【宽客学院】零基础小白可以学习的AI量化课程

iQuant · 2020-07-07 07:26:54 UTC

AI量化是未来趋势，金融机构对量化方向的人才求贤若渴，存在大量的人才缺失。对于金融知识一片空白的小白来说，难以听懂量化中专业的术语。因此，BigQuant整理了一套适合金融小白的培训课程，精心挑选量化中所需要具备的金融基础知识，为大家打开金融世界的一扇门。点击下方的视频来学习吧！（视频会持续更新！）

更多的知识需要个人不断地积累和沉淀，有什么不懂的就来问小Q吧！

iQuant · 2020-07-07 07:30:41 UTC

iQuant · 2020-07-10 08:39:20 UTC

iQuant · 2020-09-23 06:48:45 UTC

课程相关案例及源代码

1.1量化数据研究

克隆策略

In [8]:

# 本代码由可视化策略环境自动生成 2020年9月23日 14:39
# 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。


m1 = M.instruments.v2(
    start_date='2019-03-01',
    end_date='2019-03-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

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
pe_ttm_0
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

m4 = M.dropnan.v2(
    input_data=m15.data
)

[2019-07-13 13:56:39.598088] INFO: bigquant: instruments.v2 开始运行..

[2019-07-13 13:56:39.724063] INFO: bigquant: 命中缓存

[2019-07-13 13:56:39.726585] INFO: bigquant: instruments.v2 运行完成[0.128489s].

[2019-07-13 13:56:39.731266] INFO: bigquant: input_features.v1 开始运行..

[2019-07-13 13:56:39.782459] INFO: bigquant: 命中缓存

[2019-07-13 13:56:39.788018] INFO: bigquant: input_features.v1 运行完成[0.056733s].

[2019-07-13 13:56:39.919480] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-07-13 13:56:40.018003] INFO: bigquant: 命中缓存

[2019-07-13 13:56:40.020095] INFO: bigquant: general_feature_extractor.v7 运行完成[0.100616s].

[2019-07-13 13:56:40.023082] INFO: bigquant: dropnan.v1 开始运行..

[2019-07-13 13:56:40.075193] INFO: bigquant: 命中缓存

[2019-07-13 13:56:40.077928] INFO: bigquant: dropnan.v1 运行完成[0.054836s].

1.2因子构建

克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2019年7月13日 14:07
# 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。


m1 = M.instruments.v2(
    start_date='2016-01-01',
    end_date='2016-03-01',
    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)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=True
)

m3 = M.standardlize.v8(
    input_1=m2.data,
    columns_input=['label']
)

[2019-07-13 14:02:34.411943] INFO: bigquant: instruments.v2 开始运行..

[2019-07-13 14:02:34.558733] INFO: bigquant: instruments.v2 运行完成[0.146801s].

[2019-07-13 14:02:34.565602] INFO: bigquant: advanced_auto_labeler.v2 开始运行..

[2019-07-13 14:02:35.058736] INFO: 自动标注(股票): 加载历史数据: 94453 行

[2019-07-13 14:02:35.060750] INFO: 自动标注(股票): 开始标注 ..

[2019-07-13 14:02:35.653953] INFO: bigquant: advanced_auto_labeler.v2 运行完成[1.088338s].

[2019-07-13 14:02:35.661276] INFO: bigquant: standardlize.v8 开始运行..

[2019-07-13 14:02:35.958987] INFO: bigquant: standardlize.v8 运行完成[0.297696s].

2.1 固定买卖周期逻辑

克隆策略

{"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-215:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-215:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-222:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-231:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-238:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:model","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:model"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-250:options_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:predictions"},{"DestinationInputPortId":"-231:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-250:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60:data","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-222:input_data","SourceOutputPortId":"-215:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-222:data"},{"DestinationInputPortId":"-238:input_data","SourceOutputPortId":"-231:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-238:data"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2015-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"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\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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"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","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","ModuleId":"BigQuantSpace.stock_ranker_train.stock_ranker_train-v5","ModuleParameters":[{"Name":"learning_algorithm","Value":"排序","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_leaves","Value":30,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"minimum_docs_per_leaf","Value":1000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"number_of_trees","Value":20,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_bins","Value":1023,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43"}],"OutputPortsInternal":[{"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"feature_gains","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-43","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","ModuleId":"BigQuantSpace.stock_ranker_predict.stock_ranker_predict-v5","ModuleParameters":[{"Name":"m_lazy_run","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60"}],"OutputPortsInternal":[{"Name":"predictions","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null},{"Name":"m_lazy_run","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-60","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2015-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"IsPartOfPartialRun":null,"Comment":"预测数据，用于回测和模拟","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":13,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-86","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-86"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-86","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-215","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-215"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-215"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-215","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-222","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-222"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-222"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-222","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-231","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-231"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-231"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-231","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-238","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-238"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-238"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-238","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-250","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":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'] = 3\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"handle_data","Value":"# 回测引擎：每日数据处理函数，每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n\n # 1. 资金分配\n # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金\n # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）\n is_staging = context.trading_day_index+1 < 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, cash_avg)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.portfolio.positions.items()}\n\n # 2. 持有固定天数卖出\n #----------------------------START：持有固定交易日天数卖出---------------------------\n today = data.current_dt.strftime('%Y-%m-%d')\n # 不是建仓期（在前hold_days属于建仓期）\n if not is_staging:\n equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}\n for instrument in equities:\n sid = equities[instrument].sid # 交易标的\n # 今天和上次交易的时间相隔hold_days就全部卖出\n dt = pd.to_datetime(D.trading_days(end_date = today).iloc[-context.options['hold_days']+1].values[0])\n if pd.to_datetime(equities[instrument].last_sale_date.strftime('%Y-%m-%d')) <= dt and data.can_trade(context.symbol(instrument)):\n context.order_target_percent(sid, 0)\n #--------------------------------END:持有固定天数卖出---------------------------\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,这里要过滤掉已经持仓的股票否则last_sale_date会被再次买入覆盖\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction[~ranker_prediction.instrument.isin(positions)].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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎：准备数据，只执行一次\ndef bigquant_run(context):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":1000000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"真实价格","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-250"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-250","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='211,64,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,183,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='765,21,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-43' Position='638,561,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-60' Position='906,647,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1074,127,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='376,467,200,200'/><NodePosition Node='-86' Position='1078,418,200,200'/><NodePosition Node='-215' Position='381,188,200,200'/><NodePosition Node='-222' Position='385,280,200,200'/><NodePosition Node='-231' Position='1078,236,200,200'/><NodePosition Node='-238' Position='1081,327,200,200'/><NodePosition Node='-250' Position='1006.32568359375,802.9885864257812,200,200'/></NodePositions><NodeGroups /></DataV1>"},"IsDraft":true,"ParentExperimentId":null,"WebService":{"IsWebServiceExperiment":false,"Inputs":[],"Outputs":[],"Parameters":[{"Name":"交易日期","Value":"","ParameterDefinition":{"Name":"交易日期","FriendlyName":"交易日期","DefaultValue":"","ParameterType":"String","HasDefaultValue":true,"IsOptional":true,"ParameterRules":[],"HasRules":false,"MarkupType":0,"CredentialDescriptor":null}}],"WebServiceGroupId":null,"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions></NodePositions><NodeGroups /></DataV1>"},"DisableNodesUpdate":false,"Category":"user","Tags":[],"IsPartialRun":false}

