克隆策略

    {"description":"实验创建于2017/8/26","graph":{"edges":[{"to_node_id":"-50:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-57:features","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"to_node_id":"-50:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-102:instruments","from_node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"to_node_id":"-57:input_data","from_node_id":"-50:data"},{"to_node_id":"-689:input_data","from_node_id":"-57:data"},{"to_node_id":"-102:options_data","from_node_id":"-689:data"}],"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\nbuy_condition=where(mean(close_0,5)>mean(close_0,10),1,0)\nsell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)","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":false,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-05-01","type":"Literal","bound_global_parameter":"交易日期"},{"name":"end_date","value":"2021-06-01","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":"600519.SHA\n600333.SHA","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":2,"comment":"预测数据,用于回测和模拟","comment_collapsed":false},{"node_id":"-50","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":"60","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-50"},{"name":"features","node_id":"-50"}],"output_ports":[{"name":"data","node_id":"-50"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"-57","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":"-57"},{"name":"features","node_id":"-57"}],"output_ports":[{"name":"data","node_id":"-57"}],"cacheable":true,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"-102","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"initialize","value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n","type":"Literal","bound_global_parameter":null},{"name":"handle_data","value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 获取今日的日期\n today = data.current_dt.strftime('%Y-%m-%d') \n # 通过positions对象,使用列表生成式的方法获取目前持仓的股票列表\n stock_hold_now = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 记录用于买入股票的可用现金,因为是早盘卖股票,需要记录卖出的股票市值并在买入下单前更新可用现金;\n # 如果是早盘买尾盘卖,则卖出时不需更新可用现金,因为尾盘卖出股票所得现金无法使用\n cash_for_buy = context.portfolio.cash \n \n try:\n buy_stock = context.daily_stock_buy[today] # 当日符合买入条件的股票\n except:\n buy_stock=[] # 如果没有符合条件的股票,就设置为空\n \n try:\n sell_stock = context.daily_stock_sell[today] # 当日符合卖出条件的股票\n except:\n sell_stock=[] # 如果没有符合条件的股票,就设置为空\n \n # 需要卖出的股票:已有持仓中符合卖出条件的股票\n stock_to_sell = [ i for i in stock_hold_now if i in sell_stock ]\n # 需要买入的股票:没有持仓且符合买入条件的股票\n stock_to_buy = [ i for i in buy_stock if i not in stock_hold_now ] \n # 需要调仓的股票:已有持仓且不符合卖出条件的股票\n stock_to_adjust=[ i for i in stock_hold_now if i not in sell_stock ]\n \n # 如果有卖出信号\n if len(stock_to_sell)>0:\n for instrument in stock_to_sell:\n sid = context.symbol(instrument) # 将标的转化为equity格式\n cur_position = context.portfolio.positions[sid].amount # 持仓\n if cur_position > 0 and data.can_trade(sid):\n context.order_target_percent(sid, 0) # 全部卖出 \n # 因为设置的是早盘卖出早盘买入,需要根据卖出的股票更新可用现金;如果设置尾盘卖出早盘买入,则不需更新可用现金(可以删除下面的语句)\n cash_for_buy += stock_hold_now[instrument]\n \n # 如果有买入信号/有持仓\n if len(stock_to_buy)+len(stock_to_adjust)>0:\n weight = 1/(len(stock_to_buy)+len(stock_to_adjust)) # 每只股票的比重为等资金比例持有\n for instrument in stock_to_buy+stock_to_adjust:\n sid = context.symbol(instrument) # 将标的转化为equity格式\n if data.can_trade(sid):\n context.order_target_value(sid, weight*cash_for_buy) # 买入","type":"Literal","bound_global_parameter":null},{"name":"prepare","value":"# 回测引擎:准备数据,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n df = context.options['data'].read_df()\n\n # 函数:求满足开仓条件的股票列表\n def open_pos_con(df):\n return list(df[df['buy_condition']>0].instrument)\n\n # 函数:求满足平仓条件的股票列表\n def close_pos_con(df):\n return list(df[df['sell_condition']>0].instrument)\n\n # 每日买入股票的数据框\n context.daily_stock_buy= df.groupby('date').apply(open_pos_con)\n # 每日卖出股票的数据框\n