复制链接

克隆策略

In [2]:

# 本代码由可视化策略环境自动生成 2022年3月31日 22:52
# 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 m19_initialize_bigquant_run(context):
    print('初始化函数，只执行一次')
    # 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 = 10
    # 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 = T.norm([1 / math.log(i+2) 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 = 0.3
    context.options['hold_days'] = 30

def getMa(today,context,instruments):
    # 加载原始数据
    import datetime
    stock_raw_data = D.history_data(instruments, today+datetime.timedelta(days=-100), today, ['date','close','low'])
    #print('11111',stock_raw_data)
    stock_raw_data=stock_raw_data.iloc[-55:] 
    #stock_raw_data=stock_raw_data[:55]
    #print('22222',stock_raw_data)
    sumMa=0
    lastClose=0
    for index,row in stock_raw_data.iterrows():
        #print(index,row)
        sumMa += row['close']
        lastClose=row['close']
        
    # 包含多个周期均线值的股票数据
   # stock_ma_data = stock_raw_data.groupby('instrument').apply(ma_calculate)
    return [sumMa/55,lastClose]


# 计算多个周期均线的函数
def ma_calculate(df):
    #ma_list = [5,10,34,55]
    for ma_len in ma_list:
        print('ma_len==',ma_len)
        df['ma_'+str(ma_len)] = df['close'].rolling(ma_len).mean()
    return df

# 回测引擎：每日数据处理函数，每天执行一次
def m19_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')]
    df = context.options['data'].read_df()
    df_today = df[df.date == data.current_dt.strftime('%Y-%m-%d')]
    df_today.set_index('instrument')
    
    today = data.current_dt.strftime('%Y-%m-%d')
    #print('日期:',today)
    # 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']
    
    print('context.portfolio.cash:',context.portfolio.cash)
    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
    print('cash_avg==',cash_avg,'  cash_for_buy:',cash_for_buy,' context.portfolio.cash:',context.portfolio.cash)
    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
    print('context.portfolio.portfolio_value:',context.portfolio.portfolio_value)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.portfolio.positions.items()}
    print('is_staging:',is_staging,' cash_for_sell:',cash_for_sell)
    
    equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
    stocks=len(equities)
    # 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:
    if not is_staging :
        if stocks > 0:
            for i in equities.keys():
               # print(today,' sell I===',i)
                instruments=[]
                instruments.append(i)  
                #ri55=getMa(data.current_dt,context,instruments)
                #print('df after get ma 55==',ri55)
                try :
                    a=getMa(data.current_dt,context,instruments)
                    ri55=a[0]
                    lastClose=a[1]
                except :
                    ri55=0
                    lastClose=0
                print(i,today,'ma55===',ri55,'lastClose===',lastClose)
                
                #try :
                #   ri34s=list(df_today[df_today.instrument==i]['ri34'])
                #    ri34=ri34s[0]
                #print('df_today===',df_today)
               # ri55s=list(df_today[df_today.instrument==i]['ma_20'])
            
               # print('ri55===',ri55[0])
               # ri55s=list(df_today[df_today.instrument==i]['ri55'])
               # print('ri55s==',ri55s)
               # ri55=ri55s[0]
                #except :
                #    ri34=0
                #    ri55=0
                    
                stock_market_price = data.current(context.symbol(i), 'price')  # 最新市场价格
                stock_market_today_high = data.current(context.symbol(i), 'high') #今日最高价      
                stock_market_today_close = data.current(context.symbol(i), 'close') #今日收盘价
                last_sale_date = equities[i].last_sale_date   # 上次交易日期
                last_cost_price = equities[i].cost_basis # 上次交易金额
                delta_days = data.current_dt - last_sale_date  
                hold_days = delta_days.days # 持仓天数
        # 最高收益
        #high_return = (highclose_price_since_buy-last_cost_price)/last_cost_price
        
