克隆策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"-215:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"to_node_id":"-215:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-222:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-145:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-185:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-178:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"to_node_id":"-145:training_ds","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"to_node_id":"-222:input_data","from_node_id":"-215:data"},{"to_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","from_node_id":"-222:data"},{"to_node_id":"-156:model","from_node_id":"-145:model"},{"to_node_id":"-167:instruments","from_node_id":"-159:data"},{"to_node_id":"-178:instruments","from_node_id":"-159:data"},{"to_node_id":"-194:data1","from_node_id":"-167:data"},{"to_node_id":"-185:input_data","from_node_id":"-178:data"},{"to_node_id":"-194:data2","from_node_id":"-185:data"},{"to_node_id":"-156:data","from_node_id":"-200:data"},{"to_node_id":"-200:input_data","from_node_id":"-194:data"}],"nodes":[{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2014-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2015-01-01","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"002049.SZA","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"cacheable":true,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","module_id":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","parameters":[{"name":"label_expr","value":"# #号开始的表示注释\n# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html\n# 添加benchmark_前缀,可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(open, -1)\n\n# 极值处理:用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类,这里使用20个分类\nall_wbins(label, 20)\n\n# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","type":"Literal","bound_global_parameter":null},{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.SHA","type":"Literal","bound_global_parameter":null},{"name":"drop_na_label","value":"True","type":"Literal","bound_global_parameter":null},{"name":"cast_label_int","value":"True","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"cacheable":true,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"# #号开始的表示注释\n# 多个特征,每行一个,可以包含基础特征和衍生特征\nreturn_5\nreturn_10\nreturn_20\navg_amount_0/avg_amount_5\navg_amount_5/avg_amount_20","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"cacheable":true,"seq_num":3,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","module_id":"BigQuantSpace.join.join-v3","parameters":[{"name":"on","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"how","value":"inner","type":"Literal","bound_global_parameter":null},{"name":"sort","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"data1","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"name":"data2","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"cacheable":true,"seq_num":13,"comment":"","comment_collapsed":true},{"node_id":"-215","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":90,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-215"},{"name":"features","node_id":"-215"}],"output_ports":[{"name":"data","node_id":"-215"}],"cacheable":true,"seq_num":15,"comment":"","comment_collapsed":true},{"node_id":"-222","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-222"},{"name":"features","node_id":"-222"}],"output_ports":[{"name":"data","node_id":"-222"}],"cacheable":true,"seq_num":16,"comment":"","comment_collapsed":true},{"node_id":"-145","module_id":"BigQuantSpace.linear_sgd_train.linear_sgd_train-v2","parameters":[{"name":"loss","value":"auto","type":"Literal","bound_global_parameter":null},{"name":"penalty","value":"l2","type":"Literal","bound_global_parameter":null},{"name":"alpha","value":0.0001,"type":"Literal","bound_global_parameter":null},{"name":"n_iter","value":5,"type":"Literal","bound_global_parameter":null},{"name":"shuffle","value":"True","type":"Literal","bound_global_parameter":null},{"name":"eta0","value":0.1,"type":"Literal","bound_global_parameter":null},{"name":"algo","value":"classifier","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"training_ds","node_id":"-145"},{"name":"features","node_id":"-145"},{"name":"test_ds","node_id":"-145"}],"output_ports":[{"name":"model","node_id":"-145"}],"cacheable":true,"seq_num":6,"comment":"","comment_collapsed":true},{"node_id":"-156","module_id":"BigQuantSpace.linear_sgd_predict.linear_sgd_predict-v2","parameters":[],"input_ports":[{"name":"model","node_id":"-156"},{"name":"data","node_id":"-156"}],"output_ports":[{"name":"predictions","node_id":"-156"}],"cacheable":true,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-159","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2017-04-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2017-05-01","type":"Literal","bound_global_parameter":null},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"002049.SZA","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"-159"}],"output_ports":[{"name":"data","node_id":"-159"}],"cacheable":true,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"-167","module_id":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","parameters":[{"name":"label_expr","value":"# #号开始的表示注释\n# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html\n# 添加benchmark_前缀,可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(open, -1)\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\n","type":"Literal","bound_global_parameter":null},{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.SHA","type":"Literal","bound_global_parameter":null},{"name":"drop_na_label","value":"True","type":"Literal","bound_global_parameter":null},{"name":"cast_label_int","value":"True","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-167"}],"output_ports":[{"name":"data","node_id":"-167"}],"cacheable":true,"seq_num":9,"comment":"","comment_collapsed":true},{"node_id":"-178","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":90,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-178"},{"name":"features","node_id":"-178"}],"output_ports":[{"name":"data","node_id":"-178"}],"cacheable":true,"seq_num":10,"comment":"","comment_collapsed":true},{"node_id":"-185","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-185"},{"name":"features","node_id":"-185"}],"output_ports":[{"name":"data","node_id":"-185"}],"cacheable":true,"seq_num":11,"comment":"","comment_collapsed":true},{"node_id":"-200","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"-200"}],"output_ports":[{"name":"data","node_id":"-200"}],"cacheable":true,"seq_num":14,"comment":"","comment_collapsed":true},{"node_id":"-194","module_id":"BigQuantSpace.join.join-v3","parameters":[{"name":"on","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"how","value":"inner","type":"Literal","bound_global_parameter":null},{"name":"sort","value":"False","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"data1","node_id":"-194"},{"name":"data2","node_id":"-194"}],"output_ports":[{"name":"data","node_id":"-194"}],"cacheable":true,"seq_num":12,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='211,64,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='70,184,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='765,21,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='249,375,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='327,476,200,200'/><node_position Node='-215' Position='387.75286865234375,182.7528533935547,200,200'/><node_position Node='-222' Position='386,280,200,200'/><node_position Node='-145' Position='464,614,200,200'/><node_position Node='-156' Position='683,736,200,200'/><node_position Node='-159' Position='1124.7802734375,-20.299766540527344,200,200'/><node_position Node='-167' Position='1196.72314453125,228.7070770263672,200,200'/><node_position Node='-178' Position='752.2173461914062,232.29290771484375,200,200'/><node_position Node='-185' Position='945,334,200,200'/><node_position Node='-200' Position='1096,634,200,200'/><node_position Node='-194' Position='995.3203125,478.04571533203125,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [10]:
    # 本代码由可视化策略环境自动生成 2021年8月9日 10:38
    # 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='2014-01-01',
        end_date='2015-01-01',
        market='CN_STOCK_A',
        instrument_list='002049.SZA',
        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"""
    )
    