context.daily_stock_sell= df.groupby('date').apply(close_pos_con)","type":"Literal","bound_global_parameter":null},{"name":"before_trading_start","value":"","type":"Literal","bound_global_parameter":null},{"name":"volume_limit","value":0.025,"type":"Literal","bound_global_parameter":null},{"name":"order_price_field_buy","value":"open","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"open","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":1000000,"type":"Literal","bound_global_parameter":null},{"name":"auto_cancel_non_tradable_orders","value":"True","type":"Literal","bound_global_parameter":null},{"name":"data_frequency","value":"daily","type":"Literal","bound_global_parameter":null},{"name":"price_type","value":"后复权","type":"Literal","bound_global_parameter":null},{"name":"product_type","value":"股票","type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"backtest_only","value":"False","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-102"},{"name":"options_data","node_id":"-102"},{"name":"history_ds","node_id":"-102"},{"name":"benchmark_ds","node_id":"-102"},{"name":"trading_calendar","node_id":"-102"}],"output_ports":[{"name":"raw_perf","node_id":"-102"}],"cacheable":false,"seq_num":3,"comment":"","comment_collapsed":true},{"node_id":"-689","module_id":"BigQuantSpace.dropnan.dropnan-v2","parameters":[],"input_ports":[{"name":"input_data","node_id":"-689"},{"name":"features","node_id":"-689"}],"output_ports":[{"name":"data","node_id":"-689"}],"cacheable":true,"seq_num":4,"comment":"","comment_collapsed":true},{"node_id":"-1541","module_id":"BigQuantSpace.hyper_parameter_search.hyper_parameter_search-v1","parameters":[{"name":"param_grid_builder","value":"def bigquant_run():\n param_grid = {}\n para_list = []\n # 在这里设置需要调优的参数备选\n for p in [[10,20],[5,20],[5,10],[2,8],[10,20],[5,20],[5,10],[2,8],[5,10],[2,8]]:\n paras = \"\"\"buy_condition=where(mean(close_0,%s)>mean(close_0,%s),1,0)\n sell_condition=where(mean(close_0,%s)<mean(close_0,%s),1,0)\"\"\"%(p[0],p[1],p[0],p[1])\n \n para_list.append(paras)\n \n param_grid[\"m1.features\"] = para_list\n \n return param_grid\n","type":"Literal","bound_global_parameter":null},{"name":"scoring","value":"def bigquant_run(result):\n score = result.get('m3').read_raw_perf()['sharpe'].tail(1)[0]\n max_drawdown = result.get('m3').read_raw_perf()['max_drawdown'].tail(1)[0]\n win_percent = result.get('m3').read_raw_perf()['win_percent'].tail(1)[0]\n\n return {'score': score,\"max_drawdown\":max_drawdown,\"win_percent\":win_percent}\n","type":"Literal","bound_global_parameter":null},{"name":"search_algorithm","value":"网格搜索","type":"Literal","bound_global_parameter":null},{"name":"search_iterations","value":10,"type":"Literal","bound_global_parameter":null},{"name":"random_state","value":"","type":"Literal","bound_global_parameter":null},{"name":"workers","value":"1","type":"Literal","bound_global_parameter":null},{"name":"worker_distributed_run","value":"True","type":"Literal","bound_global_parameter":null},{"name":"worker_silent","value":"True","type":"Literal","bound_global_parameter":null},{"name":"run_now","value":"True","type":"Literal","bound_global_parameter":null},{"name":"bq_graph","value":"True","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"bq_graph_port","node_id":"-1541"},{"name":"input_1","node_id":"-1541"},{"name":"input_2","node_id":"-1541"},{"name":"input_3","node_id":"-1541"}],"output_ports":[{"name":"result","node_id":"-1541"}],"cacheable":false,"seq_num":5,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='1232,40,200,200'/><node_position Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='879,25,200,200'/><node_position Node='-50' Position='1078,234,200,200'/><node_position Node='-57' Position='1076,327,200,200'/><node_position Node='-102' Position='1047,531,200,200'/><node_position Node='-689' Position='1078,418,200,200'/><node_position Node='-1541' Position='624,291,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
    In [ ]:
    # 本代码由可视化策略环境自动生成 2021年8月18日 11:37
    # 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。
    
    
    # 回测引擎:初始化函数,只执行一次
    def m3_initialize_bigquant_run(context):
    
        # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
        context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m3_handle_data_bigquant_run(context, data):
        # 获取今日的日期
        today = data.current_dt.strftime('%Y-%m-%d')  
        # 通过positions对象,使用列表生成式的方法获取目前持仓的股票列表
        stock_hold_now = {e.symbol: p.amount * p.last_sale_price
                     for e, p in context.perf_tracker.position_tracker.positions.items()}
    
        # 记录用于买入股票的可用现金,因为是早盘卖股票,需要记录卖出的股票市值并在买入下单前更新可用现金;
        # 如果是早盘买尾盘卖,则卖出时不需更新可用现金,因为尾盘卖出股票所得现金无法使用
        cash_for_buy = context.portfolio.cash    
        
        try:
            buy_stock = context.daily_stock_buy[today]  # 当日符合买入条件的股票
        except:
            buy_stock=[]  # 如果没有符合条件的股票,就设置为空
        
        try:
            sell_stock = context.daily_stock_sell[today]  # 当日符合卖出条件的股票
        except:
            sell_stock=[] # 如果没有符合条件的股票,就设置为空
        
        # 需要卖出的股票:已有持仓中符合卖出条件的股票
        stock_to_sell = [ i for i in stock_hold_now if i in sell_stock ]
        # 需要买入的股票:没有持仓且符合买入条件的股票
        stock_to_buy = [ i for i in buy_stock if i not in stock_hold_now ]  
        # 需要调仓的股票:已有持仓且不符合卖出条件的股票
        stock_to_adjust=[ i for i in stock_hold_now if i not in sell_stock ]
        
        # 如果有卖出信号
        if len(stock_to_sell)>0:
            for instrument in stock_to_sell:
                sid = context.symbol(instrument) # 将标的转化为equity格式
                cur_position = context.portfolio.positions[sid].amount # 持仓
                if cur_position > 0 and data.can_trade(sid):
                    context.order_target_percent(sid, 0) # 全部卖出 
                    # 因为设置的是早盘卖出早盘买入,需要根据卖出的股票更新可用现金;如果设置尾盘卖出早盘买入,则不需更新可用现金(可以删除下面的语句)
                    cash_for_buy += stock_hold_now[instrument]
        
        # 如果有买入信号/有持仓
        if len(stock_to_buy)+len(stock_to_adjust)>0:
            weight = 1/(len(stock_to_buy)+len(stock_to_adjust)) # 每只股票的比重为等资金比例持有
            for instrument in stock_to_buy+stock_to_adjust:
                sid = context.symbol(instrument) # 将标的转化为equity格式
                if  data.can_trade(sid):
                    context.order_target_value(sid, weight*cash_for_buy) # 买入
    # 回测引擎:准备数据,只执行一次
    def m3_prepare_bigquant_run(context):
        # 加载预测数据
        df = context.options['data'].read_df()
    
        # 函数:求满足开仓条件的股票列表
        def open_pos_con(df):
            return list(df[df['buy_condition']>0].instrument)
    
        # 函数:求满足平仓条件的股票列表
        def close_pos_con(df):
            return list(df[df['sell_condition']>0].instrument)
    
        # 每日买入股票的数据框
        context.daily_stock_buy= df.groupby('date').apply(open_pos_con)
        # 每日卖出股票的数据框
        context.daily_stock_sell= df.groupby('date').apply(close_pos_con)
    
    g = T.Graph({
    
        'm1': 'M.input_features.v1',
        'm1.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
    buy_condition=where(mean(close_0,5)>mean(close_0,10),1,0)
    sell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)""",
        'm1.m_cached': False,
    
        'm2': 'M.instruments.v2',
        'm2.start_date': T.live_run_param('trading_date', '2021-05-01'),
        'm2.end_date': T.live_run_param('trading_date', '2021-06-01'),
        'm2.market': 'CN_STOCK_A',
        'm2.instrument_list': """600519.SHA
    600333.SHA""",
        'm2.max_count': 0,
    
        'm7': 'M.general_feature_extractor.v7',
        'm7.instruments': T.Graph.OutputPort('m2.data'),
        'm7.features': T.Graph.OutputPort('m1.data'),
        'm7.start_date': '',
        'm7.end_date': '',
        'm7.before_start_days': 60,
    
        'm8': 'M.derived_feature_extractor.v3',
        'm8.input_data': T.Graph.OutputPort('m7.data'),
        'm8.features': T.Graph.OutputPort('m1.data'),
        'm8.date_col': 'date',
        'm8.instrument_col': 'instrument',
        'm8.drop_na': False,
        'm8.remove_extra_columns': False,
    
        'm4': 'M.dropnan.v2',
        'm4.input_data': T.Graph.OutputPort('m8.data'),
    
        'm3': 'M.trade.v4',
        'm3.instruments': T.Graph.OutputPort('m2.data'),
        'm3.options_data': T.Graph.OutputPort('m4.data'),
        'm3.start_date': '',
        'm3.end_date': '',
        'm3.initialize': m3_initialize_bigquant_run,
        'm3.handle_data': m3_handle_data_bigquant_run,
        'm3.prepare': m3_prepare_bigquant_run,
        'm3.volume_limit': 0.025,
        'm3.order_price_field_buy': 'open',
        'm3.order_price_field_sell': 'open',
        'm3.capital_base': 1000000,
        'm3.auto_cancel_non_tradable_orders': True,
        'm3.data_frequency': 'daily',
        'm3.price_type': '后复权',
        'm3.product_type': '股票',
        'm3.plot_charts': True,
        'm3.backtest_only': False,
        'm3.benchmark': '',
    })
    
    # g.run({})
    
    
    def m5_param_grid_builder_bigquant_run():
        param_grid = {}
        para_list = []
        # 在这里设置需要调优的参数备选
        for p in [[10,20],[5,20],[5,10],[2,8],[10,20],[5,20],[5,10],[2,8],[5,10],[2,8]]:
            paras = """buy_condition=where(mean(close_0,%s)>mean(close_0,%s),1,0)
            sell_condition=where(mean(close_0,%s)<mean(close_0,%s),1,0)"""%(p[0],p[1],p[0],p[1])
            
            para_list.append(paras)
            
        param_grid["m1.features"] = para_list
        
        return param_grid
    
    def m5_scoring_bigquant_run(result):
        score = result.get('m3').read_raw_perf()['sharpe'].tail(1)[0]
        max_drawdown = result.get('m3').read_raw_perf()['max_drawdown'].tail(1)[0]
        win_percent = result.get('m3').read_raw_perf()['win_percent'].tail(1)[0]
    
        return {'score': score,"max_drawdown":max_drawdown,"win_percent":win_percent}
    
    
    m5 = M.hyper_parameter_search.v1(
        param_grid_builder=m5_param_grid_builder_bigquant_run,
        scoring=m5_scoring_bigquant_run,
        search_algorithm='网格搜索',
        search_iterations=10,
        workers=1,
        worker_distributed_run=True,
        worker_silent=True,
        run_now=True,
        bq_graph=g
    )
    
    Fitting 1 folds for each of 10 candidates, totalling 10 fits
    [Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
    [CV 1/1; 1/10] START m1.features=buy_condition=where(mean(close_0,10)>mean(close_0,20),1,0)
            sell_condition=where(mean(close_0,10)<mean(close_0,20),1,0)
    
    [CV 1/1; 1/10] END m1.features=buy_condition=where(mean(close_0,10)>mean(close_0,20),1,0)
            sell_condition=where(mean(close_0,10)<mean(close_0,20),1,0); max_drawdown: (test=-0.076) score: (test=-7.195) win_percent: (test=0.143) total time=  30.4s
    [Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:   30.4s remaining:    0.0s
    [CV 1/1; 2/10] START m1.features=buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0)
            sell_condition=where(mean(close_0,5)<mean(close_0,20),1,0)
    
    In [20]:
    m5.result.best_params_ 
    
    Out[20]:
    {'m1.features': 'buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0)\n        sell_condition=where(mean(close_0,5)<mean(close_0,20),1,0)'}
    In [21]:
    m5.result.best_score_
    
    Out[21]:
    1.0153028365345904
    In [22]:
    m5.result.cv_results_
    
    Out[22]:
    {'mean_fit_time': array([30.36400747, 30.42320204, 30.41112638]),
     'std_fit_time': array([0., 0., 0.]),
     'mean_score_time': array([0.2663281 , 0.15257883, 0.14403033]),
     'std_score_time': array([0., 0., 0.]),
     'param_m1.features': masked_array(data=['buy_condition=where(mean(close_0,10)>mean(close_0,20),1,0)\n        sell_condition=where(mean(close_0,10)<mean(close_0,20),1,0)',
                        'buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0)\n        sell_condition=where(mean(close_0,5)<mean(close_0,20),1,0)',
                        'buy_condition=where(mean(close_0,5)>mean(close_0,10),1,0)\n        sell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)'],
                  mask=[False, False, False],
            fill_value='?',
                 dtype=object),
     'params': [{'m1.features': 'buy_condition=where(mean(close_0,10)>mean(close_0,20),1,0)\n        sell_condition=where(mean(close_0,10)<mean(close_0,20),1,0)'},
      {'m1.features': 'buy_condition=where(mean(close_0,5)>mean(close_0,20),1,0)\n        sell_condition=where(mean(close_0,5)<mean(close_0,20),1,0)'},
      {'m1.features': 'buy_condition=where(mean(close_0,5)>mean(close_0,10),1,0)\n        sell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)'}],
     'split0_test_score': array([-7.19497509,  1.01530284, -5.14553214]),
     'mean_test_score': array([-7.19497509,  1.01530284, -5.14553214]),
     'std_test_score': array([0., 0., 0.]),
     'rank_test_score': array([3, 1, 2], dtype=int32),
     'split0_test_max_drawdown': array([-0.07649075, -0.02333598, -0.08132875]),
     'mean_test_max_drawdown': array([-0.07649075, -0.02333598, -0.08132875]),
     'std_test_max_drawdown': array([0., 0., 0.]),
     'rank_test_max_drawdown': array([2, 1, 3], dtype=int32),
     'split0_test_win_percent': array([0.14285714, 0.55555556, 0.3       ]),
     'mean_test_win_percent': array([0.14285714, 0.55555556, 0.3       ]),
     'std_test_win_percent': array([0., 0., 0.]),
     'rank_test_win_percent': array([3, 1, 2], dtype=int32)}