复制链接
克隆策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"-113:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-7701:input_2","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-185:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-189:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-122:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-129:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-2070:input_2","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-503:input_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-7701:input_1","from_node_id":"-113:data"},{"to_node_id":"-185:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-180:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-7701:data_1"},{"to_node_id":"-189:training_ds","from_node_id":"-503:data"},{"to_node_id":"-2070:input_1","from_node_id":"-503:data"},{"to_node_id":"-113:input_data","from_node_id":"-185:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","from_node_id":"-180:data"},{"to_node_id":"-122:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-141:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-189:predict_ds","from_node_id":"-86:data"},{"to_node_id":"-2070:input_3","from_node_id":"-86:data"},{"to_node_id":"-129:input_data","from_node_id":"-122:data"},{"to_node_id":"-86:input_data","from_node_id":"-129:data"},{"to_node_id":"-141:options_data","from_node_id":"-2070:data_1"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"return_5\nreturn_10\nreturn_20\navg_amount_0/avg_amount_5\navg_amount_5/avg_amount_20\nrank_avg_amount_0/rank_avg_amount_5\nrank_avg_amount_5/rank_avg_amount_10\nrank_return_0\nrank_return_5\nrank_return_10\nrank_return_0/rank_return_5\nrank_return_5/rank_return_10\npe_ttm_0\n","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"cacheable":true,"seq_num":1,"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":2,"comment":"","comment_collapsed":true},{"node_id":"-113","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-113"},{"name":"features","node_id":"-113"}],"output_ports":[{"name":"data","node_id":"-113"}],"cacheable":true,"seq_num":3,"comment":"","comment_collapsed":true},{"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":"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":4,"comment":"","comment_collapsed":true},{"node_id":"-7701","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, columns_input):\n # 示例代码如下。在这里编写您的代码\n df = input_1.read_df()\n if input_2==None:\n if columns_input==[]:\n print('请输入标准化的列名或连接输入因子列表模块')\n else:\n columns = columns_input\n else:\n columns = input_2.read_pickle()\n\n def standard(x):\n return (x-x.mean())/x.std() \n \n \n for fac in columns:\n median = df[fac].median()\n std = df[fac].std()\n df[fac] = df.groupby('date')[fac].apply(standard)\n \n ds = DataSource().write_df(df)\n return Outputs(data_1=ds)","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":"{\n 'columns_input': []\n}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"data_1","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-7701"},{"name":"input_2","node_id":"-7701"},{"name":"input_3","node_id":"-7701"}],"output_ports":[{"name":"data_1","node_id":"-7701"},{"name":"data_2","node_id":"-7701"},{"name":"data_3","node_id":"-7701"}],"cacheable":true,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-503","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-503"},{"name":"features","node_id":"-503"}],"output_ports":[{"name":"data","node_id":"-503"}],"cacheable":true,"seq_num":6,"comment":"","comment_collapsed":true},{"node_id":"-185","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":"-185"},{"name":"features","node_id":"-185"}],"output_ports":[{"name":"data","node_id":"-185"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"-180","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/develop/datasource/deprecated/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/develop/bigexpr/usage.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(open, -1)\n\n# 极值处理:用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类,这里使用20个分类\n# all_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":"-180"}],"output_ports":[{"name":"data","node_id":"-180"}],"cacheable":true,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"-189","module_id":"BigQuantSpace.xgboost.xgboost-v1","parameters":[{"name":"num_boost_round","value":"10","type":"Literal","bound_global_parameter":null},{"name":"objective","value":"排序(pairwise)","type":"Literal","bound_global_parameter":null},{"name":"booster","value":"gbtree","type":"Literal","bound_global_parameter":null},{"name":"max_depth","value":"6","type":"Literal","bound_global_parameter":null},{"name":"key_cols","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"group_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"nthread","value":"1","type":"Literal","bound_global_parameter":null},{"name":"n_gpus","value":"-1","type":"Literal","bound_global_parameter":null},{"name":"other_train_parameters","value":"{\n# \"feval\": evalerror,\n# \"objective\": squared_log\n \n}","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"training_ds","node_id":"-189"},{"name":"features","node_id":"-189"},{"name":"model","node_id":"-189"},{"name":"predict_ds","node_id":"-189"}],"output_ports":[{"name":"output_model","node_id":"-189"},{"name":"predictions","node_id":"-189"}],"cacheable":true,"seq_num":9,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2016-01-02","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2016-02-02","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-bdf8-104b137c8601-62"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"cacheable":true,"seq_num":10,"comment":"预测数据,用于回测和模拟","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":11,"comment":"","comment_collapsed":true},{"node_id":"-122","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-122"},{"name":"features","node_id":"-122"}],"output_ports":[{"name":"data","node_id":"-122"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-129","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-129"},{"name":"features","node_id":"-129"}],"output_ports":[{"name":"data","node_id":"-129"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true},{"node_id":"-141","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"initialize","value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n stock_count = 5\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 = 0.2\n context.options['hold_days'] = 5\n","type":"Literal","bound_global_parameter":null},{"name":"handle_data","value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 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 # 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":"000300.SHA","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-141"},{"name":"options_data","node_id":"-141"},{"name":"history_ds","node_id":"-141"},{"name":"benchmark_ds","node_id":"-141"},{"name":"trading_calendar","node_id":"-141"}],"output_ports":[{"name":"raw_perf","node_id":"-141"}],"cacheable":false,"seq_num":14,"comment":"","comment_collapsed":true},{"node_id":"-2070","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"import numpy as np\nimport xgboost as xgb\nfrom sklearn.model_selection import train_test_split\n\n#评估函数\ndef evalerror(preds, dtrain):\n labels = dtrain.get_label()\n # return a pair metric_name, result\n # since preds are margin(before logistic transformation, cutoff at 0)\n return 'error', float(sum(labels != (preds > 0.0))) / len(labels)\n\n#损失函数\ndef gradient(predt: np.ndarray, dtrain: xgb.DMatrix) -> np.ndarray:\n '''Compute the gradient squared log error.'''\n y = dtrain.get_label()\n return (np.log1p(predt) - np.log1p(y)) / (predt + 1)\n\ndef hessian(predt: np.ndarray, dtrain: xgb.DMatrix) -> np.ndarray:\n '''Compute the hessian for squared log error.'''\n y = dtrain.get_label()\n return ((-np.log1p(predt) + np.log1p(y) + 1) /\n np.power(predt + 1, 2))\n\ndef squared_log(predt: np.ndarray,\n dtrain: xgb.DMatrix):\n '''Squared Log Error objective. A simplified version for RMSLE used as\n objective function.\n '''\n predt[predt < -1] = -1 + 1e-6\n grad = gradient(predt, dtrain)\n hess = hessian(predt, dtrain)\n return grad, hess\n\n# 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 # 读取数据和特征\n train_data = input_1.read()\n feature = input_2.read()\n test_data = input_3.read()\n #设置训练集和验证集\n train, val = train_test_split(train_data, shuffle=False, test_size=0.3)\n #设置xgboost数据格式\n dtrain = xgb.DMatrix(train[feature], train[\"label\"])\n dtrain.set_group(list(train.groupby('date').apply(len)))\n dtrain.feature_names = feature\n \n dval = xgb.DMatrix(val[feature], val[\"label\"])\n dval.set_group(list(val.groupby('date').apply(len)))\n dval.feature_names = feature\n \n dtest = xgb.DMatrix(test_data[feature], label = None)\n dtest.set_group(list(test_data.groupby('date').apply(len)))\n dtest.feature_names = feature\n params = {\n 'tree_method': 'hist', \n 'seed': 1994,\n 'disable_default_eval_metric': 1\n }\n #指定训练数据和验证数据\n watchlist = [(dval, 'eval'), (dtrain, 'train')]\n #训练\n model = xgb.train(params=params,\n dtrain=dtrain,\n evals=watchlist,\n num_boost_round=10,\n obj=squared_log,\n feval=evalerror)\n #获取预测结果\n pred = model.predict(dtest)\n test_data['prediction'] = pred\n data = test_data[['date','instrument','prediction']].groupby('date').apply(lambda x:x.sort_values('prediction',ascending=False)).reset_index(drop=True)\n return Outputs(data_1=DataSource.write_df(data), 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":"-2070"},{"name":"input_2","node_id":"-2070"},{"name":"input_3","node_id":"-2070"}],"output_ports":[{"name":"data_1","node_id":"-2070"},{"name":"data_2","node_id":"-2070"},{"name":"data_3","node_id":"-2070"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='244,-177,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='-166,308,200,200'/><node_position Node='-113' Position='-14,102,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='-195,-95,200,200'/><node_position Node='-7701' Position='0,200,200,200'/><node_position Node='-503' Position='-155,400,200,200'/><node_position Node='-185' Position='-63,6,200,200'/><node_position Node='-180' Position='-381,27,200,200'/><node_position Node='-189' Position='-56,568,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='545,32,200,200'/><node_position Node='-86' Position='520,362,200,200'/><node_position Node='-122' Position='510,157,200,200'/><node_position Node='-129' Position='550,267,200,200'/><node_position Node='-141' Position='265,686,200,200'/><node_position Node='-2070' Position='375,579,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [4]:
    # 本代码由可视化策略环境自动生成 2022年4月21日 14:20
    # 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 m5_run_bigquant_run(input_1,input_2, columns_input):
        # 示例代码如下。在这里编写您的代码
        df = input_1.read_df()
        if input_2==None:
            if columns_input==[]:
                print('请输入标准化的列名或连接输入因子列表模块')
            else:
                columns = columns_input
        else:
            columns = input_2.read_pickle()
    