    m15 = M.general_feature_extractor.v7(
        instruments=m1.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=90
    )
    
    m16 = M.derived_feature_extractor.v3(
        input_data=m15.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m7 = M.join.v3(
        data1=m2.data,
        data2=m16.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m13 = M.dropnan.v1(
        input_data=m7.data
    )
    
    m6 = M.linear_sgd_train.v2(
        training_ds=m13.data,
        features=m3.data,
        loss='auto',
        penalty='l2',
        alpha=0.0001,
        n_iter=5,
        shuffle=True,
        eta0=0.1,
        algo='classifier'
    )
    
    m8 = M.instruments.v2(
        start_date='2017-04-01',
        end_date='2017-05-01',
        market='CN_STOCK_A',
        instrument_list='002049.SZA',
        max_count=0
    )
    
    m9 = M.advanced_auto_labeler.v2(
        instruments=m8.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
    )
    
    m10 = M.general_feature_extractor.v7(
        instruments=m8.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=90
    )
    
    m11 = M.derived_feature_extractor.v3(
        input_data=m10.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m12 = M.join.v3(
        data1=m9.data,
        data2=m11.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m14 = M.dropnan.v1(
        input_data=m12.data
    )
    
    m4 = M.linear_sgd_predict.v2(
        model=m6.model,
        data=m14.data
    )
    
    ---------------------------------------------------------------------------
    ValueError                                Traceback (most recent call last)
    <ipython-input-10-b042d54d5464> in <module>
         11 )
         12 
    ---> 13 m9 = M.advanced_auto_labeler.v2(
         14     instruments=m8.data,
         15     label_expr="""# #号开始的表示注释
    
    ValueError: Bin edges must be unique: array([-inf,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,
            nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  nan,  inf]).
    You can drop duplicate edges by setting the 'duplicates' kwarg