复制链接

克隆策略

In [25]:

# 本代码由可视化策略环境自动生成 2023年2月21日 11:01
# 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 m64_run_bigquant_run(input_1, input_2, input_3, SW_type):
    feature_list = input_1.read()
    new_feature_list = []
    feature_jc_list = []
    for feature in feature_list:
        splitStrindex = feature.find("=")
        feature_key = feature[0:splitStrindex].strip()
        feature_value = feature[splitStrindex:-1].strip()
        feature_jc_list.append(feature_key)
        new_feature_list.append('n_'+feature_key+'=rank('+feature_key+')')
    print('因子个数：{}'.format(len(new_feature_list)))
    data_1 = DataSource.write_pickle(new_feature_list)
    data_2 = DataSource.write_pickle(feature_jc_list)
    return Outputs(data_1=data_1,data_2=data_2)

# 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 m64_post_run_bigquant_run(outputs):
    return outputs


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2016-01-01',
    'm1.end_date': '2021-01-20',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.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/data_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/big_expr.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, -2) / shift(open, -1) - 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))

# 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)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': False,

    'm13': 'M.standardlize.v8',
    'm13.input_1': T.Graph.OutputPort('m2.data'),
    'm13.columns_input': 'label',

    'm3': 'M.input_features.v1',
    'm3.features': '',

    'm40': 'M.input_features.v1',
    'm40.features_ds': T.Graph.OutputPort('m3.data'),
    'm40.features': """buy_cond_1 = 1#where(sum(price_limit_status_1==3, 5)>0, 1, 0)
buy_cond_2 = where(volume_0/volume_1>1, 1, 0)
buy_cond_3 = where(return_0>1.05, 1, 0)
buy_cond_4 = where(list_days_0>120, 1, 0)

e1 = mf_net_amount_l_0

#目标变量
y = shift(close_0,-2)/shift(open_0,-1)

#未来两日股票的收益
return_2_day=(shift(close_0, -2)-shift(open_0, -1))/shift(open_0, -1)
#未来三日股票的收益
return_3_day=(shift(close_0, -3)-shift(open_0, -1))/shift(open_0, -1)
""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m40.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 121,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m40.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': False,
    'm16.remove_extra_columns': False,

    'm5': 'M.chinaa_stock_filter.v1',
    'm5.input_data': T.Graph.OutputPort('m16.data'),
    'm5.index_constituent_cond': ['全部'],
    'm5.board_cond': ['上证主板', '深证主板', '创业板'],
    'm5.industry_cond': ['全部'],
    'm5.st_cond': ['正常'],
    'm5.delist_cond': ['非退市'],
    'm5.output_left_data': False,

    'm52': 'M.filter.v3',
    'm52.input_data': T.Graph.OutputPort('m5.data'),
    'm52.expr': 'buy_cond_1==1&buy_cond_2==1&buy_cond_3==1&buy_cond_4==1',
    'm52.output_left_data': False,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m52.data'),
    'm7.data2': T.Graph.OutputPort('m13.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm14': 'M.input_features.v1',
    'm14.features': '',

    'm41': 'M.features_append.v1',
    'm41.input_1': T.Graph.OutputPort('m3.data'),
    'm41.input_2': T.Graph.OutputPort('m14.data'),

    'm64': 'M.cached.v3',
    'm64.input_1': T.Graph.OutputPort('m41.data_1'),
    'm64.run': m64_run_bigquant_run,
    'm64.post_run': m64_post_run_bigquant_run,
    'm64.input_ports': '',
    'm64.params': """{
    'SW_type':'name_SW2'
}""",
    'm64.output_ports': 'data_1,data_2',

    'm21': 'M.fillnan.v1',
    'm21.input_data': T.Graph.OutputPort('m7.data'),
    'm21.features': T.Graph.OutputPort('m64.data_2'),
    'm21.fill_value': 'mean',
})

# g.run({})



def m8_run_bigquant_run(bq_graph, inputs):
    g = bq_graph
    parameters_list = []
    #原始因子
    features = [
    ]
    add_features = [
        'd1 = turn_0',
        'd2 = turn_5'
    ]
    i = 0
    for feature in add_features:
        parameters = {}
        temp = list(set(features)).copy()
        if isinstance(feature,list)==True:
            for x in feature:
                temp.append(x) 
        else:
            temp.append(feature)
        temp = list(set(temp))
        parameters['m3.features'] = '\n'.join(temp)
        parameters_list.append({'parameters': parameters})
        i+=1
  
    #每组因子进行回测
    def run(parameters):
        try:
            result = g.run(parameters)
            return result
        except Exception as e:
            print('ERROR --------', e)
            return None
    results = T.parallel_map(run, parameters_list, max_workers=2, remote_run=False, silent=True)
       
    return results

m8 = M.hyper_run.v1(
    run=m8_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2023-02-21 11:01:09.846159] INFO: AI: 开始并行运算, remote_run=False, workers=2 ..

[2023-02-21 11:01:09.862324] INFO: AI: [ParallelEx(n_jobs=2)]: Using backend LokyBackend with 2 concurrent workers.

[2023-02-21 11:01:28.850299] INFO: AI: [ParallelEx(n_jobs=2)]: Done   1 tasks      | elapsed:   19.0s

[2023-02-21 11:01:28.854887] INFO: AI: [ParallelEx(n_jobs=2)]: Done   2 out of   2 | elapsed:   19.0s finished

[2023-02-21 11:01:28.854093] INFO: AI: [ParallelEx(n_jobs=2)]: Done   2 out of   2 | elapsed:   19.0s remaining:    0.0s

[2023-02-21 11:01:28.858101] INFO: moduleinvoker: hyper_run.v1 运行完成[19.012583s].

In [26]:

m8.result

Out[26]:

[None, None]