复制链接
克隆策略

    {"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":"-106: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":"-106:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-113:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-122:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-129:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-690:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-967:input_1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-122:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-141:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-113:input_data","from_node_id":"-106:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-113:data"},{"to_node_id":"-129:input_data","from_node_id":"-122:data"},{"to_node_id":"-1277:input_1","from_node_id":"-129:data"},{"to_node_id":"-690:training_ds","from_node_id":"-47836:data"},{"to_node_id":"-690:predict_ds","from_node_id":"-47840:data"},{"to_node_id":"-47836:input_data","from_node_id":"-967:data_1"},{"to_node_id":"-47840:input_data","from_node_id":"-1277:data_1"},{"to_node_id":"-141:options_data","from_node_id":"-690:predictions"},{"to_node_id":"-270:instruments","from_node_id":"-293:data"},{"to_node_id":"-306:instruments","from_node_id":"-293:data"},{"to_node_id":"-306:features","from_node_id":"-301:data"},{"to_node_id":"-313:features","from_node_id":"-301:data"},{"to_node_id":"-313:input_data","from_node_id":"-306:data"},{"to_node_id":"-270:feature_datas","from_node_id":"-313:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:features_ds","from_node_id":"-313:data"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2015-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2019-1-01","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, -2) / 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":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","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":"","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-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2019-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2021-08-20","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":true},{"node_id":"-106","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-106"},{"name":"features","node_id":"-106"}],"output_ports":[{"name":"data","node_id":"-106"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-113","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":"-113"},{"name":"features","node_id":"-113"}],"output_ports":[{"name":"data","node_id":"-113"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-122","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-122"},{"name":"features","node_id":"-122"}],"output_ports":[{"name":"data","node_id":"-122"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-129","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":"-129"},{"name":"features","node_id":"-129"}],"output_ports":[{"name":"data","node_id":"-129"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-141","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","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=0.0003, 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 = 4\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 = [1 / stock_count 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 = 1\n context.options['hold_days'] = 1\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 # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金\n # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n tmp = 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 instruments = equities\n# # print('rank order for sell %s' % instruments)\n for instrument in instruments:\n# if instrument in tmp:\n# print(\"涨停,不卖出\",instrument)\n# continue\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n \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","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_buy","value":"open","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"close","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":"100000","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.SHA","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-141"},{"name":"options_data","node_id":"-141"},{"name":"history_ds","node_id":"-141"},{"name":"benchmark_ds","node_id":"-141"},{"name":"trading_calendar","node_id":"-141"}],"output_ports":[{"name":"raw_perf","node_id":"-141"}],"cacheable":false,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-47836","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-47836"},{"name":"features","node_id":"-47836"}],"output_ports":[{"name":"data","node_id":"-47836"}],"cacheable":true,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-47840","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-47840"},{"name":"features","node_id":"-47840"}],"output_ports":[{"name":"data","node_id":"-47840"}],"cacheable":true,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-967","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n