克隆策略

    {"Description":"实验创建于2018/1/23","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"-43:instruments","SourceOutputPortId":"-4129:data"},{"DestinationInputPortId":"-331:instruments","SourceOutputPortId":"-4129:data"},{"DestinationInputPortId":"-2932:data2","SourceOutputPortId":"-43:data"},{"DestinationInputPortId":"-43:features","SourceOutputPortId":"-49:data"},{"DestinationInputPortId":"-2932:data1","SourceOutputPortId":"-331:data"},{"DestinationInputPortId":"-331:features","SourceOutputPortId":"-337:data"},{"DestinationInputPortId":"-355:features","SourceOutputPortId":"-350:data"},{"DestinationInputPortId":"-3888:data2","SourceOutputPortId":"-2932:data"},{"DestinationInputPortId":"-780:input_1","SourceOutputPortId":"-387:data"},{"DestinationInputPortId":"-556:input_1","SourceOutputPortId":"-780:data_1"},{"DestinationInputPortId":"-474:input_1","SourceOutputPortId":"-380:data"},{"DestinationInputPortId":"-556:input_2","SourceOutputPortId":"-474:data_1"},{"DestinationInputPortId":"-606:input_1","SourceOutputPortId":"-556:data_1"},{"DestinationInputPortId":"-606:input_2","SourceOutputPortId":"-596:data"},{"DestinationInputPortId":"-996:input_data","SourceOutputPortId":"-606:data_1"},{"DestinationInputPortId":"-3888:data1","SourceOutputPortId":"-996:data"},{"DestinationInputPortId":"-355:input_data","SourceOutputPortId":"-3888:data"}],"ModuleNodes":[{"Id":"-4129","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"\n\n ","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"-4129"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-4129","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-43","ModuleId":"BigQuantSpace.use_datasource.use_datasource-v1","ModuleParameters":[{"Name":"datasource_id","Value":"financial_statement_CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-43"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-43"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-43","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-49","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\nfs_net_income_x","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-49"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-49","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-331","ModuleId":"BigQuantSpace.use_datasource.use_datasource-v1","ModuleParameters":[{"Name":"datasource_id","Value":"market_value_CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-331"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-331"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-331","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-337","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\nmarket_cap","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-337"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-337","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":4,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-350","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\nlog(market_cap)\nmarket_cap\nfs_net_income_x/market_cap","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"-350"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-350","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":8,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-355","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":"-355"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-355"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-355","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-2932","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":"-2932"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-2932"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-2932","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":6,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-387","ModuleId":"BigQuantSpace.use_datasource.use_datasource-v1","ModuleParameters":[{"Name":"datasource_id","Value":"basic_info_IndustrySw","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-01-01","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-387"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-387"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-387","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-780","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# 修改数据列名\ndef bigquant_run(input_ds):\n df = input_ds.read_df()\n df['code'] = df['code'].astype(int)\n ds = DataSource().write_df(df)\n return Outputs(data_1=ds)\n","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"input_ds","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"data_1","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-780"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-780"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-780"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-780","OutputType":null},{"Name":"data_2","NodeId":"-780","OutputType":null},{"Name":"data_3","NodeId":"-780","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":10,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-380","ModuleId":"BigQuantSpace.use_datasource.use_datasource-v1","ModuleParameters":[{"Name":"datasource_id","Value":"industry_CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-01-01","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-380"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-380"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-380","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":11,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-474","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"Name":"run","Value":"# 修改数据列名\ndef bigquant_run(input_ds):\n df = input_ds.read_df()\n df.rename(columns={'industry_sw_level1':'code'},inplace=True)\n df['code'] = df['code'].astype(int)\n ds = DataSource().write_df(df)\n return Outputs(data_1=ds)\n","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"input_ds","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"data_1","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-474"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-474"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-474"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-474","OutputType":null},{"Name":"data_2","NodeId":"-474","OutputType":null},{"Name":"data_3","NodeId":"-474","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":12,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-556","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"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):\n # 示例代码如下。在这里编写您的代码\n df_1=input_1.read_df()\n df_2=input_2.read_df()\n data = DataSource.write_df(pd.merge(df_1,df_2,on='code'))\n return Outputs(data_1=data)","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"input_1, input_2","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"data_1","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-556"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-556"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-556"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-556","OutputType":null},{"Name":"data_2","NodeId":"-556","OutputType":null},{"Name":"data_3","NodeId":"-556","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":13,"IsPartOfPartialRun":null,"Comment":"得出行业与股票代码的dataframe","CommentCollapsed":true},{"Id":"-596","ModuleId":"BigQuantSpace.use_datasource.use_datasource-v1","ModuleParameters":[{"Name":"datasource_id","Value":"financial_statement_CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2018-01-01","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-596"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-596"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-596","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-606","ModuleId":"BigQuantSpace.cached.cached-v3","ModuleParameters":[{"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):\n # 示例代码如下。在这里编写您的代码\n df_1=input_1.read_df()\n df_2=input_2.read_df()\n data = DataSource.write_df(pd.merge(df_1[['name','date','instrument']],df_2,on=['instrument','date']))\n return Outputs(data_1=data)\n","ValueType":"Literal","LinkedGlobalParameter":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","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"input_ports","Value":"input_1, input_2","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"params","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"output_ports","Value":"data_1","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_1","NodeId":"-606"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_2","NodeId":"-606"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_3","NodeId":"-606"}],"OutputPortsInternal":[{"Name":"data_1","NodeId":"-606","OutputType":null},{"Name":"data_2","NodeId":"-606","OutputType":null},{"Name":"data_3","NodeId":"-606","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-996","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-996"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-996","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-3888","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":"-3888"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"-3888"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-3888","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"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='-4129' Position='183,654,200,200'/><NodePosition Node='-43' Position='266,779,200,200'/><NodePosition Node='-49' Position='468,651,200,200'/><NodePosition Node='-331' Position='-39,777,200,200'/><NodePosition Node='-337' Position='-104,655,200,200'/><NodePosition Node='-350' Position='466,871,200,200'/><NodePosition Node='-355' Position='117,966,200,200'/><NodePosition Node='-2932' Position='40,862,200,200'/><NodePosition Node='-387' Position='-980,436,200,200'/><NodePosition Node='-780' Position='-973,513,200,200'/><NodePosition Node='-380' Position='-647,435,200,200'/><NodePosition Node='-474' Position='-624,522,200,200'/><NodePosition Node='-556' Position='-783,612,200,200'/><NodePosition Node='-596' Position='-469,620,200,200'/><NodePosition Node='-606' Position='-616,706,200,200'/><NodePosition Node='-996' Position='-545,783,200,200'/><NodePosition Node='-3888' Position='-345,892,200,200'/></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 [3]:
    # 本代码由可视化策略环境自动生成 2019年1月15日 13:35
# 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。


