复制链接
克隆策略

StockRanker多因子ETF策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"-209:input_1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-145:data1","from_node_id":"-189:data"},{"to_node_id":"-189:input_data","from_node_id":"-209:data_1"},{"to_node_id":"-451:input_data","from_node_id":"-209:data_1"},{"to_node_id":"-11927:input_data","from_node_id":"-145:data"},{"to_node_id":"-468:training_ds","from_node_id":"-151:data"},{"to_node_id":"-145:data2","from_node_id":"-451:data"},{"to_node_id":"-468:features","from_node_id":"-459:data"},{"to_node_id":"-11938:features_ds","from_node_id":"-459:data"},{"to_node_id":"-765:model","from_node_id":"-468:model"},{"to_node_id":"-250:options_data","from_node_id":"-765:predictions"},{"to_node_id":"-781:input_1","from_node_id":"-769:data"},{"to_node_id":"-250:instruments","from_node_id":"-769:data"},{"to_node_id":"-1086:input_data","from_node_id":"-781:data_1"},{"to_node_id":"-11933:input_data","from_node_id":"-1086:data"},{"to_node_id":"-765:data","from_node_id":"-1398:data"},{"to_node_id":"-151:input_data","from_node_id":"-11927:data"},{"to_node_id":"-1398:input_data","from_node_id":"-11933:data"},{"to_node_id":"-451:features","from_node_id":"-11938:data"},{"to_node_id":"-1086:features","from_node_id":"-11938:data"}],"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_FUND","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":"-189","module_id":"BigQuantSpace.auto_labeler_on_datasource.auto_labeler_on_datasource-v1","parameters":[{"name":"label_expr","value":"# #号开始的表示注释\n# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_\n\n# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(open, -1)\n\n# 极值处理：用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类，这里使用20个分类\nall_wbins(label, 20)\n\n","type":"Literal","bound_global_parameter":null},{"name":"drop_na_label","value":"True","type":"Literal","bound_global_parameter":null},{"name":"cast_label_int","value":"True","type":"Literal","bound_global_parameter":null},{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"{}","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-189"}],"output_ports":[{"name":"data","node_id":"-189"}],"cacheable":true,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-209","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 instruments = input_1.read()['instruments']\n start_date = input_1.read()['start_date']\n end_date = input_1.read()['end_date']\n df = DataSource('bar1d_CN_FUND').read(instruments=instruments,start_date=start_date,end_date=end_date)\n df = df.drop(columns=['turn'])\n data_1 = DataSource.write_df(df)\n return Outputs(data_1=data_1)\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":"-209"},{"name":"input_2","node_id":"-209"},{"name":"input_3","node_id":"-209"}],"output_ports":[{"name":"data_1","node_id":"-209"},{"name":"data_2","node_id":"-209"},{"name":"data_3","node_id":"-209"}],"cacheable":true,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-145","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":"-145"},{"name":"data2","node_id":"-145"}],"output_ports":[{"name":"data","node_id":"-145"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true},{"node_id":"-151","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"-151"}],"output_ports":[{"name":"data","node_id":"-151"}],"cacheable":true,"seq_num":19,"comment":"","comment_collapsed":true},{"node_id":"-451","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":"-451"},{"name":"features","node_id":"-451"}],"output_ports":[{"name":"data","node_id":"-451"}],"cacheable":true,"seq_num":22,"comment":"","comment_collapsed":true},{"node_id":"-459","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\nclose/shift(close, 5)-1 \nstd(close, 5)\ndecay_linear(close, 5)\nts_max(close, 5)\nts_min(close, 5)\n \n\n\n","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-459"}],"output_ports":[{"name":"data","node_id":"-459"}],"cacheable":true,"seq_num":23,"comment":"","comment_collapsed":true},{"node_id":"-468","module_id":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","parameters":[{"name":"learning_algorithm","value":"排序","type":"Literal","bound_global_parameter":null},{"name":"number_of_leaves","value":"30","type":"Literal","bound_global_parameter":null},{"name":"minimum_docs_per_leaf","value":"100","type":"Literal","bound_global_parameter":null},{"name":"number_of_trees","value":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":"-468"},{"name":"features","node_id":"-468"},{"name":"test_ds","node_id":"-468"},{"name":"base_model","node_id":"-468"}],"output_ports":[{"name":"model","node_id":"-468"},{"name":"feature_gains","node_id":"-468"},{"name":"m_lazy_run","node_id":"-468"}],"cacheable":true,"seq_num":21,"comment":"","comment_collapsed":true},{"node_id":"-765","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":"-765"},{"name":"data","node_id":"-765"}],"output_ports":[{"name":"predictions","node_id":"-765"},{"name":"m_lazy_run","node_id":"-765"}],"cacheable":true,"seq_num":20,"comment":"","comment_collapsed":true},{"node_id":"-769","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2021-12-31","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_FUND","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":"-769"}],"output_ports":[{"name":"data","node_id":"-769"}],"cacheable":true,"seq_num":10,"comment":"","comment_collapsed":true},{"node_id":"-781","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 