In [24]:

# 本代码由可视化策略环境自动生成 2019年9月19日 16:25
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# 回测引擎：初始化函数，只执行一次
def m19_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 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'] = 3

# 回测引擎：每日数据处理函数，每天执行一次
def m19_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]

    # 1. 资金分配
    # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
    # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
    is_staging = context.trading_day_index+1 < 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, cash_avg)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.portfolio.positions.items()}

    # 2. 持有固定天数卖出
    #----------------------------START：持有固定交易日天数卖出---------------------------
    today = data.current_dt.strftime('%Y-%m-%d')
    # 不是建仓期（在前hold_days属于建仓期）
    if not is_staging:
        equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
        for instrument in equities:
            sid = equities[instrument].sid  # 交易标的
            # 今天和上次交易的时间相隔hold_days就全部卖出
            dt = pd.to_datetime(D.trading_days(end_date = today).iloc[-context.options['hold_days']+1].values[0])
            if  pd.to_datetime(equities[instrument].last_sale_date.strftime('%Y-%m-%d')) <= dt and data.can_trade(context.symbol(instrument)):
                context.order_target_percent(sid, 0)
    #--------------------------------END:持有固定天数卖出---------------------------

    # 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,这里要过滤掉已经持仓的股票否则last_sale_date会被再次买入覆盖
    buy_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction[~ranker_prediction.instrument.isin(positions)].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='2010-01-01',
    end_date='2015-01-01',
    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)

# 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
)

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
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

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
)

m6 = M.stock_ranker_train.v5(
    training_ds=m13.data,
    features=m3.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-01-01'),
    end_date=T.live_run_param('trading_date', '2017-01-01'),
    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=0
)

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
)

m8 = M.stock_ranker_predict.v5(
    model=m6.model,
    data=m14.data,
    m_lazy_run=False
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_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='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.SHA'
)

[2019-09-19 16:22:37.314384] INFO: bigquant: instruments.v2 开始运行..

[2019-09-19 16:22:37.467404] INFO: bigquant: 命中缓存

[2019-09-19 16:22:37.469960] INFO: bigquant: instruments.v2 运行完成[0.155594s].

[2019-09-19 16:22:37.473510] INFO: bigquant: advanced_auto_labeler.v2 开始运行..

[2019-09-19 16:22:37.598530] INFO: bigquant: 命中缓存

[2019-09-19 16:22:37.601114] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.127574s].

[2019-09-19 16:22:37.604060] INFO: bigquant: input_features.v1 开始运行..

[2019-09-19 16:22:37.790840] INFO: bigquant: 命中缓存

[2019-09-19 16:22:37.793394] INFO: bigquant: input_features.v1 运行完成[0.189287s].

[2019-09-19 16:22:37.868594] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-09-19 16:22:37.998596] INFO: bigquant: 命中缓存

[2019-09-19 16:22:38.001394] INFO: bigquant: general_feature_extractor.v7 运行完成[0.132778s].

[2019-09-19 16:22:38.004921] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-19 16:22:38.121376] INFO: bigquant: 命中缓存

[2019-09-19 16:22:38.123756] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.118816s].

[2019-09-19 16:22:38.127014] INFO: bigquant: join.v3 开始运行..

[2019-09-19 16:22:38.263526] INFO: bigquant: 命中缓存

[2019-09-19 16:22:38.267304] INFO: bigquant: join.v3 运行完成[0.140269s].

[2019-09-19 16:22:38.271402] INFO: bigquant: dropnan.v1 开始运行..

[2019-09-19 16:22:38.338102] INFO: bigquant: 命中缓存

[2019-09-19 16:22:38.340817] INFO: bigquant: dropnan.v1 运行完成[0.069399s].

[2019-09-19 16:22:38.344412] INFO: bigquant: stock_ranker_train.v5 开始运行..

[2019-09-19 16:22:38.581109] INFO: bigquant: 命中缓存

[2019-09-19 16:22:38.861015] INFO: bigquant: stock_ranker_train.v5 运行完成[0.516574s].

[2019-09-19 16:22:38.864610] INFO: bigquant: instruments.v2 开始运行..

[2019-09-19 16:22:38.973400] INFO: bigquant: 命中缓存

[2019-09-19 16:22:38.976130] INFO: bigquant: instruments.v2 运行完成[0.111477s].

[2019-09-19 16:22:39.140937] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-09-19 16:22:39.241174] INFO: bigquant: 命中缓存

[2019-09-19 16:22:39.243482] INFO: bigquant: general_feature_extractor.v7 运行完成[0.102433s].

[2019-09-19 16:22:39.252239] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-19 16:22:39.411864] INFO: bigquant: 命中缓存

[2019-09-19 16:22:39.414129] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.161888s].

[2019-09-19 16:22:39.418185] INFO: bigquant: dropnan.v1 开始运行..

[2019-09-19 16:22:39.539314] INFO: bigquant: 命中缓存

[2019-09-19 16:22:39.543370] INFO: bigquant: dropnan.v1 运行完成[0.125149s].

[2019-09-19 16:22:39.555560] INFO: bigquant: stock_ranker_predict.v5 开始运行..

[2019-09-19 16:22:39.759810] INFO: bigquant: 命中缓存

[2019-09-19 16:22:39.764539] INFO: bigquant: stock_ranker_predict.v5 运行完成[0.208961s].

[2019-09-19 16:22:39.895190] INFO: bigquant: backtest.v8 开始运行..

[2019-09-19 16:22:39.904613] INFO: bigquant: biglearning backtest:V8.2.12

[2019-09-19 16:22:39.907244] INFO: bigquant: product_type:stock by specified

[2019-09-19 16:22:40.270991] INFO: bigquant: cached.v2 开始运行..

[2019-09-19 16:22:40.362436] INFO: bigquant: 命中缓存

[2019-09-19 16:22:40.364843] INFO: bigquant: cached.v2 运行完成[0.093865s].

[2019-09-19 16:22:52.283166] INFO: algo: TradingAlgorithm V1.5.8

[2019-09-19 16:22:55.159307] INFO: algo: trading transform...

[2019-09-19 16:23:07.259762] INFO: algo: handle_splits get splits [dt:2015-04-16 00:00:00+00:00] [asset:Equity(683 [300390.SZA]), ratio:0.6630872981901985]

[2019-09-19 16:23:07.263554] INFO: Position: position stock handle split[sid:683, orig_amount:1100, new_amount:1658.0, orig_cost:39.020005629016886, new_cost:25.87, ratio:0.6630872981901985, last_sale_price:24.700001857584894]

[2019-09-19 16:23:07.268982] INFO: Position: after split: PositionStock(asset:Equity(683 [300390.SZA]), amount:1658.0, cost_basis:25.87, last_sale_price:37.25)

[2019-09-19 16:23:07.273662] INFO: Position: returning cash: 22.4

[2019-09-19 16:23:10.762021] INFO: algo: handle_splits get splits [dt:2015-05-15 00:00:00+00:00] [asset:Equity(2169 [000736.SZA]), ratio:0.9987076835878506]

[2019-09-19 16:23:10.768078] INFO: Position: position stock handle split[sid:2169, orig_amount:16900, new_amount:16921.0, orig_cost:15.350013840478981, new_cost:15.33, ratio:0.9987076835878506, last_sale_price:15.459995437209697]

[2019-09-19 16:23:10.773651] INFO: Position: after split: PositionStock(asset:Equity(2169 [000736.SZA]), amount:16921.0, cost_basis:15.33, last_sale_price:15.480000495910645)

[2019-09-19 16:23:10.775780] INFO: Position: returning cash: 13.43

[2019-09-19 16:23:11.696404] INFO: algo: handle_splits get splits [dt:2015-05-22 00:00:00+00:00] [asset:Equity(1892 [300119.SZA]), ratio:0.9944382925109119]

[2019-09-19 16:23:11.698545] INFO: Position: position stock handle split[sid:1892, orig_amount:6500, new_amount:6536.0, orig_cost:16.360001220667378, new_cost:16.27, ratio:0.9944382925109119, last_sale_price:17.88000194086899]

[2019-09-19 16:23:11.700719] INFO: Position: after split: PositionStock(asset:Equity(1892 [300119.SZA]), amount:6536.0, cost_basis:16.27, last_sale_price:17.98000144958496)

[2019-09-19 16:23:11.702665] INFO: Position: returning cash: 6.32

[2019-09-19 16:23:16.008936] INFO: algo: handle_splits get splits [dt:2015-06-23 00:00:00+00:00] [asset:Equity(2250 [300077.SZA]), ratio:0.9998031228727998]

[2019-09-19 16:23:16.011546] INFO: Position: position stock handle split[sid:2250, orig_amount:3600, new_amount:3600.0, orig_cost:51.989998192647114, new_cost:51.98, ratio:0.9998031228727998, last_sale_price:50.770001359017975]

[2019-09-19 16:23:16.014384] INFO: Position: after split: PositionStock(asset:Equity(2250 [300077.SZA]), amount:3600.0, cost_basis:51.98, last_sale_price:50.779998779296875)

[2019-09-19 16:23:16.016089] INFO: Position: returning cash: 35.99

[2019-09-19 16:23:16.913829] INFO: algo: handle_splits get splits [dt:2015-06-29 00:00:00+00:00] [asset:Equity(1560 [000716.SZA]), ratio:0.9974734355876671]

[2019-09-19 16:23:16.916250] INFO: Position: position stock handle split[sid:1560, orig_amount:4700, new_amount:4711.0, orig_cost:23.850001497022188, new_cost:23.79, ratio:0.9974734355876671, last_sale_price:23.689994095207094]

[2019-09-19 16:23:16.918203] INFO: Position: after split: PositionStock(asset:Equity(1560 [000716.SZA]), amount:4711.0, cost_basis:23.79, last_sale_price:23.75)

[2019-09-19 16:23:16.920206] INFO: Position: returning cash: 21.44

[2019-09-19 16:23:18.798835] INFO: algo: handle_splits get splits [dt:2015-07-08 00:00:00+00:00] [asset:Equity(2351 [002133.SZA]), ratio:0.9865547066162149]

[2019-09-19 16:23:20.869417] INFO: algo: handle_splits get splits [dt:2015-07-15 00:00:00+00:00] [asset:Equity(915 [300006.SZA]), ratio:0.9972134668014038]

[2019-09-19 16:23:20.872141] INFO: Position: position stock handle split[sid:915, orig_amount:3000, new_amount:3008.0, orig_cost:41.50000433930211, new_cost:41.38, ratio:0.9972134668014038, last_sale_price:35.789994518919066]

[2019-09-19 16:23:20.874222] INFO: Position: after split: PositionStock(asset:Equity(915 [300006.SZA]), amount:3008.0, cost_basis:41.38, last_sale_price:35.8900032043457)

[2019-09-19 16:23:20.876093] INFO: Position: returning cash: 13.71

[2019-09-19 16:23:30.611719] INFO: algo: handle_splits get splits [dt:2015-09-17 00:00:00+00:00] [asset:Equity(821 [600446.SHA]), ratio:0.33293942190663656]

[2019-09-19 16:23:30.615900] INFO: Position: position stock handle split[sid:821, orig_amount:1400, new_amount:4204.0, orig_cost:114.0000000482192, new_cost:37.96, ratio:0.33293942190663656, last_sale_price:33.80999677054322]

[2019-09-19 16:23:30.618103] INFO: Position: after split: PositionStock(asset:Equity(821 [600446.SHA]), amount:4204.0, cost_basis:37.96, last_sale_price:101.54999542236328)

[2019-09-19 16:23:30.620093] INFO: Position: returning cash: 32.77

[2019-09-19 16:23:59.022229] INFO: algo: handle_splits get splits [dt:2016-05-16 00:00:00+00:00] [asset:Equity(2340 [300081.SZA]), ratio:0.3987395579718062]

[2019-09-19 16:23:59.031922] INFO: Position: position stock handle split[sid:2340, orig_amount:5400, new_amount:13542.0, orig_cost:35.13000261128855, new_cost:14.01, ratio:0.3987395579718062, last_sale_price:13.919997907952927]

[2019-09-19 16:23:59.033981] INFO: Position: after split: PositionStock(asset:Equity(2340 [300081.SZA]), amount:13542.0, cost_basis:14.01, last_sale_price:34.90999984741211)

[2019-09-19 16:23:59.035735] INFO: Position: returning cash: 9.39

[2019-09-19 16:24:02.715411] INFO: algo: handle_splits get splits [dt:2016-06-20 00:00:00+00:00] [asset:Equity(2029 [600873.SHA]), ratio:0.9842022100472294]

[2019-09-19 16:24:02.726603] INFO: Position: position stock handle split[sid:2029, orig_amount:28000, new_amount:28449.0, orig_cost:6.260000416173964, new_cost:6.16, ratio:0.9842022100472294, last_sale_price:6.229999914510293]

[2019-09-19 16:24:02.732622] INFO: Position: after split: PositionStock(asset:Equity(2029 [600873.SHA]), amount:28449.0, cost_basis:6.16, last_sale_price:6.329999923706055)

[2019-09-19 16:24:02.738357] INFO: Position: returning cash: 2.73

[2019-09-19 16:24:06.366421] INFO: algo: handle_splits get splits [dt:2016-07-08 00:00:00+00:00] [asset:Equity(364 [603699.SHA]), ratio:0.9860337230776506]

[2019-09-19 16:24:06.372718] INFO: Position: position stock handle split[sid:364, orig_amount:13300, new_amount:13488.0, orig_cost:18.010052061145977, new_cost:17.76, ratio:0.9860337230776506, last_sale_price:17.65000326694793]