# 修改数据列名
def m10_run_bigquant_run(input_ds):
    df = input_ds.read_df()
    df['code'] = df['code'].astype(int)
    ds = DataSource().write_df(df)
    return Outputs(data_1=ds)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m10_post_run_bigquant_run(outputs):
    return outputs

# 修改数据列名
def m12_run_bigquant_run(input_ds):
    df = input_ds.read_df()
    df.rename(columns={'industry_sw_level1':'code'},inplace=True)
    df['code'] = df['code'].astype(int)
    ds = DataSource().write_df(df)
    return Outputs(data_1=ds)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m12_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 m13_run_bigquant_run(input_1, input_2):
    # 示例代码如下。在这里编写您的代码
    df_1=input_1.read_df()
    df_2=input_2.read_df()
    data = DataSource.write_df(pd.merge(df_1,df_2,on='code'))
    return Outputs(data_1=data)
# 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 m13_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 m15_run_bigquant_run(input_1, input_2):
    # 示例代码如下。在这里编写您的代码
    df_1=input_1.read_df()
    df_2=input_2.read_df()
    data = DataSource.write_df(pd.merge(df_1[['name','date','instrument']],df_2,on=['instrument','date']))
    return Outputs(data_1=data)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m15_post_run_bigquant_run(outputs):
    return outputs


m1 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2018-01-01',
    market='CN_STOCK_A',
    instrument_list="""