        def standard(x):
            return (x-x.mean())/x.std()        
            
            
        for fac in columns:
            median = df[fac].median()
            std = df[fac].std()
            df[fac] = df.groupby('date')[fac].apply(standard)
            
        ds = DataSource().write_df(df)
        return Outputs(data_1=ds)
    # 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 m5_post_run_bigquant_run(outputs):
        return outputs
    
    import numpy as np
    import xgboost as xgb
    from sklearn.model_selection import train_test_split
    
    #评估函数
    def evalerror(preds, dtrain):
        labels = dtrain.get_label()
        # return a pair metric_name, result
        # since preds are margin(before logistic transformation, cutoff at 0)
        return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
    
    #损失函数
    def gradient(predt: np.ndarray, dtrain: xgb.DMatrix) -> np.ndarray:
        '''Compute the gradient squared log error.'''
        y = dtrain.get_label()
        return (np.log1p(predt) - np.log1p(y)) / (predt + 1)
    
    def hessian(predt: np.ndarray, dtrain: xgb.DMatrix) -> np.ndarray:
        '''Compute the hessian for squared log error.'''
        y = dtrain.get_label()
        return ((-np.log1p(predt) + np.log1p(y) + 1) /
                np.power(predt + 1, 2))
    
    def squared_log(predt: np.ndarray,
                    dtrain: xgb.DMatrix):
        '''Squared Log Error objective. A simplified version for RMSLE used as
        objective function.
        '''
        predt[predt < -1] = -1 + 1e-6
        grad = gradient(predt, dtrain)
        hess = hessian(predt, dtrain)
        return grad, hess
    
    # 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 m15_run_bigquant_run(input_1, input_2, input_3):
        # 读取数据和特征
        train_data = input_1.read()
        feature = input_2.read()
        test_data = input_3.read()
        #设置训练集和验证集
        train, val = train_test_split(train_data, shuffle=False, test_size=0.3)
        #设置xgboost数据格式
        dtrain = xgb.DMatrix(train[feature], train["label"])
        dtrain.set_group(list(train.groupby('date').apply(len)))
        dtrain.feature_names = feature
        
        dval = xgb.DMatrix(val[feature], val["label"])
        dval.set_group(list(val.groupby('date').apply(len)))
        dval.feature_names = feature
        
        dtest = xgb.DMatrix(test_data[feature], label = None)
        dtest.set_group(list(test_data.groupby('date').apply(len)))
        dtest.feature_names = feature
        params = {
            'tree_method': 'hist', 
            'seed': 1994,
            'disable_default_eval_metric': 1
        }
        #指定训练数据和验证数据
        watchlist = [(dval, 'eval'), (dtrain, 'train')]
        #训练
        model = xgb.train(params=params,
                  dtrain=dtrain,
                  evals=watchlist,
                  num_boost_round=10,
                  obj=squared_log,
                  feval=evalerror)
        #获取预测结果
        pred = model.predict(dtest)
        test_data['prediction'] = pred
        data = test_data[['date','instrument','prediction']].groupby('date').apply(lambda x:x.sort_values('prediction',ascending=False)).reset_index(drop=True)
        return Outputs(data_1=DataSource.write_df(data), 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 m15_post_run_bigquant_run(outputs):
        return outputs
    