[2019-09-19 16:24:06.378282] INFO: Position: after split: PositionStock(asset:Equity(364 [603699.SHA]), amount:13488.0, cost_basis:17.76, last_sale_price:17.899999618530273)

[2019-09-19 16:24:06.383724] INFO: Position: returning cash: 6.75

[2019-09-19 16:24:11.138147] INFO: algo: handle_splits get splits [dt:2016-08-12 00:00:00+00:00] [asset:Equity(76 [600578.SHA]), ratio:0.95623635873562]

[2019-09-19 16:24:11.140197] INFO: Position: position stock handle split[sid:76, orig_amount:38700, new_amount:40471.0, orig_cost:4.560004052334111, new_cost:4.36, ratio:0.95623635873562, last_sale_price:4.3700003235706335]

[2019-09-19 16:24:11.141920] INFO: Position: after split: PositionStock(asset:Equity(76 [600578.SHA]), amount:40471.0, cost_basis:4.36, last_sale_price:4.570000171661377)

[2019-09-19 16:24:11.144057] INFO: Position: returning cash: 0.72

[2019-09-19 16:24:29.010979] INFO: Performance: Simulated 488 trading days out of 488.

[2019-09-19 16:24:29.017198] INFO: Performance: first open: 2015-01-05 09:30:00+00:00

[2019-09-19 16:24:29.022608] INFO: Performance: last close: 2016-12-30 15:00:00+00:00

[2019-09-19 16:24:49.609929] INFO: bigquant: backtest.v8 运行完成[129.714736s].

StockRanker
特征重要性
模型
NDCG

设置测试数据集，查看训练迭代过程的NDCG

bigcharts-data-start/{"__id":"bigchart-28cd2240310243b2bf633f9c8f4dfe28","__type":"tabs"}/bigcharts-data-end

收益率418.09%
年化收益率133.84%
基准收益率-6.33%
阿尔法0.92
贝塔0.96
夏普比率2.14
胜率0.6
盈亏比0.96
收益波动率42.58%
信息比率0.2
最大回撤48.58%

bigcharts-data-start/{"__id":"bigchart-de2d674fa952460db9c8f8d748db85b7","__type":"tabs"}/bigcharts-data-end

3.1 股票配对交易策略

克隆策略

配对交易策略¶

In [7]:

# 本代码由可视化策略环境自动生成 2020年9月23日 14:42
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# 回测引擎：初始化函数，只执行一次
def m3_initialize_bigquant_run(context):
    # 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))
# 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):
    today = data.current_dt.strftime('%Y-%m-%d')
    zscore_today =context.zscore.ix[today]
    #获取股票的列表
    stocklist=context.instruments
    # 转换成回测引擎所需要的symbol格式
    symbol_1 = context.symbol(stocklist[0]) 
    symbol_2 = context.symbol(stocklist[1])  

    # 持仓
    cur_position_1 = context.portfolio.positions[symbol_1].amount
    cur_position_2 = context.portfolio.positions[symbol_2].amount
       
    # 交易逻辑
    # 如果zscore大于上轨（>1），则价差会向下回归均值，因此需要买入股票x，卖出股票y
    if zscore_today > 1 and cur_position_1 == 0 and data.can_trade(symbol_1) and data.can_trade(symbol_2):  
        context.order_target_percent(symbol_2, 0)
        context.order_target_percent(symbol_1, 1)
        print(today, '全仓买入：',stocklist[0])
        
    # 如果zscore小于下轨（<-1），则价差会向上回归均值，因此需要买入股票y，卖出股票x
    elif zscore_today < -1 and cur_position_2 == 0 and data.can_trade(symbol_1) and data.can_trade(symbol_2):  
        context.order_target_percent(symbol_1, 0)  
        context.order_target_percent(symbol_2, 1)
        print(today, '全仓买入：',stocklist[1])
 
          

# 回测引擎：准备数据，只执行一次
def m3_prepare_bigquant_run(context):
    pass
# 回测引擎：准备数据，只执行一次
def m3_before_trading_start_bigquant_run(context,data):
    # 加载股票历史数据
    df = context.options['data'].read_df()
    df['date'] = df['date'].apply(lambda x:x.strftime('%Y-%m-%d'))
    today = data.current_dt.strftime('%Y-%m-%d')
    # 获取前240个自然日的数据
    start_date = (pd.to_datetime(data.current_dt)-datetime.timedelta(days=240)).strftime('%Y-%m-%d')
    stock_data = df[df.date <= today]
    # 由于可能上市天数不同，对缺失值填充处理
    prices_df=pd.pivot_table(stock_data, values='close_0', index=['date'], columns=['instrument'])
    prices_df.fillna(method='ffill',inplace=True)
    
    x = prices_df[context.instruments[0]] # 股票1
    y = prices_df[context.instruments[1]] # 股票2
    
    # 线性回归两个股票的股价 y=ax+b
    from pyfinance import ols
    model = ols.OLS(y=y, x=x)
 
    def zscore(series):
        return (series - series.mean()) / np.std(series)
    
    # 计算 y-a*x 序列的zscore值序列
    zscore_calcu = zscore(y-model.beta*x)
    context.zscore=zscore_calcu

m1 = 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_0
"""
)

m2 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-01-01'),
    end_date=T.live_run_param('trading_date', '2018-10-28'),
    market='CN_STOCK_A',
    instrument_list="""601328.SHA
601998.SHA""",
    max_count=0
)

m7 = M.general_feature_extractor.v7(
    instruments=m2.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=300
)

m4 = 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,
    user_functions={}
)

m5 = M.dropnan.v2(
    input_data=m4.data
)

m3 = M.trade.v4(
    instruments=m2.data,
    options_data=m5.data,
    start_date='',
    end_date='',
    initialize=m3_initialize_bigquant_run,
    handle_data=m3_handle_data_bigquant_run,
    prepare=m3_prepare_bigquant_run,
    before_trading_start=m3_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='open',
    capital_base=1000000,
    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=''
)

[2019-06-21 09:53:38.503017] INFO: bigquant: input_features.v1 开始运行..

[2019-06-21 09:53:38.545842] INFO: bigquant: 命中缓存

[2019-06-21 09:53:38.556901] INFO: bigquant: input_features.v1 运行完成[0.053881s].

[2019-06-21 09:53:38.560006] INFO: bigquant: instruments.v2 开始运行..

[2019-06-21 09:53:38.602468] INFO: bigquant: 命中缓存

[2019-06-21 09:53:38.604658] INFO: bigquant: instruments.v2 运行完成[0.044642s].

[2019-06-21 09:53:38.635206] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-06-21 09:53:38.665744] INFO: bigquant: 命中缓存

[2019-06-21 09:53:38.667802] INFO: bigquant: general_feature_extractor.v7 运行完成[0.032597s].

[2019-06-21 09:53:38.670660] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-06-21 09:53:38.711715] INFO: bigquant: 命中缓存

[2019-06-21 09:53:38.713990] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.04332s].