 """,
    max_count=0
)

m5 = 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
fs_net_income_x"""
)

m3 = M.use_datasource.v1(
    instruments=m1.data,
    features=m5.data,
    datasource_id='financial_statement_CN_STOCK_A',
    start_date='',
    end_date='',
    m_cached=False
)

m4 = 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
market_cap"""
)

m2 = M.use_datasource.v1(
    instruments=m1.data,
    features=m4.data,
    datasource_id='market_value_CN_STOCK_A',
    start_date='',
    end_date=''
)

m6 = M.join.v3(
    data1=m2.data,
    data2=m3.data,
    on='date,instrument',
    how='inner',
    sort=False
)

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
log(market_cap)
market_cap
fs_net_income_x/market_cap"""
)

m7 = M.use_datasource.v1(
    datasource_id='basic_info_IndustrySw',
    start_date='2010-01-01',
    end_date='2018-01-01'
)

m10 = M.cached.v3(
    input_1=m7.data,
    run=m10_run_bigquant_run,
    post_run=m10_post_run_bigquant_run,
    input_ports='input_ds',
    params="""{}
""",
    output_ports='data_1'
)

m11 = M.use_datasource.v1(
    datasource_id='industry_CN_STOCK_A',
    start_date='2010-01-01',
    end_date='2018-01-01'
)

m12 = M.cached.v3(
    input_1=m11.data,
    run=m12_run_bigquant_run,
    post_run=m12_post_run_bigquant_run,
    input_ports='input_ds',
    params="""{}
""",
    output_ports='data_1'
)

m13 = M.cached.v3(
    input_1=m10.data_1,
    input_2=m12.data_1,
    run=m13_run_bigquant_run,
    post_run=m13_post_run_bigquant_run,
    input_ports='input_1, input_2',
    params='{}',
    output_ports='data_1'
)

m14 = M.use_datasource.v1(
    datasource_id='financial_statement_CN_STOCK_A',
    start_date='2010-01-01',
    end_date='2018-01-01'
)

m15 = M.cached.v3(
    input_1=m13.data_1,
    input_2=m14.data,
    run=m15_run_bigquant_run,
    post_run=m15_post_run_bigquant_run,
    input_ports='input_1, input_2',
    params='{}',
    output_ports='data_1'
)

m16 = M.dropnan.v1(
    input_data=m15.data_1
)

m17 = M.join.v3(
    data1=m16.data,
    data2=m6.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m9 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m8.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

