:48:30.187839] INFO: StockRanker: sort ..
[2022-04-18 15:48:48.118921] INFO: StockRanker训练: ecbdd802 准备训练: 1281741 行数
[2022-04-18 15:48:48.120734] INFO: StockRanker训练: AI模型训练，将在1281741*13=1666.26万数据上对模型训练进行20轮迭代训练。预计将需要6～12分钟。请耐心等待。
[2022-04-18 15:48:48.360142] INFO: StockRanker训练: 正在训练 ..
[2022-04-18 15:48:48.454727] INFO: StockRanker训练: 任务状态: Pending
[2022-04-18 15:48:58.568014] INFO: StockRanker训练: 任务状态: Running
[2022-04-18 15:50:08.967878] INFO: StockRanker训练: 00:01:14.4107377, finished iteration 1
[2022-04-18 15:50:29.064738] INFO: StockRanker训练: 00:01:27.3497228, finished iteration 2
[2022-04-18 15:50:39.104111] INFO: StockRanker训练: 00:01:41.5757237, finished iteration 3
[2022-04-18 15:50:49.176411] INFO: StockRanker训练: 00:01:55.3840214, finished iteration 4
[2022-04-18 15:51:09.268148] INFO: StockRanker训练: 00:02:09.5409177, finished iteration 5
[2022-04-18 15:51:19.311862] INFO: StockRanker训练: 00:02:23.8956874, finished iteration 6
[2022-04-18 15:51:39.407298] INFO: StockRanker训练: 00:02:38.6233494, finished iteration 7
[2022-04-18 15:51:49.463673] INFO: StockRanker训练: 00:02:53.4450893, finished iteration 8
[2022-04-18 15:52:09.557465] INFO: StockRanker训练: 00:03:09.6460976, finished iteration 9
[2022-04-18 15:52:19.600197] INFO: StockRanker训练: 00:03:27.0035096, finished iteration 10
[2022-04-18 15:52:39.702167] INFO: StockRanker训练: 00:03:45.4629499, finished iteration 11
[2022-04-18 15:52:59.816459] INFO: StockRanker训练: 00:04:03.6811927, finished iteration 12
[2022-04-18 15:53:19.972559] INFO: StockRanker训练: 00:04:22.3400744, finished iteration 13
[2022-04-18 15:53:40.108230] INFO: StockRanker训练: 00:04:40.5128809, finished iteration 14
[2022-04-18 15:54:00.195399] INFO: StockRanker训练: 00:04:59.7195061, finished iteration 15
[2022-04-18 15:54:10.243283] INFO: StockRanker训练: 00:05:17.8264635, finished iteration 16
[2022-04-18 15:54:30.369517] INFO: StockRanker训练: 00:05:35.6093295, finished iteration 17
[2022-04-18 15:54:50.526774] INFO: StockRanker训练: 00:05:53.7909459, finished iteration 18
[2022-04-18 15:55:10.647152] INFO: StockRanker训练: 00:06:13.4929276, finished iteration 19
[2022-04-18 15:55:35.302424] INFO: StockRanker训练: 00:06:32.3629519, finished iteration 20
[2022-04-18 15:56:05.475172] INFO: StockRanker训练: 任务状态: Succeeded
[2022-04-18 15:56:05.850365] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[461.854821s].
[2022-04-18 15:56:05.858835] INFO: moduleinvoker: instruments.v2 开始运行..
[2022-04-18 15:56:05.866907] INFO: moduleinvoker: 命中缓存
[2022-04-18 15:56:05.868682] INFO: moduleinvoker: instruments.v2 运行完成[0.009872s].
[2022-04-18 15:56:05.897612] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2022-04-18 15:56:09.994176] INFO: 基础特征抽取: 年份 2020, 特征行数=179288
[2022-04-18 15:56:16.988708] INFO: 基础特征抽取: 年份 2021, 特征行数=1061527
[2022-04-18 15:56:19.252441] INFO: 基础特征抽取: 年份 2022, 特征行数=316265
[2022-04-18 15:56:19.418714] INFO: 基础特征抽取: 总行数: 1557080
[2022-04-18 15:56:19.426489] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[13.528879s].
[2022-04-18 15:56:19.440772] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2022-04-18 15:56:23.168323] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.005s
[2022-04-18 15:56:23.175490] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.005s
[2022-04-18 15:56:23.180604] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.004s
[2022-04-18 15:56:23.185517] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.003s
[2022-04-18 15:56:23.190505] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.003s
[2022-04-18 15:56:23.195319] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.003s
[2022-04-18 15:56:24.023979] INFO: derived_feature_extractor: /y_2020, 179288
[2022-04-18 15:56:26.548955] INFO: derived_feature_extractor: /y_2021, 1061527
[2022-04-18 15:56:28.170859] INFO: derived_feature_extractor: /y_2022, 316265
[2022-04-18 15:56:28.549974] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[9.109182s].
[2022-04-18 15:56:28.589330] INFO: moduleinvoker: filtet_st_stock.v2 开始运行..
[2022-04-18 15:56:34.847992] INFO: moduleinvoker: filtet_st_stock.v2 运行完成[6.258672s].
[2022-04-18 15:56:34.872209] INFO: moduleinvoker: filter_delist_stock.v4 开始运行..
[2022-04-18 15:56:41.659729] INFO: moduleinvoker: filter_delist_stock.v4 运行完成[6.787521s].
[2022-04-18 15:56:41.671849] INFO: moduleinvoker: dropnan.v2 开始运行..
[2022-04-18 15:56:44.971461] INFO: dropnan: /data, 1473742/1490548
[2022-04-18 15:56:45.073441] INFO: dropnan: 行数: 1473742/1490548
[2022-04-18 15:56:45.096448] INFO: moduleinvoker: dropnan.v2 运行完成[3.424596s].
[2022-04-18 15:56:45.111329] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..
[2022-04-18 15:56:47.115750] INFO: StockRanker预测: /data ..
[2022-04-18 15:56:51.289022] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[6.177694s].
[2022-04-18 15:56:51.365231] INFO: moduleinvoker: backtest.v8 开始运行..
[2022-04-18 15:56:51.381133] INFO: backtest: biglearning backtest:V8.6.2
[2022-04-18 15:56:51.383079] INFO: backtest: product_type:stock by specified
[2022-04-18 15:56:51.497001] INFO: moduleinvoker: cached.v2 开始运行..
[2022-04-18 15:57:03.457571] INFO: backtest: 读取股票行情完成:2452321
[2022-04-18 15:57:06.914044] INFO: moduleinvoker: cached.v2 运行完成[15.417053s].
[2022-04-18 15:57:10.367875] INFO: algo: TradingAlgorithm V1.8.7
[2022-04-18 15:57:15.248801] INFO: algo: trading transform...
[2022-04-18 15:57:24.240161] INFO: algo: handle_splits get splits [dt:2021-06-11 00:00:00+00:00] [asset:Equity(3842 [000014.SZA]), ratio:0.9987372756004333]
[2022-04-18 15:57:24.242029] INFO: Position: position stock handle split[sid:3842, orig_amount:7000, new_amount:7008.0, orig_cost:7.967257327125186, new_cost:7.9572, ratio:0.9987372756004333, last_sale_price:7.909999370574951]
[2022-04-18 15:57:24.243335] INFO: Position: after split: PositionStock(asset:Equity(3842 [000014.SZA]), amount:7008.0, cost_basis:7.9572, last_sale_price:7.920000076293945)
[2022-04-18 15:57:24.248460] INFO: Position: returning cash: 6.7254
[2022-04-18 15:57:27.203769] INFO: algo: handle_splits get splits [dt:2021-08-13 00:00:00+00:00] [asset:Equity(4502 [300086.SZA]), ratio:0.9964913129806519]
[2022-04-18 15:57:27.205429] INFO: Position: position stock handle split[sid:4502, orig_amount:5100, new_amount:5117.0, orig_cost:5.737999598185222, new_cost:5.7179, ratio:0.9964913129806519, last_sale_price:5.680000305175781]
[2022-04-18 15:57:27.206580] INFO: Position: after split: PositionStock(asset:Equity(4502 [300086.SZA]), amount:5117.0, cost_basis:5.7179, last_sale_price:5.699999809265137)
[2022-04-18 15:57:27.207785] INFO: Position: returning cash: 5.4375
[2022-04-18 15:57:39.630959] ERROR: moduleinvoker: module name: backtest, module version: v8, trackeback: zipline.errors.SymbolNotFound: Symbol '430047.BJA' was not found.
[2022-04-18 15:57:39.643937] ERROR: moduleinvoker: module name: trade, module version: v4, trackeback: zipline.errors.SymbolNotFound: Symbol '430047.BJA' was not found.