{"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":"-215: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":"-215:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-222:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-231:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-238:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-587:input_2","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-231:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-250:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-587:input_1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"to_node_id":"-599:input_2","from_node_id":"-86:data"},{"to_node_id":"-222:input_data","from_node_id":"-215:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-222:data"},{"to_node_id":"-238:input_data","from_node_id":"-231:data"},{"to_node_id":"-86:input_data","from_node_id":"-238:data"},{"to_node_id":"-599:input_1","from_node_id":"-587:data_1"},{"to_node_id":"-250:options_data","from_node_id":"-599:data_1"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2018-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2020-12-31","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/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) # 5天后收盘价除以明日开盘价\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.HIX","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\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":false,"seq_num":3,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","module_id":"BigQuantSpace.join.join-v3","parameters":[{"name":"on","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"how","value":"inner","type":"Literal","bound_global_parameter":null},{"name":"sort","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"data1","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"name":"data2","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2021-12-31","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":"-215","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":"-215"},{"name":"features","node_id":"-215"}],"output_ports":[{"name":"data","node_id":"-215"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-222","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":"-222"},{"name":"features","node_id":"-222"}],"output_ports":[{"name":"data","node_id":"-222"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-231","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":"-231"},{"name":"features","node_id":"-231"}],"output_ports":[{"name":"data","node_id":"-231"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-238","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":"-238"},{"name":"features","node_id":"-238"}],"output_ports":[{"name":"data","node_id":"-238"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-250","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 \n \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 \n ranker_prediction = ranker_prediction.sort_values('pred', ascending=False)\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.portfolio.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.portfolio.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities)])))\n\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":"0.028","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":"1000001","type":"Literal","bound_global_parameter":null},{"name":"auto_cancel_non_tradable_orders","value":"True","type":"Literal","bound_global_parameter":null},{"name":"data_frequency","value":"daily","type":"Literal","bound_global_parameter":null},{"name":"price_type","value":"真实价格","type":"Literal","bound_global_parameter":null},{"name":"product_type","value":"股票","type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"backtest_only","value":"False","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.HIX","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-250"},{"name":"options_data","node_id":"-250"},{"name":"history_ds","node_id":"-250"},{"name":"benchmark_ds","node_id":"-250"},{"name":"trading_calendar","node_id":"-250"}],"output_ports":[{"name":"raw_perf","node_id":"-250"}],"cacheable":false,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-587","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 \n\n import pandas as pd\n from biglearning.api import M\n from biglearning.module2.common.data import DataSource, Outputs\n \n\n objective_map = {\n \"线性回归\": \"reg:linear\",\n \"逻辑回归\": \"reg:logistic\",\n \"二分类(逻辑回归)\": \"binary:logistic\",\n \"多分类\": \"multi:softmax\",\n \"排序(pairwise)\": \"rank:pairwise\",\n \"排序(ndcg)\": \"rank:ndcg\",\n \"排序(map)\": \"rank:map\",\n }\n\n training_ds = input_1\n