df = input_1.read_df()\n ins = m1.data.read_pickle()['instruments']\n start = m1.data.read_pickle()['start_date']\n end = m1.data.read_pickle()['end_date']\n \n df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])\n df_final = pd.merge(df,df1,on=['date','instrument'])\n df_final = df_final[df_final['instrument'].str.startswith(\"688\") == False]\n df_final = df_final[df_final['instrument'].str.startswith(\"3\") == False]\n\n df_final = df_final[df_final[\"st_status_0\"] == 0]\n df_final = df_final[df_final['rank_turn_0'] >= 0.9]\n df_final = df_final[df_final['rank_amount_0'] >= 0.85]\n print(\"用于训练的样本总个数为\",len(df_final))\n print(df_final.iloc[0])\n data_1 = DataSource.write_df(df_final)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","type":"Literal","bound_global_parameter":null},{"name":"post_run","value":"# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。\ndef bigquant_run(outputs):\n return outputs\n","type":"Literal","bound_global_parameter":null},{"name":"input_ports","value":"","type":"Literal","bound_global_parameter":null},{"name":"params","value":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-967"},{"name":"input_2","node_id":"-967"},{"name":"input_3","node_id":"-967"}],"output_ports":[{"name":"data_1","node_id":"-967"},{"name":"data_2","node_id":"-967"},{"name":"data_3","node_id":"-967"}],"cacheable":true,"seq_num":6,"comment":"","comment_collapsed":true},{"node_id":"-1277","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n df = input_1.read_df()\n ins = m9.data.read_pickle()['instruments']\n start = m9.data.read_pickle()['start_date']\n end = m9.data.read_pickle()['end_date']\n \n df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])\n df_final = pd.merge(df,df1,on=['date','instrument'])\n df_final = df_final[df_final['instrument'].str.startswith(\"688\") == False]\n df_final = df_final[df_final['instrument'].str.startswith(\"3\") == False]\n\n df_final = df_final[df_final[\"st_status_0\"] == 0]\n df_final = df_final[df_final['rank_turn_0'] >= 0.9]\n df_final = df_final[df_final['rank_amount_0'] >= 0.85]\n print(\"用于回测的样本总个数为\",len(df_final))\n data_1 = DataSource.write_df(df_final)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","type":"Literal","bound_global_parameter":null},{"name":"post_run","value":"# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。\ndef bigquant_run(outputs):\n return outputs\n","type":"Literal","bound_global_parameter":null},{"name":"input_ports","value":"","type":"Literal","bound_global_parameter":null},{"name":"params","value":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-1277"},{"name":"input_2","node_id":"-1277"},{"name":"input_3","node_id":"-1277"}],"output_ports":[{"name":"data_1","node_id":"-1277"},{"name":"data_2","node_id":"-1277"},{"name":"data_3","node_id":"-1277"}],"cacheable":true,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"-690","module_id":"BigQuantSpace.lightgbm.lightgbm-v2","parameters":[{"name":"num_boost_round","value":"79","type":"Literal","bound_global_parameter":null},{"name":"objective","value":"排序(ndcg)","type":"Literal","bound_global_parameter":null},{"name":"num_class","value":"1","type":"Literal","bound_global_parameter":null},{"name":"num_leaves","value":"60","type":"Literal","bound_global_parameter":null},{"name":"learning_rate","value":"0.1","type":"Literal","bound_global_parameter":null},{"name":"min_data_in_leaf","value":"900","type":"Literal","bound_global_parameter":null},{"name":"max_bin","value":"1023","type":"Literal","bound_global_parameter":null},{"name":"key_cols","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"group_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"random_seed","value":"101","type":"Literal","bound_global_parameter":null},{"name":"other_train_parameters","value":"{'n_jobs':4,'label_gain':','.join([str(x) for x in range(20)]),\"max_position\":29,\"eval_at\":\"1,3,5,10\"}","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"training_ds","node_id":"-690"},{"name":"features","node_id":"-690"},{"name":"model","node_id":"-690"},{"name":"predict_ds","node_id":"-690"}],"output_ports":[{"name":"output_model","node_id":"-690"},{"name":"predictions","node_id":"-690"},{"name":"feature_gains","node_id":"-690"}],"cacheable":true,"seq_num":10,"comment":"","comment_collapsed":true},{"node_id":"-270","module_id":"BigQuantSpace.genetic_algorithm.genetic_algorithm-v1","parameters":[{"name":"all_start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"all_end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"short_date_range_ratio","value":"1","type":"Literal","bound_global_parameter":null},{"name":"return_field","value":"wap_3_vwap_buy","type":"Literal","bound_global_parameter":null},{"name":"rebalance_period","value":1,"type":"Literal","bound_global_parameter":null},{"name":"train_test_ratio","value":"1","type":"Literal","bound_global_parameter":null},{"name":"train_validate_ratio","value":"1","type":"Literal","bound_global_parameter":null},{"name":"mtime","value":"2","type":"Literal","bound_global_parameter":null},{"name":"init_ind_num","value":"10","type":"Literal","bound_global_parameter":null},{"name":"ngen","value":"3","type":"Literal","bound_global_parameter":null},{"name":"fitness_func","value":"long_return","type":"Literal","bound_global_parameter":null},{"name":"train_fitness","value":"0.16","type":"Literal","bound_global_parameter":null},{"name":"test_fitness","value":"0.1","type":"Literal","bound_global_parameter":null},{"name":"ir_type","value":"ir","type":"Literal","bound_global_parameter":null},{"name":"cxpb","value":0.5,"type":"Literal","bound_global_parameter":null},{"name":"mutpb","value":0.3,"type":"Literal","bound_global_parameter":null},{"name":"mutspb","value":0.3,"type":"Literal","bound_global_parameter":null},{"name":"mutnrpb","value":0.3,"type":"Literal","bound_global_parameter":null},{"name":"constant","value":"1,11","type":"Literal","bound_global_parameter":null},{"name":"pool_processes_limit","value":"5","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-270"},{"name":"feature_datas","node_id":"-270"},{"name":"base_features","node_id":"-270"}],"output_ports":[{"name":"factors","node_id":"-270"}],"cacheable":false,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-293","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2018-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2018-06-20","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":"-293"}],"output_ports":[{"name":"data","node_id":"-293"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-301","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"close_0\nopen_0\nhigh_0\nlow_0 \namount_0\nturn_0 \nreturn_0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-301"}],"output_ports":[{"name":"data","node_id":"-301"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true},{"node_id":"-306","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":90,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-306"},{"name":"features","node_id":"-306"}],"output_ports":[{"name":"data","node_id":"-306"}],"cacheable":true,"seq_num":14,"comment":"","comment_collapsed":true},{"node_id":"-313","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":"-313"},{"name":"features","node_id":"-313"}],"output_ports":[{"name":"data","node_id":"-313"}],"cacheable":true,"seq_num":20,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='215,66,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,183,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='708,50,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1076,123,200,200'/><node_position Node='-106' Position='381,188,200,200'/><node_position Node='-113' Position='385,280,200,200'/><node_position Node='-122' Position='1082,249,200,200'/><node_position Node='-129' Position='1081,327,200,200'/><node_position Node='-141' Position='1069,944,200,200'/><node_position Node='-47836' Position='344,643,200,200'/><node_position Node='-47840' Position='1084,615,200,200'/><node_position Node='-967' Position='224,520,200,200'/><node_position Node='-1277' Position='1189,477,200,200'/><node_position Node='-690' Position='521,818,200,200'/><node_position Node='-270' Position='479,-94,200,200'/><node_position Node='-293' Position='428,-399,200,200'/><node_position Node='-301' Position='850,-455,200,200'/><node_position Node='-306' Position='793,-239,200,200'/><node_position Node='-313' Position='848,-120,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [25]:
    # 本代码由可视化策略环境自动生成 2021年12月9日 13:35
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m6_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df = input_1.read_df()
    ins = m1.data.read_pickle()['instruments']
    start = m1.data.read_pickle()['start_date']
    end = m1.data.read_pickle()['end_date']
    
    df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])
    df_final = pd.merge(df,df1,on=['date','instrument'])
    df_final = df_final[df_final['instrument'].str.startswith("688") == False]
    df_final = df_final[df_final['instrument'].str.startswith("3") == False]

    df_final = df_final[df_final["st_status_0"] == 0]
    df_final = df_final[df_final['rank_turn_0'] >= 0.9]
    df_final = df_final[df_final['rank_amount_0'] >= 0.85]
    print("用于训练的样本总个数为",len(df_final))
    print(df_final.iloc[0])
    data_1 = DataSource.write_df(df_final)
    return Outputs(data_1=data_1, data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m6_post_run_bigquant_run(outputs):
    return outputs

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m8_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df = input_1.read_df()
    ins = m9.data.read_pickle()['instruments']
    start = m9.data.read_pickle()['start_date']
    end = m9.data.read_pickle()['end_date']
    
    df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])
    df_final = pd.merge(df,df1,on=['date','instrument'])
    df_final = df_final[df_final['instrument'].str.startswith("688") == False]
    df_final = df_final[df_final['instrument'].str.startswith("3") == False]

    df_final = df_final[df_final["st_status_0"] == 0]
    df_final = df_final[df_final['rank_turn_0'] >= 0.9]
    df_final = df_final[df_final['rank_amount_0'] >= 0.85]
    print("用于回测的样本总个数为",len(df_final))
    data_1 = DataSource.write_df(df_final)
    return Outputs(data_1=data_1, data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m8_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m19_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 4
    # 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 = [1 / stock_count 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 = 1
    context.options['hold_days'] = 1

# 回测引擎：每日数据处理函数，每天执行一次
def m19_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]

    # 1. 资金分配
    # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
    # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
    is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.perf_tracker.position_tracker.positions.items()}

    # 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按机器学习算法预测的排序末位淘汰
    if not is_staging and cash_for_sell > 0:
        equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
        tmp = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        instruments = equities
#         # print('rank order for sell %s' % instruments)
        for instrument in instruments:
#             if instrument in tmp:
#                 print("涨停,不卖出",instrument)
#                 continue
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[instrument]
            if cash_for_sell <= 0:
                break

    # 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
    buy_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    for i, instrument in enumerate(buy_instruments):
        cash = cash_for_buy * buy_cash_weights[i]
        if cash > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
            cash = max_cash_per_instrument - positions.get(instrument, 0)
        if cash > 0:
           
            context.order_value(context.symbol(instrument), cash)

# 回测引擎：准备数据，只执行一次
def m19_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2015-01-01',
    end_date='2019-1-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -2) / shift(open, -1)

# 极值处理：用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=True
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2019-01-01'),
    end_date=T.live_run_param('trading_date', '2021-08-20'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m12 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2018-06-20',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m13 = M.input_features.v1(
    features="""close_0
open_0
high_0
low_0 
amount_0
turn_0 
return_0"""
)

m14 = M.general_feature_extractor.v7(
    instruments=m12.data,
    features=m13.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m20 = M.derived_feature_extractor.v3(
    input_data=m14.data,
    features=m13.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m11 = M.genetic_algorithm.v1(
    instruments=m12.data,
    feature_datas=m20.data,
    all_start_date='',
    all_end_date='',
    short_date_range_ratio=1,
    return_field='wap_3_vwap_buy',
    rebalance_period=1,
    train_test_ratio=1,
    train_validate_ratio=1,
    mtime=2,
    init_ind_num=10,
    ngen=3,
    fitness_func='long_return',
    train_fitness=0.16,
    test_fitness=0.1,
    ir_type='ir',
    cxpb=0.5,
    mutpb=0.3,
    mutspb=0.3,
    mutnrpb=0.3,
    constant='1,11',
    pool_processes_limit=5,
    m_cached=False
)

m3 = M.input_features.v1(
    features_ds=m20.data,
    features=''
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    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.cached.v3(
    input_1=m7.data,
    run=m6_run_bigquant_run,
    post_run=m6_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m4 = M.dropnan.v2(
    input_data=m6.data_1
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