                target_return = stock_market_today_close/last_cost_price
                print(today,i,'stock_market_today_close== ',stock_market_today_close)
                if hold_days>=30 :
                    context.order_target(context.symbol(i), 0)
                    print(today,'超期卖出 :','收益： ',target_return,equities[i], ' context.symbol(i):',context.symbol(i))
                    context.order_target(context.symbol(i), 0)
                    stocks = stocks-1
                    context.portfolio.cash=context.portfolio.cash+positions[i]
                elif target_return>=1.2 :
                    context.order_target(context.symbol(i), 0)
                    print(today,' 盈利卖出 :','收益： ',target_return,equities[i],' context.symbol(i):',context.symbol(i))
                    stocks = stocks-1
                    context.portfolio.cash=context.portfolio.cash+positions[i]
                elif lastClose<ri55 :
                    context.order_target(context.symbol(i), 0)
                    print(today,' 跌破55日线卖出 :','收益： ',target_return,equities[i],' context.symbol(i):',context.symbol(i))
                    stocks = stocks-1
                    context.portfolio.cash=context.portfolio.cash+positions[i]
                elif target_return<=0.9 :
                    context.order_target(context.symbol(i), 0)
                    print(today,' 止损卖出 :','收益： ',target_return,equities[i],' context.symbol(i):',context.symbol(i))
                    stocks = stocks-1
                    context.portfolio.cash=context.portfolio.cash+positions[i]
                    

    # 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[:10-stocks])
    #print('buy_instruments:',buy_instruments,'buy_cash_weights:',buy_cash_weights,'ranker_prediction:',ranker_prediction)
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    cash = context.portfolio.cash/(10-stocks)
    for i, instrument in enumerate(buy_instruments):
      
        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)
        #print(today,i,cash)
        if cash > 0:
            context.order_value(context.symbol(instrument), cash)
            
        print(today,' 买入 ',instrument, ' 金额',cash)   
            
            
# 回测引擎：准备数据，只执行一次
def m19_prepare_bigquant_run(context):
    # 加载预测数据
    print('准备数据，只执行一次')
    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['fantanbili']>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['fantanbili']>0].instrument)
    
    # 每日卖出股票的数据框
    context.daily_sell_stock= df.groupby('date').apply(close_pos_con)  
    # 每日买入股票的数据框
    context.daily_buy_stock= df.groupby('date').apply(open_pos_con)  
    
    #---------
    stock_raw_data = D.history_data(context.instruments, context.start_date, context.end_date, ['close','low'])
    # 包含多个周期均线值的股票数据
    stock_ma_data = stock_raw_data.groupby('instrument').apply(ma_calculate)
   

# 计算多个周期均线的函数
def ma_calculate(df):
    ma_list = [5,10,20,40,120]
    for ma_len in ma_list:
        df['ma_'+str(ma_len)] = df['close'].rolling( ma_len).mean()
    return df



m1 = M.instruments.v2(
    start_date='2019-01-01',
    end_date='2019-12-30',
    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/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, -30) / 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.HIX',
    drop_na_label=True,
    cast_label_int=True
)

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
#pe_ttm_0
close_0/mean(close_0,5)
close_0/mean(close_0,10)
close_0/mean(close_0,20)
close_0/open_0
open_0/mean(close_0,5)
open_0/mean(close_0,10)
open_0/mean(close_0,20)
high_0/adjust_factor_0
low_0/adjust_factor_0

#timeperiod移动平均线
#zhouma34=ta_ma(close_0, timeperiod=166)/adjust_factor_0
zhouma34=ta_ma(close_0, timeperiod=166)
#timeperiod移动平均线
zhouma55=ta_ma(close_0, timeperiod=258)
isup=zhouma34/zhouma55
#sy=shift(close_0, -100)/shift(open_0, -1)

#ts_max(high_0,10)/adjust_factor_0
#ts_min(low_0,10)/adjust_factor_0

ts_argmax(high_0, 258*5)
#4年高点，1年按258个交易日算
isgaodian=where(ts_argmax(high_0, 258*4)<500.0,1,0)