features = input_2.read() \n \n num_boost_round=30\n objective= \"排序(pairwise)\"\n booster=\"gbtree\"\n max_depth=6\n key_cols=\"date,instrument\"\n group_col=\"date\"\n nthread = 5\n tree_method = \"hist\"\n\n\n import xgboost as xgb\n\n def prepare_data(df, features, group_col):\n import xgboost as xgb\n\n if group_col:\n df.sort_values(group_col, inplace=True)\n try:\n data = df[features].values\n if \"label\" in df.columns:\n label = df[\"label\"].values\n else:\n label = None\n dm = xgb.DMatrix(data, label=label)\n if group_col:\n dm.set_group(list(df.groupby(group_col).apply(len)))\n dm.feature_names = features\n return dm\n except KeyError as e:\n log.error(\"部分特征没有在数据中，执行失败\")\n raise e\n\n df = training_ds.read_df()\n \n dm = prepare_data(df, features, group_col)\n parameters = {\"objective\":objective_map[objective], \"booster\": booster, \"max_depth\": max_depth, \"nthread\": nthread}\n print('-----', parameters)\n if tree_method is not None:\n parameters[\"tree_method\"] = tree_method\n\n # parameters.update(other_train_parameters)\n model = xgb.train(params=parameters, dtrain=dm, num_boost_round=num_boost_round)\n \n print('model train done!')\n\n if booster == \"dart\":\n model_info = {\"model\": model, \"features\": features, \"parameters\": parameters}\n else:\n feature_gains = pd.DataFrame(list(model.get_score().items()), columns=[\"feature\", \"gain\"])\n \n feature_gains.sort_values(\"gain\", inplace=True, ascending=False)\n model_info = {\"model\": model, \"features\": features, \"feature_gains\": feature_gains, \"parameters\": parameters}\n \n model_info_ds = DataSource.write_pickle(model_info)\n return Outputs(data_1=model_info_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":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-587"},{"name":"input_2","node_id":"-587"},{"name":"input_3","node_id":"-587"}],"output_ports":[{"name":"data_1","node_id":"-587"},{"name":"data_2","node_id":"-587"},{"name":"data_3","node_id":"-587"}],"cacheable":true,"seq_num":4,"comment":"model train","comment_collapsed":false},{"node_id":"-599","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 \n \n model =input_1.read() # 模型信息（字典）\n df = input_2.read() # 测试集\n features = model['features']\n \n group_col = 'date'\n \n def prepare_data(df, features, group_col):\n import xgboost as xgb\n\n if group_col:\n df.sort_values(group_col, inplace=True)\n try:\n data = df[features].values\n if \"label\" in df.columns:\n label = df[\"label\"].values\n else:\n label = None\n dm = xgb.DMatrix(data, label=label)\n if group_col:\n dm.set_group(list(df.groupby(group_col).apply(len)))\n dm.feature_names = features\n return dm\n except KeyError as e:\n log.error(\"部分特征没有在数据中，执行失败\")\n raise e\n \n \n dm = prepare_data(df, features, group_col)\n pred_label = model['model'].predict(dm)\n \n pred_df = pd.DataFrame(\n data={'prediction': pred_label}, index=df.index)\n df['pred'] = pred_df\n \n return Outputs(data_1=DataSource.write_df(df))","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":"-599"},{"name":"input_2","node_id":"-599"},{"name":"input_3","node_id":"-599"}],"output_ports":[{"name":"data_1","node_id":"-599"},{"name":"data_2","node_id":"-599"},{"name":"data_3","node_id":"-599"}],"cacheable":true,"seq_num":5,"comment":"model predict 模型预测","comment_collapsed":false}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='236.10772705078125,122.93927764892578,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='63.33421325683594,207.1961669921875,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='601.7720947265625,80.12929224967957,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='220.1417236328125,334.5984191894531,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1075.9317626953125,149.2164306640625,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='301.4455261230469,403.3663330078125,200,200'/><node_position Node='-86' Position='1050.5848388671875,380.4842529296875,200,200'/><node_position Node='-215' Position='382.931884765625,216.97793579101562,200,200'/><node_position Node='-222' Position='383.55706787109375,275.6712646484375,200,200'/><node_position Node='-231' Position='1078,236,200,200'/><node_position Node='-238' Position='1079.55712890625,309.6850280761719,200,200'/><node_position Node='-250' Position='480.1058349609375,661.1114501953125,200,200'/><node_position Node='-587' Position='482.15167236328125,454.26318359375,200,200'/><node_position Node='-599' Position='660.72998046875,555.2667846679688,200,200'/></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6月7日 16:19
# 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。
 
# 显式导入 BigQuant 相关 SDK 模块
from bigdatasource.api import DataSource
from biglearning.api import M
from biglearning.api import tools as T
from biglearning.module2.common.data import Outputs

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m4_run_bigquant_run(input_1, input_2, input_3):
    

    import pandas as pd
    from biglearning.api import M
    from biglearning.module2.common.data import DataSource, Outputs
     

    objective_map = {
        "线性回归": "reg:linear",
        "逻辑回归": "reg:logistic",
        "二分类(逻辑回归)": "binary:logistic",
        "多分类": "multi:softmax",
        "排序(pairwise)": "rank:pairwise",
        "排序(ndcg)": "rank:ndcg",
        "排序(map)": "rank:map",
    }

    training_ds = input_1
    features = input_2.read() 
    
    num_boost_round=30
    objective= "排序(pairwise)"
    booster="gbtree"
    max_depth=6
    key_cols="date,instrument"
    group_col="date"
    nthread = 5
    tree_method = "hist"


    import xgboost as xgb

    def prepare_data(df, features, group_col):
        import xgboost as xgb

        if group_col:
            df.sort_values(group_col, inplace=True)
        try:
            data = df[features].values
            if "label" in df.columns:
                label = df["label"].values
            else:
                label = None
            dm = xgb.DMatrix(data, label=label)
            if group_col:
                dm.set_group(list(df.groupby(group_col).apply(len)))
            dm.feature_names = features
            return dm
        except KeyError as e:
            log.error("部分特征没有在数据中，执行失败")
            raise e

    df = training_ds.read_df()
   
    dm = prepare_data(df, features, group_col)
    parameters = {"objective":objective_map[objective], "booster": booster, "max_depth": max_depth, "nthread": nthread}
    print('-----', parameters)
    if tree_method is not None:
        parameters["tree_method"] = tree_method

    # parameters.update(other_train_parameters)
    model = xgb.train(params=parameters, dtrain=dm, num_boost_round=num_boost_round)
    
    print('model train done!')

    if booster == "dart":
        model_info = {"model": model, "features": features, "parameters": parameters}
    else:
        feature_gains = pd.DataFrame(list(model.get_score().items()), columns=["feature", "gain"])
        
        feature_gains.sort_values("gain", inplace=True, ascending=False)
        model_info = {"model": model, "features": features, "feature_gains": feature_gains, "parameters": parameters}
    
    model_info_ds = DataSource.write_pickle(model_info)
    return Outputs(data_1=model_info_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 m4_post_run_bigquant_run(outputs):
    return outputs

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m5_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    
    
    model =input_1.read()  # 模型信息（字典）
    df = input_2.read() # 测试集
    features = model['features']
    
    group_col = 'date'
    
    def prepare_data(df, features, group_col):
        import xgboost as xgb

        if group_col:
            df.sort_values(group_col, inplace=True)
        try:
            data = df[features].values
            if "label" in df.columns:
                label = df["label"].values
            else:
                label = None
            dm = xgb.DMatrix(data, label=label)
            if group_col:
                dm.set_group(list(df.groupby(group_col).apply(len)))
            dm.feature_names = features
            return dm
        except KeyError as e:
            log.error("部分特征没有在数据中，执行失败")
            raise e
    
    
    dm = prepare_data(df, features, group_col)
    pred_label = model['model'].predict(dm)
    
    pred_df = pd.DataFrame(
    data={'prediction': pred_label}, index=df.index)
    df['pred'] = pred_df
    
    return Outputs(data_1=DataSource.write_df(df))
# 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

# 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))
     
 
    # 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 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')]
    
    ranker_prediction = ranker_prediction.sort_values('pred', ascending=False)

    # 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.portfolio.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.portfolio.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities)])))

        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


m1 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2020-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/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)  # 5天后收盘价除以明日开盘价

# 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.HIX',
    drop_na_label=True,
    cast_label_int=True
)

m3 = M.input_features.v1(
    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
""",
    m_cached=False
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m13 = M.dropnan.v1(
    input_data=m7.data
)

m4 = M.cached.v3(
    input_1=m13.data,
    input_2=m3.data,
    run=m4_run_bigquant_run,
    post_run=m4_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2021-12-31'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m14 = M.dropnan.v1(
    input_data=m18.data
)