    # 回测引擎:初始化函数,只执行一次
    def m14_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 = 5
        # 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 = 0.2
        context.options['hold_days'] = 5
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m14_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 m14_prepare_bigquant_run(context):
        pass
    
    
    m1 = M.input_features.v1(
        features="""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
    """
    )
    
    m4 = M.instruments.v2(
        start_date='2010-01-01',
        end_date='2016-01-01',
        market='CN_STOCK_A',
        instrument_list=' ',
        max_count=0
    )
    
    m7 = M.general_feature_extractor.v7(
        instruments=m4.data,
        features=m1.data,
        start_date='',
        end_date='',
        before_start_days=90
    )
    
    m3 = M.derived_feature_extractor.v3(
        input_data=m7.data,
        features=m1.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m5 = M.cached.v3(
        input_1=m3.data,
        input_2=m1.data,
        run=m5_run_bigquant_run,
        post_run=m5_post_run_bigquant_run,
        input_ports='',
        params="""{
        'columns_input': []
    }""",
        output_ports='data_1'
    )
    
    m8 = M.advanced_auto_labeler.v2(
        instruments=m4.data,
        label_expr="""# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/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/develop/bigexpr/usage.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -5) / shift(open, -1)
    
    # 极值处理:用1%和99%分位的值做clip
    clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
    
    # 将分数映射到分类,这里使用20个分类
    # all_wbins(label, 20)
    
    # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
    where(shift(high, -1) == shift(low, -1), NaN, label)
    """,
        start_date='',
        end_date='',
        benchmark='000300.SHA',
        drop_na_label=True,
        cast_label_int=True,
        user_functions={}
    )
    
    m2 = M.join.v3(
        data1=m8.data,
        data2=m5.data_1,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m6 = M.dropnan.v2(
        input_data=m2.data
    )
    
    m10 = M.instruments.v2(
        start_date='2016-01-02',
        end_date='2016-02-02',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m12 = M.general_feature_extractor.v7(
        instruments=m10.data,
        features=m1.data,
        start_date='',
        end_date='',
        before_start_days=0
    )
    
    m13 = M.derived_feature_extractor.v3(
        input_data=m12.data,
        features=m1.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m11 = M.dropnan.v1(
        input_data=m13.data
    )
    
    m9 = M.xgboost.v1(
        training_ds=m6.data,
        features=m1.data,
        predict_ds=m11.data,
        num_boost_round=10,
        objective='排序(pairwise)',
        booster='gbtree',
        max_depth=6,
        key_cols='date,instrument',
        group_col='date',
        nthread=1,
        n_gpus=-1,
        other_train_parameters={
    #     "feval": evalerror,
    #     "objective": squared_log
        
    }
    )
    
    m15 = M.cached.v3(
        input_1=m6.data,
        input_2=m1.data,
        input_3=m11.data,
        run=m15_run_bigquant_run,
        post_run=m15_post_run_bigquant_run,
        input_ports='',
        params='{}',
        output_ports=''
    )
    
    m14 = M.trade.v4(
        instruments=m10.data,
        options_data=m15.data_1,
        start_date='',
        end_date='',
        initialize=m14_initialize_bigquant_run,
        handle_data=m14_handle_data_bigquant_run,
        prepare=m14_prepare_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy='open',
        order_price_field_sell='close',
        capital_base=1000000,
        auto_cancel_non_tradable_orders=True,
        data_frequency='daily',
        price_type='后复权',
        product_type='股票',
        plot_charts=True,
        backtest_only=False,
        benchmark='000300.SHA'
    )
    
    [0]	eval-error:0.417992	train-error:0.481985
    [1]	eval-error:0.417992	train-error:0.481985
    [2]	eval-error:0.417992	train-error:0.481985
    [3]	eval-error:0.417992	train-error:0.481985
    [4]	eval-error:0.417992	train-error:0.481985
    [5]	eval-error:0.417992	train-error:0.481985
    [6]	eval-error:0.417992	train-error:0.481985
    [7]	eval-error:0.417992	train-error:0.481985
    [8]	eval-error:0.417992	train-error:0.481985
    [9]	eval-error:0.417992	train-error:0.481985
    
    • 收益率-18.92%
    • 年化收益率-90.96%
    • 基准收益率-20.63%
    • 阿尔法0.06
    • 贝塔0.91
    • 夏普比率-3.73
    • 胜率0.26
    • 盈亏比0.66
    • 收益波动率60.2%
    • 信息比率0.05
    • 最大回撤24.47%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-2d74b6969dfe45daaccb07fbc3290784"}/bigcharts-data-end