    [2019-01-15 13:34:04.675264] INFO: bigquant: instruments.v2 开始运行..
[2019-01-15 13:34:04.690632] INFO: bigquant: 命中缓存
[2019-01-15 13:34:04.691708] INFO: bigquant: instruments.v2 运行完成[0.01652s].
[2019-01-15 13:34:04.694921] INFO: bigquant: input_features.v1 开始运行..
[2019-01-15 13:34:04.699434] INFO: bigquant: 命中缓存
[2019-01-15 13:34:04.700146] INFO: bigquant: input_features.v1 运行完成[0.005228s].
[2019-01-15 13:34:04.713268] INFO: bigquant: use_datasource.v1 开始运行..
[2019-01-15 13:34:07.283494] INFO: bigquant: use_datasource.v1 运行完成[2.570216s].
[2019-01-15 13:34:07.286481] INFO: bigquant: input_features.v1 开始运行..
[2019-01-15 13:34:07.291983] INFO: bigquant: 命中缓存
[2019-01-15 13:34:07.292736] INFO: bigquant: input_features.v1 运行完成[0.006266s].
[2019-01-15 13:34:07.294629] INFO: bigquant: use_datasource.v1 开始运行..
[2019-01-15 13:34:07.299764] INFO: bigquant: 命中缓存
[2019-01-15 13:34:07.300646] INFO: bigquant: use_datasource.v1 运行完成[0.006011s].
[2019-01-15 13:34:07.304150] INFO: bigquant: join.v3 开始运行..
[2019-01-15 13:34:12.213706] INFO: join: /data, 行数=64682/80558, 耗时=2.281733s
[2019-01-15 13:34:12.362616] INFO: join: 最终行数: 64682
[2019-01-15 13:34:12.366024] INFO: bigquant: join.v3 运行完成[5.061824s].
[2019-01-15 13:34:12.368899] INFO: bigquant: input_features.v1 开始运行..
[2019-01-15 13:34:12.377781] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.379120] INFO: bigquant: input_features.v1 运行完成[0.010217s].
[2019-01-15 13:34:12.381561] INFO: bigquant: use_datasource.v1 开始运行..
[2019-01-15 13:34:12.388813] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.389618] INFO: bigquant: use_datasource.v1 运行完成[0.008068s].
[2019-01-15 13:34:12.395604] INFO: bigquant: cached.v3 开始运行..
[2019-01-15 13:34:12.400521] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.401215] INFO: bigquant: cached.v3 运行完成[0.005596s].
[2019-01-15 13:34:12.403281] INFO: bigquant: use_datasource.v1 开始运行..
[2019-01-15 13:34:12.408214] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.408879] INFO: bigquant: use_datasource.v1 运行完成[0.005626s].
[2019-01-15 13:34:12.412835] INFO: bigquant: cached.v3 开始运行..
[2019-01-15 13:34:12.418017] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.418803] INFO: bigquant: cached.v3 运行完成[0.005983s].
[2019-01-15 13:34:12.421829] INFO: bigquant: cached.v3 开始运行..
[2019-01-15 13:34:12.426440] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.427476] INFO: bigquant: cached.v3 运行完成[0.005621s].
[2019-01-15 13:34:12.430287] INFO: bigquant: use_datasource.v1 开始运行..
[2019-01-15 13:34:12.443093] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.444096] INFO: bigquant: use_datasource.v1 运行完成[0.013784s].
[2019-01-15 13:34:12.447698] INFO: bigquant: cached.v3 开始运行..
[2019-01-15 13:34:12.454352] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.455434] INFO: bigquant: cached.v3 运行完成[0.007738s].
[2019-01-15 13:34:12.478016] INFO: bigquant: dropnan.v1 开始运行..
[2019-01-15 13:34:12.484621] INFO: bigquant: 命中缓存
[2019-01-15 13:34:12.485533] INFO: bigquant: dropnan.v1 运行完成[0.007549s].
[2019-01-15 13:34:12.487864] INFO: bigquant: join.v3 开始运行..
[2019-01-15 13:34:12.578448] INFO: join: /data, 行数=3643/64682, 耗时=0.060292s
[2019-01-15 13:34:12.590838] INFO: join: 最终行数: 3643
[2019-01-15 13:34:12.592651] INFO: bigquant: join.v3 运行完成[0.104779s].
[2019-01-15 13:34:12.597725] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-01-15 13:34:12.617506] WARNING: derived_feature_extractor: 特征 fs_net_income_x/market_cap，找不到依赖的列：fs_net_income_x
[2019-01-15 13:34:12.624628] INFO: derived_feature_extractor: 提取完成 log(market_cap), 0.001s
[2019-01-15 13:34:12.625890] INFO: derived_feature_extractor: 提取失败 fs_net_income_x/market_cap: Unknown fs_net_income_x
[2019-01-15 13:34:12.648518] INFO: derived_feature_extractor: /data, 3643
[2019-01-15 13:34:12.682232] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.084412s].
    In [4]:
    m9.data.read_df().head()
    Out[4]:
    date instrument fs_quarter_index_x market_cap name fs_account_payable fs_account_receivable fs_bps fs_capital_reserves fs_paicl_up_capital ... fs_total_profit fs_undistributed_profit fs_common_equity fs_eps_yoy fs_net_profit_yoy fs_operating_revenue_yoy fs_quarter fs_quarter_year fs_quarter_index_y log(market_cap)
    0 2010-01-29 000860.SZA 4 7.718304e+09 食品饮料 380763008.0 249083904.0 5.47 1.208242e+09 4.385400e+08 ... 245111792.0 575305536.0 2.397787e+09 -26.000000 -27.341499 17.613600 20091231 2009 4 7.718304e+09
    1 2010-02-08 600703.SHA 4 1.564477e+10 电子 67495256.0 118568024.0 5.26 1.159715e+09 2.776850e+08 ... 204681120.0 12674759.0 1.461065e+09 153.571426 246.108398 120.628403 20091231 2009 4 1.564477e+10
    2 2010-02-09 000155.SZA 4 3.684800e+09 化工 122345456.0 36059852.0 3.81 8.102781e+08 4.700000e+08 ... 80090016.0 287790688.0 1.788389e+09 -33.333332 -34.674500 -14.791800 20091231 2009 4 3.684800e+09
    3 2010-02-10 000822.SZA 4 6.462564e+09 化工 521201440.0 273611488.0 3.67 1.500998e+09 8.950919e+08 ... -917584384.0 595832512.0 3.282417e+09 -443.478271 -435.690887 -36.361900 20091231 2009 4 6.462564e+09
    4 2010-02-11 600533.SHA 4 6.289500e+09 房地产 389854208.0 31424230.0 2.58 1.026469e+09 1.050000e+09 ... 397046336.0 493017184.0 2.709020e+09 10.850286 18.800301 38.354900 20091231 2009 4 6.289500e+09

