{"description":"实验创建于2022/4/8","graph":{"edges":[{"to_node_id":"-1290:features","from_node_id":"-1278:data"},{"to_node_id":"-2427:features","from_node_id":"-1278:data"},{"to_node_id":"-1290:input_data","from_node_id":"-1283:data"},{"to_node_id":"-1079:input_data","from_node_id":"-1283:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-1290:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","from_node_id":"-1079:data"},{"to_node_id":"-186:input_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"to_node_id":"-3135:options_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"to_node_id":"-2427:input_data","from_node_id":"-2411:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","from_node_id":"-2427:data"},{"to_node_id":"-760:input","from_node_id":"-512:data"},{"to_node_id":"-2411:instruments","from_node_id":"-760:instrument_list"},{"to_node_id":"-3135:instruments","from_node_id":"-760:instrument_list"},{"to_node_id":"-1283:instruments","from_node_id":"-123:data"},{"to_node_id":"-512:instruments","from_node_id":"-177:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","from_node_id":"-186:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","from_node_id":"-189:data"},{"to_node_id":"-186:features","from_node_id":"-189:data"}],"nodes":[{"node_id":"-1278","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"return_5 = close/shift(close, 5)\nreturn_10 = close/shift(close, 10)\nreturn_20 = close/shift(close, 20)\namount/mean(amount,5)\nmean(amount,5)/mean(amount,20)\nrank(amount)/rank(mean(amount,5))\nrank(mean(amount,5))/rank(mean(amount,10))\nrank(close/shift(close, 1))\nrank(close/shift(close, 5))\nrank(close/shift(close, 10)) \nrank(close/shift(close, 1))/rank(close/shift(close, 5)) \nrank(close/shift(close, 5))/rank(close/shift(close, 10))","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-1278"}],"output_ports":[{"name":"data","node_id":"-1278"}],"cacheable":true,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-1283","module_id":"BigQuantSpace.use_datasource.use_datasource-v1","parameters":[{"name":"datasource_id","value":"bar1d_CN_CONBOND","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}],"input_ports":[{"name":"instruments","node_id":"-1283"},{"name":"features","node_id":"-1283"}],"output_ports":[{"name":"data","node_id":"-1283"}],"cacheable":false,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-1290","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":"-1290"},{"name":"features","node_id":"-1290"}],"output_ports":[{"name":"data","node_id":"-1290"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true},{"node_id":"-1079","module_id":"BigQuantSpace.auto_labeler_on_datasource.auto_labeler_on_datasource-v1","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/develop/datasource/deprecated/history_data.html\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.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":"drop_na_label","value":"True","type":"Literal","bound_global_parameter":null},{"name":"cast_label_int","value":"True","type":"Literal","bound_global_parameter":null},{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"{}","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-1079"}],"output_ports":[{"name":"data","node_id":"-1079"}],"cacheable":true,"seq_num":14,"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":15,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","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":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"name":"features","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"name":"test_ds","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"name":"base_model","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"output_ports":[{"name":"model","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"name":"feature_gains","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"name":"m_lazy_run","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"cacheable":true,"seq_num":16,"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":17,"comment":"","comment_collapsed":true},{"node_id":"-2411","module_id":"BigQuantSpace.use_datasource.use_datasource-v1","parameters":[{"name":"datasource_id","value":"bar1d_CN_CONBOND","type":"Literal","bound_global_parameter":null},{"name":"start_date","value":"2018-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2021-09-15","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-2411"},{"name":"features","node_id":"-2411"}],"output_ports":[{"name":"data","node_id":"-2411"}],"cacheable":true,"seq_num":28,"comment":"","comment_collapsed":true},{"node_id":"-2427","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":"-2427"},{"name":"features","node_id":"-2427"}],"output_ports":[{"name":"data","node_id":"-2427"}],"cacheable":true,"seq_num":30,"comment":"","comment_collapsed":true},{"node_id":"-3135","module_id":"BigQuantSpace.hftrade.hftrade-v2","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"initialize","value":"# 交易引擎：初始化函数，只执行一次\ndef bigquant_run(context):\n # 加载股票指标数据,数据继承自m6模块\n context.indicator_data = 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 \n # 设置数量\n context.stock_num = 10\n \n # 调仓天数,22个交易日大概就是一个月。可以理解为一个月换仓一次\n context.rebalance_days = 22\n \n # 如果策略运行中，需要将数据进行保存，可以借用extension这个对象，类型为dict\n # 比如当前运行的k线的索引，比如个股持仓天数、买入均价\n context.extension.index = 0\n context.subscribe(context.instruments)\n ","type":"Literal","bound_global_parameter":null},{"name":"before_trading_start","value":"# 交易引擎：每个单位时间开盘前调用一次。\ndef bigquant_run(context, data):\n pass","type":"Literal","bound_global_parameter":null},{"name":"handle_tick","value":"# 交易引擎：tick数据处理函数，每个tick执行一次\ndef bigquant_run(context, data):\n pass\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 context.extension.index += 1\n # 不在换仓日就return,相当于后面的代码只会一个月运行一次，买入的股票会持有1个月\n if context.extension.index % context.rebalance_days != 0:\n return\n \n # 当前的日期\n date = data.current_dt.strftime('%Y-%m-%d')\n cur_data = context.indicator_data[context.indicator_data['date'] == date]\n\n stock_to_buy = list(cur_data.instrument[:context.stock_num])\n # 通过positions对象，使用列表生成式的方法获取目前持仓的股票列表\n stock_hold_now = [equity for equity in context.portfolio.positions]\n # 继续持有的股票：调仓时，如果买入的股票已经存在于目前的持仓里，那么应继续持有\n no_need_to_sell = [i for i in stock_hold_now if i in stock_to_buy]\n # 需要卖出的股票\n stock_to_sell = [i for i in stock_hold_now if i not in no_need_to_sell] \n \n # 卖出\n\n for stock in stock_to_sell:\n context.order_target_percent(stock, 0)\n \n # 如果当天没有买入的股票，就返回\n if len(stock_to_buy) == 0:\n print(date,'当天没有买入的股票')\n return\n\n # 等权重买入 \n weight = 1 / len(stock_to_buy)\n print(stock_to_buy,weight)\n # 买入\n for stock in stock_to_buy:\n context.order_target_percent(stock, weight)\n ","type":"Literal","bound_global_parameter":null},{"name":"handle_trade","value":"# 交易引擎：成交回报处理函数，每个成交发生时执行一次\ndef bigquant_run(context, data):\n pass\n","type":"Literal","bound_global_parameter":null},{"name":"handle_order","value":"# 交易引擎：委托回报处理函数，每个委托变化时执行一次\ndef bigquant_run(context, data):\n pass\n","type":"Literal","bound_global_parameter":null},{"name":"after_trading","value":"# 交易引擎：盘后处理函数，每日盘后执行一次\ndef bigquant_run(context, data):\n pass\n","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":"1000001","type":"Literal","bound_global_parameter":null},{"name":"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":"可转债","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":"0","type":"Literal","bound_global_parameter":null},{"name":"volume_limit","value":1,"type":"Literal","bound_global_parameter":null},{"name":"order_price_field_buy","value":"close","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"close","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.HIX","type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"disable_cache","value":"False","type":"Literal","bound_global_parameter":null},{"name":"replay_bdb","value":"False","type":"Literal","bound_global_parameter":null},{"name":"show_debug_info","value":"False","type":"Literal","bound_global_parameter":null},{"name":"backtest_only","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-3135"},{"name":"options_data","node_id":"-3135"},{"name":"history_ds","node_id":"-3135"},{"name":"benchmark_ds","node_id":"-3135"}],"output_ports":[{"name":"raw_perf","node_id":"-3135"}],"cacheable":false,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-512","module_id":"BigQuantSpace.use_datasource.use_datasource-v1","parameters":[{"name":"datasource_id","value":"market_performance_CN_CONBOND","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}],"input_ports":[{"name":"instruments","node_id":"-512"},{"name":"features","node_id":"-512"}],"output_ports":[{"name":"data","node_id":"-512"}],"cacheable":false,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"-760","module_id":"BigQuantSpace.trade_data_generation.trade_data_generation-v1","parameters":[{"name":"category","value":"CN_STOCK","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input","node_id":"-760"}],"output_ports":[{"name":"history_data","node_id":"-760"},{"name":"instrument_list","node_id":"-760"},{"name":"calendar","node_id":"-760"}],"cacheable":false,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"-127","module_id":"BigQuantSpace.hyper_rolling_train.hyper_rolling_train-v1","parameters":[{"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='m4', # 训练数据 证券代码列表 模块id\n test_instruments_mid='m22', # 测试数据 证券代码列表 模块id\n predict_mid='m17', # 预测 模块id\n trade_mid='m19', # 回测 模块id\n start_date='2017-01-01', # 数据开始日期\n end_date=T.live_run_param('trading_date', '2022-09-16'), # 数据结束日期\n train_update_days=22, # 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=250, # 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=250, # 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').loc[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","type":"Literal","bound_global_parameter":null},{"name":"run_now","value":"True","type":"Literal","bound_global_parameter":null},{"name":"bq_graph","value":"True","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"bq_graph_port","node_id":"-127"},{"name":"input_1","node_id":"-127"},{"name":"input_2","node_id":"-127"},{"name":"input_3","node_id":"-127"}],"output_ports":[{"name":"result","node_id":"-127"}],"cacheable":false,"seq_num":3,"comment":"","comment_collapsed":true},{"node_id":"-123","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2017-01-03","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2018-01-09","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_CONBOND","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":"-123"}],"output_ports":[{"name":"data","node_id":"-123"}],"cacheable":true,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-177","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2018-01-10","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2018-02-08","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_CONBOND","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":"-177"}],"output_ports":[{"name":"data","node_id":"-177"}],"cacheable":true,"seq_num":22,"comment":"","comment_collapsed":true},{"node_id":"-186","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-186"},{"name":"features","node_id":"-186"}],"output_ports":[{"name":"data","node_id":"-186"}],"cacheable":true,"seq_num":23,"comment":"","comment_collapsed":true},{"node_id":"-189","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"return_5\nreturn_10\nreturn_20\namount/mean(amount,5)\nmean(amount,5)/mean(amount,20)\nrank(amount)/rank(mean(amount,5))\nrank(mean(amount,5))/rank(mean(amount,10))\nrank(close/shift(close, 1))\nrank(close/shift(close, 5))\nrank(close/shift(close, 10)) \nrank(close/shift(close, 1))/rank(close/shift(close, 5)) \nrank(close/shift(close, 5))/rank(close/shift(close, 10))","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-189"}],"output_ports":[{"name":"data","node_id":"-189"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='-1278' Position='1318,-545,200,200'/><node_position Node='-1283' Position='982.5711669921875,-486.3546142578125,200,200'/><node_position Node='-1290' Position='1194,-247,200,200'/><node_position Node='-1079' Position='816.7484130859375,-321.18145751953125,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='1097,-104,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='1265.961669921875,107,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='1471,245,200,200'/><node_position Node='-2411' Position='1729,-192,200,200'/><node_position Node='-2427' Position='1722,6,200,200'/><node_position Node='-3135' Position='1742,400,200,200'/><node_position Node='-512' Position='1734,-522,200,200'/><node_position Node='-760' Position='1764.272216796875,-401.3488464355469,200,200'/><node_position Node='-127' Position='535.4886474609375,0.2774391174316406,200,200'/><node_position Node='-123' Position='980.08984375,-585.123779296875,200,200'/><node_position Node='-177' Position='1736.416015625,-620.9364013671875,200,200'/><node_position Node='-186' Position='1107.6002197265625,0.377838134765625,200,200'/><node_position Node='-189' Position='1432.8509521484375,-121.7753677368164,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}

# 本代码由可视化策略环境自动生成 2022年12月6日 18:46
# 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。


# 交易引擎：初始化函数，只执行一次
def m19_initialize_bigquant_run(context):
       # 加载股票指标数据,数据继承自m6模块
    context.indicator_data = 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))
    
    # 设置数量
    context.stock_num = 10
    
    # 调仓天数,22个交易日大概就是一个月。可以理解为一个月换仓一次
    context.rebalance_days = 22
    
    # 如果策略运行中，需要将数据进行保存，可以借用extension这个对象，类型为dict
    # 比如当前运行的k线的索引，比如个股持仓天数、买入均价
    context.extension.index = 0
    context.subscribe(context.instruments)
 
# 交易引擎：每个单位时间开盘前调用一次。
def m19_before_trading_start_bigquant_run(context, data):
    pass
# 交易引擎：tick数据处理函数，每个tick执行一次
def m19_handle_tick_bigquant_run(context, data):
    pass

# 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):
    
    context.extension.index += 1
    # 不在换仓日就return,相当于后面的代码只会一个月运行一次，买入的股票会持有1个月
    if  context.extension.index % context.rebalance_days != 0:
        return
    
    # 当前的日期
    date = data.current_dt.strftime('%Y-%m-%d')
    cur_data = context.indicator_data[context.indicator_data['date'] == date]

    stock_to_buy = list(cur_data.instrument[:context.stock_num])
    # 通过positions对象，使用列表生成式的方法获取目前持仓的股票列表
    stock_hold_now = [equity for equity in context.portfolio.positions]
    # 继续持有的股票：调仓时，如果买入的股票已经存在于目前的持仓里，那么应继续持有
    no_need_to_sell = [i for i in stock_hold_now if i in stock_to_buy]
    # 需要卖出的股票
    stock_to_sell = [i for i in stock_hold_now if i not in no_need_to_sell] 
    
    # 卖出

    for stock in stock_to_sell:
        context.order_target_percent(stock, 0)
    
    # 如果当天没有买入的股票，就返回
    if len(stock_to_buy) == 0:
        print(date,'当天没有买入的股票')
        return

    # 等权重买入 
    weight =  1 / len(stock_to_buy)
    print(stock_to_buy,weight)
    # 买入
    for stock in stock_to_buy:
        context.order_target_percent(stock, weight)
 
# 交易引擎：成交回报处理函数，每个成交发生时执行一次
def m19_handle_trade_bigquant_run(context, data):
    pass

# 交易引擎：委托回报处理函数，每个委托变化时执行一次
def m19_handle_order_bigquant_run(context, data):
    pass

# 交易引擎：盘后处理函数，每日盘后执行一次
def m19_after_trading_bigquant_run(context, data):
    pass


g = T.Graph({

    'm11': 'M.input_features.v1',
    'm11.features': """return_5 = close/shift(close, 5)
return_10 = close/shift(close, 10)
return_20 = close/shift(close, 20)
amount/mean(amount,5)
mean(amount,5)/mean(amount,20)
rank(amount)/rank(mean(amount,5))
rank(mean(amount,5))/rank(mean(amount,10))
rank(close/shift(close, 1))
rank(close/shift(close, 5))
rank(close/shift(close, 10))     
rank(close/shift(close, 1))/rank(close/shift(close, 5))    
rank(close/shift(close, 5))/rank(close/shift(close, 10))""",

    'm4': 'M.instruments.v2',
    'm4.start_date': '2017-01-03',
    'm4.end_date': '2018-01-09',
    'm4.market': 'CN_CONBOND',
    'm4.instrument_list': '',
    'm4.max_count': 0,

    'm12': 'M.use_datasource.v1',
    'm12.instruments': T.Graph.OutputPort('m4.data'),
    'm12.datasource_id': 'bar1d_CN_CONBOND',
    'm12.start_date': '',
    'm12.end_date': '',
    'm12.m_cached': False,

    'm13': 'M.derived_feature_extractor.v3',
    'm13.input_data': T.Graph.OutputPort('m12.data'),
    'm13.features': T.Graph.OutputPort('m11.data'),
    'm13.date_col': 'date',
    'm13.instrument_col': 'instrument',
    'm13.drop_na': False,
    'm13.remove_extra_columns': False,
    'm13.user_functions': {},

    'm14': 'M.auto_labeler_on_datasource.v1',
    'm14.input_data': T.Graph.OutputPort('m12.data'),
    'm14.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/develop/datasource/deprecated/history_data.html
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.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)
""",
    'm14.drop_na_label': True,
    'm14.cast_label_int': True,
    'm14.date_col': 'date',
    'm14.instrument_col': 'instrument',
    'm14.user_functions': {},

    'm15': 'M.join.v3',
    'm15.data1': T.Graph.OutputPort('m14.data'),
    'm15.data2': T.Graph.OutputPort('m13.data'),
    'm15.on': 'date,instrument',
    'm15.how': 'inner',
    'm15.sort': False,

    'm22': 'M.instruments.v2',
    'm22.start_date': '2018-01-10',
    'm22.end_date': '2018-02-08',
    'm22.market': 'CN_CONBOND',
    'm22.instrument_list': '',
    'm22.max_count': 0,

    'm1': 'M.use_datasource.v1',
    'm1.instruments': T.Graph.OutputPort('m22.data'),
    'm1.datasource_id': 'market_performance_CN_CONBOND',
    'm1.start_date': '',
    'm1.end_date': '',
    'm1.m_cached': False,

    'm2': 'M.trade_data_generation.v1',
    'm2.input': T.Graph.OutputPort('m1.data'),
    'm2.category': 'CN_STOCK',
    'm2.m_cached': False,

    'm28': 'M.use_datasource.v1',
    'm28.instruments': T.Graph.OutputPort('m2.instrument_list'),
    'm28.datasource_id': 'bar1d_CN_CONBOND',
    'm28.start_date': '2018-01-01',
    'm28.end_date': '2021-09-15',

    'm30': 'M.derived_feature_extractor.v3',
    'm30.input_data': T.Graph.OutputPort('m28.data'),
    'm30.features': T.Graph.OutputPort('m11.data'),
    'm30.date_col': 'date',
    'm30.instrument_col': 'instrument',
    'm30.drop_na': False,
    'm30.remove_extra_columns': False,
    'm30.user_functions': {},

    'm18': 'M.input_features.v1',
    'm18.features': """return_5
return_10
return_20
amount/mean(amount,5)
mean(amount,5)/mean(amount,20)
rank(amount)/rank(mean(amount,5))
rank(mean(amount,5))/rank(mean(amount,10))
rank(close/shift(close, 1))
rank(close/shift(close, 5))
rank(close/shift(close, 10))     
rank(close/shift(close, 1))/rank(close/shift(close, 5))    
rank(close/shift(close, 5))/rank(close/shift(close, 10))""",

    'm23': 'M.dropnan.v2',
    'm23.input_data': T.Graph.OutputPort('m15.data'),
    'm23.features': T.Graph.OutputPort('m18.data'),