instruments = input_1.read()['instruments']\n start_date = input_1.read()['start_date']\n end_date = input_1.read()['end_date']\n df = DataSource('bar1d_CN_FUND').read(instruments=instruments,start_date=start_date,end_date=end_date)\n df = df.drop(columns=['turn'])\n \n data_1 = DataSource.write_df(df)\n return Outputs(data_1=data_1)\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":"-781"},{"name":"input_2","node_id":"-781"},{"name":"input_3","node_id":"-781"}],"output_ports":[{"name":"data_1","node_id":"-781"},{"name":"data_2","node_id":"-781"},{"name":"data_3","node_id":"-781"}],"cacheable":true,"seq_num":24,"comment":"","comment_collapsed":true},{"node_id":"-1086","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":"-1086"},{"name":"features","node_id":"-1086"}],"output_ports":[{"name":"data","node_id":"-1086"}],"cacheable":true,"seq_num":25,"comment":"","comment_collapsed":true},{"node_id":"-1398","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"-1398"}],"output_ports":[{"name":"data","node_id":"-1398"}],"cacheable":true,"seq_num":26,"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=0.00015, sell_cost=0.00015, min_cost=0))\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 = 20\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 today = 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.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":"1","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":"100000","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":3,"comment":"","comment_collapsed":true},{"node_id":"-11927","module_id":"BigQuantSpace.filter.filter-v3","parameters":[{"name":"expr","value":"v_mean > 100000","type":"Literal","bound_global_parameter":null},{"name":"output_left_data","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-11927"}],"output_ports":[{"name":"data","node_id":"-11927"},{"name":"left_data","node_id":"-11927"}],"cacheable":true,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"-11933","module_id":"BigQuantSpace.filter.filter-v3","parameters":[{"name":"expr","value":"v_mean > 100000","type":"Literal","bound_global_parameter":null},{"name":"output_left_data","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-11933"}],"output_ports":[{"name":"data","node_id":"-11933"},{"name":"left_data","node_id":"-11933"}],"cacheable":true,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-11938","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"#用于过滤\nv_mean=mean(volume,5)","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-11938"}],"output_ports":[{"name":"data","node_id":"-11938"}],"cacheable":true,"seq_num":6,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='233,-642,200,200'/><node_position Node='-189' Position='122,-435,200,200'/><node_position Node='-209' Position='227,-539,200,200'/><node_position Node='-145' Position='253,-345,200,200'/><node_position Node='-151' Position='264,-195,200,200'/><node_position Node='-451' Position='452,-427,200,200'/><node_position Node='-459' Position='746,-731,200,200'/><node_position Node='-468' Position='598,-172,200,200'/><node_position Node='-765' Position='732,-58,200,200'/><node_position Node='-769' Position='1110,-552,200,200'/><node_position Node='-781' Position='1034,-450,200,200'/><node_position Node='-1086' Position='1048,-351,200,200'/><node_position Node='-1398' Position='1059,-199,200,200'/><node_position Node='-250' Position='651,40,200,200'/><node_position Node='-11927' Position='269,-272,200,200'/><node_position Node='-11933' Position='1103,-273,200,200'/><node_position Node='-11938' Position='567,-609,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [1]:
    # 本代码由可视化策略环境自动生成 2022年2月15日 16:46
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# 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 m11_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    instruments = input_1.read()['instruments']
    start_date = input_1.read()['start_date']
    end_date = input_1.read()['end_date']
    df = DataSource('bar1d_CN_FUND').read(instruments=instruments,start_date=start_date,end_date=end_date)
    df = df.drop(columns=['turn'])
    data_1 = DataSource.write_df(df)
    return Outputs(data_1=data_1)

# 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 m11_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 m24_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    instruments = input_1.read()['instruments']
    start_date = input_1.read()['start_date']
    end_date = input_1.read()['end_date']
    df = DataSource('bar1d_CN_FUND').read(instruments=instruments,start_date=start_date,end_date=end_date)
    df = df.drop(columns=['turn'])
    
    data_1 = DataSource.write_df(df)
    return Outputs(data_1=data_1)

# 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 m24_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m3_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=0.00015, sell_cost=0.00015, min_cost=0))
    # 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 = 20
    # 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 m3_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')]
    today = 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.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 m3_prepare_bigquant_run(context):
    pass


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

m11 = M.cached.v3(
    input_1=m1.data,
    run=m11_run_bigquant_run,
    post_run=m11_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m5 = M.auto_labeler_on_datasource.v1(
    input_data=m11.data_1,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_

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

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

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

""",
    drop_na_label=True,
    cast_label_int=True,
    date_col='date',
    instrument_col='instrument',
    user_functions={}
)

m23 = 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
close/shift(close, 5)-1 
std(close, 5)
decay_linear(close, 5)
ts_max(close, 5)
ts_min(close, 5)
 


"""
)

m6 = M.input_features.v1(
    features_ds=m23.data,
    features="""#用于过滤
v_mean=mean(volume,5)"""
)

m22 = M.derived_feature_extractor.v3(
    input_data=m11.data_1,
    features=m6.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m12 = M.join.v3(
    data1=m5.data,
    data2=m22.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m2 = M.filter.v3(
    input_data=m12.data,
    expr='v_mean  > 100000',
    output_left_data=False
)

m19 = M.dropnan.v1(
    input_data=m2.data
)

m21 = M.stock_ranker_train.v5(
    training_ds=m19.data,
    features=m23.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=100,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    m_lazy_run=False
)

m10 = M.instruments.v2(
    start_date='2021-01-01',
    end_date='2021-12-31',
    market='CN_FUND',
    instrument_list='',
    max_count=0
)

m24 = M.cached.v3(
    input_1=m10.data,
    run=m24_run_bigquant_run,
    post_run=m24_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m25 = M.derived_feature_extractor.v3(
    input_data=m24.data_1,
    features=m6.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m4 = M.filter.v3(
    input_data=m25.data,
    expr='v_mean  > 100000',
    output_left_data=False
)

m26 = M.dropnan.v1(
    input_data=m4.data
)

m20 = M.stock_ranker_predict.v5(
    model=m21.model,
    data=m26.data,
    m_lazy_run=False
)

m3 = M.trade.v4(
    instruments=m10.data,
    options_data=m20.predictions,
    start_date='',
    end_date='',
    initialize=m3_initialize_bigquant_run,
    handle_data=m3_handle_data_bigquant_run,
    prepare=m3_prepare_bigquant_run,
    volume_limit=1,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000,
    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'
)
    设置测试数据集，查看训练迭代过程的NDCG
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-f03e787afb994fb6a4025203596b5ff0"}/bigcharts-data-end
    • 收益率2.47%
    • 年化收益率2.56%
    • 基准收益率-5.2%
    • 阿尔法0.01
    • 贝塔0.23
    • 夏普比率-0.03
    • 胜率0.49
    • 盈亏比0.6
    • 收益波动率6.58%
    • 信息比率0.03
    • 最大回撤4.51%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-66311f71889b40d5b4dbd90277f6c579"}/bigcharts-data-end