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
)

m8 = M.cached.v3(
    input_1=m18.data,
    run=m8_run_bigquant_run,
    post_run=m8_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m5 = M.dropnan.v2(
    input_data=m8.data_1
)

m10 = M.lightgbm.v2(
    training_ds=m4.data,
    features=m3.data,
    predict_ds=m5.data,
    num_boost_round=79,
    objective='排序(ndcg)',
    num_class=1,
    num_leaves=60,
    learning_rate=0.1,
    min_data_in_leaf=900,
    max_bin=1023,
    key_cols='date,instrument',
    group_col='date',
    random_seed=101,
    other_train_parameters={'n_jobs':4,'label_gain':','.join([str(x) for x in range(20)]),"max_position":29,"eval_at":"1,3,5,10"}
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m10.predictions,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    volume_limit=0,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000,
    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.SHA'
)

    -- 开始第「1」次循环第「1」代挖掘 --

    去重前的个体数10
去重后的个体数10

    每代的平均适应度：[nan]
因子ts_max(high_0, 3)在训练集适应度值为-0.16492953403956184
因子mul(ts_argmin(return_0, 7), ts_max(open_0, 6))在训练集适应度值为-0.08625163439300082
因子mul(low_0, covariance(close_0, amount_0, 8))在训练集适应度值为-0.00150738071121432
因子ts_argmax(ta_sma(low_0, 8), constant(4))在训练集适应度值为-0.11119503690936552
因子rank(ts_rank(amount_0, 1))在训练集适应度值为nan
因子ts_max(open_0, 8)在训练集适应度值为-0.1619802967641491
因子max(turn_0, low_0)在训练集适应度值为-0.16546927933198363
因子decay_linear(high_0, 5)在训练集适应度值为-0.14965954038673704
因子mul(low_0, high_0)在训练集适应度值为-0.11341945301817474
因子add(mul(open_0, amount_0), return_0)在训练集适应度值为-0.09825704247236519

    pass:0, record:10, population: 10

    下一代挖掘的个体数：10

    -- 开始第「1」次循环第「2」代挖掘 --

    去重前的个体数10
去重后的个体数5

    每代的平均适应度：[nan, nan]
因子mul(low_0, ta_sma(low_0, 8))在训练集适应度值为-0.13209478366663086
因子ts_argmax(high_0, constant(6))在训练集适应度值为-0.16125183438194995
因子rank(ts_max(open_0, 6))在训练集适应度值为-0.16415441444148307
因子mul(return_0, ta_sma(amount_0, 1))在训练集适应度值为0.05254806069925043
因子add(mul(open_0, return_0), return_0)在训练集适应度值为-0.1461754627368608

    pass:0, record:5, population: 5

    下一代挖掘的个体数：10

    -- 开始第「1」次循环第「3」代挖掘 --

    去重前的个体数10
去重后的个体数6

    每代的平均适应度：[nan, nan, nan]
因子add(open_0, return_0)在训练集适应度值为-0.16707874182691768
因子mul(low_0, ta_sma(low_0, 1))在训练集适应度值为-0.11308810222749309
因子mul(return_0, ta_sma(amount_0, 8))在训练集适应度值为-0.21237566069373037
因子mul(return_0, amount_0)在训练集适应度值为0.05254806069925043
因子mul(normalize(delta(high_0, 1)), ta_sma(amount_0, 1))在训练集适应度值为0.42183007114973436
因子mul(low_0, high_0)在训练集适应度值为-0.11341945301817474

    因子mul(normalize(delta(high_0, 1)), ta_sma(amount_0, 1))在测试集适应度值为nan

    pass:1, record:6, population: 1

    下一代挖掘的个体数：10

    -- 开始第「2」次循环第「1」代挖掘 --

    去重前的个体数10
去重后的个体数10

    每代的平均适应度：[nan]
因子ts_argmax(product(amount_0, 5), constant(5))在训练集适应度值为-0.08266251763788747
因子add(sub(close_0, close_0), log(high_0))在训练集适应度值为0.2792694740992681
因子product(high_0, 2)在训练集适应度值为-0.12141455194709203
因子sum(close_0, 3)在训练集适应度值为-0.1651593792519855
因子rank(return_0)在训练集适应度值为0.7300338707634783
因子sub(close_0, close_0)在训练集适应度值为-0.17632488862515142
因子min(sub(low_0, return_0), open_0)在训练集适应度值为-0.16679367702870915
因子div(turn_0, close_0)在训练集适应度值为0.13213932862840527
因子max(high_0, open_0)在训练集适应度值为-0.15690126763658407
因子ts_max(low_0, 1)在训练集适应度值为-0.16609000078676364