[2019-06-21 09:53:38.716530] INFO: bigquant: dropnan.v1 开始运行..

[2019-06-21 09:53:38.742758] INFO: bigquant: 命中缓存

[2019-06-21 09:53:38.744626] INFO: bigquant: dropnan.v1 运行完成[0.028085s].

[2019-06-21 09:53:38.791453] INFO: bigquant: backtest.v8 开始运行..

[2019-06-21 09:53:38.794461] INFO: bigquant: biglearning backtest:V8.2.2

[2019-06-21 09:53:38.795752] INFO: bigquant: product_type:stock by specified

[2019-06-21 09:53:39.084577] INFO: bigquant: cached.v2 开始运行..

[2019-06-21 09:53:39.128779] INFO: bigquant: 命中缓存

[2019-06-21 09:53:39.130639] INFO: bigquant: cached.v2 运行完成[0.046066s].

[2019-06-21 09:53:39.184503] INFO: algo: TradingAlgorithm V1.5.0

[2019-06-21 09:53:39.373587] INFO: algo: trading transform...

[2019-06-21 09:54:29.600489] INFO: algo: handle_splits get splits [dt:2016-07-25 00:00:00+00:00] [asset:Equity(0 [601998.SHA]), ratio:0.9657426445424234]

[2019-06-21 09:54:29.602455] INFO: Position: position stock handle split[sid:0, orig_amount:183300, new_amount:189802.0, orig_cost:5.690047724566808, new_cost:5.5, ratio:0.9657426445424234, last_sale_price:5.9200025215655305]

[2019-06-21 09:54:29.604078] INFO: Position: after split: asset: Equity(0 [601998.SHA]), amount: 189802.0, cost_basis: 5.5,             last_sale_price: 6.130000114440918

[2019-06-21 09:54:29.605697] INFO: Position: returning cash: 0.7

[2019-06-21 09:55:01.107468] INFO: algo: handle_splits get splits [dt:2017-07-24 00:00:00+00:00] [asset:Equity(0 [601998.SHA]), ratio:0.9700427168666901]

[2019-06-21 09:55:01.110080] INFO: Position: position stock handle split[sid:0, orig_amount:218600, new_amount:225350.0, orig_cost:6.1500281882553605, new_cost:5.97, ratio:0.9700427168666901, last_sale_price:6.799999667260655]

[2019-06-21 09:55:01.112385] INFO: Position: after split: asset: Equity(0 [601998.SHA]), amount: 225350.0, cost_basis: 5.97,             last_sale_price: 7.010000228881836

[2019-06-21 09:55:01.114301] INFO: Position: returning cash: 6.13

[2019-06-21 09:55:33.612472] INFO: algo: handle_splits get splits [dt:2018-07-16 00:00:00+00:00] [asset:Equity(1 [601328.SHA]), ratio:0.9517470390385913]

[2019-06-21 09:55:33.614314] INFO: Position: position stock handle split[sid:1, orig_amount:254600, new_amount:267508.0, orig_cost:7.0600000818200925, new_cost:6.72, ratio:0.9517470390385913, last_sale_price:5.7199994686311895]

[2019-06-21 09:55:33.615812] INFO: Position: after split: asset: Equity(1 [601328.SHA]), amount: 267508.0, cost_basis: 6.72,             last_sale_price: 6.009999752044678

[2019-06-21 09:55:33.617095] INFO: Position: returning cash: 0.32

[2019-06-21 09:55:42.568981] INFO: Performance: Simulated 930 trading days out of 930.

[2019-06-21 09:55:42.571150] INFO: Performance: first open: 2015-01-05 09:30:00+00:00

[2019-06-21 09:55:42.573583] INFO: Performance: last close: 2018-10-26 15:00:00+00:00

[2019-06-21 09:55:44.571635] INFO: bigquant: backtest.v8 运行完成[125.780166s].

2015-01-05 全仓买入： 601328.SHA
2015-06-01 全仓买入： 601998.SHA
2015-07-08 全仓买入： 601328.SHA
2015-08-31 全仓买入： 601998.SHA
2015-11-18 全仓买入： 601328.SHA
2016-06-06 全仓买入： 601998.SHA

2016-11-28 全仓买入： 601328.SHA
2017-04-19 全仓买入： 601998.SHA

2018-02-05 全仓买入： 601328.SHA

2018-09-14 全仓买入： 601998.SHA

收益率54.33%
年化收益率12.48%
基准收益率-10.19%
阿尔法0.15
贝塔0.74
夏普比率0.44
胜率0.67
盈亏比0.69
收益波动率30.75%
信息比率0.04
最大回撤40.63%

bigcharts-data-start/{"__id":"bigchart-56cff1c73cbc45268d29cd7a4da5d1ce","__type":"tabs"}/bigcharts-data-end

3.2 双均线策略+固定百分比止损

克隆策略

双均线策略+固定百分比止损¶

In [5]:

# 本代码由可视化策略环境自动生成 2020年9月23日 14:46
# 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。


# 回测引擎：初始化函数，只执行一次
def m3_initialize_bigquant_run(context):

    # 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))

# 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):
    
 #------------------------------------------止损模块START------------------------------------------- #
    date = data.current_dt.strftime('%Y-%m-%d')
    positions = {e.symbol: p.cost_basis  for e, p in context.portfolio.positions.items()}
    # 新建当日止赢股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
    current_stopwin_stock = [] 
    if len(positions) > 0:
        for i in positions.keys():
            stock_cost = positions[i] 
            stock_market_price = data.current(context.symbol(i), 'price') 
            # 赚10%止盈
            if stock_market_price / stock_cost -1 > 0.1:   
                context.order_target_percent(context.symbol(i),0)     
                current_stopwin_stock.append(i)
                print('日期：',date,'股票：',i,'出现上涨10%，触发止盈')
 #-------------------------------------------止损模块END---------------------------------------------#




    # 1. 获取今日的日期
    today = data.current_dt.strftime('%Y-%m-%d')
    
    # 2. 获取目前持仓的股票和最新市值
    stock_hold_now = {e.symbol: p.amount * p.last_sale_price for e, p in context.portfolio.positions.items()} 
    
    # 3. 获取当前账户可用现金
    cash_for_buy = context.portfolio.cash
    
    # 4. 获取当日的买卖信号股票列表
    try:
        buy_stock = context.daily_stock_buy[today]
    except:
        buy_stock=[]  # 如果没有符合条件的股票，就设置为空
    
    try:
        sell_stock = context.daily_stock_sell[today]
    except:
        sell_stock=[] # 如果没有符合条件的股票，就设置为空 
        
    # 5. 确认需要卖出的股票:已有持仓中符合卖出条件的股票
    stock_to_sell = [ i for i in stock_hold_now if i in sell_stock ]
    
    # 6. 执行卖出操作
    if len(stock_to_sell)>0:
        for instrument in stock_to_sell:
            # 如果股票已经在止盈列表中，则跳过卖出操作
            if instrument in current_stopwin_stock:
                continue
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 当前持仓
            if cur_position > 0 and data.can_trade(sid):
                context.order_target_percent(sid, 0) # 全部卖出
                # 根据卖出的股票市值更新可用现金:
                cash_for_buy += stock_hold_now[instrument]
    
