{"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":"-560: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":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-560:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-567:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-574:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-581:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-591:options_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"to_node_id":"-574:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-591:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"to_node_id":"-567:input_data","from_node_id":"-560:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-567:data"},{"to_node_id":"-581:input_data","from_node_id":"-574:data"},{"to_node_id":"-86:input_data","from_node_id":"-581:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","from_node_id":"-86: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":"2016-01-01","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, -22) / 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":"# #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\ndeal_number_0\npe_lyr_0\nturn_0\nta_ma(close, derive='golden_cross')\nbeta_gem_10_0\nlist_days_0\nreturn_9\nvolume_0\nvolume_1\nvolatility_10_0\nsh_holder_num_0\nbeta_csi800_5_0\nfs_roe_0\nfs_roa_ttm_0\nfs_net_profit_yoy_0\nrank_pb_lf_0\nrank_return_9\nrank_pe_ttm_0\ncompany_found_date_0\nclose_0\nmf_net_amount_0\nmarket_cap_0\ndeal_number_0\nhigh_0\nprice_limit_status_0\nin_sse50_0\nswing_volatility_120_0\nlow_0\nlist_board_0\nvolume_0\nvolatility_120_0\nbeta_industry1_120_0\nmarket_cap_float_0","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-bdf8-104b137c8601-43","module_id":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","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":"100","type":"Literal","bound_global_parameter":null},{"name":"number_of_trees","value":"1","type":"Literal","bound_global_parameter":null},{"name":"learning_rate","value":"0.025","type":"Literal","bound_global_parameter":null},{"name":"max_bins","value":1023,"type":"Literal","bound_global_parameter":null},{"name":"feature_fraction","value":"0.7","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":6,"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":"True","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":"2016-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2023-01-01","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":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true},{"node_id":"-560","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":"-560"},{"name":"features","node_id":"-560"}],"output_ports":[{"name":"data","node_id":"-560"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-567","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":"True","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"True","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-567"},{"name":"features","node_id":"-567"}],"output_ports":[{"name":"data","node_id":"-567"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-574","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":"-574"},{"name":"features","node_id":"-574"}],"output_ports":[{"name":"data","node_id":"-574"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-581","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":"True","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"True","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-581"},{"name":"features","node_id":"-581"}],"output_ports":[{"name":"data","node_id":"-581"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-591","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 = 8\n # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]\n context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.3\n context.options['hold_days'] = 12\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 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 context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","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":"open","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"close","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":"50000","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":"后复权","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":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-591"},{"name":"options_data","node_id":"-591"},{"name":"history_ds","node_id":"-591"},{"name":"benchmark_ds","node_id":"-591"},{"name":"trading_calendar","node_id":"-591"}],"output_ports":[{"name":"raw_perf","node_id":"-591"}],"cacheable":false,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-86","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"-86"}],"output_ports":[{"name":"data","node_id":"-86"}],"cacheable":true,"seq_num":14,"comment":"","comment_collapsed":true},{"node_id":"-613","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\n train_instruments_mid='m1', # 训练数据 证券代码列表 模块id\n test_instruments_mid='m9', # 测试数据 证券代码列表 模块id\n predict_mid='m8', # 预测 模块id\n trade_mid='m19', # 回测 模块id\n start_date='2015-09-01', # 数据开始日期\n end_date=T.live_run_param('trading_date', '2023-01-01'), # 数据结束日期\n train_update_days=500, # 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=500, # 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=500, # 最大数据天数，按交易日计算，0，表示没有限制，否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期\n rolling_count_for_live=1, #实盘模式下滚动次数，模拟实盘模式下，取最后多少次滚动。一般在模拟实盘模式下，只用到最后一次滚动训练的模型，这里可以设置为1；如果你的滚动训练数据时间段很短，以至于期间可能没有训练数据，这里可以设置大一点。0表示没有限制\n):\n def merge_datasources(input_1):\n df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]\n df = pd.concat(df_list)\n instrument_data = {\n 'start_date': df['date'].min().strftime('%Y-%m-%d'),\n 'end_date': df['date'].max().strftime('%Y-%m-%d'),\n 'instruments': list(set(df['instrument'])),\n }\n return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))\n\n def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):\n # 是否实盘模式\n tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])\n is_live_run = T.live_run_param('trading_date', None) is not None\n\n if is_live_run and train_update_days_for_live:\n train_update_days = train_update_days_for_live\n\n rollings = []\n train_end_date = train_data_min_days\n while train_end_date < len(tdays):\n if train_data_max_days is not None:\n train_start_date = max(train_end_date - train_data_max_days, 0)\n else:\n train_start_date = start_date\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":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"bq_graph_port","node_id":"-613"},{"name":"input_1","node_id":"-613"},{"name":"input_2","node_id":"-613"},{"name":"input_3","node_id":"-613"}],"output_ports":[{"name":"result","node_id":"-613"}],"cacheable":false,"seq_num":4,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='207,75,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,194,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='585,-25,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='639,561,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='906,647,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1071,125,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='376,469,200,200'/><node_position Node='-560' Position='381,188,200,200'/><node_position Node='-567' Position='385,280,200,200'/><node_position Node='-574' Position='1078,236,200,200'/><node_position Node='-581' Position='1082,327,200,200'/><node_position Node='-591' Position='1033,749,200,200'/><node_position Node='-86' Position='1070,522,200,200'/><node_position Node='-613' Position='268.277587890625,741,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}

# 本代码由可视化策略环境自动生成 2023年1月11日 14:48
# 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=0.0003, 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 = 8
    # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
    context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.3
    context.options['hold_days'] = 12

# 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()}
        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:
            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


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2015-01-01',
    'm1.end_date': '2016-01-01',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.label_expr': """# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -22) / shift(open, -1)

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

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

# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.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
deal_number_0
pe_lyr_0
turn_0
ta_ma(close, derive='golden_cross')
beta_gem_10_0
list_days_0
return_9
volume_0
volume_1
volatility_10_0
sh_holder_num_0
beta_csi800_5_0
fs_roe_0
fs_roa_ttm_0
fs_net_profit_yoy_0
rank_pb_lf_0
rank_return_9
rank_pe_ttm_0
company_found_date_0
close_0
mf_net_amount_0
market_cap_0
deal_number_0
high_0
price_limit_status_0
in_sse50_0
swing_volatility_120_0
low_0
list_board_0
volume_0
volatility_120_0
beta_industry1_120_0
market_cap_float_0""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 90,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m3.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': True,
    'm16.remove_extra_columns': True,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m2.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': True,

    'm13': 'M.dropnan.v1',
    'm13.input_data': T.Graph.OutputPort('m7.data'),

    'm6': 'M.stock_ranker_train.v5',
    'm6.training_ds': T.Graph.OutputPort('m13.data'),
    'm6.features': T.Graph.OutputPort('m3.data'),
    'm6.learning_algorithm': '排序',
    'm6.number_of_leaves': 30,
    'm6.minimum_docs_per_leaf': 100,
    'm6.number_of_trees': 1,
    'm6.learning_rate': 0.025,
    'm6.max_bins': 1023,
    'm6.feature_fraction': 0.7,
    'm6.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2016-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2023-01-01'),
    'm9.market': 'CN_STOCK_A',
    'm9.instrument_list': '',
    'm9.max_count': 0,

    'm17': 'M.general_feature_extractor.v7',
    'm17.instruments': T.Graph.OutputPort('m9.data'),
    'm17.features': T.Graph.OutputPort('m3.data'),
    'm17.start_date': '',
    'm17.end_date': '',
    'm17.before_start_days': 90,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m17.data'),
    'm18.features': T.Graph.OutputPort('m3.data'),
    'm18.date_col': 'date',
    'm18.instrument_col': 'instrument',
    'm18.drop_na': True,
    'm18.remove_extra_columns': True,

    'm14': 'M.dropnan.v1',
    'm14.input_data': T.Graph.OutputPort('m18.data'),

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m14.data'),
    'm8.m_lazy_run': False,

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m8.predictions'),
    'm19.start_date': '',
    'm19.end_date': '',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.prepare': m19_prepare_bigquant_run,
    'm19.volume_limit': 0.025,
    'm19.order_price_field_buy': 'open',
    'm19.order_price_field_sell': 'close',
    'm19.capital_base': 50000,
    'm19.auto_cancel_non_tradable_orders': True,
    'm19.data_frequency': 'daily',
    'm19.price_type': '后复权',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '',
})

# g.run({})


def m4_run_bigquant_run(
    bq_graph,
    inputs,
    trading_days_market='CN', # 使用那个市场的交易日历
    train_instruments_mid='m1', # 训练数据 证券代码列表 模块id
    test_instruments_mid='m9', # 测试数据 证券代码列表 模块id
    predict_mid='m8', # 预测 模块id
    trade_mid='m19', # 回测 模块id
    start_date='2015-09-01', # 数据开始日期
    end_date=T.live_run_param('trading_date', '2023-01-01'), # 数据结束日期
    train_update_days=500, # 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=500, # 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=500, # 最大数据天数，按交易日计算，0，表示没有限制，否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期
    rolling_count_for_live=1, #实盘模式下滚动次数，模拟实盘模式下，取最后多少次滚动。一般在模拟实盘模式下，只用到最后一次滚动训练的模型，这里可以设置为1；如果你的滚动训练数据时间段很短，以至于期间可能没有训练数据，这里可以设置大一点。0表示没有限制
):
    def merge_datasources(input_1):
        df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]
        df = pd.concat(df_list)
        instrument_data = {
            'start_date': df['date'].min().strftime('%Y-%m-%d'),
            'end_date': df['date'].max().strftime('%Y-%m-%d'),
            'instruments': list(set(df['instrument'])),
        }
        return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))

    def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):
        # 是否实盘模式
        tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])
        is_live_run = T.live_run_param('trading_date', None) is not None

        if is_live_run and train_update_days_for_live:
            train_update_days = train_update_days_for_live

        rollings = []
        train_end_date = train_data_min_days
        while train_end_date < len(tdays):
            if train_data_max_days is not None:
                train_start_date = max(train_end_date - train_data_max_days, 0)
            else:
                train_start_date = start_date
            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}


m4 = M.hyper_rolling_train.v1(
    run=m4_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2023-01-11 14:32:30.610799] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-11 14:32:30.741843] INFO: moduleinvoker: instruments.v2 运行完成[0.131059s].

[2023-01-11 14:32:30.747930] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-01-11 14:32:30.758259] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:32:30.760041] INFO: moduleinvoker: input_features.v1 运行完成[0.012123s].

[2023-01-11 14:32:30.766225] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-11 14:32:30.847166] INFO: moduleinvoker: instruments.v2 运行完成[0.080936s].

[2023-01-11 14:32:30.856645] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-01-11 14:32:32.565990] INFO: 自动标注(股票): 加载历史数据: 1357857 行

[2023-01-11 14:32:32.567713] INFO: 自动标注(股票): 开始标注 ..

[2023-01-11 14:32:34.163453] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[3.306802s].

[2023-01-11 14:32:34.307987] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-11 14:32:37.781205] INFO: 基础特征抽取: 年份 2015, 特征行数=335071

[2023-01-11 14:32:43.832305] INFO: 基础特征抽取: 年份 2016, 特征行数=641546

[2023-01-11 14:32:49.012422] INFO: 基础特征抽取: 年份 2017, 特征行数=521324

[2023-01-11 14:32:49.206438] INFO: 基础特征抽取: 总行数: 1497941

[2023-01-11 14:32:49.218801] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[14.91083s].

[2023-01-11 14:32:49.235690] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-11 14:32:53.543911] INFO: 基础特征抽取: 年份 2017, 特征行数=418227

[2023-01-11 14:33:01.419754] INFO: 基础特征抽取: 年份 2018, 特征行数=816987

[2023-01-11 14:33:08.104598] INFO: 基础特征抽取: 年份 2019, 特征行数=677314

[2023-01-11 14:33:08.261249] INFO: 基础特征抽取: 总行数: 1912528

[2023-01-11 14:33:08.268612] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[19.032943s].