m5 = M.cached.v3(
    input_1=m4.data_1,
    input_2=m14.data,
    run=m5_run_bigquant_run,
    post_run=m5_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m5.data_1,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    volume_limit=0.028,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000001,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2023-06-07 15:49:03.469340] INFO moduleinvoker: instruments.v2 开始运行..
[2023-06-07 15:49:03.481262] INFO moduleinvoker: 命中缓存
[2023-06-07 15:49:03.484096] INFO moduleinvoker: instruments.v2 运行完成[0.014832s].
[2023-06-07 15:49:03.491139] INFO moduleinvoker: advanced_auto_labeler.v2 开始运行..
[2023-06-07 15:49:03.499313] INFO moduleinvoker: 命中缓存
[2023-06-07 15:49:03.501221] INFO moduleinvoker: advanced_auto_labeler.v2 运行完成[0.010119s].
[2023-06-07 15:49:03.504711] INFO moduleinvoker: input_features.v1 开始运行..
[2023-06-07 15:49:03.547630] INFO moduleinvoker: input_features.v1 运行完成[0.042768s].
[2023-06-07 15:49:03.567937] INFO moduleinvoker: general_feature_extractor.v7 开始运行..
[2023-06-07 15:49:03.576982] INFO moduleinvoker: 命中缓存
[2023-06-07 15:49:03.579068] INFO moduleinvoker: general_feature_extractor.v7 运行完成[0.011221s].
[2023-06-07 15:49:03.584560] INFO moduleinvoker: derived_feature_extractor.v3 开始运行..
[2023-06-07 15:49:09.457941] INFO derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.021s
[2023-06-07 15:49:09.473926] INFO derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.013s
[2023-06-07 15:49:09.485561] INFO derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.009s
[2023-06-07 15:49:09.496560] INFO derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.009s
[2023-06-07 15:49:09.507194] INFO derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.008s
[2023-06-07 15:49:09.519334] INFO derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.010s
[2023-06-07 15:49:10.745140] INFO derived_feature_extractor: /y_2017, 193398
[2023-06-07 15:49:12.402097] INFO derived_feature_extractor: /y_2018, 816987
[2023-06-07 15:49:14.503990] INFO derived_feature_extractor: /y_2019, 884867
[2023-06-07 15:49:16.962196] INFO derived_feature_extractor: /y_2020, 945961
[2023-06-07 15:49:17.754729] INFO moduleinvoker: derived_feature_extractor.v3 运行完成[14.17008s].
[2023-06-07 15:49:17.761886] INFO moduleinvoker: join.v3 开始运行..
[2023-06-07 15:49:24.740846] INFO join: /y_2017, 行数=0/193398, 耗时=1.21854s
[2023-06-07 15:49:28.429165] INFO join: /y_2018, 行数=813508/816987, 耗时=3.684876s
[2023-06-07 15:49:32.421676] INFO join: /y_2019, 行数=881288/884867, 耗时=3.983822s
[2023-06-07 15:49:36.357628] INFO join: /y_2020, 行数=919362/945961, 耗时=3.893897s
[2023-06-07 15:49:36.523959] INFO join: 最终行数: 2614158
[2023-06-07 15:49:36.546554] INFO moduleinvoker: join.v3 运行完成[18.784612s].
[2023-06-07 15:49:36.555047] INFO moduleinvoker: dropnan.v1 开始运行..
[2023-06-07 15:49:37.429216] INFO dropnan: /y_2017, 0/0
[2023-06-07 15:49:40.011833] INFO dropnan: /y_2018, 811828/813508
[2023-06-07 15:49:42.801868] INFO dropnan: /y_2019, 877946/881288
[2023-06-07 15:49:45.811153] INFO dropnan: /y_2020, 911045/919362
[2023-06-07 15:49:45.989708] INFO dropnan: 行数: 2600819/2614158
[2023-06-07 15:49:46.004155] INFO moduleinvoker: dropnan.v1 运行完成[9.449063s].
[2023-06-07 15:49:46.015213] INFO moduleinvoker: cached.v3 开始运行..
----- {'objective': 'rank:pairwise', 'booster': 'gbtree', 'max_depth': 6, 'nthread': 5}
model train done!
[2023-06-07 15:51:05.816165] INFO moduleinvoker: cached.v3 运行完成[79.800936s].
[2023-06-07 15:51:05.829376] INFO moduleinvoker: instruments.v2 开始运行..
[2023-06-07 15:51:05.856653] INFO moduleinvoker: 命中缓存
[2023-06-07 15:51:05.859441] INFO moduleinvoker: instruments.v2 运行完成[0.030051s].
[2023-06-07 15:51:05.872765] INFO moduleinvoker: general_feature_extractor.v7 开始运行..
[2023-06-07 15:51:05.879586] INFO moduleinvoker: 命中缓存
[2023-06-07 15:51:05.882556] INFO moduleinvoker: general_feature_extractor.v7 运行完成[0.00983s].
[2023-06-07 15:51:05.889137] INFO moduleinvoker: derived_feature_extractor.v3 开始运行..
[2023-06-07 15:51:08.605557] INFO derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.008s
[2023-06-07 15:51:08.615223] INFO derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.008s
[2023-06-07 15:51:08.621880] INFO derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.005s
[2023-06-07 15:51:08.629192] INFO derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.005s
[2023-06-07 15:51:08.635666] INFO derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s
[2023-06-07 15:51:08.641773] INFO derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.004s
[2023-06-07 15:51:09.379876] INFO derived_feature_extractor: /y_2020, 243745
[2023-06-07 15:51:11.718518] INFO derived_feature_extractor: /y_2021, 1061527
[2023-06-07 15:51:12.532492] INFO moduleinvoker: derived_feature_extractor.v3 运行完成[6.643394s].
[2023-06-07 15:51:12.539108] INFO moduleinvoker: dropnan.v1 开始运行..
[2023-06-07 15:51:13.482841] INFO dropnan: /y_2020, 239876/243745
[2023-06-07 15:51:16.457501] INFO dropnan: /y_2021, 1049627/1061527
[2023-06-07 15:51:16.579385] INFO dropnan: 行数: 1289503/1305272
[2023-06-07 15:51:16.593896] INFO moduleinvoker: dropnan.v1 运行完成[4.054713s].
[2023-06-07 15:51:16.603720] INFO moduleinvoker: cached.v3 开始运行..
[2023-06-07 15:51:24.907780] INFO moduleinvoker: cached.v3 运行完成[8.303957s].
[2023-06-07 15:51:24.964208] INFO moduleinvoker: backtest.v8 开始运行..
[2023-06-07 15:51:24.971419] INFO backtest: biglearning backtest:V8.6.3
[2023-06-07 15:51:24.974777] INFO backtest: product_type:stock by specified
[2023-06-07 15:51:25.070058] INFO moduleinvoker: cached.v2 开始运行..
[2023-06-07 15:51:25.080214] INFO moduleinvoker: 命中缓存
[2023-06-07 15:51:25.082742] INFO moduleinvoker: cached.v2 运行完成[0.012707s].
[2023-06-07 15:51:37.170295] INFO backtest: algo history_data=DataSource(005d386546924a08bdb0977f21de7505T)
[2023-06-07 15:51:37.172784] INFO algo: TradingAlgorithm V1.8.9
[2023-06-07 15:51:41.823959] INFO algo: trading transform...