    # 7. 执行买入操作
    if len(buy_stock)>0:
        weight = 1/len(buy_stock)  # 每只股票的比重为等资金比例持有
        for instrument in buy_stock:
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 当前持仓
            if  data.can_trade(sid) and cur_position==0:
                context.order_target_value(sid, weight*cash_for_buy) # 按可用现金等比例买入
# 回测引擎：准备数据，只执行一次
def m3_prepare_bigquant_run(context):
    # 加载预测数据
    df = context.options['data'].read_df()

    # 函数：求满足开仓条件的股票列表
    def open_pos_con(df):
        return list(df[df['buy_condition']>0].instrument)

    # 函数：求满足平仓条件的股票列表
    def close_pos_con(df):
        return list(df[df['sell_condition']>0].instrument)

    # 每日买入股票的数据框
    context.daily_stock_buy= df.groupby('date').apply(open_pos_con)
    # 每日卖出股票的数据框
    context.daily_stock_sell= df.groupby('date').apply(close_pos_con)

m1 = 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
buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0)
sell_condition=where(mean(close_0,5)<mean(close_0,20),1,0)""",
    m_cached=False
)

m2 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2016-01-01'),
    end_date=T.live_run_param('trading_date', '2017-01-01'),
    market='CN_STOCK_A',
    instrument_list='600519.SHA',
    max_count=0
)

m7 = M.general_feature_extractor.v7(
    instruments=m2.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=200,
    m_cached=False
)

m8 = 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
)

m4 = M.dropnan.v2(
    input_data=m8.data
)

m3 = M.trade.v4(
    instruments=m2.data,
    options_data=m4.data,
    start_date='',
    end_date='',
    initialize=m3_initialize_bigquant_run,
    handle_data=m3_handle_data_bigquant_run,
    prepare=m3_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='open',
    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=''
)

[2019-09-19 17:23:07.792873] INFO: bigquant: input_features.v1 开始运行..

[2019-09-19 17:23:08.186172] INFO: bigquant: input_features.v1 运行完成[0.393294s].

[2019-09-19 17:23:08.197696] INFO: bigquant: instruments.v2 开始运行..

[2019-09-19 17:23:08.701834] INFO: bigquant: 命中缓存

[2019-09-19 17:23:08.704262] INFO: bigquant: instruments.v2 运行完成[0.506546s].

[2019-09-19 17:23:09.307162] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-09-19 17:23:09.853597] INFO: 基础特征抽取: 年份 2015, 特征行数=136

[2019-09-19 17:23:09.896071] INFO: 基础特征抽取: 年份 2016, 特征行数=244

[2019-09-19 17:23:09.918153] INFO: 基础特征抽取: 年份 2017, 特征行数=0

[2019-09-19 17:23:10.247284] INFO: 基础特征抽取: 总行数: 380

[2019-09-19 17:23:10.254148] INFO: bigquant: general_feature_extractor.v7 运行完成[0.946984s].

[2019-09-19 17:23:10.261087] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-19 17:23:10.718868] INFO: derived_feature_extractor: 提取完成 buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0), 0.012s

[2019-09-19 17:23:10.743357] INFO: derived_feature_extractor: 提取完成 sell_condition=where(mean(close_0,5)[2019-09-19 17:23:11.037936] INFO: derived_feature_extractor: /y_2015, 136
[2019-09-19 17:23:11.095965] INFO: derived_feature_extractor: /y_2016, 244
[2019-09-19 17:23:11.450596] INFO: bigquant: derived_feature_extractor.v3 运行完成[1.189501s].
[2019-09-19 17:23:11.458106] INFO: bigquant: dropnan.v1 开始运行..
[2019-09-19 17:23:11.694375] INFO: dropnan: /y_2015, 136/136
[2019-09-19 17:23:11.733158] INFO: dropnan: /y_2016, 244/244
[2019-09-19 17:23:11.935565] INFO: dropnan: 行数: 380/380
[2019-09-19 17:23:11.950387] INFO: bigquant: dropnan.v1 运行完成[0.492258s].
[2019-09-19 17:23:12.028427] INFO: bigquant: backtest.v8 开始运行..
[2019-09-19 17:23:12.117618] INFO: bigquant: biglearning backtest:V8.2.13
[2019-09-19 17:23:13.218853] INFO: bigquant: product_type:stock by specified
[2019-09-19 17:23:13.622276] INFO: bigquant: cached.v2 开始运行..
[2019-09-19 17:23:13.739935] INFO: bigquant: 命中缓存
[2019-09-19 17:23:13.745772] INFO: bigquant: cached.v2 运行完成[0.123481s].
[2019-09-19 17:23:13.916656] INFO: algo: TradingAlgorithm V1.5.8
[2019-09-19 17:23:14.001222] INFO: algo: trading transform...
[2019-09-19 17:23:15.111988] INFO: Performance: Simulated 244 trading days out of 244.
[2019-09-19 17:23:15.117268] INFO: Performance: first open: 2016-01-04 09:30:00+00:00
[2019-09-19 17:23:15.124464] INFO: Performance: last close: 2016-12-30 15:00:00+00:00
[2019-09-19 17:23:17.419454] INFO: bigquant: backtest.v8 运行完成[5.391029s].

日期： 2016-03-03 股票： 600519.SHA 出现上涨10%，触发止盈
日期： 2016-06-03 股票： 600519.SHA 出现上涨10%，触发止盈
日期： 2016-07-05 股票： 600519.SHA 出现上涨10%，触发止盈

收益率28.16%
年化收益率29.21%
基准收益率-11.28%
阿尔法0.29
贝塔0.3
夏普比率1.2
胜率0.56
盈亏比3.01
收益波动率20.66%
信息比率0.09
最大回撤10.38%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-98dd58eca2ef47d28cebe0c77f0b82b4"}/bigcharts-data-end

3.3 多因子选股

克隆策略

In [3]:

# 本代码由可视化策略环境自动生成 2020年12月8日 14:15
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# 回测引擎：初始化函数，只执行一次
def m2_initialize_bigquant_run(context):
    
    # 设置交易费用，买入是万三，卖出是千分之1.3，如果不足5元按5元算
    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    
    # 如果策略运行中，需要将数据(比如运行天数)进行保存，可以借用extension这个对象，类型为dict
    if 'index' not in context.extension:
        context.extension['index'] = 0
# 回测引擎：每日数据处理函数，每天执行一次
def m2_handle_data_bigquant_run(context, data):
    
    # 1. 按每个K线递增，记录策略运行天数
    context.extension['index']  += 1
    
    # 2. 每隔22个交易日进行换仓
    if context.extension['index'] % context.rebalance_days != 1:
        return 
    
    # 3. 买入股票列表
    stock_to_buy = context.daily_stock_buy.ix[data.current_dt.strftime('%Y-%m-%d')]
    
    # 4. 当前持仓列表    
    stock_hold_now = [equity.symbol for equity in context.portfolio.positions]
    no_need_to_sell = [i for i in stock_hold_now if (i in stock_to_buy) and (i in stock_hold_now)]

    # 5. 卖出股票列表 
    stock_to_sell = [i for i in stock_hold_now if i not in no_need_to_sell]
    
    # 6. 执行卖出
    for stock in stock_to_sell:
        if data.can_trade(context.symbol(stock)):
            context.order_target_percent(context.symbol(stock), 0)
            
    # 7. 执行买入
    if len(stock_to_buy)>0: 
        weight = 1 / len(stock_to_buy) # 等权重
        for  instrument in stock_to_buy:
            if data.can_trade(context.symbol(instrument)):
                context.order_target_percent(context.symbol(instrument), weight)
# 回测引擎：准备数据，只执行一次
def m2_prepare_bigquant_run(context):
    # 加载股票指标数据,数据继承自m4模块
    context.indicator_data = context.options['data'].read_df()

     # 设置股票数量
    context.stock_num = 30
    
    def open_pos_con(df):
        return list(df.instrument)[:context.stock_num]
    
    # 计算每日股票买入列表
    context.daily_stock_buy = context.indicator_data.groupby('date').apply(open_pos_con)
    
    # 调仓天数,22个交易日大概就是一个月。可以理解为一个月换仓一次
    context.rebalance_days = 22
    


m3 = M.instruments.v2(
    start_date='2015-01-01',
    end_date='2019-04-23',
    market='CN_STOCK_A',
    instrument_list=''
)

m5 = M.input_features.v1(
    features="""pb_lf_0
pe_ttm_0
amount_0"""
)

m1 = M.general_feature_extractor.v7(
    instruments=m3.data,
    features=m5.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m6 = M.sort.v4(
    input_ds=m1.data,
    sort_by='pe_ttm_0,pb_lf_0',
    group_by='date',
    keep_columns='--',
    ascending=True
)

m4 = M.filter.v3(
    input_data=m6.sorted_data,
    expr='pb_lf_0 < 1.5 & pe_ttm_0 < 15 & amount_0 > 0 & pb_lf_0 > 0 & pe_ttm_0 > 0',
    output_left_data=False
)

m2 = M.trade.v4(
    instruments=m3.data,
    options_data=m4.data,
    start_date='',
    end_date='',
    initialize=m2_initialize_bigquant_run,
    handle_data=m2_handle_data_bigquant_run,
    prepare=m2_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='open',
    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=''
)

[2020-12-08 14:15:20.454254] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-12-08 14:15:20.490386] INFO: moduleinvoker: 命中缓存

[2020-12-08 14:15:20.491638] INFO: moduleinvoker: instruments.v2 运行完成[0.037397s].

[2020-12-08 14:15:20.494466] INFO: moduleinvoker: input_features.v1 开始运行..

[2020-12-08 14:15:20.565296] INFO: moduleinvoker: 命中缓存

[2020-12-08 14:15:20.567009] INFO: moduleinvoker: input_features.v1 运行完成[0.072525s].

[2020-12-08 14:15:20.736726] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-12-08 14:15:20.813343] INFO: moduleinvoker: 命中缓存

[2020-12-08 14:15:20.814775] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.078066s].

[2020-12-08 14:15:20.821709] INFO: moduleinvoker: sort.v4 开始运行..

[2020-12-08 14:15:20.899792] INFO: moduleinvoker: 命中缓存

[2020-12-08 14:15:20.901264] INFO: moduleinvoker: sort.v4 运行完成[0.079535s].

[2020-12-08 14:15:20.907554] INFO: moduleinvoker: filter.v3 开始运行..

[2020-12-08 14:15:20.951400] INFO: moduleinvoker: 命中缓存

[2020-12-08 14:15:20.953147] INFO: moduleinvoker: filter.v3 运行完成[0.045599s].

[2020-12-08 14:15:22.418218] INFO: moduleinvoker: backtest.v8 开始运行..

[2020-12-08 14:15:22.423311] INFO: backtest: biglearning backtest:V8.4.2

[2020-12-08 14:15:22.617669] INFO: backtest: product_type:stock by specified

[2020-12-08 14:15:22.858733] INFO: moduleinvoker: cached.v2 开始运行..

[2020-12-08 14:15:22.870786] INFO: moduleinvoker: 命中缓存

[2020-12-08 14:15:22.871936] INFO: moduleinvoker: cached.v2 运行完成[0.013229s].

[2020-12-08 14:15:25.985701] INFO: algo: TradingAlgorithm V1.6.10

[2020-12-08 14:15:28.225896] INFO: algo: trading transform...

[2020-12-08 14:15:35.552759] INFO: Performance: Simulated 1049 trading days out of 1049.

[2020-12-08 14:15:35.554640] INFO: Performance: first open: 2015-01-05 09:30:00+00:00

[2020-12-08 14:15:35.556695] INFO: Performance: last close: 2019-04-23 15:00:00+00:00

[2020-12-08 14:15:49.515487] INFO: moduleinvoker: backtest.v8 运行完成[27.097269s].

[2020-12-08 14:15:49.517069] INFO: moduleinvoker: trade.v4 运行完成[28.553024s].

收益率79.85%
年化收益率15.14%
基准收益率13.73%
阿尔法0.11
贝塔0.84
夏普比率0.57
胜率0.46
盈亏比2.35
收益波动率25.06%
信息比率0.05
最大回撤30.7%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-2207eaab72e04a6dbc4201d8f5a24e2d"}/bigcharts-data-end

3.4 双均线策略

克隆策略

双均线策略¶

In [37]:

# 本代码由可视化策略环境自动生成 2019年6月20日 15:59
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# 回测引擎：每日数据处理函数，每天执行一次
def m3_handle_data_bigquant_run(context, data):
    # 1. 获取今日的日期
    today = data.current_dt.strftime('%Y-%m-%d')
    
    # 2. 获取目前持仓的股票和最新市值
    stock_hold_now = {e.symbol: p.amount * p.last_sale_price for e, p in context.portfolio.positions.items()} 
    
    # 3. 获取当前账户可用现金
    cash_for_buy = context.portfolio.cash
    
    # 4. 获取当日的买卖信号股票列表
    try:
        buy_stock = context.daily_stock_buy[today]
    except:
        buy_stock=[]  # 如果没有符合条件的股票，就设置为空
    
    try:
        sell_stock = context.daily_stock_sell[today]
    except:
        sell_stock=[] # 如果没有符合条件的股票，就设置为空 
        
    # 5. 确认需要卖出的股票:已有持仓中符合卖出条件的股票
    stock_to_sell = [ i for i in stock_hold_now if i in sell_stock ]
    
    # 6. 执行卖出操作
    if len(stock_to_sell)>0:
        for instrument in stock_to_sell:
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 当前持仓
            if cur_position > 0 and data.can_trade(sid):
                context.order_target_percent(sid, 0) 
                # 根据卖出的股票市值更新可用现金；
                cash_for_buy += stock_hold_now[instrument]
    
    # 7. 执行买入操作
    if len(buy_stock)>0:
        weight = 1/len(buy_stock)  # 每只股票的比重为等资金比例持有
        for instrument in buy_stock:
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 当前持仓
            if  data.can_trade(sid) and cur_position==0:
                context.order_target_value(sid, weight*cash_for_buy) # 按可用现金等比例买入
# 回测引擎：准备数据，只执行一次
def m3_prepare_bigquant_run(context):
    # 加载预测数据
    df = context.options['data'].read_df()

    # 函数：求满足开仓条件的股票列表
    def open_pos_con(df):
        return list(df[df['buy_condition']>0].instrument)

    # 函数：求满足平仓条件的股票列表
    def close_pos_con(df):
        return list(df[df['sell_condition']>0].instrument)

    # 每日买入股票的数据框
    context.daily_stock_buy= df.groupby('date').apply(open_pos_con)
    # 每日卖出股票的数据框
    context.daily_stock_sell= df.groupby('date').apply(close_pos_con)
# 回测引擎：初始化函数，只执行一次
def m3_initialize_bigquant_run(context):
 
    # 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))

m1 = 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
buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0)
sell_condition=where(mean(close_0,5)<mean(close_0,20),1,0)""",
    m_cached=False
)

m2 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2016-01-01'),
    end_date=T.live_run_param('trading_date', '2017-01-01'),
    market='CN_STOCK_A',
    instrument_list='600519.SHA',
    max_count=0
)

m7 = M.general_feature_extractor.v7(
    instruments=m2.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=200,
    m_cached=False
)

m8 = 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
)

m6 = M.dropnan.v1(
    input_data=m8.data
)

m3 = M.trade.v4(
    instruments=m2.data,
    options_data=m6.data,
    start_date='',
    end_date='',
    handle_data=m3_handle_data_bigquant_run,
    prepare=m3_prepare_bigquant_run,
    initialize=m3_initialize_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='close',
    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=''
)

[2019-06-20 13:14:10.005262] INFO: bigquant: input_features.v1 开始运行..

[2019-06-20 13:14:10.063670] INFO: bigquant: input_features.v1 运行完成[0.058405s].

[2019-06-20 13:14:10.067459] INFO: bigquant: instruments.v2 开始运行..

[2019-06-20 13:14:10.094217] INFO: bigquant: 命中缓存

[2019-06-20 13:14:10.095947] INFO: bigquant: instruments.v2 运行完成[0.028497s].

[2019-06-20 13:14:10.128575] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-06-20 13:14:10.246481] INFO: 基础特征抽取: 年份 2015, 特征行数=136

[2019-06-20 13:14:10.273475] INFO: 基础特征抽取: 年份 2016, 特征行数=244

[2019-06-20 13:14:10.285415] INFO: 基础特征抽取: 年份 2017, 特征行数=0

[2019-06-20 13:14:10.345540] INFO: 基础特征抽取: 总行数: 380

[2019-06-20 13:14:10.347480] INFO: bigquant: general_feature_extractor.v7 运行完成[0.218905s].

[2019-06-20 13:14:10.350536] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-06-20 13:14:10.436890] INFO: derived_feature_extractor: 提取完成 buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0), 0.007s

[2019-06-20 13:14:10.446629] INFO: derived_feature_extractor: 提取完成 sell_condition=where(mean(close_0,5)[2019-06-20 13:14:10.486996] INFO: derived_feature_extractor: /y_2015, 136
[2019-06-20 13:14:10.513525] INFO: derived_feature_extractor: /y_2016, 244
[2019-06-20 13:14:10.613676] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.263128s].
[2019-06-20 13:14:10.616840] INFO: bigquant: dropnan.v1 开始运行..
[2019-06-20 13:14:10.695606] INFO: dropnan: /y_2015, 136/136
[2019-06-20 13:14:10.726307] INFO: dropnan: /y_2016, 244/244
[2019-06-20 13:14:10.813265] INFO: dropnan: 行数: 380/380
[2019-06-20 13:14:10.816473] INFO: bigquant: dropnan.v1 运行完成[0.199615s].
[2019-06-20 13:14:10.860465] INFO: bigquant: backtest.v8 开始运行..
[2019-06-20 13:14:10.864171] INFO: bigquant: biglearning backtest:V8.2.2
[2019-06-20 13:14:11.500200] INFO: bigquant: product_type:stock by specified
[2019-06-20 13:14:11.687216] INFO: bigquant: cached.v2 开始运行..
[2019-06-20 13:14:11.726424] INFO: bigquant: 命中缓存
[2019-06-20 13:14:11.729266] INFO: bigquant: cached.v2 运行完成[0.04205s].
[2019-06-20 13:14:11.768565] INFO: algo: TradingAlgorithm V1.5.0
[2019-06-20 13:14:11.812191] INFO: algo: trading transform...
[2019-06-20 13:14:12.482313] INFO: Performance: Simulated 244 trading days out of 244.
[2019-06-20 13:14:12.484003] INFO: Performance: first open: 2016-01-04 09:30:00+00:00
[2019-06-20 13:14:12.485730] INFO: Performance: last close: 2016-12-30 15:00:00+00:00
[2019-06-20 13:14:13.484915] INFO: bigquant: backtest.v8 运行完成[2.624447s].

收益率40.57%
年化收益率42.15%
基准收益率-11.28%
阿尔法0.38
贝塔0.3
夏普比率1.59
胜率0.67
盈亏比3.01
收益波动率21.81%
信息比率0.12
最大回撤11.05%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-712f0f11151f472d97bd3a10ef466e4c"}/bigcharts-data-end

sena · 2020-10-23 03:53:22 UTC

整没用的绪论

clearyf · 2020-11-19 06:20:31 UTC

这是基础课，你可以看进阶的

youquan · 2020-11-30 08:49:50 UTC

这个克隆后不能运行，哪里的原因？

NameError Traceback (most recent call last)
in ()
114 plot_charts=True,
115 backtest_only=False,
–> 116 benchmark=’’
117 )

in m2_handle_data_bigquant_run(context, data)
29
30 # 5. 卖出股票列表
—> 31 stock_to_sell = [i for i in stock_hold_now if i not in no_need_to_sell]
32
33 # 6. 执行卖出

in (.0)
29
30 # 5. 卖出股票列表
—> 31 stock_to_sell = [i for i in stock_hold_now if i not in no_need_to_sell]
32
33 # 6. 执行卖出

NameError: name ‘no_need_to_sell’ is not defined

iQuant · 2020-12-08 06:28:23 UTC

已经修复了，可以重新克隆哈

gaoguohong · 2021-03-15 05:14:11 UTC

这个计算要搞清楚哪个数据是先发生的基准数据？五天前的数据是基准，后面是后续发生的，所以收益率的分子分母颠倒了。哈哈~ 一个明显的灯下黑错误。

gaoguohong · 2021-03-16 07:39:40 UTC

这里的入门小白的策略，怎么克隆不到了呢？点击就是404