[2023-01-11 14:33:08.281722] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-11 14:33:12.732244] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.006s

[2023-01-11 14:33:12.739703] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.005s

[2023-01-11 14:33:12.744392] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.003s

[2023-01-11 14:33:12.790239] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.044s

[2023-01-11 14:33:12.796068] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s

[2023-01-11 14:33:12.801736] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.003s

[2023-01-11 14:33:24.424702] INFO: derived_feature_extractor: 提取完成 ta_ma(close, derive='golden_cross'), 11.621s

[2023-01-11 14:33:26.232106] INFO: derived_feature_extractor: /y_2015, 335071

[2023-01-11 14:33:28.305090] INFO: derived_feature_extractor: /y_2016, 641546

[2023-01-11 14:33:30.557308] INFO: derived_feature_extractor: /y_2017, 521324

[2023-01-11 14:33:31.543335] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[23.261604s].

[2023-01-11 14:33:31.551813] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-11 14:33:36.920661] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.006s

[2023-01-11 14:33:36.929196] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.007s

[2023-01-11 14:33:36.934080] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.003s

[2023-01-11 14:33:36.990257] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.055s

[2023-01-11 14:33:36.995849] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s

[2023-01-11 14:33:37.000810] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.003s

[2023-01-11 14:33:49.975877] INFO: derived_feature_extractor: 提取完成 ta_ma(close, derive='golden_cross'), 12.973s

[2023-01-11 14:33:51.972894] INFO: derived_feature_extractor: /y_2017, 418227

[2023-01-11 14:33:54.815852] INFO: derived_feature_extractor: /y_2018, 816987

[2023-01-11 14:33:58.074914] INFO: derived_feature_extractor: /y_2019, 677314

[2023-01-11 14:33:59.598016] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[28.046182s].

[2023-01-11 14:33:59.608644] INFO: moduleinvoker: join.v3 开始运行..

[2023-01-11 14:34:04.483338] INFO: join: /y_2015, 行数=181895/309560, 耗时=1.962837s

[2023-01-11 14:34:09.159552] INFO: join: /y_2016, 行数=607130/608596, 耗时=4.672488s

[2023-01-11 14:34:12.355616] INFO: join: /y_2017, 行数=403001/470421, 耗时=3.190824s

[2023-01-11 14:34:12.509662] INFO: join: 最终行数: 1192026

[2023-01-11 14:34:12.528339] INFO: moduleinvoker: join.v3 运行完成[12.91969s].

[2023-01-11 14:34:12.538652] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-11 14:34:14.964926] INFO: dropnan: /y_2017, 381252/381252

[2023-01-11 14:34:17.987807] INFO: dropnan: /y_2018, 760436/760436

[2023-01-11 14:34:20.499002] INFO: dropnan: /y_2019, 622561/622561

[2023-01-11 14:34:20.660722] INFO: dropnan: 行数: 1764249/1764249

[2023-01-11 14:34:20.673111] INFO: moduleinvoker: dropnan.v1 运行完成[8.134456s].

[2023-01-11 14:34:20.683641] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-11 14:34:22.124867] INFO: dropnan: /y_2015, 181895/181895

[2023-01-11 14:34:24.741709] INFO: dropnan: /y_2016, 607130/607130

[2023-01-11 14:34:26.554558] INFO: dropnan: /y_2017, 403001/403001

[2023-01-11 14:34:26.773878] INFO: dropnan: 行数: 1192026/1192026

[2023-01-11 14:34:26.782533] INFO: moduleinvoker: dropnan.v1 运行完成[6.098885s].

[2023-01-11 14:34:26.792779] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2023-01-11 14:34:31.311072] INFO: StockRanker: 特征预处理 ..

[2023-01-11 14:34:37.582097] INFO: StockRanker: prepare data: training ..

[2023-01-11 14:35:12.959850] INFO: StockRanker训练: feab9714 准备训练: 1192026 行数

[2023-01-11 14:35:13.222540] INFO: StockRanker训练: 正在训练 ..

[2023-01-11 14:36:33.874065] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[127.081281s].

