复制链接

克隆策略

In [ ]:

# 本代码由可视化策略环境自动生成 2023年4月25日 13:00
# 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 m19_run_bigquant_run(input_1, input_2, input_3):
    import talib 
    # 示例代码如下。在这里编写您的代码
    input_df = input_1.read_df().reset_index(drop=True)
    
    def cal(df):
        # 将价格数据转化成float类型
        close = [float(x) for x in df['close_0']]
        # 通过talib计算移动平均值（方法2）
        df['MA10'] = talib.MA(np.array(close), timeperiod=20)
        df['cond'] = (df['close_0']>df['MA10']).astype(int)
        df.drop('MA10',axis=1)
        return df
    # 计算指标条件
    result = input_df.groupby('instrument').apply(cal)
    # 过滤
    filter_result = result[result['cond']>0]
    # 输出
    data_1 = DataSource.write_df(filter_result)
    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 m19_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 m10_run_bigquant_run(input_1, input_2, input_3):
    import talib
    # 示例代码如下。在这里编写您的代码
    input_df = input_1.read_df().reset_index(drop=True)
    
    def cal(df):
        # 将价格数据转化成float类型
        close = [float(x) for x in df['close_0']]
        # 通过talib计算移动平均值（方法2）
        df['MA10'] = talib.MA(np.array(close), timeperiod=20)
        df['cond'] = (df['close_0']>df['MA10']).astype(int)
        df.drop('MA10',axis=1)
        return df
    # 计算指标条件
    result = input_df.groupby('instrument').apply(cal)
    # 过滤
    filter_result = result[result['cond']>0]
    # 输出
    data_1 = DataSource.write_df(filter_result)
    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 m10_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m4_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 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))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 50
    # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
    context.stock_weights = [1/stock_count for i in range(stock_count)]
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 1/10
    context.options['hold_days'] = 3

# 回测引擎：每日数据处理函数，每天执行一次
def m4_handle_data_bigquant_run(context, data):
    #-------------------大盘风控代码---------------------------#
    #获取当日日期
    today = data.current_dt.strftime('%Y-%m-%d')
    benckmark_risk=context.benckmark_risk.loc[today]
    benckmark_buys=context.benckmark_buys.loc[today]
    benckmark_buys2=context.benckmark_buys2.loc[today]
    benckmark_risk2=context.benckmark_risk2.loc[today]
    benckmark_risk4=context.benckmark_risk4.loc[today]
    benckmark_risk5=context.benckmark_risk5.loc[today]
    benckmark_zd1=context.benckmark_zd1.loc[today]
    benckmark_risk6=context.benckmark_risk6.loc[today]
    benckmark_ret120=context.benckmark_ret120.loc[today]
    
    print(today,benckmark_ret120)
        #------------------------------------------止损模块START--------------------------------------------
    equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
    
    # 新建当日止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
    stoploss_stock = []
    stopwin_stock = []
    add_stock = []
    if len(equities) > 0:
        for i in equities.keys():
            #print(equities)
            stock_cost = equities[i].cost_basis
            v1=equities[i].available_close_amount
            #print(equities)
            stock_market_price = data.current(context.symbol(i), 'price')
            #stock_market_price = data.current(context.symbol(i), 'price')# 最新市场价格
            last_sale_date = equities[i].last_sale_date   # 上次交易日期
            delta_days = data.current_dt - last_sale_date  
            hold_days = delta_days.days # 持仓天数
            # 建仓以来的最高价
            highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
            highest_price_since_10days = data.history(context.symbol(i), 'high', 10, '1d').max()
            # 确定止损位置
            stock_p_ma = data.history(context.symbol(i),'price',30,'1d').mean()
           
            stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.2
            #if (stock_p_ma5>stock_p_ma10) and (stock_p_ma5_1<stock_p_ma10_1):
                 #if stock_market_price*v1<context.portfolio.cash*0.2:
                    #context.order_target(context.symbol(i),v1*2)
            #if (benckmark_buys2==1)and(stock_market_price > stock_p_ma5):
                #if stock_market_price*v1<context.portfolio.cash*0.2:
                    #context.order_target(context.symbol(i),v1*2)
                    #context.portfolio.cash-=v1*2*stock_market_price
                    #stoploss_stock.append(i)
            if i not in  stoploss_stock:
                if (stock_market_price < stoploss_line)|(stock_market_price<stock_p_ma):
                    context.order_target_percent(context.symbol(i), 0)     
                    stoploss_stock.append(i)
                #if stock_market_price<highest_price_since_10days*0.9:
                
                    #context.order_target(context.symbol(i),0)
                    #stoploss_stock.append(i)
            if i not in  stopwin_stock:
                if (benckmark_zd1==0)and(benckmark_buys==0)and((stock_market_price - stock_cost ) / stock_cost>= 0.2):   
                    context.order_target_percent(context.symbol(i),0)
                    stopwin_stock.append(i)
                if (benckmark_zd1==0)and(benckmark_risk4==1)and((stock_market_price - stock_cost ) / stock_cost>= 0.15):   
                    context.order_target_percent(context.symbol(i),0)
                    stopwin_stock.append(i)
                if (benckmark_buys==1)and((stock_market_price - stock_cost ) / stock_cost>= 0.4):   
                    context.order_target(context.symbol(i),v1/2)
                    stopwin_stock.append(i)
                
                
                if (benckmark_zd1==0)and(benckmark_buys2==1)and(stock_market_price<highest_price_since_buy*0.95):   
                    context.order_target_percent(context.symbol(i),0)
                    stopwin_stock.append(i)
                #print('日期：',today,'股票：',stopwin_stock,'出现下跌市场止盈10状况')
           
            #if benckmark_zd1 == 1 :
        
               #context.order_target(context.symbol(i), v1*2)
               #stoploss_stock.append(i)
        #if len(stoploss_stock)>0:
            #print('日期：', today, '股票：', stoploss_stock, '出现跟踪止损状况')
        #if len(stopwin_stock)>0:    
            #print('日期：', today, '股票：', stopwin_stock, '出现跟踪止yin状况')
        #if len(add_stock)>0:
            #print('日期：', today, '股票：', add_stock, 'add')
            
    #-------------------------------------------止损模块END---------------------------------------------  
    stock_hold_now = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}  
    #stock_hold_now = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}   
    #print(stock_hold_now)
    #print(ss)
    #v2=context.portfolio.positions[context.symbol(instrument)].available_close_amount
    #equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
    #当risk为1时，市场有风险，全部平仓，不再执行其它操作
    #if benckmark_zd1 == 1 :
        #return
        #for  instrument in stock_hold_now:
            
            #v3=context.portfolio.positions[context.symbol(instrument)].available_close_amount
            #pp = context.portfolio.positions[context.symbol(instrument)].last_sale_price
          
           # addam = np.where((v3*pp*2>context.portfolio.cash*0.2),(v3*pp*2),(context.portfolio.cash*0.2))
        
            #if context.portfolio.cash  > addam:
                #context.order_value(symbol(instrument),addam )
                #context.portfolio.cash -= addam
       
  
            
        
    #-------------------大盘风控代码---------------------------#
    # 按日期过滤得到今日的预测数据
    
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]

    # 1. 资金分配
    # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
    # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
    is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.perf_tracker.position_tracker.positions.items()}

    # 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按机器学习算法预测的排序末位淘汰
    if not is_staging and cash_for_sell > 0:
        equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
        positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        #print(instruments)
        #price_limit_status = context.price_limit_status
        #status_today = price_limit_status[price_limit_status.date==today]
        for instrument in equities:
            sid = equities[instrument].sid
            cur_position = context.portfolio.positions[sid].amount
            v2=context.portfolio.positions[context.symbol(instrument)].available_close_amount
            # 如果已经移动止损卖出过则不再轮仓卖出,以防止出现空头持仓
            if instrument in stoploss_stock:
                continue
            #if instrument in stopwin_stock:
                #continue
    
         
        
            if cur_position > 0 and benckmark_buys==0 and data.current_dt - equities[instrument].last_sale_date>=datetime.timedelta(2) and data.can_trade(context.symbol(instrument)):
                context.order_target_percent(sid, 0)
            #context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
            if cur_position > 0 and benckmark_buys==1 and data.current_dt - equities[instrument].last_sale_date>=datetime.timedelta(1) and data.can_trade(context.symbol(instrument)):
                context.order_target_percent(sid, 0)
            #context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
            # 记录轮仓卖出的股票
            #sell_stock.append(instrument)
            if cash_for_sell <= 0:
                break

    # 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
    buy_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
    #print(buy_instruments)
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    #print(buy_instruments)
    
    
    
    if benckmark_zd1==1:
        
        for i, instrument in enumerate(buy_instruments):
            
            cash = cash_for_buy * buy_cash_weights[i]
            cash1 = cash/3
            if cash1 > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
                cash1 = max_cash_per_instrument - positions.get(instrument, 0)
                #cash == cash/2
            if cash1 > 0:
                price = data.current(context.symbol(instrument), 'price')  # 最新价格
                stock_num = np.floor(cash1/price/100)*100
                if instrument in stoploss_stock:
                    continue
                if instrument in add_stock:
                    continue
                context.order(context.symbol(instrument), stock_num)
    if benckmark_buys2 == 1 and benckmark_zd1 == 0:
        #print(today,benckmark_buys2,cash_for_buy)
        
        for i, instrument in enumerate(buy_instruments):
        #cash == cash/2
            cash = cash_for_buy * buy_cash_weights[i]
            cash == cash
            if cash > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
                cash = max_cash_per_instrument - positions.get(instrument, 0)
            
            if cash > 0:
                price = data.current(context.symbol(instrument), 'price')  # 最新价格
                stock_num = np.floor(cash/price/100)*100
                if instrument in stoploss_stock:
                    continue
                if instrument in add_stock:
                    continue
                context.order(context.symbol(instrument), stock_num)
        # print(today,cash)
    if benckmark_buys2 ==0 and benckmark_zd1 ==0:
        for i, instrument in enumerate(buy_instruments):
        #cash == cash/2
            cash = cash_for_buy * buy_cash_weights[i]
            cash== cash/2
            if cash > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
                cash = max_cash_per_instrument - positions.get(instrument, 0)
            
            if cash > 0:
                price = data.current(context.symbol(instrument), 'price')  # 最新价格
                stock_num = np.floor(cash/price/100)*100
                if instrument in stoploss_stock:
                    continue
                if instrument in add_stock:
                    continue
                context.order(context.symbol(instrument), stock_num)
# 回测引擎：准备数据，只执行一次
def m4_prepare_bigquant_run(context):
    # 获取涨跌停状态
    #context.price_limit_status = DataSource('stock_status_CN_STOCK_A').read(fields=['price_limit_status'])
    #在数据准备函数中一次性计算每日的大盘风控条件相比于在handle中每日计算风控条件可以提高回测速度
    # 多取50天的数据便于计算均值(保证回测的第一天均值不为Nan值)，
    # 其中context.start_date和context.end_date是回测指定的起始时间和终止时间
    start_date= (pd.to_datetime(context.start_date) - datetime.timedelta(days=60)).strftime('%Y-%m-%d') 
    
    df=DataSource('bar1d_index_CN_STOCK_A').read(start_date=start_date,end_date=context.end_date,fields=['close'])

    #这里以上证指数000001.HIX为例
    benckmark_data=df[df.instrument=='000905.HIX']
    #计算上证指数5日涨幅
    #print(benckmark_data)
    benckmark_data['ret5']=talib.MA(benckmark_data['close'], timeperiod=5)
    benckmark_data['ret10']=talib.MA(benckmark_data['close'], timeperiod=10)
    benckmark_data['ret20']=talib.MA(benckmark_data['close'], timeperiod=20)
    benckmark_data['ret40']=talib.MA(benckmark_data['close'], timeperiod=40)
    benckmark_data['ret1']=benckmark_data['close']/benckmark_data['close'].shift(3)-1
    benckmark_data['ret120']=talib.MA(benckmark_data['close'], timeperiod=120)
    #print()
    #计算大盘风控条件，如果5日涨幅小于-10%则设置风险状态risk为1，否则为0
    benckmark_data['risk1'] = np.where(((benckmark_data['close']<benckmark_data['ret20'])&(benckmark_data['close'].shift(3)<benckmark_data['ret20'].shift(3))),1,0)
    benckmark_data['risk2'] = np.where(benckmark_data['ret1']<-0.03,1,0)
    benckmark_data['risk3'] = np.where(((benckmark_data['close']<benckmark_data['ret20'])&(benckmark_data['ret10']<benckmark_data['ret20'])&(benckmark_data['ret20']<benckmark_data['ret40'])),1,0)
    benckmark_data['risk4'] = np.where(((benckmark_data['close']<benckmark_data['ret5'])&(benckmark_data['ret5']<benckmark_data['ret10'])&(benckmark_data['ret10']<benckmark_data['ret20'])&(benckmark_data['ret20']<benckmark_data['ret40'])),1,0)
    benckmark_data['risk5'] = np.where(((benckmark_data['close']<benckmark_data['close'].shift(3))&(benckmark_data['close']<benckmark_data['ret40']*0.96)),1,0)
    benckmark_data['risk6'] = np.where((benckmark_data['risk3']==1)&(benckmark_data['close']<benckmark_data['close'].shift(3))&(benckmark_data['close']<benckmark_data['ret120']*0.93),1,0)
    benckmark_data['buy1'] = np.where(((benckmark_data['close']>benckmark_data['close'].shift(1))&(benckmark_data['close']>benckmark_data['ret20'])&(benckmark_data['ret10']>benckmark_data['ret20'])&(benckmark_data['ret20']>benckmark_data['ret40'])),1,0)
    benckmark_data['buy2'] = np.where(((benckmark_data['close']>benckmark_data['ret5'])&(benckmark_data['close']>benckmark_data['close'].shift(1))&(benckmark_data['close']>benckmark_data['ret20'])&(benckmark_data['ret10']>benckmark_data['ret20'])&(benckmark_data['ret20']>benckmark_data['ret40'])),1,0)
    #震荡区间
    benckmark_data['zd1'] = np.where((abs(benckmark_data['ret40']-benckmark_data['ret20'])<10),1,0)
    
    
    benckmark_data.set_index('date',inplace=True)
    #把风控序列输出给全局变量context.benckmark_risk
    context.benckmark_risk=benckmark_data['risk4']+benckmark_data['risk5']
    context.benckmark_buys=benckmark_data['buy1']
    context.benckmark_buys2=benckmark_data['buy2']
    context.benckmark_risk2=benckmark_data['risk2']
    context.benckmark_risk4=benckmark_data['risk4']
    context.benckmark_risk5=benckmark_data['risk5']
    context.benckmark_risk6=benckmark_data['risk6']
    context.benckmark_ret120=benckmark_data['ret120']
    context.benckmark_zd1=benckmark_data['zd1']


m1 = M.instruments.v2(
    start_date='2014-01-01',
    end_date='2018-12-30',
    market='CN_STOCK_A',
    instrument_list='',
    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/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, -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="""return_5
return_10
return_20
return_3
avg_amount_10
avg_amount_20
avg_turn_3
pe_ttm_0
avg_turn_1
avg_mf_net_amount_10
market_cap_float_0
beta_csi500_5_0

"""
)

m20 = M.input_features.v1(
    features_ds=m3.data,
    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
close_0
high_0
ta_ema_5_0
ta_ema_10_0
in_csi500_0
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m20.data,
    start_date='',
    end_date='',
    before_start_days=300
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m20.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m19 = M.cached.v3(
    input_1=m16.data,
    run=m19_run_bigquant_run,
    post_run=m19_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m19.data_1,
    on='date,instrument',
    how='inner',
    sort=False
)

m21 = M.filter.v3(
    input_data=m7.data,
    expr='in_csi500_0==1',
    output_left_data=False
)

m5 = M.filtet_st_stock.v7(
    input_1=m21.data
)

m13 = M.dropnan.v1(
    input_data=m5.data_1
)

m6 = M.stock_ranker_train.v6(
    training_ds=m13.data,
    features=m3.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    data_row_fraction=1,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2019-01-01'),
    end_date=T.live_run_param('trading_date', '2023-04-21'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m20.data,
    start_date='',
    end_date='',
    before_start_days=300
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m20.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m11 = M.filtet_st_stock.v7(
    input_1=m18.data
)

m12 = M.filter.v3(
    input_data=m11.data_1,
    expr='in_csi500_0==1',
    output_left_data=False
)

m10 = M.cached.v3(
    input_1=m12.data,
    run=m10_run_bigquant_run,
    post_run=m10_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m14 = M.dropnan.v1(
    input_data=m10.data_1
)

m8 = M.stock_ranker_predict.v5(
    model=m6.model,
    data=m14.data,
    m_lazy_run=False
)

m4 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m4_initialize_bigquant_run,
    handle_data=m4_handle_data_bigquant_run,
    prepare=m4_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=10000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000905.HIX'
)

[2023-04-25 13:00:08.841748] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-04-25 13:00:09.016370] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.017925] INFO: moduleinvoker: instruments.v2 运行完成[0.176182s].

[2023-04-25 13:00:09.025044] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-04-25 13:00:09.040524] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.041887] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.016841s].

[2023-04-25 13:00:09.045422] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-04-25 13:00:09.057159] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.058902] INFO: moduleinvoker: input_features.v1 运行完成[0.013478s].

[2023-04-25 13:00:09.062821] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-04-25 13:00:09.079172] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.080800] INFO: moduleinvoker: input_features.v1 运行完成[0.017951s].

[2023-04-25 13:00:09.115840] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-04-25 13:00:09.124917] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.126371] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010551s].

[2023-04-25 13:00:09.133394] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-04-25 13:00:09.147248] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.149186] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.015784s].

[2023-04-25 13:00:09.160498] INFO: moduleinvoker: cached.v3 开始运行..

[2023-04-25 13:00:09.170027] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.171532] INFO: moduleinvoker: cached.v3 运行完成[0.01104s].

[2023-04-25 13:00:09.178841] INFO: moduleinvoker: join.v3 开始运行..

[2023-04-25 13:00:09.193206] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.194616] INFO: moduleinvoker: join.v3 运行完成[0.015773s].

[2023-04-25 13:00:09.201808] INFO: moduleinvoker: filter.v3 开始运行..

[2023-04-25 13:00:09.212214] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.213650] INFO: moduleinvoker: filter.v3 运行完成[0.011857s].

[2023-04-25 13:00:09.235663] INFO: moduleinvoker: filtet_st_stock.v7 开始运行..

[2023-04-25 13:00:09.251856] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.253303] INFO: moduleinvoker: filtet_st_stock.v7 运行完成[0.017651s].

[2023-04-25 13:00:09.261449] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-04-25 13:00:09.273070] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.274591] INFO: moduleinvoker: dropnan.v1 运行完成[0.013152s].

[2023-04-25 13:00:09.282470] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2023-04-25 13:00:09.307610] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.471621] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.189132s].

[2023-04-25 13:00:09.480296] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-04-25 13:00:09.494290] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.495897] INFO: moduleinvoker: instruments.v2 运行完成[0.015603s].

[2023-04-25 13:00:09.513206] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-04-25 13:00:09.525290] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.526972] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01378s].

[2023-04-25 13:00:09.535100] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-04-25 13:00:09.546931] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.548587] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.013492s].

[2023-04-25 13:00:09.560615] INFO: moduleinvoker: filtet_st_stock.v7 开始运行..

[2023-04-25 13:00:09.573671] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.575085] INFO: moduleinvoker: filtet_st_stock.v7 运行完成[0.014481s].

[2023-04-25 13:00:09.584510] INFO: moduleinvoker: filter.v3 开始运行..

[2023-04-25 13:00:09.598052] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.599541] INFO: moduleinvoker: filter.v3 运行完成[0.015032s].

[2023-04-25 13:00:09.611892] INFO: moduleinvoker: cached.v3 开始运行..

[2023-04-25 13:00:09.622699] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.624426] INFO: moduleinvoker: cached.v3 运行完成[0.012544s].

[2023-04-25 13:00:09.632667] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-04-25 13:00:09.644543] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.646138] INFO: moduleinvoker: dropnan.v1 运行完成[0.013464s].

[2023-04-25 13:00:09.654101] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-04-25 13:00:09.664822] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:09.666233] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.012127s].

[2023-04-25 13:00:09.718238] INFO: moduleinvoker: backtest.v8 开始运行..

[2023-04-25 13:00:09.724961] INFO: backtest: biglearning backtest:V8.6.3

[2023-04-25 13:00:09.985581] INFO: backtest: product_type:stock by specified

[2023-04-25 13:00:10.058815] INFO: moduleinvoker: cached.v2 开始运行..

[2023-04-25 13:00:10.072134] INFO: moduleinvoker: 命中缓存

[2023-04-25 13:00:10.074269] INFO: moduleinvoker: cached.v2 运行完成[0.015471s].

设置评估测试数据集，查看训练曲线
[视频教程]StockRanker训练曲线

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-402ee9c75a1646b9bcad8d1b1b483cff"}/bigcharts-data-end