    'm16': 'M.stock_ranker_train.v6',
    'm16.training_ds': T.Graph.OutputPort('m23.data'),
    'm16.features': T.Graph.OutputPort('m18.data'),
    'm16.learning_algorithm': '排序',
    'm16.number_of_leaves': 30,
    'm16.minimum_docs_per_leaf': 1000,
    'm16.number_of_trees': 20,
    'm16.learning_rate': 0.1,
    'm16.max_bins': 1023,
    'm16.feature_fraction': 1,
    'm16.data_row_fraction': 1,
    'm16.plot_charts': True,
    'm16.ndcg_discount_base': 1,
    'm16.m_lazy_run': False,

    'm17': 'M.stock_ranker_predict.v5',
    'm17.model': T.Graph.OutputPort('m16.model'),
    'm17.data': T.Graph.OutputPort('m30.data'),
    'm17.m_lazy_run': False,

    'm19': 'M.hftrade.v2',
    'm19.instruments': T.Graph.OutputPort('m2.instrument_list'),
    'm19.options_data': T.Graph.OutputPort('m17.predictions'),
    'm19.start_date': '',
    'm19.end_date': '',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.before_trading_start': m19_before_trading_start_bigquant_run,
    'm19.handle_tick': m19_handle_tick_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.handle_trade': m19_handle_trade_bigquant_run,
    'm19.handle_order': m19_handle_order_bigquant_run,
    'm19.after_trading': m19_after_trading_bigquant_run,
    'm19.capital_base': 1000001,
    'm19.frequency': 'daily',
    'm19.price_type': '真实价格',
    'm19.product_type': '可转债',
    'm19.before_start_days': '0',
    'm19.volume_limit': 1,
    'm19.order_price_field_buy': 'close',
    'm19.order_price_field_sell': 'close',
    'm19.benchmark': '000300.HIX',
    'm19.plot_charts': True,
    'm19.disable_cache': False,
    'm19.replay_bdb': False,
    'm19.show_debug_info': False,
    'm19.backtest_only': False,
})

# g.run({})


def m3_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='m4', # 训练数据 证券代码列表 模块id
    test_instruments_mid='m22', # 测试数据 证券代码列表 模块id
    predict_mid='m17', # 预测 模块id
    trade_mid='m19', # 回测 模块id
    start_date='2017-01-01', # 数据开始日期
    end_date=T.live_run_param('trading_date', '2022-09-16'), # 数据结束日期
    train_update_days=22, # 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=250, # 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=250, # 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').loc[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}


m3 = M.hyper_rolling_train.v1(
    run=m3_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2022-12-06 18:44:21.780750] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-12-06 18:44:21.789316] INFO: moduleinvoker: 命中缓存

[2022-12-06 18:44:21.795749] INFO: moduleinvoker: input_features.v1 运行完成[0.015012s].

[2022-12-06 18:44:21.825511] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-12-06 18:44:21.832707] INFO: moduleinvoker: 命中缓存

[2022-12-06 18:44:21.835457] INFO: moduleinvoker: instruments.v2 运行完成[0.009959s].

[2022-12-06 18:44:21.866524] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-12-06 18:44:21.877402] INFO: moduleinvoker: 命中缓存

[2022-12-06 18:44:21.882118] INFO: moduleinvoker: instruments.v2 运行完成[0.015613s].

[2022-12-06 18:44:21.888563] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-12-06 18:44:21.898145] INFO: moduleinvoker: 命中缓存

[2022-12-06 18:44:21.901507] INFO: moduleinvoker: input_features.v1 运行完成[0.012954s].

[2022-12-06 18:44:21.913984] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-12-06 18:44:22.156585] INFO: moduleinvoker: use_datasource.v1 运行完成[0.242615s].

[2022-12-06 18:44:22.169753] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-12-06 18:44:22.405636] INFO: moduleinvoker: use_datasource.v1 运行完成[0.235895s].

[2022-12-06 18:44:22.456484] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-12-06 18:44:22.523750] INFO: 自动标注(任意数据源): 开始标注 ..

[2022-12-06 18:44:22.681736] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.225248s].

[2022-12-06 18:44:22.718520] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-12-06 18:44:22.847205] INFO: derived_feature_extractor: 提取完成 return_5 = close/shift(close, 5), 0.006s

[2022-12-06 18:44:22.858083] INFO: derived_feature_extractor: 提取完成 return_10 = close/shift(close, 10), 0.007s

[2022-12-06 18:44:22.874149] INFO: derived_feature_extractor: 提取完成 return_20 = close/shift(close, 20), 0.013s

[2022-12-06 18:44:22.901814] INFO: derived_feature_extractor: 提取完成 amount/mean(amount,5), 0.020s

[2022-12-06 18:44:22.933791] INFO: derived_feature_extractor: 提取完成 mean(amount,5)/mean(amount,20), 0.029s

[2022-12-06 18:44:22.972563] INFO: derived_feature_extractor: 提取完成 rank(amount)/rank(mean(amount,5)), 0.027s

[2022-12-06 18:44:23.026287] INFO: derived_feature_extractor: 提取完成 rank(mean(amount,5))/rank(mean(amount,10)), 0.051s

[2022-12-06 18:44:23.042304] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1)), 0.013s

[2022-12-06 18:44:23.057439] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5)), 0.012s

[2022-12-06 18:44:23.077409] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 10)), 0.017s

[2022-12-06 18:44:23.107349] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1))/rank(close/shift(close, 5)), 0.027s

[2022-12-06 18:44:23.140015] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5))/rank(close/shift(close, 10)), 0.030s

[2022-12-06 18:44:23.287211] INFO: derived_feature_extractor: /data, 5038

[2022-12-06 18:44:23.438198] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.719658s].

[2022-12-06 18:44:23.531939] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-12-06 18:44:23.916475] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.384534s].

[2022-12-06 18:44:23.936278] INFO: moduleinvoker: join.v3 开始运行..

[2022-12-06 18:44:24.240664] INFO: join: /data, 行数=4627/5038, 耗时=0.092066s

[2022-12-06 18:44:24.310350] INFO: join: 最终行数: 4627

[2022-12-06 18:44:24.319203] INFO: moduleinvoker: join.v3 运行完成[0.38291s].

[2022-12-06 18:44:24.355251] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-12-06 18:44:24.750725] INFO: moduleinvoker: use_datasource.v1 运行完成[0.395488s].

[2022-12-06 18:44:24.774348] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-12-06 18:44:25.015133] INFO: dropnan: /data, 3966/4627

[2022-12-06 18:44:25.082153] INFO: dropnan: 行数: 3966/4627

[2022-12-06 18:44:25.089066] INFO: moduleinvoker: dropnan.v2 运行完成[0.314718s].

[2022-12-06 18:44:25.108740] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-12-06 18:44:25.189529] INFO: derived_feature_extractor: 提取完成 return_5 = close/shift(close, 5), 0.005s

[2022-12-06 18:44:25.198389] INFO: derived_feature_extractor: 提取完成 return_10 = close/shift(close, 10), 0.005s

[2022-12-06 18:44:25.205828] INFO: derived_feature_extractor: 提取完成 return_20 = close/shift(close, 20), 0.005s

[2022-12-06 18:44:25.224511] INFO: derived_feature_extractor: 提取完成 amount/mean(amount,5), 0.015s

[2022-12-06 18:44:25.291815] INFO: derived_feature_extractor: 提取完成 mean(amount,5)/mean(amount,20), 0.064s

[2022-12-06 18:44:25.320311] INFO: derived_feature_extractor: 提取完成 rank(amount)/rank(mean(amount,5)), 0.026s

[2022-12-06 18:44:25.364312] INFO: derived_feature_extractor: 提取完成 rank(mean(amount,5))/rank(mean(amount,10)), 0.040s

[2022-12-06 18:44:25.376235] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1)), 0.009s

[2022-12-06 18:44:25.389145] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5)), 0.010s

[2022-12-06 18:44:25.402813] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 10)), 0.011s

[2022-12-06 18:44:25.425941] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1))/rank(close/shift(close, 5)), 0.019s

[2022-12-06 18:44:25.447928] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5))/rank(close/shift(close, 10)), 0.018s

[2022-12-06 18:44:25.556931] INFO: derived_feature_extractor: /data, 1049

[2022-12-06 18:44:25.652881] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.544073s].

[2022-12-06 18:44:25.673847] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-12-06 18:44:25.898848] INFO: StockRanker: 特征预处理 ..

[2022-12-06 18:44:25.952444] INFO: StockRanker: prepare data: training ..

[2022-12-06 18:44:26.137118] INFO: StockRanker训练: f3d6db98 准备训练: 3966 行数

[2022-12-06 18:44:26.139742] INFO: StockRanker训练: AI模型训练，将在3966*12=4.76万数据上对模型训练进行20轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-12-06 18:44:26.456615] INFO: StockRanker训练: 正在训练 ..

[2022-12-06 18:44:26.532194] INFO: StockRanker训练: 任务状态: Pending

[2022-12-06 18:44:36.576686] INFO: StockRanker训练: 任务状态: Running

[2022-12-06 18:45:36.889656] INFO: StockRanker训练: 00:01:01.3040428, finished iteration 1

[2022-12-06 18:45:36.894942] INFO: StockRanker训练: 00:01:01.3093931, finished iteration 2

[2022-12-06 18:45:36.897397] INFO: StockRanker训练: 00:01:01.3117017, finished iteration 3

[2022-12-06 18:45:36.899905] INFO: StockRanker训练: 00:01:01.3138669, finished iteration 4

[2022-12-06 18:45:36.915548] INFO: StockRanker训练: 00:01:01.3162274, finished iteration 5

[2022-12-06 18:45:36.923840] INFO: StockRanker训练: 00:01:01.3184242, finished iteration 6

[2022-12-06 18:45:36.934991] INFO: StockRanker训练: 00:01:01.3208856, finished iteration 7

[2022-12-06 18:45:36.939160] INFO: StockRanker训练: 00:01:01.3232744, finished iteration 8

[2022-12-06 18:45:36.948833] INFO: StockRanker训练: 00:01:01.3254839, finished iteration 9

[2022-12-06 18:45:36.956005] INFO: StockRanker训练: 00:01:01.3276112, finished iteration 10

[2022-12-06 18:45:36.960989] INFO: StockRanker训练: 00:01:01.3298007, finished iteration 11

[2022-12-06 18:45:36.963731] INFO: StockRanker训练: 00:01:01.3345073, finished iteration 12

[2022-12-06 18:45:36.966643] INFO: StockRanker训练: 00:01:01.3371222, finished iteration 13

[2022-12-06 18:45:36.969318] INFO: StockRanker训练: 00:01:01.3394894, finished iteration 14

[2022-12-06 18:45:36.982174] INFO: StockRanker训练: 00:01:01.3417296, finished iteration 15

[2022-12-06 18:45:36.984966] INFO: StockRanker训练: 00:01:01.3438799, finished iteration 16

[2022-12-06 18:45:36.987573] INFO: StockRanker训练: 00:01:01.3463149, finished iteration 17

[2022-12-06 18:45:36.992438] INFO: StockRanker训练: 00:01:01.3485414, finished iteration 18

[2022-12-06 18:45:36.995408] INFO: StockRanker训练: 00:01:01.3509106, finished iteration 19

[2022-12-06 18:45:36.998903] INFO: StockRanker训练: 00:01:01.3532266, finished iteration 20

[2022-12-06 18:45:37.001602] INFO: StockRanker训练: 任务状态: Succeeded

[2022-12-06 18:45:37.265420] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[71.591577s].

[2022-12-06 18:45:37.316080] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-12-06 18:45:38.226798] INFO: StockRanker预测: /data ..

[2022-12-06 18:45:38.666756] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[1.350665s].

[2022-12-06 18:45:38.684199] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-12-06 18:45:38.697544] INFO: moduleinvoker: 命中缓存

[2022-12-06 18:45:38.700521] INFO: moduleinvoker: input_features.v1 运行完成[0.01634s].

[2022-12-06 18:45:38.715874] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-12-06 18:45:38.839671] INFO: moduleinvoker: instruments.v2 运行完成[0.123802s].

[2022-12-06 18:45:38.857995] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-12-06 18:45:38.997188] INFO: moduleinvoker: instruments.v2 运行完成[0.139181s].

[2022-12-06 18:45:39.009381] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-12-06 18:45:39.018664] INFO: moduleinvoker: 命中缓存

[2022-12-06 18:45:39.021716] INFO: moduleinvoker: input_features.v1 运行完成[0.012353s].

[2022-12-06 18:45:39.030676] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-12-06 18:45:39.347473] INFO: moduleinvoker: use_datasource.v1 运行完成[0.3168s].

[2022-12-06 18:45:39.356814] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-12-06 18:45:39.588624] INFO: moduleinvoker: use_datasource.v1 运行完成[0.231829s].

[2022-12-06 18:45:39.625343] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-12-06 18:45:39.736840] INFO: 自动标注(任意数据源): 开始标注 ..

[2022-12-06 18:45:39.906958] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.281598s].

[2022-12-06 18:45:39.919993] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-12-06 18:45:40.052917] INFO: derived_feature_extractor: 提取完成 return_5 = close/shift(close, 5), 0.006s

[2022-12-06 18:45:40.073250] INFO: derived_feature_extractor: 提取完成 return_10 = close/shift(close, 10), 0.012s

[2022-12-06 18:45:40.087140] INFO: derived_feature_extractor: 提取完成 return_20 = close/shift(close, 20), 0.011s

[2022-12-06 18:45:40.112411] INFO: derived_feature_extractor: 提取完成 amount/mean(amount,5), 0.019s

[2022-12-06 18:45:40.169226] INFO: derived_feature_extractor: 提取完成 mean(amount,5)/mean(amount,20), 0.054s

[2022-12-06 18:45:40.205283] INFO: derived_feature_extractor: 提取完成 rank(amount)/rank(mean(amount,5)), 0.033s

[2022-12-06 18:45:40.263944] INFO: derived_feature_extractor: 提取完成 rank(mean(amount,5))/rank(mean(amount,10)), 0.055s

[2022-12-06 18:45:40.281037] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1)), 0.013s

[2022-12-06 18:45:40.297429] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5)), 0.013s

[2022-12-06 18:45:40.313723] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 10)), 0.013s

[2022-12-06 18:45:40.344269] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1))/rank(close/shift(close, 5)), 0.028s

[2022-12-06 18:45:40.378202] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5))/rank(close/shift(close, 10)), 0.030s

[2022-12-06 18:45:40.502774] INFO: derived_feature_extractor: /data, 5771

[2022-12-06 18:45:40.610250] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.690243s].

[2022-12-06 18:45:40.625135] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-12-06 18:45:40.864139] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.238995s].

[2022-12-06 18:45:40.897193] INFO: moduleinvoker: join.v3 开始运行..

[2022-12-06 18:45:41.212729] INFO: join: /data, 行数=5249/5771, 耗时=0.125134s

[2022-12-06 18:45:41.314150] INFO: join: 最终行数: 5249

[2022-12-06 18:45:41.325230] INFO: moduleinvoker: join.v3 运行完成[0.42803s].

[2022-12-06 18:45:41.334384] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-12-06 18:45:41.820125] INFO: moduleinvoker: use_datasource.v1 运行完成[0.485713s].

[2022-12-06 18:45:41.851560] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-12-06 18:45:42.116874] INFO: dropnan: /data, 4325/5249

[2022-12-06 18:45:42.209186] INFO: dropnan: 行数: 4325/5249

[2022-12-06 18:45:42.215709] INFO: moduleinvoker: dropnan.v2 运行完成[0.364149s].

[2022-12-06 18:45:42.229631] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-12-06 18:45:42.336904] INFO: derived_feature_extractor: 提取完成 return_5 = close/shift(close, 5), 0.007s

[2022-12-06 18:45:42.344704] INFO: derived_feature_extractor: 提取完成 return_10 = close/shift(close, 10), 0.005s

[2022-12-06 18:45:42.353478] INFO: derived_feature_extractor: 提取完成 return_20 = close/shift(close, 20), 0.006s

[2022-12-06 18:45:42.375334] INFO: derived_feature_extractor: 提取完成 amount/mean(amount,5), 0.019s

[2022-12-06 18:45:42.415972] INFO: derived_feature_extractor: 提取完成 mean(amount,5)/mean(amount,20), 0.036s

[2022-12-06 18:45:42.439695] INFO: derived_feature_extractor: 提取完成 rank(amount)/rank(mean(amount,5)), 0.020s

[2022-12-06 18:45:42.489540] INFO: derived_feature_extractor: 提取完成 rank(mean(amount,5))/rank(mean(amount,10)), 0.046s

[2022-12-06 18:45:42.504110] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1)), 0.010s

[2022-12-06 18:45:42.515427] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5)), 0.009s

[2022-12-06 18:45:42.530382] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 10)), 0.012s

[2022-12-06 18:45:42.557328] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 1))/rank(close/shift(close, 5)), 0.022s

[2022-12-06 18:45:42.584454] INFO: derived_feature_extractor: 提取完成 rank(close/shift(close, 5))/rank(close/shift(close, 10)), 0.020s

[2022-12-06 18:45:42.705170] INFO: derived_feature_extractor: /data, 1223

[2022-12-06 18:45:42.846605] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.616979s].

[2022-12-06 18:45:42.880401] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-12-06 18:45:43.120689] INFO: StockRanker: 特征预处理 ..

[2022-12-06 18:45:43.162498] INFO: StockRanker: prepare data: training ..

[2022-12-06 18:45:43.413378] INFO: StockRanker训练: 21e2e5b8 准备训练: 4325 行数

[2022-12-06 18:45:43.420651] INFO: StockRanker训练: AI模型训练，将在4325*12=5.19万数据上对模型训练进行20轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-12-06 18:45:43.724046] INFO: StockRanker训练: 正在训练 ..

[2022-12-06 18:45:43.777258] INFO: StockRanker训练: 任务状态: Pending

[2022-12-06 18:45:53.826389] INFO: StockRanker训练: 任务状态: Running

------ rolling_train: {'m19.__enabled__': False, 'm4.start_date': '2017-01-03', 'm4.end_date': '2018-01-09', 'm22.start_date': '2018-01-10', 'm22.end_date': '2018-02-08'}

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-8ad44a39151e4d069ac46999f4c5d4ca"}/bigcharts-data-end

------ rolling_train: {'m19.__enabled__': False, 'm4.start_date': '2017-02-09', 'm4.end_date': '2018-02-08', 'm22.start_date': '2018-02-09', 'm22.end_date': '2018-03-19'}