克隆策略

In [13]:

# 本代码由可视化策略环境自动生成 2021年10月25日 10:42
# 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 m25_run_bigquant_run(input_1, input_2):
    #input_1是使用in_csi500_0过滤后的df数据。
    #input_2是来自与证卷代码列表，用于提取日期
    #输出作为新的证卷代码列表
    # 示例代码如下。在这里编写您的代码
    df=input_1.read_df()
    #df.head()
    code=df['instrument']
    
    code=pd.DataFrame(code)
    
    
    code=code.drop_duplicates()
     
    codeList=list(code.instrument)
     
    codedate=input_2.read_pickle()
    startdate=codedate["start_date"]
    enddate=codedate["end_date"]
    print(startdate)
    print(enddate)    
    #df = DataSource("index_constituent_CN_STOCK_A").read(start_date="2021-06-01", end_date="2021-06-01")
    #code=df.loc[df.in_csi800==1].instrument 
    #codeList=list(code.drop_duplicates())  #获取上证50代码
    #dictList={"instruments":codeList,"start_date":"2020-11-20","end_date":"2021-06-20"}  # 将日期长度更改成一年，但是取得是2021年的漂亮50
    #trainingCodes=DataSource().write_pickle(dictList)  #训练集股票代码
    
    dictList={"instruments":codeList,"start_date":startdate,"end_date":enddate}  # 将日期长度更改成一年，但是取得是2021年的漂亮50
    Codes=DataSource().write_pickle(dictList) #测试集合股票代码
 
    return Outputs(data_1=Codes, 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 m25_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 m29_run_bigquant_run(input_1, input_2):
    #input_1是使用in_csi500_0过滤后的df数据。
    #input_2是来自与证卷代码列表，用于提取日期
    #输出作为新的证卷代码列表
    # 示例代码如下。在这里编写您的代码
    df=input_1.read_df()
    #df.head()
    code=df['instrument']
    
    code=pd.DataFrame(code)
    
    
    code=code.drop_duplicates()
     
    codeList=list(code.instrument)
     
    codedate=input_2.read_pickle()
    startdate=codedate["start_date"]
    enddate=codedate["end_date"]
    print(startdate)
    print(enddate)    
    #df = DataSource("index_constituent_CN_STOCK_A").read(start_date="2021-06-01", end_date="2021-06-01")
    #code=df.loc[df.in_csi800==1].instrument 
    #codeList=list(code.drop_duplicates())  #获取上证50代码
    #dictList={"instruments":codeList,"start_date":"2020-11-20","end_date":"2021-06-20"}  # 将日期长度更改成一年，但是取得是2021年的漂亮50
    #trainingCodes=DataSource().write_pickle(dictList)  #训练集股票代码
    
    dictList={"instruments":codeList,"start_date":startdate,"end_date":enddate}  # 将日期长度更改成一年，但是取得是2021年的漂亮50
    Codes=DataSource().write_pickle(dictList) #测试集合股票代码
 
    return Outputs(data_1=Codes, 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 m29_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m17_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 =2
    # 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(0, stock_count)]
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 1
    context.options['hold_days'] = 2

# 回测引擎：每日数据处理函数，每天执行一次
def m17_handle_data_bigquant_run(context, data):

    # 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
    equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
    tmp = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
    sell_instruments = equities #instruments为卖出订单  
        
    if not is_staging and cash_for_sell > 0:

#         # print('rank order for sell %s' % instruments)
        for instrument in sell_instruments:
#             if instrument in tmp:
#                 print("涨停,不卖出",instrument)
#                 continue
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[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)])
    
    #自己加入的 防止同一天卖出后又买入'''
    '''buySet=set(buy_instruments)
    sellSet=[]
    for key in sell_instruments.keys():
        sellSet.append(key)
    sellSet=set(sellSet)
    buySet=buySet.difference(sellSet) #去除重复股票代码
    buy_instruments=list(buySet)
    print("buySet=")
    print(buy_instruments)
    print("sellSet")
    print(sellSet)    '''
     #自己加入的 防止同一天卖出后又买入**********
    
    
    
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    #个股风控模块################################### 
    '''
    if len(ranker_prediction)==0:
        return
     
    end_date =ranker_prediction.date.iloc[0]
    start_date = pd.to_datetime(end_date)-datetime.timedelta(days=4)

    
    print(end_date)
    
    #获取数据
    buy_df = DataSource("bar1d_CN_STOCK_A").read(instruments=buy_instruments,start_date=start_date.strftime("%Y-%m-%d"),end_date=end_date,feild=['date','instrument','close'])
    def riskCp(subdf):    
        subdf2=subdf.iloc[::-1] #颠倒顺序，最新的放在前面
        subdf2.set_index('date',inplace=True)
        subdf2.reset_index(inplace=True)
        #print(subdf2)
        try:
            close1=subdf2.loc[0,'close'] #前一日的收盘价
            close2=subdf2.loc[1,'close'] #前二日的开盘价 , 
        #print("close1=")
        #print(close1)
        #print("close2=")
        #print(close2)
        #print("abs=")
         
        
        except BaseException:
            return 2
        if abs((close1-close2)/close2)<0.09:
            return 0
        else:
            return 1   # 如果是1 说明有风险  
    #获得风险列表
    riskList=buy_df.groupby(by="instrument").apply(riskCp)
    for StockName in buy_instruments:
        if riskList[StockName]!=0:
            buy_instruments.remove(StockName)  #去除buy_instruments中的风险代码
            
    print('riskList=')
    print(riskList)
    print('buy_instruments=')
    print(buy_instruments)
    '''
    #################################################个股风控代码结束
    for i, instrument in enumerate(buy_instruments):
        cash = cash_for_buy * buy_cash_weights[i]
        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&data.can_trade(context.symbol(instrument)):
           
            context.order_value(context.symbol(instrument), cash)

# 回测引擎：准备数据，只执行一次
def m17_prepare_bigquant_run(context):
    pass


m4 = M.input_features.v1(
    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
#支持np  pd  ta math库  支持pandas内置函数  支持自定义表达式
#close_=close.loc[145700] #抽取14点57分收盘价
#(close*volume).sum()/volume.sum() #等同于vwap
#vwap(close,volume)  #vwap为自定义表达式
#mean_4=close.loc[103000]+close.loc[113000]+close.loc[140000]+close.loc[145700]
_ret=close.pct_change().fillna(close.iloc[0]/open.iloc[0])

#分钟收益各阶局
skew=_ret.skew()
inday_ret=close.loc[145700]/close.loc[95900]-1   #日内涨跌幅累计
low_volume_cov=low.cov(volume)                #日内成交量与最低价的协方差
some_rsi=ta.RSI(close).loc[95900] #RSI技术指标
sar=ta.SAR(high,low,0.02,0.2).loc[145700]            #SAR抛物线转向
_pvt=(_ret*volume).cumsum()
pvt=_pvt.iloc[-1]-_pvt.mean()   #PVT量价趋势因子

#聪明钱指标
_st=((close/close.shift(1)-1).abs()/volume.pow(0.5)).sort_values(ascending=False)
_volume=volume[_st.index]
_close=close[_st.index]
_smart_money=(_volume.cumsum()/volume.sum())>=0.2
smart_money=((_volume[_smart_money]*_close[_smart_money]).sum()/_volume[_smart_money].sum())/((volume*close).sum()/volume.sum())

#成交量各阶矩
mean_v=volume.mean()
std_v=volume.std()
skew_v=volume.skew()
kurt_v=volume.kurt()
#人气指标
_mid=(high+low+close)/3
_strong_sum=where(high>_mid.shift(1), high-_mid.shift(1), 0).sum()
_weak_sum=where(low<_mid.shift(1),_mid.shift(1)-low,0).sum()
cr=_strong_sum/_weak_sum
#MFI资金流因子
_mf=_mid*volume
_mf_p=where(_mid>_mid.shift(1), _mf, 0)
_mf_n=where(_mid<_mid.shift(1), -1*_mf, 0)
_positive_mf=_mf_p.loc[100000:145700].sum()
_negative_mf=_mf_n.loc[100000:145700].sum()
_mr=_positive_mf/_negative_mf
mfi=100-(100/(1+_mr))
#MACD指数平滑异同平均
_dif=ta.EMA(close,12)-ta.EMA(close,26)
macd=_dif.loc[145700]

#SRDM动向速度比率
_dmz=where(high+low<high.shift(1)+low.shift(1), 0, max(abs(high-high.shift(1)),abs(low-low.shift(1))))
_dmf=where(high+low>=high.shift(1)+low.shift(1), 0, max(abs(high-high.shift(1)),abs(low-low.shift(1))))
_admz=mean(_dmz,10)
_admf=mean(_dmf,10)
_srdm=where(_admz>_admf, (_admz-_admf)/_admz, where(_admz==_admf, 0, (_admz-_admf)/_admf))
asrdm=mean(_srdm,10).loc[145700]
# 真正的强度指数TSI
_mom=close-close.shift(1)
_mom_real=np.array(_mom,dtype='f8')
_tsi_series=(ta.EMA(ta.EMA(_mom_real,25),13)/ta.EMA(ta.EMA(abs(_mom_real),25),13))*100
tsi=_tsi_series.loc[145700]

#日内大单流入
_up_volumes=volume[_ret>0]
my_mf_net_amount_l=_up_volumes.nlargest(math.floor(0.1*len(_up_volumes))).sum()"""
)

m9 = M.input_features.v1(
    features="""#用在高频因子抽取的模块上
# #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
#支持np  pd  ta math库  支持pandas内置函数  支持自定义表达式
return_5
return_10
return_20
avg_amount_5/avg_amount_10
return_5/return_10
ta_cci_14_0
turn_5/avg_turn_10
avg_amount_0/avg_amount_5
swing_volatility_5_0/swing_volatility_60_0
amount_10/amount_30
rank_volatility_10_0
return_0
ta_ema_5_0/close_0
close_0/low_0
ta_ema_20_0/close_0
open_0/close_1
high_1/close_0
ta_ema_30_0/close_0
ta_rsi(close_0, 6)
amount_0/amount_1
riskOK=where(abs((close_1-open_1)/open_1)<0.09, 1,0) #前一天是否有极端行情"""
)

m14 = M.input_features.v1(
    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
#支持np  pd  ta math库  支持pandas内置函数  支持自定义表达式
#close_=close.loc[145700] #抽取14点57分收盘价
#(close*volume).sum()/volume.sum() #等同于vwap
#vwap(close,volume)  #vwap为自定义表达式
#mean_4=close.loc[103000]+close.loc[113000]+close.loc[140000]+close.loc[145700]

skew
inday_ret
low_volume_cov
some_rsi
sar
pvt
smart_money
#成交量各阶矩
mean_v
std_v
skew_v
kurt_v
#MFI资金流因子
mfi 
#MACD指数平滑异同平均

macd

#SRDM动向速度比率

asrdm
# 真正的强度指数TSI

tsi

#日内大单流入

#my_mf_net_amount_l

#cr
#以下为日频因子


#avg_amount_5/avg_amount_10
#return_5/return_10
#ta_cci_14_0
#turn_5/avg_turn_10
#avg_amount_0/avg_amount_5
#swing_volatility_5_0/swing_volatility_60_0
#amount_10/amount_30
#rank_volatility_10_0
#return_0
#ta_ema_5_0/close_0
#close_0/low_0
#ta_ema_20_0/close_0
#open_0/close_1
#high_1/close_0
#ta_ema_30_0/close_0
#ta_rsi(close_0, 6)
#amount_0/amount_1
 """
)

m26 = M.input_features.v1(
    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
in_csi500_0"""
)

m21 = M.instruments.v2(
    start_date='2021-01-20',
    end_date='2021-06-20',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m22 = M.input_features.v1(
    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
in_csi500_0"""
)

m23 = M.general_feature_extractor.v7(
    instruments=m21.data,
    features=m22.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m24 = M.filter.v3(
    input_data=m23.data,
    expr='in_csi500_0 == 1',
    output_left_data=False
)

m25 = M.cached.v3(
    input_1=m24.data,
    input_2=m21.data,
    run=m25_run_bigquant_run,
    post_run=m25_post_run_bigquant_run,
    input_ports='input_1,input_2',
    params='{}',
    output_ports='data_1'
)

m2 = M.feature_extractor_1m.v2(
    instruments=m25.data_1,
    features=m4.data,
    start_date='',
    end_date='',
    before_start_days=0,
    workers=10,
    parallel_mode='单机',
    table_1m='降频分钟数据(股票)'
)

m5 = M.advanced_auto_labeler.v2(
    instruments=m25.data_1,
    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, -2) / 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, 8)

# 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,
    user_functions={}
)

m7 = M.join.v3(
    data1=m5.data,
    data2=m2.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m11 = M.general_feature_extractor.v7(
    instruments=m25.data_1,
    features=m9.data,
    start_date='',
    end_date='',
    before_start_days=10
)

m19 = M.derived_feature_extractor.v3(
    input_data=m11.data,
    features=m9.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m8 = M.join.v3(
    data1=m7.data,
    data2=m19.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m6 = M.dropnan.v2(
    input_data=m8.data
)

m15 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-06-22'),
    end_date=T.live_run_param('trading_date', '2021-10-22'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m27 = M.general_feature_extractor.v7(
    instruments=m15.data,
    features=m26.data,
    start_date='',
    end_date='',
    before_start_days=5
)

m28 = M.filter.v3(
    input_data=m27.data,
    expr='in_csi500_0 == 1',
    output_left_data=False
)

m29 = M.cached.v3(
    input_1=m28.data,
    input_2=m15.data,
    run=m29_run_bigquant_run,
    post_run=m29_post_run_bigquant_run,
    input_ports='input_1,input_2',
    params='{}',
    output_ports='data_1'
)

m3 = M.feature_extractor_1m.v2(
    instruments=m29.data_1,
    features=m4.data,
    start_date='',
    end_date='',
    before_start_days=0,
    workers=10,
    parallel_mode='单机',
    table_1m='降频分钟数据(股票)'
)

m12 = M.general_feature_extractor.v7(
    instruments=m29.data_1,
    features=m9.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m20 = M.derived_feature_extractor.v3(
    input_data=m12.data,
    features=m9.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={},
    m_cached=False
)

m10 = M.join.v3(
    data1=m3.data,
    data2=m20.data,
    on='date,instrument',
    how='inner',
    sort=False,
    m_cached=False
)

m13 = M.dropnan.v2(
    input_data=m10.data
)

m16 = M.lightgbm.v2(
    training_ds=m6.data,
    features=m14.data,
    predict_ds=m13.data,
    num_boost_round=79,
    objective='排序(ndcg)',
    num_class=1,
    num_leaves=60,
    learning_rate=0.1,
    min_data_in_leaf=900,
    max_bin=1023,
    key_cols='date,instrument',
    group_col='date',
    random_seed=101,
    other_train_parameters={'n_jobs':4,'label_gain':','.join([str(x) for x in range(20)]),"max_position":29,"eval_at":"1,3,5,10"}
)

m17 = M.trade.v4(
    instruments=m29.data_1,
    options_data=m16.predictions,
    start_date='',
    end_date='',
    initialize=m17_initialize_bigquant_run,
    handle_data=m17_handle_data_bigquant_run,
    prepare=m17_prepare_bigquant_run,
    volume_limit=0,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000,
    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='000300.SHA'
)

[2021-10-25 10:41:55.465577] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-25 10:41:55.499337] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.501644] INFO: moduleinvoker: input_features.v1 运行完成[0.036079s].

[2021-10-25 10:41:55.507968] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-25 10:41:55.516981] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.518992] INFO: moduleinvoker: input_features.v1 运行完成[0.011017s].

[2021-10-25 10:41:55.525350] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-25 10:41:55.535115] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.536713] INFO: moduleinvoker: input_features.v1 运行完成[0.011402s].

[2021-10-25 10:41:55.541807] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-25 10:41:55.547378] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.549194] INFO: moduleinvoker: input_features.v1 运行完成[0.007387s].

[2021-10-25 10:41:55.555820] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-25 10:41:55.564278] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.565531] INFO: moduleinvoker: instruments.v2 运行完成[0.009709s].

[2021-10-25 10:41:55.568943] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-25 10:41:55.573293] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.574568] INFO: moduleinvoker: input_features.v1 运行完成[0.005624s].

[2021-10-25 10:41:55.586148] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-25 10:41:55.594375] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.596381] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010221s].

[2021-10-25 10:41:55.606917] INFO: moduleinvoker: filter.v3 开始运行..

[2021-10-25 10:41:55.624080] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.626587] INFO: moduleinvoker: filter.v3 运行完成[0.019668s].

[2021-10-25 10:41:55.643499] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-25 10:41:55.652952] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.654455] INFO: moduleinvoker: cached.v3 运行完成[0.010988s].

[2021-10-25 10:41:55.660379] INFO: moduleinvoker: feature_extractor_1m.v2 开始运行..

[2021-10-25 10:41:55.665170] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.666331] INFO: moduleinvoker: feature_extractor_1m.v2 运行完成[0.005952s].

[2021-10-25 10:41:55.677771] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-25 10:41:55.704146] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.707011] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.029222s].

[2021-10-25 10:41:55.721155] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-25 10:41:55.730484] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.732945] INFO: moduleinvoker: join.v3 运行完成[0.0118s].

[2021-10-25 10:41:55.748808] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-25 10:41:55.758692] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.760350] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011579s].

[2021-10-25 10:41:55.768224] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-25 10:41:55.777478] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.779532] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.011308s].

[2021-10-25 10:41:55.788468] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-25 10:41:55.798979] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.801929] INFO: moduleinvoker: join.v3 运行完成[0.013438s].

[2021-10-25 10:41:55.814976] INFO: moduleinvoker: dropnan.v2 开始运行..

[2021-10-25 10:41:55.826802] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.829479] INFO: moduleinvoker: dropnan.v2 运行完成[0.014513s].

[2021-10-25 10:41:55.836575] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-25 10:41:55.843698] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.845819] INFO: moduleinvoker: instruments.v2 运行完成[0.009251s].

[2021-10-25 10:41:55.858167] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-25 10:41:55.864096] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.865852] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.007689s].

[2021-10-25 10:41:55.875334] INFO: moduleinvoker: filter.v3 开始运行..

[2021-10-25 10:41:55.880840] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.882531] INFO: moduleinvoker: filter.v3 运行完成[0.007195s].

[2021-10-25 10:41:55.893473] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-25 10:41:55.901424] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.903827] INFO: moduleinvoker: cached.v3 运行完成[0.010359s].

[2021-10-25 10:41:55.913816] INFO: moduleinvoker: feature_extractor_1m.v2 开始运行..

[2021-10-25 10:41:55.921708] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.923500] INFO: moduleinvoker: feature_extractor_1m.v2 运行完成[0.009719s].

[2021-10-25 10:41:55.940078] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-25 10:41:55.949942] INFO: moduleinvoker: 命中缓存

[2021-10-25 10:41:55.951798] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01174s].

[2021-10-25 10:41:55.958797] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-25 10:41:56.119059] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_10, 0.003s

[2021-10-25 10:41:56.123567] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.002s

[2021-10-25 10:41:56.127590] INFO: derived_feature_extractor: 提取完成 turn_5/avg_turn_10, 0.002s

[2021-10-25 10:41:56.130559] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.001s

[2021-10-25 10:41:56.134087] INFO: derived_feature_extractor: 提取完成 swing_volatility_5_0/swing_volatility_60_0, 0.002s

[2021-10-25 10:41:56.138227] INFO: derived_feature_extractor: 提取完成 amount_10/amount_30, 0.002s

[2021-10-25 10:41:56.141767] INFO: derived_feature_extractor: 提取完成 ta_ema_5_0/close_0, 0.002s

[2021-10-25 10:41:56.145651] INFO: derived_feature_extractor: 提取完成 close_0/low_0, 0.002s

[2021-10-25 10:41:56.148762] INFO: derived_feature_extractor: 提取完成 ta_ema_20_0/close_0, 0.002s

[2021-10-25 10:41:56.152148] INFO: derived_feature_extractor: 提取完成 open_0/close_1, 0.002s

[2021-10-25 10:41:56.154397] INFO: derived_feature_extractor: 提取完成 high_1/close_0, 0.001s

[2021-10-25 10:41:56.156443] INFO: derived_feature_extractor: 提取完成 ta_ema_30_0/close_0, 0.001s

[2021-10-25 10:41:56.869820] INFO: derived_feature_extractor: 提取完成 ta_rsi(close_0, 6), 0.712s

[2021-10-25 10:41:56.872978] INFO: derived_feature_extractor: 提取完成 amount_0/amount_1, 0.001s

[2021-10-25 10:41:56.876269] INFO: derived_feature_extractor: 提取完成 riskOK=where(abs((close_1-open_1)/open_1)<0.09, 1,0) #前一天是否有极端行情, 0.002s

[2021-10-25 10:41:57.041050] INFO: derived_feature_extractor: /y_2021, 28912

[2021-10-25 10:41:57.131161] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[1.17235s].

[2021-10-25 10:41:57.141194] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-25 10:41:57.360552] INFO: join: /y_2021, 行数=499/28912, 耗时=0.144228s

[2021-10-25 10:41:57.393120] INFO: join: 最终行数: 499

[2021-10-25 10:41:57.399951] INFO: moduleinvoker: join.v3 运行完成[0.258728s].

[2021-10-25 10:41:57.411549] INFO: moduleinvoker: dropnan.v2 开始运行..

[2021-10-25 10:41:57.491819] INFO: dropnan: /y_2021, 496/499

[2021-10-25 10:41:57.521344] INFO: dropnan: 行数: 496/499

[2021-10-25 10:41:57.528272] INFO: moduleinvoker: dropnan.v2 运行完成[0.116734s].

[2021-10-25 10:41:57.540504] INFO: moduleinvoker: lightgbm.v2 开始运行..

[2021-10-25 10:41:59.002122] INFO: moduleinvoker: lightgbm.v2 运行完成[1.461633s].

[2021-10-25 10:42:00.902884] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-10-25 10:42:00.910199] INFO: backtest: biglearning backtest:V8.5.0

[2021-10-25 10:42:00.911925] INFO: backtest: product_type:stock by specified

[2021-10-25 10:42:00.997058] INFO: moduleinvoker: cached.v2 开始运行..

[2021-10-25 10:42:02.046552] INFO: backtest: 读取股票行情完成:204614

[2021-10-25 10:42:02.492260] INFO: moduleinvoker: cached.v2 运行完成[1.49523s].

[2021-10-25 10:42:02.773610] INFO: algo: TradingAlgorithm V1.8.5

[2021-10-25 10:42:02.886929] INFO: algo: trading transform...

[2021-10-25 10:42:02.936704] INFO: Performance: Simulated 1 trading days out of 1.

[2021-10-25 10:42:02.938924] INFO: Performance: first open: 2021-10-22 09:30:00+00:00

[2021-10-25 10:42:02.940601] INFO: Performance: last close: 2021-10-22 15:00:00+00:00

[2021-10-25 10:42:05.018753] INFO: moduleinvoker: backtest.v8 运行完成[4.115862s].

[2021-10-25 10:42:05.020935] INFO: moduleinvoker: trade.v4 运行完成[6.006686s].

收益率0.0%
年化收益率0.0%
基准收益率0.64%
阿尔法0
贝塔0
夏普比率0
胜率0.0
盈亏比0.0
收益波动率0%
信息比率0
最大回撤0.0%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-aeae573432924d3eb96b4982d201cd31"}/bigcharts-data-end

In [ ]:

test=m16.predictions.read_df()
test

[2021-10-21 09:07:43.078969] INFO: 高频特征抽取-分钟到日频: 计算中:   2%|5                          | 16/800 [00:19<01:38,  8.00it/s]