    因子add(sub(close_0, close_0), log(high_0))在测试集适应度值为nan
因子rank(return_0)在测试集适应度值为nan

    pass:2, record:10, population: 2

    下一代挖掘的个体数：10

    -- 开始第「2」次循环第「2」代挖掘 --

    去重前的个体数10
去重后的个体数10

    每代的平均适应度：[nan, nan]
因子rank(return_0)在训练集适应度值为0.7300338707634783
因子rank(close_0)在训练集适应度值为-0.08152747592554727
因子add(log(close_0), log(high_0))在训练集适应度值为-0.14300649716870859
因子add(sub(close_0, close_0), sub(close_0, close_0))在训练集适应度值为0.382173726449295
因子add(sub(close_0, close_0), log(close_0))在训练集适应度值为0.2824717741164672
因子add(sub(high_0, close_0), log(high_0))在训练集适应度值为0.04310646142061168
因子rank(rank(high_0))在训练集适应度值为-0.0877312976220958
因子add(sub(close_0, close_0), return_0)在训练集适应度值为0.8723688718209505
因子add(sub(close_0, close_0), rank(high_0))在训练集适应度值为-0.0845733701125854
因子rank(low_0)在训练集适应度值为-0.09743774579211603

    因子rank(return_0)在测试集适应度值为nan
因子add(sub(close_0, close_0), sub(close_0, close_0))在测试集适应度值为nan
因子add(sub(close_0, close_0), log(close_0))在测试集适应度值为nan
因子add(sub(close_0, close_0), return_0)在测试集适应度值为nan

    pass:4, record:10, population: 4

    下一代挖掘的个体数：10

    -- 开始第「2」次循环第「3」代挖掘 --

    去重前的个体数10
去重后的个体数9

    每代的平均适应度：[nan, nan, nan]
因子decay_linear(ts_argmin(close_0, 7), constant(6))在训练集适应度值为-0.002286894299573947
因子add(sub(open_0, close_0), log(close_0))在训练集适应度值为-0.22906814212210594
因子rank(low_0)在训练集适应度值为-0.09743774579211603
因子rank(shift(product(low_0, 10), constant(8)))在训练集适应度值为-0.19189911865473427
因子add(sub(turn_0, close_0), sub(close_0, turn_0))在训练集适应度值为0.382173726449295
因子add(sub(close_0, return_0), return_0)在训练集适应度值为-0.15126067755155834
因子add(sub(close_0, close_0), sub(close_0, close_0))在训练集适应度值为0.382173726449295
因子add(sub(close_0, close_0), sub(close_0, close_0))在训练集适应度值为0.382173726449295
因子add(sub(close_0, close_0), close_0)在训练集适应度值为-0.14678567390660682

    因子add(sub(turn_0, close_0), sub(close_0, turn_0))在测试集适应度值为nan
因子add(sub(close_0, close_0), sub(close_0, close_0))在测试集适应度值为nan
因子add(sub(close_0, close_0), sub(close_0, close_0))在测试集适应度值为nan

    pass:3, record:9, population: 3

    下一代挖掘的个体数：10

    ---------------------------------------------------------------------------
UnpicklingError                           Traceback (most recent call last)
<ipython-input-25-4debdd7d9ffb> in <module>
    223 )
    224 
--> 225 m3 = M.input_features.v1(
    226     features_ds=m20.data,
    227     features=''

UnpicklingError: invalid load key, 'H'.
    In [ ]:
    m10.feature_gains.read().sort_values('gain',ascending=False)
    In [ ]: