克隆策略

StockRanker多因子选股策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-274: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":"-274:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-281:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-288:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-295: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":"-6060:options_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"to_node_id":"-288:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-6060:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-598:input_1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","from_node_id":"-86:data"},{"to_node_id":"-281:input_data","from_node_id":"-274:data"},{"to_node_id":"-177:input_data","from_node_id":"-281:data"},{"to_node_id":"-295:input_data","from_node_id":"-288:data"},{"to_node_id":"-181:input_data","from_node_id":"-295:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:features_ds","from_node_id":"-173:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","from_node_id":"-173:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-177:data"},{"to_node_id":"-86:input_data","from_node_id":"-181:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","from_node_id":"-598:data_1"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2010-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2021-11-01","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, -5) / shift(open, -1)\n\n# 极值处理:用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类,这里使用20个分类\nall_wbins(label, 20)\n\n# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","type":"Literal","bound_global_parameter":null},{"name":"start_date","value":"","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\n\nrank(((high_0+low_0+close_0+open_0)/4-max((high_0+low_0+close_0+open_0)/4,15)))**delta(close_0,5)\n(ts_rank(volume_0/mean(volume_0,20),20)*ts_rank((-1*delta(close_0,7)),8))\nfs_net_cash_flow_0/fs_net_income_0\nmean(mf_net_pct_l_0,90)\nmean(mf_net_pct_l_0,60)\nmean(mf_net_pct_l_0,30)\navg_amount_180\nmean(mf_net_pct_l_0,120)\nean(mf_net_pct_main_0,90)\nsh_holder_avg_pct_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":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":"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":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"data1","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"name":"data2","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","module_id":"BigQuantSpace.stock_ranker_predict.stock_ranker_predict-v5","parameters":[{"name":"m_lazy_run","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"model","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"output_ports":[{"name":"predictions","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"name":"m_lazy_run","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"cacheable":true,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2020-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2021-07-01","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":"-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":"-274","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-274"},{"name":"features","node_id":"-274"}],"output_ports":[{"name":"data","node_id":"-274"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-281","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":"-281"},{"name":"features","node_id":"-281"}],"output_ports":[{"name":"data","node_id":"-281"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-288","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":"60","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-288"},{"name":"features","node_id":"-288"}],"output_ports":[{"name":"data","node_id":"-288"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-295","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":"-295"},{"name":"features","node_id":"-295"}],"output_ports":[{"name":"data","node_id":"-295"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-6060","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"2020-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2021-01-01","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 = 3\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 = 0.5\n context.options['hold_days'] = 1\n","type":"Literal","bound_global_parameter":null},{"name":"handle_data","value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金\n # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}\n 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 # print('rank order for sell %s' % instruments)\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":1000000,"type":"Literal","bound_global_parameter":null},{"name":"auto_cancel_non_tradable_orders","value":"True","type":"Literal","bound_global_parameter":null},{"name":"data_frequency","value":"daily","type":"Literal","bound_global_parameter":null},{"name":"price_type","value":"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":"-6060"},{"name":"options_data","node_id":"-6060"},{"name":"history_ds","node_id":"-6060"},{"name":"benchmark_ds","node_id":"-6060"},{"name":"trading_calendar","node_id":"-6060"}],"output_ports":[{"name":"raw_perf","node_id":"-6060"}],"cacheable":false,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-200","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='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='m4', # 回测 模块id\n start_date='2015-01-01', # 数据开始日期\n end_date=T.live_run_param('trading_date', '2021-01-01'), # 数据结束日期\n train_update_days=250, # 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":"-200"},{"name":"input_1","node_id":"-200"},{"name":"input_2","node_id":"-200"},{"name":"input_3","node_id":"-200"}],"output_ports":[{"name":"result","node_id":"-200"}],"cacheable":false,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-173","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\n\nrank(((high_0+low_0+close_0+open_0)/4-max((high_0+low_0+close_0+open_0)/4,15)))**delta(close_0,5)\n (ts_rank(volume_0/mean(volume_0,20),20)*ts_rank((-1*delta(close_0,7)),8))\nfs_net_cash_flow_0/fs_net_income_0\nmean(mf_net_pct_l_0,90)\nmean(mf_net_pct_l_0,60)\nmean(mf_net_pct_l_0,30)\navg_amount_180\nmean(mf_net_pct_l_0,120)\nean(mf_net_pct_main_0,90)\nsh_holder_avg_pct_0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-173"}],"output_ports":[{"name":"data","node_id":"-173"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-177","module_id":"BigQuantSpace.aa.aa-v5","parameters":[{"name":"day_number","value":100,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-177"}],"output_ports":[{"name":"data","node_id":"-177"}],"cacheable":true,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-181","module_id":"BigQuantSpace.aa.aa-v5","parameters":[{"name":"day_number","value":100,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-181"}],"output_ports":[{"name":"data","node_id":"-181"}],"cacheable":true,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-598","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"# Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n # 示例代码如下。在这里编写您的代码\n df = input_1.read_df()#读取上一个模块的数据\n ins= list(df.instrument.unique())\n start = df.date.min()\n end = df.date.max()\n df1=D.history_data(instruments=ins,start_date=start,end_date=end,fields=['close_0','high_0','low_0','st_status_0'])\n df_final=pd.merge(df,df1,on=['date''instrument'])\n df_final=df_final[df_final['st_status_0']==0]\n df_final=df_final[df_final['low_0']>df_final['high_1']]\n df_final=df_final[df_final['close_0']>df_final['open_0']+0.02]\n data_1=DataSource.write_df(df_final)\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","type":"Literal","bound_global_parameter":null},{"name":"post_run","value":"# 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。\ndef bigquant_run(outputs):\n return outputs\n","type":"Literal","bound_global_parameter":null},{"name":"input_ports","value":"","type":"Literal","bound_global_parameter":null},{"name":"params","value":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-598"},{"name":"input_2","node_id":"-598"},{"name":"input_3","node_id":"-598"}],"output_ports":[{"name":"data_1","node_id":"-598"},{"name":"data_2","node_id":"-598"},{"name":"data_3","node_id":"-598"}],"cacheable":true,"seq_num":10,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='211,64,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,183,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='625,-8,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='620,742,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='116,429,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='662,919,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1073,125,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='244,526,200,200'/><node_position Node='-86' Position='1066,535,200,200'/><node_position Node='-274' Position='381,188,200,200'/><node_position Node='-281' Position='379,278,200,200'/><node_position Node='-288' Position='1078,236,200,200'/><node_position Node='-295' Position='1081,325,200,200'/><node_position Node='-6060' Position='926,1069,200,200'/><node_position Node='-200' Position='-21,709,200,200'/><node_position Node='-173' Position='784,-132,200,200'/><node_position Node='-177' Position='360,365,200,200'/><node_position Node='-181' Position='1062,412,200,200'/><node_position Node='-598' Position='395.53094482421875,614.2508544921875,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [31]:
    # 本代码由可视化策略环境自动生成 2021年11月17日 13:04
    # 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
    
    
    # Python 代码入口函数,input_1/2/3 对应三个输入端,data_1/2/3 对应三个输出端
    def m10_run_bigquant_run(input_1, input_2, input_3):
        # 示例代码如下。在这里编写您的代码
        df = input_1.read_df()#读取上一个模块的数据
        ins= list(df.instrument.unique())
        start = df.date.min()
        end = df.date.max()
        df1=D.history_data(instruments=ins,start_date=start,end_date=end,fields=['close_0','high_0','low_0','st_status_0'])
        df_final=pd.merge(df,df1,on=['date''instrument'])
        df_final=df_final[df_final['st_status_0']==0]
        df_final=df_final[df_final['low_0']>df_final['high_1']]
        df_final=df_final[df_final['close_0']>df_final['open_0']+0.02]
        data_1=DataSource.write_df(df_final)
        return Outputs(data_1=data_1, data_2=None, data_3=None)
    
    # 后处理函数,可选。输入是主函数的输出,可以在这里对数据做处理,或者返回更友好的outputs数据格式。此函数输出不会被缓存。
    def m10_post_run_bigquant_run(outputs):
        return outputs
    
    # 回测引擎:初始化函数,只执行一次
    def m4_initialize_bigquant_run(context):
        # 加载预测数据
        context.ranker_prediction = context.options['data'].read_df()
    
        # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
        context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
        # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
        # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
        stock_count = 3
        # 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 = 0.5
        context.options['hold_days'] = 1
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m4_handle_data_bigquant_run(context, data):
        # 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]))])))
            # print('rank order for sell %s' % instruments)
            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 m4_prepare_bigquant_run(context):
        pass
    
    
    g = T.Graph({
    
        'm1': 'M.instruments.v2',
        'm1.start_date': '2010-01-01',
        'm1.end_date': '2021-11-01',
        'm1.market': 'CN_STOCK_A',
        'm1.instrument_list': '',
        'm1.max_count': 0,
    
        'm2': 'M.advanced_auto_labeler.v2',
        'm2.instruments': T.Graph.OutputPort('m1.data'),
        'm2.label_expr': """# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
    #   添加benchmark_前缀,可使用对应的benchmark数据
    # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -5) / shift(open, -1)
    
    # 极值处理:用1%和99%分位的值做clip
    clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
    
    # 将分数映射到分类,这里使用20个分类
    all_wbins(label, 20)
    
    # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
    where(shift(high, -1) == shift(low, -1), NaN, label)
    """,
        'm2.start_date': '',
        'm2.end_date': '',
        'm2.benchmark': '000300.SHA',
        'm2.drop_na_label': True,
        'm2.cast_label_int': True,
    
        'm9': 'M.instruments.v2',
        'm9.start_date': T.live_run_param('trading_date', '2020-01-01'),
        'm9.end_date': T.live_run_param('trading_date', '2021-07-01'),
        'm9.market': 'CN_STOCK_A',
        'm9.instrument_list': '',
        'm9.max_count': 0,
    
        'm12': 'M.input_features.v1',
        'm12.features': """# #号开始的表示注释
    # 多个特征,每行一个,可以包含基础特征和衍生特征
    
    rank(((high_0+low_0+close_0+open_0)/4-max((high_0+low_0+close_0+open_0)/4,15)))**delta(close_0,5)
     (ts_rank(volume_0/mean(volume_0,20),20)*ts_rank((-1*delta(close_0,7)),8))
    fs_net_cash_flow_0/fs_net_income_0
    mean(mf_net_pct_l_0,90)
    mean(mf_net_pct_l_0,60)
    mean(mf_net_pct_l_0,30)
    avg_amount_180
    mean(mf_net_pct_l_0,120)
    ean(mf_net_pct_main_0,90)
    sh_holder_avg_pct_0""",
    
        'm3': 'M.input_features.v1',
        'm3.features_ds': T.Graph.OutputPort('m12.data'),
        '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
    
    rank(((high_0+low_0+close_0+open_0)/4-max((high_0+low_0+close_0+open_0)/4,15)))**delta(close_0,5)
    (ts_rank(volume_0/mean(volume_0,20),20)*ts_rank((-1*delta(close_0,7)),8))
    fs_net_cash_flow_0/fs_net_income_0
    mean(mf_net_pct_l_0,90)
    mean(mf_net_pct_l_0,60)
    mean(mf_net_pct_l_0,30)
    avg_amount_180
    mean(mf_net_pct_l_0,120)
    ean(mf_net_pct_main_0,90)
    sh_holder_avg_pct_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': 0,
    
        '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': False,
        'm16.remove_extra_columns': False,
    
        'm11': 'M.aa.v5',
        'm11.input_data': T.Graph.OutputPort('m16.data'),
        'm11.day_number': 100,
    
        'm7': 'M.join.v3',
        'm7.data1': T.Graph.OutputPort('m2.data'),
        'm7.data2': T.Graph.OutputPort('m11.data'),
        'm7.on': 'date,instrument',
        'm7.how': 'inner',
        'm7.sort': False,
    
        'm13': 'M.dropnan.v1',
        'm13.input_data': T.Graph.OutputPort('m7.data'),
    
        'm10': 'M.cached.v3',
        'm10.input_1': T.Graph.OutputPort('m13.data'),
        'm10.run': m10_run_bigquant_run,
        'm10.post_run': m10_post_run_bigquant_run,
        'm10.input_ports': '',
        'm10.params': '{}',
        'm10.output_ports': '',
    
        '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': 60,
    
        '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': False,
        'm18.remove_extra_columns': False,
    
        'm19': 'M.aa.v5',
        'm19.input_data': T.Graph.OutputPort('m18.data'),
        'm19.day_number': 100,
    
        'm14': 'M.dropnan.v1',
        'm14.input_data': T.Graph.OutputPort('m19.data'),
    
        'm6': 'M.stock_ranker_train.v5',
        'm6.training_ds': T.Graph.OutputPort('m10.data_1'),
        'm6.features': T.Graph.OutputPort('m12.data'),
        'm6.learning_algorithm': '排序',
        'm6.number_of_leaves': 30,
        'm6.minimum_docs_per_leaf': 1000,
        'm6.number_of_trees': 20,
        'm6.learning_rate': 0.1,
        'm6.max_bins': 1023,
        'm6.feature_fraction': 1,
        'm6.m_lazy_run': False,
    
        '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,
    
        'm4': 'M.trade.v4',
        'm4.instruments': T.Graph.OutputPort('m9.data'),
        'm4.options_data': T.Graph.OutputPort('m8.predictions'),
        'm4.start_date': '2020-01-01',
        'm4.end_date': '2021-01-01',
        'm4.initialize': m4_initialize_bigquant_run,
        'm4.handle_data': m4_handle_data_bigquant_run,
        'm4.prepare': m4_prepare_bigquant_run,
        'm4.volume_limit': 0.025,
        'm4.order_price_field_buy': 'open',
        'm4.order_price_field_sell': 'close',
        'm4.capital_base': 1000000,
        'm4.auto_cancel_non_tradable_orders': True,
        'm4.data_frequency': 'daily',
        'm4.price_type': '后复权',
        'm4.product_type': '股票',
        'm4.plot_charts': True,
        'm4.backtest_only': False,
        'm4.benchmark': '',
    })
    
    # g.run({})
    
    
    def m5_run_bigquant_run(
        bq_graph,
        inputs,
        trading_days_market='CN', # 使用那个市场的交易日历, TODO
        train_instruments_mid='m1', # 训练数据 证券代码列表 模块id
        test_instruments_mid='m9', # 测试数据 证券代码列表 模块id
        predict_mid='m8', # 预测 模块id
        trade_mid='m4', # 回测 模块id
        start_date='2015-01-01', # 数据开始日期
        end_date=T.live_run_param('trading_date', '2021-01-01'), # 数据结束日期
        train_update_days=250, # 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}
    
    
    m5 = M.hyper_rolling_train.v1(
        run=m5_run_bigquant_run,
        run_now=True,
        bq_graph=g
    )
    
    ---------------------------------------------------------------------------
    KeyError                                  Traceback (most recent call last)
    <ipython-input-31-40d7eb170148> in <module>
        344 
        345 
    --> 346 m5 = M.hyper_rolling_train.v1(
        347     run=m5_run_bigquant_run,
        348     run_now=True,
    
    <ipython-input-31-40d7eb170148> in m5_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)
        329         parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']
        330         # print('------ rolling_train:', parameters)
    --> 331         results.append(g.run(parameters))
        332 
        333     # 合并预测结果并回测
    
    <ipython-input-31-40d7eb170148> in m10_run_bigquant_run(input_1, input_2, input_3)
         10     start = df.date.min()
         11     end = df.date.max()
    ---> 12     df1=D.history_data(instruments=ins,start_date=start,end_date=end,fields=['close_0','high_0','low_0','st_status_0'])
         13     df_final=pd.merge(df,df1,on=['date''instrument'])
         14     df_final=df_final[df_final['st_status_0']==0]
    
    KeyError: 'instrument'