[2023-01-11 14:36:33.885097] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-01-11 14:36:35.946092] INFO: StockRanker预测: /y_2017 ..

[2023-01-11 14:36:38.108114] INFO: StockRanker预测: /y_2018 ..

[2023-01-11 14:36:40.217138] INFO: StockRanker预测: /y_2019 ..

[2023-01-11 14:36:42.557885] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[8.672789s].

[2023-01-11 14:36:42.564867] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-11 14:36:42.571715] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:36:42.573553] INFO: moduleinvoker: instruments.v2 运行完成[0.00869s].

[2023-01-11 14:36:42.577665] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-01-11 14:36:42.584395] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:36:42.586214] INFO: moduleinvoker: input_features.v1 运行完成[0.008544s].

[2023-01-11 14:36:42.591642] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-11 14:36:42.695781] INFO: moduleinvoker: instruments.v2 运行完成[0.104111s].

[2023-01-11 14:36:42.709836] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-01-11 14:36:44.888114] INFO: 自动标注(股票): 加载历史数据: 1716210 行

[2023-01-11 14:36:44.890451] INFO: 自动标注(股票): 开始标注 ..

[2023-01-11 14:36:46.786932] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[4.077099s].

[2023-01-11 14:36:46.806594] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-11 14:36:46.814630] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:36:46.817034] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010475s].

[2023-01-11 14:36:46.832591] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-11 14:36:51.419510] INFO: 基础特征抽取: 年份 2019, 特征行数=419475

[2023-01-11 14:37:00.497965] INFO: 基础特征抽取: 年份 2020, 特征行数=945961

[2023-01-11 14:37:09.323873] INFO: 基础特征抽取: 年份 2021, 特征行数=867534

[2023-01-11 14:37:09.490090] INFO: 基础特征抽取: 总行数: 2232970

[2023-01-11 14:37:09.499088] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[22.666506s].

[2023-01-11 14:37:09.508819] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-11 14:37:09.516345] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:37:09.518219] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009403s].

[2023-01-11 14:37:09.529362] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-11 14:37:17.594960] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.007s

[2023-01-11 14:37:17.605713] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.008s

[2023-01-11 14:37:17.613767] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.006s

[2023-01-11 14:37:17.619591] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.004s

[2023-01-11 14:37:17.625008] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s

[2023-01-11 14:37:17.689986] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.063s

[2023-01-11 14:37:34.105950] INFO: derived_feature_extractor: 提取完成 ta_ma(close, derive='golden_cross'), 16.414s

[2023-01-11 14:37:36.354799] INFO: derived_feature_extractor: /y_2019, 419475

[2023-01-11 14:37:39.431742] INFO: derived_feature_extractor: /y_2020, 945961

[2023-01-11 14:37:43.501586] INFO: derived_feature_extractor: /y_2021, 867534

[2023-01-11 14:37:45.589868] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[36.060492s].

[2023-01-11 14:37:45.600402] INFO: moduleinvoker: join.v3 开始运行..

[2023-01-11 14:37:51.928791] INFO: join: /y_2017, 行数=203358/381252, 耗时=2.462473s

[2023-01-11 14:37:57.996715] INFO: join: /y_2018, 行数=757879/760436, 耗时=6.064534s

[2023-01-11 14:38:02.749645] INFO: join: /y_2019, 行数=548240/622561, 耗时=4.746022s

[2023-01-11 14:38:03.120762] INFO: join: 最终行数: 1509477

[2023-01-11 14:38:03.138117] INFO: moduleinvoker: join.v3 运行完成[17.537734s].

[2023-01-11 14:38:03.147211] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-11 14:38:05.931810] INFO: dropnan: /y_2019, 379913/379913

[2023-01-11 14:38:08.767012] INFO: dropnan: /y_2020, 808659/808659

[2023-01-11 14:38:11.644990] INFO: dropnan: /y_2021, 700256/700256

[2023-01-11 14:38:11.842938] INFO: dropnan: 行数: 1888828/1888828

[2023-01-11 14:38:11.852176] INFO: moduleinvoker: dropnan.v1 运行完成[8.704957s].

[2023-01-11 14:38:11.861783] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-11 14:38:14.062279] INFO: dropnan: /y_2017, 203358/203358

[2023-01-11 14:38:17.869098] INFO: dropnan: /y_2018, 757879/757879

[2023-01-11 14:38:20.443832] INFO: dropnan: /y_2019, 548240/548240

[2023-01-11 14:38:20.720478] INFO: dropnan: 行数: 1509477/1509477

[2023-01-11 14:38:20.732279] INFO: moduleinvoker: dropnan.v1 运行完成[8.870486s].

[2023-01-11 14:38:20.742206] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2023-01-11 14:38:26.805165] INFO: StockRanker: 特征预处理 ..

[2023-01-11 14:38:34.739086] INFO: StockRanker: prepare data: training ..

[2023-01-11 14:39:19.282255] INFO: StockRanker训练: 8a1d8af0 准备训练: 1509477 行数

[2023-01-11 14:39:19.632759] INFO: StockRanker训练: 正在训练 ..

[2023-01-11 14:40:40.250015] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[139.507794s].

[2023-01-11 14:40:40.260372] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-01-11 14:40:42.744618] INFO: StockRanker预测: /y_2019 ..

[2023-01-11 14:40:45.313168] INFO: StockRanker预测: /y_2020 ..

[2023-01-11 14:40:48.023753] INFO: StockRanker预测: /y_2021 ..

[2023-01-11 14:40:50.764501] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[10.50411s].

[2023-01-11 14:40:50.796058] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-11 14:40:50.804670] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:40:50.806428] INFO: moduleinvoker: instruments.v2 运行完成[0.010396s].

[2023-01-11 14:40:50.810542] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-01-11 14:40:50.817023] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:40:50.818547] INFO: moduleinvoker: input_features.v1 运行完成[0.008007s].

[2023-01-11 14:40:50.823581] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-11 14:40:50.889488] INFO: moduleinvoker: instruments.v2 运行完成[0.065885s].

[2023-01-11 14:40:50.900764] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-01-11 14:40:53.359614] INFO: 自动标注(股票): 加载历史数据: 2021042 行

[2023-01-11 14:40:53.361313] INFO: 自动标注(股票): 开始标注 ..

[2023-01-11 14:40:55.747799] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[4.847026s].

[2023-01-11 14:40:55.767833] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-11 14:40:55.777092] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:40:55.779469] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011665s].

[2023-01-11 14:40:55.795515] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-11 14:41:00.634942] INFO: 基础特征抽取: 年份 2021, 特征行数=448657

[2023-01-11 14:41:11.262940] INFO: 基础特征抽取: 年份 2022, 特征行数=1171038

[2023-01-11 14:41:11.388369] INFO: 基础特征抽取: 总行数: 1619695

[2023-01-11 14:41:11.398773] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[15.603272s].

[2023-01-11 14:41:11.408062] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-11 14:41:11.419846] INFO: moduleinvoker: 命中缓存

[2023-01-11 14:41:11.421772] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.01372s].

[2023-01-11 14:41:11.429343] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-11 14:41:16.291534] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.021s

[2023-01-11 14:41:16.299671] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.006s

[2023-01-11 14:41:16.305708] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.004s

[2023-01-11 14:41:16.311356] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.004s

[2023-01-11 14:41:16.317032] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.003s

[2023-01-11 14:41:16.321834] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.003s

[2023-01-11 14:41:33.477645] INFO: derived_feature_extractor: 提取完成 ta_ma(close, derive='golden_cross'), 17.154s

[2023-01-11 14:41:35.554204] INFO: derived_feature_extractor: /y_2021, 448657

[2023-01-11 14:41:38.937051] INFO: derived_feature_extractor: /y_2022, 1171038

[2023-01-11 14:41:41.045185] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[29.615825s].

[2023-01-11 14:41:41.057013] INFO: moduleinvoker: join.v3 开始运行..

[2023-01-11 14:41:47.683288] INFO: join: /y_2019, 行数=186589/379913, 耗时=2.623978s

[2023-01-11 14:41:55.847548] INFO: join: /y_2020, 行数=804293/808659, 耗时=8.159243s

[2023-01-11 14:42:01.433723] INFO: join: /y_2021, 行数=623380/700256, 耗时=5.580112s

[2023-01-11 14:42:01.632629] INFO: join: 最终行数: 1614262

[2023-01-11 14:42:01.651357] INFO: moduleinvoker: join.v3 运行完成[20.594346s].

[2023-01-11 14:42:01.661334] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-11 14:42:03.608983] INFO: dropnan: /y_2021, 328372/328372

[2023-01-11 14:42:07.245979] INFO: dropnan: /y_2022, 769994/769994

[2023-01-11 14:42:07.628932] INFO: dropnan: 行数: 1098366/1098366

[2023-01-11 14:42:07.639599] INFO: moduleinvoker: dropnan.v1 运行完成[5.978255s].

[2023-01-11 14:42:07.649603] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-11 14:42:09.162498] INFO: dropnan: /y_2019, 186589/186589

[2023-01-11 14:42:12.726752] INFO: dropnan: /y_2020, 804293/804293

[2023-01-11 14:42:15.507079] INFO: dropnan: /y_2021, 623380/623380

[2023-01-11 14:42:15.682844] INFO: dropnan: 行数: 1614262/1614262

[2023-01-11 14:42:15.697877] INFO: moduleinvoker: dropnan.v1 运行完成[8.048255s].

[2023-01-11 14:42:15.708023] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2023-01-11 14:42:21.810085] INFO: StockRanker: 特征预处理 ..

[2023-01-11 14:42:30.474153] INFO: StockRanker: prepare data: training ..

[2023-01-11 14:43:18.241838] INFO: StockRanker训练: 162a7fbc 准备训练: 1614262 行数

[2023-01-11 14:43:18.602193] INFO: StockRanker训练: 正在训练 ..

[2023-01-11 14:44:49.181472] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[153.473449s].

[2023-01-11 14:44:49.192407] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-01-11 14:44:50.417395] INFO: StockRanker预测: /y_2021 ..

[2023-01-11 14:44:52.464839] INFO: StockRanker预测: /y_2022 ..

[2023-01-11 14:44:54.457112] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[5.264706s].

[2023-01-11 14:44:54.520836] INFO: moduleinvoker: cached.v3 开始运行..

[2023-01-11 14:44:57.450920] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: AttributeError: 'DataFrame' object has no attribute 'ix'

[2023-01-11 14:44:57.460010] ERROR: moduleinvoker: module name: hyper_rolling_train, module version: v1, trackeback: AttributeError: 'DataFrame' object has no attribute 'ix'

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-e0ae44ff8de34d798c27d7da57b783f9"}/bigcharts-data-end

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-05539c9771a949fab358547f3987302b"}/bigcharts-data-end

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-c5fe20ece6b74818ae39bab57bc818a3"}/bigcharts-data-end

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-2-6b12df1b7ff1> in <module>
    327 
    328 
--> 329 m4 = M.hyper_rolling_train.v1(
    330     run=m4_run_bigquant_run,
    331     run_now=True,

<ipython-input-2-6b12df1b7ff1> in m4_run_bigquant_run(bq_graph, inputs, trading_days_market, train_instruments_mid, test_instruments_mid, predict_mid, trade_mid, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)
    315 
    316     # 合并预测结果并回测
--> 317     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])
    318     parameters = {}
    319     parameters['*.__enabled__'] = False

<ipython-input-2-6b12df1b7ff1> in merge_datasources(input_1)
    256 ):
    257     def merge_datasources(input_1):
--> 258         df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]
    259         df = pd.concat(df_list)
    260         instrument_data = {

<ipython-input-2-6b12df1b7ff1> in <listcomp>(.0)
    256 ):
    257     def merge_datasources(input_1):
--> 258         df_list = [ds[0].read_df().set_index('date').ix[ds[1]:].reset_index() for ds in input_1]
    259         df = pd.concat(df_list)
    260         instrument_data = {

AttributeError: 'DataFrame' object has no attribute 'ix'