#1年低点，1年按258个交易日算
ts_argmin(low_0, 258*1)
isdidian=where(ts_argmin(low_0, 258*1)<100.0,1,0)

#半年高点，1年按258个交易日算
isbanniangaodian=where(ts_argmax(high_0, 128)<80.0,1,0)
#在周34-55均线区间，日166-258
iszaiquejian=where((open_0<=zhouma34) & (close_0>=zhouma55),1,0)
#4-5线重合
junxian=where((ta_ma(close_0, timeperiod=5)<=high_0) & (ta_ma(close_0, timeperiod=13)<=high_0) &\
                       (ta_ma(close_0, timeperiod=20)<=high_0) & (ta_ma(close_0, timeperiod=34)<=high_0) &\
                       (ta_ma(close_0, timeperiod=55)<=high_0) & (ta_ma(close_0, timeperiod=5) >=low_0) &\
                       (ta_ma(close_0, timeperiod=13)>=low_0) & (ta_ma(close_0, timeperiod=20)>=low_0) &\
                       (ta_ma(close_0, timeperiod=34)>=low_0) & (ta_ma(close_0, timeperiod=55)>=low_0) &\
                       (return_0>0.001),1,0)
#55日均线，跌破止损，
ri55=ta_ma(close_0, timeperiod=55)
shangri55=shift(ta_ma(close_0, timeperiod=55),2)
#曾经前几天下过55线，触碰过日258线
#isdiyu258=where(ts_min(low_0, 3)<zhouma55,1,0)

#tmax=ts_argmax(high_0, 258*5)

#反弹比例,选比例最高的10-20只交易，后面调试
yiniandidian=ts_min(low_0, 258*1)
banniangaodian=ts_max(high_0, 128*1)
fantanbili=banniangaodian/yiniandidian

#排除ST
st_status_0
#时间序列函数， d 天内的最大值
#ts_max(high_0, 258*4)
#时间序列函数， d 天内的最小值
#ts_min(low_0, 258*1)
#是否是沪深300
in_csi300_0
#是否是中证500
in_csi500_0
#营业收入单季度环比增长率
fs_operating_revenue_qoq_0
#营业收入同比增长率
fs_operating_revenue_yoy_0
#归属母公司股东的净利润单季度环比增长率
fs_net_profit_qoq_0
#主力净流入占比
mf_net_pct_main_0

#avg_amount_* 过去 * 个交易日的平均交易额
liangisup=avg_amount_5/avg_amount_10

#isxiadie=where(ts_max(high_0, 258*4)>ts_min(low_0, 258*1),1,0)

"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=2000
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m5 = M.filter.v3(
    input_data=m16.data,
    expr='isgaodian==1&isdidian==1&isbanniangaodian==1&st_status_0==0&date>\'2019-01-01\'',
    output_left_data=True
)

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

m13 = M.dropnan.v1(
    input_data=m7.data
)

m6 = M.stock_ranker_train.v5(
    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,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2020-01-01'),
    end_date=T.live_run_param('trading_date', '2020-12-30'),
    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=2000
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m12 = M.filter.v3(
    input_data=m18.data,
    expr='isgaodian==1&isdidian==1&isbanniangaodian==1&st_status_0==0&date>=\'2020-01-01\'',
    output_left_data=True
)

m20 = M.sort.v5(
    input_ds=m12.data,
    sort_by='fantanbili',
    group_by='date',
    keep_columns='--',
    ascending=False
)

m14 = M.dropnan.v1(
    input_data=m12.data
)

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

m4 = M.join.v3(
    data1=m8.predictions,
    data2=m14.data,
    on='date,instrument',
    how='left',
    sort=False
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m4.data,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000000,
    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.HIX'
)

m10 = M.sort.v5(
    sort_by='fantanbili',
    group_by='date',
    keep_columns='--',
    ascending=False
)

[2022-03-31 22:50:11.586373] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-03-31 22:50:11.608848] INFO: moduleinvoker: 命中缓存

[2022-03-31 22:50:11.610694] INFO: moduleinvoker: instruments.v2 运行完成[0.024332s].

[2022-03-31 22:50:11.622432] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-03-31 22:50:11.633352] INFO: moduleinvoker: 命中缓存

[2022-03-31 22:50:11.636097] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.013665s].

[2022-03-31 22:50:11.642725] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-03-31 22:50:11.654069] INFO: moduleinvoker: 命中缓存

[2022-03-31 22:50:11.656577] INFO: moduleinvoker: input_features.v1 运行完成[0.013867s].

[2022-03-31 22:50:11.677073] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-03-31 22:50:11.688524] INFO: moduleinvoker: 命中缓存

[2022-03-31 22:50:11.690282] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.013225s].

[2022-03-31 22:50:11.698572] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-03-31 22:50:11.707196] INFO: moduleinvoker: 命中缓存

[2022-03-31 22:50:11.709079] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010512s].

[2022-03-31 22:50:11.719091] INFO: moduleinvoker: filter.v3 开始运行..

[2022-03-31 22:50:11.759914] INFO: filter: 使用表达式 isgaodian==1&isdidian==1&isbanniangaodian==1&st_status_0==0&date>'2019-01-01' 过滤

[2022-03-31 22:50:11.897993] INFO: filter: 过滤 /y_2013, 0/0/0

[2022-03-31 22:50:11.949679] INFO: filter: 过滤 /y_2014, 0/0/0

[2022-03-31 22:50:12.008916] INFO: filter: 过滤 /y_2015, 0/0/0

[2022-03-31 22:50:12.050245] INFO: filter: 过滤 /y_2016, 0/0/0

[2022-03-31 22:50:12.104368] INFO: filter: 过滤 /y_2017, 0/0/0

[2022-03-31 22:50:12.292929] INFO: filter: 过滤 /y_2018, 0/28878/28878

[2022-03-31 22:50:13.651939] INFO: filter: 过滤 /y_2019, 140882/269448/410330

[2022-03-31 22:50:13.732569] INFO: moduleinvoker: filter.v3 运行完成[2.013474s].

[2022-03-31 22:50:13.743598] INFO: moduleinvoker: join.v3 开始运行..

[2022-03-31 22:50:16.110552] INFO: join: /y_2019, 行数=115478/140882, 耗时=0.978638s

[2022-03-31 22:50:16.158370] INFO: join: 最终行数: 115478

[2022-03-31 22:50:16.182339] INFO: moduleinvoker: join.v3 运行完成[2.43874s].

[2022-03-31 22:50:16.193389] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-03-31 22:50:16.850010] INFO: dropnan: /y_2019, 115478/115478

[2022-03-31 22:50:17.055059] INFO: dropnan: 行数: 115478/115478

[2022-03-31 22:50:17.061803] INFO: moduleinvoker: dropnan.v1 运行完成[0.868415s].

[2022-03-31 22:50:17.073037] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2022-03-31 22:50:17.548839] INFO: StockRanker: 特征预处理 ..

[2022-03-31 22:50:17.767298] INFO: StockRanker: prepare data: training ..

[2022-03-31 22:50:18.037367] INFO: StockRanker: sort ..

[2022-03-31 22:50:20.090045] INFO: StockRanker训练: e1134b2e 准备训练: 115478 行数

[2022-03-31 22:50:20.351236] INFO: StockRanker训练: 正在训练 ..

[2022-03-31 22:51:30.699990] ERROR: moduleinvoker: module name: stock_ranker_train, module version: v5, trackeback: Exception: 模型训练失败：可能导致错误的原因是训练数据问题，请检查训练数据, err_code=1 (e1134b2eb10111ecaa8b2645fd2d8677)

---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
<ipython-input-2-17b682937095> in <module>
    349 )
    350 
--> 351 m6 = M.stock_ranker_train.v5(
    352     training_ds=m13.data,
    353     features=m3.data,

Exception: 模型训练失败：可能导致错误的原因是训练数据问题，请检查训练数据, err_code=1 (e1134b2eb10111ecaa8b2645fd2d8677)