可视化的数据 但 基础数据错误 肿么办啊

策略分享
标签: #<Tag:0x00007fb12509ceb8>

(datuoniao65) #1
克隆策略

    {"Description":"实验创建于2019/11/28","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"-370:features","SourceOutputPortId":"-172:data"},{"DestinationInputPortId":"-384:features","SourceOutputPortId":"-172:data"},{"DestinationInputPortId":"-377:features","SourceOutputPortId":"-172:data"},{"DestinationInputPortId":"-393:features","SourceOutputPortId":"-172:data"},{"DestinationInputPortId":"-86:features","SourceOutputPortId":"-172:data"},{"DestinationInputPortId":"-359:instruments","SourceOutputPortId":"-343:data"},{"DestinationInputPortId":"-370:instruments","SourceOutputPortId":"-343:data"},{"DestinationInputPortId":"-377:instruments","SourceOutputPortId":"-351:data"},{"DestinationInputPortId":"-402:data1","SourceOutputPortId":"-359:data"},{"DestinationInputPortId":"-384:input_data","SourceOutputPortId":"-370:data"},{"DestinationInputPortId":"-393:input_data","SourceOutputPortId":"-377:data"},{"DestinationInputPortId":"-402:data2","SourceOutputPortId":"-384:data"},{"DestinationInputPortId":"-411:input_data","SourceOutputPortId":"-393:data"},{"DestinationInputPortId":"-408:input_data","SourceOutputPortId":"-402:data"},{"DestinationInputPortId":"-86:training_ds","SourceOutputPortId":"-408:data"}],"ModuleNodes":[{"Id":"-172","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"\n# #号开始的表示注释,注释需单独一行\n# 多个特征,每行一个,可以包含基础特征和衍生特征,特征须为本平台特征\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":"-172"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-172","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"Comment":"","CommentCollapsed":true},{"Id":"-343","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2016-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2017-01-01","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":"-343"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-343","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"Comment":"","CommentCollapsed":true},{"Id":"-351","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2018-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2019-01-01","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":"-351"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-351","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"Comment":"","CommentCollapsed":true},{"Id":"-359","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":"-359"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-359","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"Comment":"","CommentCollapsed":true},{"Id":"-370","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":"-370"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-370"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-370","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"Comment":"","CommentCollapsed":true},{"Id":"-377","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":"-377"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-377"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-377","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"Comment":"","CommentCollapsed":true},{"Id":"-384","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":"-384"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-384"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-384","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"Comment":"","CommentCollapsed":true},{"Id":"-393","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":"-393"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-393"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-393","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"Comment":"","CommentCollapsed":true},{"Id":"-402","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":"-402"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-402"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-402","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"Comment":"","CommentCollapsed":true},{"Id":"-408","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-408"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-408","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"Comment":"","CommentCollapsed":true},{"Id":"-411","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-411"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-411","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"Comment":"","CommentCollapsed":true},{"Id":"-86","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":"-86"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-86"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"test_ds","NodeId":"-86"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"base_model","NodeId":"-86"}],"OutputPortsInternal":[{"Name":"model","NodeId":"-86","OutputType":null},{"Name":"feature_gains","NodeId":"-86","OutputType":null},{"Name":"m_lazy_run","NodeId":"-86","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":13,"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='-172' Position='473,-75,200,200'/><NodePosition Node='-343' Position='145,77,200,200'/><NodePosition Node='-351' Position='863,88,200,200'/><NodePosition Node='-359' Position='-86,211,200,200'/><NodePosition Node='-370' Position='324,214,200,200'/><NodePosition Node='-377' Position='877,221,200,200'/><NodePosition Node='-384' Position='329,323,200,200'/><NodePosition Node='-393' Position='869,327,200,200'/><NodePosition Node='-402' Position='345.89105224609375,464.4443664550781,200,200'/><NodePosition Node='-408' Position='336,583,200,200'/><NodePosition Node='-411' Position='892,542,200,200'/><NodePosition Node='-86' Position='522.4456176757812,671.21875,200,200'/></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":true}
    In [133]:
    # 本代码由可视化策略环境自动生成 2019年11月28日 19:42
    # 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。
    
    
    m8 = M.input_features.v1(
        features="""
    # #号开始的表示注释,注释需单独一行
    # 多个特征,每行一个,可以包含基础特征和衍生特征,特征须为本平台特征
    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
    """
    )
    
    m1 = M.instruments.v2(
        start_date='2016-01-01',
        end_date='2017-01-01',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m3 = 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
    )
    
    m4 = M.general_feature_extractor.v7(
        instruments=m1.data,
        features=m8.data,
        start_date='',
        end_date='',
        before_start_days=0
    )
    
    m6 = M.derived_feature_extractor.v3(
        input_data=m4.data,
        features=m8.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False,
        user_functions={}
    )
    
    m9 = M.join.v3(
        data1=m3.data,
        data2=m6.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m10 = M.dropnan.v1(
        input_data=m9.data
    )
    
    m13 = M.stock_ranker_train.v5(
        training_ds=m10.data,
        features=m8.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
    )
    
    m2 = M.instruments.v2(
        start_date='2018-01-01',
        end_date='2019-01-01',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m5 = M.general_feature_extractor.v7(
        instruments=m2.data,
        features=m8.data,
        start_date='',
        end_date='',
        before_start_days=0
    )
    
    m7 = M.derived_feature_extractor.v3(
        input_data=m5.data,
        features=m8.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False,
        user_functions={}
    )
    
    m11 = M.dropnan.v1(
        input_data=m7.data
    )
    
    设置测试数据集,查看训练迭代过程的NDCG
    bigcharts-data-start/{"__id":"bigchart-15dd9a26d49e4421a17a1c335f69c1d5","__type":"tabs"}/bigcharts-data-end

    (datuoniao65) #2


    (iQuant) #3

    可以参考一下样例教程,这里为缺失值处理模块。