/var/app/enabled/bigline/zipline/data/us_equity_pricing.py:990: FutureWarning: Indexing a timezone-naive DatetimeIndex with a timezone-aware datetime is deprecated and will raise KeyError in a future version.  Use a timezone-naive object instead.
  return df.loc[dt, field]
/usr/local/python3/lib/python3.8/site-packages/pandas/core/indexing.py:1124: FutureWarning: Indexing a timezone-naive DatetimeIndex with a timezone-aware datetime is deprecated and will raise KeyError in a future version.  Use a timezone-naive object instead.
  return self._get_label(key, axis=axis)

[2023-06-07 15:51:45.886785] WARNING Performance: maybe_close_position no price for asset:Equity(85 [600891.SHA]), field:price, dt:2021-05-12 15:00:00+00:00
[2023-06-07 15:51:53.328277] INFO Performance: Simulated 243 trading days out of 243.
[2023-06-07 15:51:53.330846] INFO Performance: first open: 2021-01-04 09:30:00+00:00
[2023-06-07 15:51:53.332687] INFO Performance: last close: 2021-12-31 15:00:00+00:00

/usr/local/python3/lib/python3.8/site-packages/pandas/core/generic.py:2605: PerformanceWarning: 
your performance may suffer as PyTables will pickle object types that it cannot
map directly to c-types [inferred_type->mixed,key->block5_values] [items->Index(['positions', 'transactions', 'orders', 'LOG', 'TRA_FAC', 'POS_FAC',
       'period_label'],
      dtype='object')]

  pytables.to_hdf(
/usr/local/python3/lib/python3.8/site-packages/pandas/core/generic.py:2605: PerformanceWarning: 
your performance may suffer as PyTables will pickle object types that it cannot
map directly to c-types [inferred_type->mixed,key->block2_values] [items->Index(['instrument', 'suspended', 'name'], dtype='object')]

  pytables.to_hdf(
/usr/local/python3/lib/python3.8/site-packages/pandas/core/indexing.py:1637: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  self._setitem_single_block(indexer, value, name)
[2023-06-07 15:51:56.330891] INFO: bigcharts.impl.render:render.py:407:render_chart Data is None, skip loading it to chart.

[2023-06-07 15:51:57.119131] INFO moduleinvoker: backtest.v8 运行完成[32.154979s].

INFO:moduleinvoker:backtest.v8 运行完成[32.154979s].

[2023-06-07 15:51:57.126720] INFO moduleinvoker: trade.v4 运行完成[32.210688s].

INFO:moduleinvoker:trade.v4 运行完成[32.210688s].