    5 rows × 67 columns

    In [5]:
    df = m9.data.read_df()[['fs_net_income','log(market_cap)','market_cap','date','instrument','name']]
df.dropna(how='any')
df_0 = df.groupby(['name']).apply(lambda x:x[['fs_net_income','log(market_cap)','market_cap']]-x[['fs_net_income','log(market_cap)','market_cap']].mean()).dropna().reset_index()
df_0.head()
    Out[5]:
    index fs_net_income log(market_cap) market_cap
    0 0 -2.112286e+09 -5.534814e+10 -5.534814e+10
    1 1 -1.036888e+08 -3.204637e+09 -3.204637e+09
    2 2 -2.855448e+06 -2.368548e+09 -2.368548e+09
    3 3 -8.153691e+08 4.092155e+08 4.092155e+08
    4 4 -7.001470e+08 -1.892655e+10 -1.892655e+10
    In [ ]:
    In [6]:
    import numpy as np
import pandas as pd
from scipy import stats, integrate
import matplotlib.pyplot as plt
import seaborn as sns
def winsorize(df, width=3):
        df = df.copy()
        factor_columns = set(df.columns).difference(['date','instrument'])
        for factor in factor_columns:
            mean = df[factor].mean()
            sigma = df[factor].std()
            df[factor] = df[factor].clip(mean-width*sigma,mean+width*sigma)
        return df
def standardlize(df):
        df = df.copy()
        factor_columns = set(df.columns).difference(['date','instrument'])
        for factor in factor_columns:
            mean = df[factor].mean()
            sigma = df[factor].std()
            df[factor] = (df[factor]-mean)/sigma
        return df
    
    
sns.set(color_codes=True)
data = df_0.values 
with sns.axes_style("ticks"):
    sns.jointplot(x="fs_net_income", y="market_cap", data=df_0,kind='reg')
    In [ ]: