复制链接
克隆策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"-231:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-238:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-231:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-119:predict_ds","from_node_id":"-86:data"},{"to_node_id":"-238:input_data","from_node_id":"-231:data"},{"to_node_id":"-86:input_data","from_node_id":"-238:data"},{"to_node_id":"-119:model","from_node_id":"-325:data_1"}],"nodes":[{"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\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","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-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2015-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2017-01-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":"0","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"output_ports":[{"name":"data","node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"cacheable":true,"seq_num":9,"comment":"预测数据，用于回测和模拟","comment_collapsed":false},{"node_id":"-86","module_id":"BigQuantSpace.dropnan.dropnan-v1","parameters":[],"input_ports":[{"name":"input_data","node_id":"-86"}],"output_ports":[{"name":"data","node_id":"-86"}],"cacheable":true,"seq_num":14,"comment":"","comment_collapsed":true},{"node_id":"-231","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":"-231"},{"name":"features","node_id":"-231"}],"output_ports":[{"name":"data","node_id":"-231"}],"cacheable":true,"seq_num":17,"comment":"","comment_collapsed":true},{"node_id":"-238","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":"-238"},{"name":"features","node_id":"-238"}],"output_ports":[{"name":"data","node_id":"-238"}],"cacheable":true,"seq_num":18,"comment":"","comment_collapsed":true},{"node_id":"-119","module_id":"BigQuantSpace.xgboost.xgboost-v1","parameters":[{"name":"num_boost_round","value":30,"type":"Literal","bound_global_parameter":null},{"name":"objective","value":"排序(pairwise)","type":"Literal","bound_global_parameter":null},{"name":"booster","value":"gbtree","type":"Literal","bound_global_parameter":null},{"name":"max_depth","value":"5","type":"Literal","bound_global_parameter":null},{"name":"key_cols","value":"date,instrument","type":"Literal","bound_global_parameter":null},{"name":"group_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"nthread","value":1,"type":"Literal","bound_global_parameter":null},{"name":"n_gpus","value":-1,"type":"Literal","bound_global_parameter":null},{"name":"other_train_parameters","value":"{}","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"training_ds","node_id":"-119"},{"name":"features","node_id":"-119"},{"name":"model","node_id":"-119"},{"name":"predict_ds","node_id":"-119"}],"output_ports":[{"name":"output_model","node_id":"-119"},{"name":"predictions","node_id":"-119"}],"cacheable":true,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-325","module_id":"BigQuantSpace.cached.cached-v3","parameters":[{"name":"run","value":"# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端\ndef bigquant_run(input_1, input_2, input_3):\n \n # 调用以csv文件保存的xgboost模型\n data_1 = DataSource.write_pickle(pd.read_pickle('xgboost.csv'))\n return Outputs(data_1=data_1, data_2=None, data_3=None)\n","type":"Literal","bound_global_parameter":null},{"name":"post_run","value":"# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。\ndef bigquant_run(outputs):\n return outputs\n","type":"Literal","bound_global_parameter":null},{"name":"input_ports","value":"","type":"Literal","bound_global_parameter":null},{"name":"params","value":"{}","type":"Literal","bound_global_parameter":null},{"name":"output_ports","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_1","node_id":"-325"},{"name":"input_2","node_id":"-325"},{"name":"input_3","node_id":"-325"}],"output_ports":[{"name":"data_1","node_id":"-325"},{"name":"data_2","node_id":"-325"},{"name":"data_3","node_id":"-325"}],"cacheable":true,"seq_num":1,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='540,59,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='914,61,200,200'/><node_position Node='-86' Position='775,434,200,200'/><node_position Node='-231' Position='743,263,200,200'/><node_position Node='-238' Position='746,356,200,200'/><node_position Node='-119' Position='290,545,200,200'/><node_position Node='-325' Position='272,417,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [3]:
    # 本代码由可视化策略环境自动生成 2021年12月11日 17:30
# 本代码单元只能在可视化模式下编辑。您也可以拷贝代码，粘贴到新建的代码单元或者策略，然后修改。


# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m1_run_bigquant_run(input_1, input_2, input_3):
    
    # 调用以csv文件保存的xgboost模型
    data_1 = DataSource.write_pickle(pd.read_pickle('xgboost.csv'))
    return Outputs(data_1=data_1, data_2=None, data_3=None)

# 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 m1_post_run_bigquant_run(outputs):
    return outputs


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
"""
)

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=90
)

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
)

m1 = M.cached.v3(
    run=m1_run_bigquant_run,
    post_run=m1_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m5 = M.xgboost.v1(
    model=m1.data_1,
    predict_ds=m14.data,
    num_boost_round=30,
    objective='排序(pairwise)',
    booster='gbtree',
    max_depth=5,
    key_cols='date,instrument',
    group_col='date',
    nthread=1,
    n_gpus=-1,
    other_train_parameters={}
)
    In [6]:
    # 查看预测结果
m5.predictions.read()
    Out[6]:
    prediction date instrument
    0 0.463205 2014-10-08 000001.SZA
    1 0.491766 2014-10-09 000001.SZA
    2 0.464150 2014-10-10 000001.SZA
    3 0.442917 2014-10-13 000001.SZA
    4 0.471160 2014-10-14 000001.SZA
    ... ... ... ...
    1352808 0.611335 2016-12-26 603999.SHA
    1352809 0.665459 2016-12-27 603999.SHA
    1352810 0.612349 2016-12-28 603999.SHA
    1352811 0.650670 2016-12-29 603999.SHA
    1352812 0.650594 2016-12-30 603999.SHA

    1342805 rows × 3 columns

    In [ ]: