克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2021年10月29日 11:13
# 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 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3只
    stock_count = 3
    # 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 = 0.6
    context.options['hold_days'] = 5

# 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):
    # 获取当前持仓
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.portfolio.positions.items()}
    
    today = data.current_dt.strftime('%Y-%m-%d')
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == today]
    
    #大盘风控模块，读取风控数据    
    benckmark_risk=ranker_prediction['bm_0'].values[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_risk > 0:
        for instrument in positions.keys():
            print("在这处理止损第二天开盘卖出")
            context.order_target(context.symbol(instrument), 0)
        print(today,'大盘风控止损触发,全仓卖出')
        return
    
    # 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)
   
    
    # 2. 根据需要加入移动止赢止损模块、固定天数卖出模块
    stock_sold = [] # 记录卖出的股票，防止多次卖出出现空单
    
    #------------------------START:止赢止损模块(含建仓期)---------------
    current_stopwin_stock=[]
    current_stoploss_stock = []   
    positions_cost={e.symbol:p.cost_basis for e,p in context.portfolio.positions.items()}
    if len(positions)>0:
        for instrument in positions.keys():
            stock_cost=positions_cost[instrument]  
            stock_market_price=data.current(context.symbol(instrument),'price')  
            # 赚9%且为可交易状态就止盈
            if stock_market_price/stock_cost-1>=0.09 and data.can_trade(context.symbol(instrument)):
                context.order_target_percent(context.symbol(instrument),0)
                cash_for_sell -= positions[instrument]
                current_stopwin_stock.append(instrument)
            # 亏5%并且为可交易状态就止损
            if stock_market_price/stock_cost-1 <= -0.05 and data.can_trade(context.symbol(instrument)):   
                context.order_target_percent(context.symbol(instrument),0)
                cash_for_sell -= positions[instrument]
                current_stoploss_stock.append(instrument)
        if len(current_stopwin_stock)>0:
            #print(today,'止盈股票列表',current_stopwin_stock)
            stock_sold += current_stopwin_stock
        if len(current_stoploss_stock)>0:
            #print(today,'止损股票列表',current_stoploss_stock)
            stock_sold += current_stoploss_stock
    #--------------------------END: 止赢止损模块--------------------------
    
    #--------------------------START：持有固定天数卖出(不含建仓期)-----------
    current_stopdays_stock = []
    positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.portfolio.positions.items()}
    # 不是建仓期（在前hold_days属于建仓期）
    if not is_staging:
        for instrument in positions.keys():
            #如果上面的止盈止损已经卖出过了，就不要重复卖出以防止产生空单
            if instrument in stock_sold:
                continue
            # 今天和上次交易的时间相隔hold_days就全部卖出 datetime.timedelta(context.options['hold_days'])也可以换成自己需要的天数，比如datetime.timedelta(5)
            if data.current_dt - positions_lastdate[instrument]>=datetime.timedelta(5) and data.can_trade(context.symbol(instrument)):
                context.order_target_percent(context.symbol(instrument), 0)
                current_stopdays_stock.append(instrument)
                cash_for_sell -= positions[instrument]
        if len(current_stopdays_stock)>0:        
            #print(today,'固定天数卖出列表',current_stopdays_stock)
            stock_sold += current_stopdays_stock
    #-------------------------  END:持有固定天数卖出-----------------------
    
    #-------------------------- START: ST和退市股卖出 ---------------------  
    st_stock_list = []
    for instrument in positions.keys():
        try:
            instrument_name = ranker_prediction[ranker_prediction.instrument==instrument].name.values[0]
            # 如果股票状态变为了st或者退市 则卖出
            if 'ST' in instrument_name or '退' in instrument_name:
                if instrument in stock_sold:
                    continue
                if data.can_trade(context.symbol(instrument)):
                    context.order_target(context.symbol(instrument), 0)
                    st_stock_list.append(instrument)
                    cash_for_sell -= positions[instrument]
        except:
            continue
    if st_stock_list!=[]:
       # print(today,'持仓出现st股/退市股',st_stock_list,'进行卖出处理')    
        stock_sold += st_stock_list

    #-------------------------- END: ST和退市股卖出 --------------------- 
    
    
    # 3. 生成轮仓卖出订单：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:
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in positions)])))
        for instrument in instruments:
            # 如果资金够了就不卖出了
            if cash_for_sell <= 0:
                break
            #防止多个止损条件同时满足，出现多次卖出产生空单
            if instrument in stock_sold:
                continue
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[instrument]
            stock_sold.append(instrument)

    # 4. 生成轮仓买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
    # 计算今日跌停的股票
    dt_list = list(ranker_prediction[ranker_prediction.price_limit_status_0==1].instrument)
    # 计算今日ST/退市的股票
    st_list = list(ranker_prediction[ranker_prediction.name.str.contains('ST')|ranker_prediction.name.str.contains('退')].instrument)
    # 计算所有禁止买入的股票池
    banned_list = stock_sold+dt_list+st_list
    buy_cash_weights = context.stock_weights
    buy_instruments=[k for k in list(ranker_prediction.instrument) if k not in banned_list][:len(buy_cash_weights)]
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    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:
            context.order_value(context.symbol(instrument), cash)
    


# 回测引擎：准备数据，只执行一次
def m4_prepare_bigquant_run(context):
    pass
def m4_before_trading_start_bigquant_run(context, data):
    #此处理只适用于设置的卖出点为收盘时有效。如果设置的是开盘价卖出，则此处理使用了未来信息。
    # 获取涨跌停状态数据
    df_price_limit_status = context.ranker_prediction.set_index('date')
    today=data.current_dt.strftime('%Y-%m-%d')
    # 得到当前未完成订单
    for orders in get_open_orders().values():
        # 循环，撤销订单
        for _order in orders:
            ins=str(_order.sid.symbol)
            try:
                #判断一下如果当日涨停，则取消卖单
                if  df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status_0.ix[today]>2 and _order.amount<0:
                    cancel_order(_order)
                    print(today,'尾盘涨停取消卖单',ins) 
            except:
                continue

m1 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2020-12-31',
    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="""# #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
return_10
return_20
avg_amount_0/avg_amount_5
avg_amount_5/avg_amount_20
rank_avg_amount_0/rank_avg_amount_5
rank_avg_amount_5/rank_avg_amount_10
rank_return_0
rank_return_5
rank_return_10
rank_return_0/rank_return_5
rank_return_5/rank_return_10
pe_ttm_0
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

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

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

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

m5 = 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,
    ndcg_discount_base=1,
    m_lazy_run=False
)

m6 = M.input_features.v1(
    features_ds=m3.data,
    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
price_limit_status_0"""
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2021-10-21'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m6.data,
    start_date='',
    end_date='',
    before_start_days=0
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m6.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m14 = M.dropnan.v1(
    input_data=m18.data
)

m8 = M.stock_ranker_predict.v5(
    model=m5.model,
    data=m14.data,
    m_lazy_run=False
)

m10 = M.select_columns.v3(
    input_ds=m14.data,
    columns='date,instrument,price_limit_status_0',
    reverse_select=False
)

m11 = M.join.v3(
    data1=m8.predictions,
    data2=m10.data,
    on='date,instrument',
    how='left',
    sort=True
)

m20 = 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
name"""
)

m22 = M.use_datasource.v1(
    instruments=m9.data,
    features=m20.data,
    datasource_id='instruments_CN_STOCK_A',
    start_date='',
    end_date=''
)

m24 = 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
bm_0 = where(close/shift(close,5)-1<-0.05,1,0)"""
)

m12 = M.index_feature_extract.v3(
    input_1=m9.data,
    input_2=m24.data,
    before_days=100,
    index='000300.HIX'
)

m26 = M.select_columns.v3(
    input_ds=m12.data_1,
    columns='date,bm_0',
    reverse_select=False
)

m25 = M.join.v3(
    data1=m22.data,
    data2=m26.data,
    on='date',
    how='left',
    sort=True
)

m27 = M.join.v3(
    data1=m11.data,
    data2=m25.data,
    on='date,instrument',
    how='left',
    sort=True
)

m19 = M.sort.v4(
    input_ds=m27.data,
    sort_by='date,position',
    group_by='--',
    keep_columns='--',
    ascending=True
)

m4 = M.trade.v4(
    instruments=m9.data,
    options_data=m19.sorted_data,
    start_date='',
    end_date='',
    initialize=m4_initialize_bigquant_run,
    handle_data=m4_handle_data_bigquant_run,
    prepare=m4_prepare_bigquant_run,
    before_trading_start=m4_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000001,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark=''
)

[2021-10-29 09:49:18.457446] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-29 09:49:18.484770] INFO: moduleinvoker: 命中缓存

[2021-10-29 09:49:18.487533] INFO: moduleinvoker: instruments.v2 运行完成[0.030094s].

[2021-10-29 09:49:18.505868] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-29 09:49:20.961981] INFO: 自动标注(股票): 加载历史数据: 2647809 行

[2021-10-29 09:49:20.964646] INFO: 自动标注(股票): 开始标注 ..

[2021-10-29 09:49:24.725732] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[6.21987s].

[2021-10-29 09:49:24.735320] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-29 09:49:24.741496] INFO: moduleinvoker: 命中缓存

[2021-10-29 09:49:24.743069] INFO: moduleinvoker: input_features.v1 运行完成[0.007765s].

[2021-10-29 09:49:24.761537] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-29 09:49:30.417615] INFO: 基础特征抽取: 年份 2018, 特征行数=816987

[2021-10-29 09:49:38.334725] INFO: 基础特征抽取: 年份 2019, 特征行数=884867

[2021-10-29 09:49:45.346226] INFO: 基础特征抽取: 年份 2020, 特征行数=945961

[2021-10-29 09:49:45.491529] INFO: 基础特征抽取: 总行数: 2647815

[2021-10-29 09:49:45.501832] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[20.740296s].

[2021-10-29 09:49:45.516166] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 09:49:51.322137] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.009s

[2021-10-29 09:49:51.331671] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.008s

[2021-10-29 09:49:51.338119] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.005s

[2021-10-29 09:49:51.344305] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.005s

[2021-10-29 09:49:51.350482] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.005s

[2021-10-29 09:49:51.356623] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.005s

[2021-10-29 09:49:53.288871] INFO: derived_feature_extractor: /y_2018, 816987

[2021-10-29 09:49:55.656155] INFO: derived_feature_extractor: /y_2019, 884867

[2021-10-29 09:49:58.071117] INFO: derived_feature_extractor: /y_2020, 945961

[2021-10-29 09:49:58.908539] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[13.392351s].

[2021-10-29 09:49:58.926603] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-29 09:50:07.257243] INFO: join: /y_2018, 行数=813508/816987, 耗时=3.635453s

[2021-10-29 09:50:11.049156] INFO: join: /y_2019, 行数=881288/884867, 耗时=3.783s

[2021-10-29 09:50:15.058596] INFO: join: /y_2020, 行数=919362/945961, 耗时=4.001766s

[2021-10-29 09:50:15.230341] INFO: join: 最终行数: 2614158

[2021-10-29 09:50:15.250717] INFO: moduleinvoker: join.v3 运行完成[16.324093s].

[2021-10-29 09:50:15.270616] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-10-29 09:50:16.968917] INFO: dropnan: /y_2018, 811828/813508

[2021-10-29 09:50:18.749980] INFO: dropnan: /y_2019, 877946/881288

[2021-10-29 09:50:20.549504] INFO: dropnan: /y_2020, 911045/919362

[2021-10-29 09:50:20.711712] INFO: dropnan: 行数: 2600819/2614158

[2021-10-29 09:50:20.722894] INFO: moduleinvoker: dropnan.v1 运行完成[5.452299s].

[2021-10-29 09:50:20.740717] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2021-10-29 09:50:24.434872] INFO: StockRanker: 特征预处理 ..

[2021-10-29 09:50:29.518739] INFO: StockRanker: prepare data: training ..

[2021-10-29 09:50:34.235913] INFO: StockRanker: sort ..

[2021-10-29 09:51:12.096680] INFO: StockRanker训练: 93166822 准备训练: 2600819 行数

[2021-10-29 09:51:12.099096] INFO: StockRanker训练: AI模型训练，将在2600819*13=3381.06万数据上对模型训练进行20轮迭代训练。预计将需要11～21分钟。请耐心等待。

[2021-10-29 09:51:12.317849] INFO: StockRanker训练: 正在训练 ..

[2021-10-29 09:51:12.370237] INFO: StockRanker训练: 任务状态: Pending

[2021-10-29 09:51:22.417502] INFO: StockRanker训练: 任务状态: Running

[2021-10-29 09:51:42.494939] INFO: StockRanker训练: 00:00:20.9375499, finished iteration 1

[2021-10-29 09:52:02.575154] INFO: StockRanker训练: 00:00:38.4514551, finished iteration 2

[2021-10-29 09:52:12.635136] INFO: StockRanker训练: 00:00:56.6991087, finished iteration 3

[2021-10-29 09:52:32.717293] INFO: StockRanker训练: 00:01:15.6431722, finished iteration 4

[2021-10-29 09:53:02.852912] INFO: StockRanker训练: 00:01:37.1223680, finished iteration 5

[2021-10-29 09:53:22.940617] INFO: StockRanker训练: 00:01:59.5665988, finished iteration 6

[2021-10-29 09:53:43.019375] INFO: StockRanker训练: 00:02:23.1281866, finished iteration 7

[2021-10-29 09:54:13.156873] INFO: StockRanker训练: 00:02:48.5245576, finished iteration 8

[2021-10-29 09:54:33.241008] INFO: StockRanker训练: 00:03:15.3068743, finished iteration 9

[2021-10-29 09:55:03.358911] INFO: StockRanker训练: 00:03:43.0089859, finished iteration 10

[2021-10-29 09:55:33.513412] INFO: StockRanker训练: 00:04:11.2818382, finished iteration 11

[2021-10-29 09:55:53.599477] INFO: StockRanker训练: 00:04:37.0387046, finished iteration 12

[2021-10-29 09:56:23.736339] INFO: StockRanker训练: 00:05:01.5441784, finished iteration 13

[2021-10-29 09:56:43.864160] INFO: StockRanker训练: 00:05:25.8305236, finished iteration 14

[2021-10-29 09:57:14.008281] INFO: StockRanker训练: 00:05:50.5965207, finished iteration 15

[2021-10-29 09:57:34.098824] INFO: StockRanker训练: 00:06:14.6779165, finished iteration 16

[2021-10-29 09:58:04.219058] INFO: StockRanker训练: 00:06:39.1891665, finished iteration 17

[2021-10-29 09:58:24.300676] INFO: StockRanker训练: 00:07:04.1792850, finished iteration 18

[2021-10-29 09:58:54.436999] INFO: StockRanker训练: 00:07:29.1532218, finished iteration 19

[2021-10-29 09:59:14.506236] INFO: StockRanker训练: 00:07:53.9624861, finished iteration 20

[2021-10-29 09:59:14.508720] INFO: StockRanker训练: 任务状态: Succeeded

[2021-10-29 09:59:14.730435] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[533.989708s].

[2021-10-29 09:59:14.735671] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-29 09:59:14.744357] INFO: moduleinvoker: 命中缓存

[2021-10-29 09:59:14.745968] INFO: moduleinvoker: input_features.v1 运行完成[0.010306s].

[2021-10-29 09:59:14.751213] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-29 09:59:14.764716] INFO: moduleinvoker: 命中缓存

[2021-10-29 09:59:14.768596] INFO: moduleinvoker: instruments.v2 运行完成[0.017366s].

[2021-10-29 09:59:14.790952] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-29 09:59:21.577870] INFO: 基础特征抽取: 年份 2021, 特征行数=826898

[2021-10-29 09:59:21.644997] INFO: 基础特征抽取: 总行数: 826898

[2021-10-29 09:59:21.652101] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[6.861196s].

[2021-10-29 09:59:21.665036] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 09:59:23.720053] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.003s

[2021-10-29 09:59:23.724434] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.003s

[2021-10-29 09:59:23.727648] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.002s

[2021-10-29 09:59:23.730881] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.002s

[2021-10-29 09:59:23.733966] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.002s

[2021-10-29 09:59:23.736957] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.002s

[2021-10-29 09:59:25.578097] INFO: derived_feature_extractor: /y_2021, 826898

[2021-10-29 09:59:26.329188] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[4.664137s].

[2021-10-29 09:59:26.338882] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-10-29 09:59:27.797384] INFO: dropnan: /y_2021, 818576/826898

[2021-10-29 09:59:27.886609] INFO: dropnan: 行数: 818576/826898

[2021-10-29 09:59:27.901966] INFO: moduleinvoker: dropnan.v1 运行完成[1.563028s].

[2021-10-29 09:59:27.924239] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2021-10-29 09:59:29.056497] INFO: StockRanker预测: /y_2021 ..

[2021-10-29 09:59:31.753758] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[3.829512s].

[2021-10-29 09:59:31.836976] INFO: moduleinvoker: select_columns.v3 开始运行..

[2021-10-29 09:59:32.715006] INFO: moduleinvoker: select_columns.v3 运行完成[0.878036s].

[2021-10-29 09:59:32.726003] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-29 09:59:35.382631] INFO: join: /data, 行数=818576/818576, 耗时=2.45192s

[2021-10-29 09:59:35.441026] INFO: join: 最终行数: 818576

[2021-10-29 09:59:35.450666] INFO: moduleinvoker: join.v3 运行完成[2.724663s].

[2021-10-29 09:59:35.455316] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-29 09:59:35.464316] INFO: moduleinvoker: 命中缓存

[2021-10-29 09:59:35.467111] INFO: moduleinvoker: input_features.v1 运行完成[0.011794s].

[2021-10-29 09:59:35.489668] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2021-10-29 09:59:36.648978] INFO: moduleinvoker: use_datasource.v1 运行完成[1.159366s].

[2021-10-29 09:59:36.654070] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-29 09:59:36.670463] INFO: moduleinvoker: 命中缓存

[2021-10-29 09:59:36.673977] INFO: moduleinvoker: input_features.v1 运行完成[0.01986s].

[2021-10-29 09:59:36.717874] INFO: moduleinvoker: index_feature_extract.v3 开始运行..

[2021-10-29 09:59:36.923064] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 09:59:36.985443] INFO: derived_feature_extractor: 提取完成 bm_0 = where(close/shift(close,5)-1[2021-10-29 09:59:37.044229] INFO: derived_feature_extractor: /data, 258
[2021-10-29 09:59:37.110392] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.187309s].
[2021-10-29 09:59:37.323305] INFO: moduleinvoker: index_feature_extract.v3 运行完成[0.605428s].
[2021-10-29 09:59:37.334151] INFO: moduleinvoker: select_columns.v3 开始运行..
[2021-10-29 09:59:37.439595] INFO: moduleinvoker: select_columns.v3 运行完成[0.105433s].
[2021-10-29 09:59:37.449936] INFO: moduleinvoker: join.v3 开始运行..
[2021-10-29 09:59:40.781719] INFO: join: /data, 行数=829988/829988, 耗时=3.2505s
[2021-10-29 09:59:40.837128] INFO: join: 最终行数: 829988
[2021-10-29 09:59:40.845220] INFO: moduleinvoker: join.v3 运行完成[3.395284s].
[2021-10-29 09:59:40.859425] INFO: moduleinvoker: join.v3 开始运行..
[2021-10-29 09:59:43.688956] INFO: join: /data, 行数=818576/818576, 耗时=2.538663s
[2021-10-29 09:59:43.761284] INFO: join: 最终行数: 818576
[2021-10-29 09:59:43.781166] INFO: moduleinvoker: join.v3 运行完成[2.921725s].
[2021-10-29 09:59:43.798282] INFO: moduleinvoker: sort.v4 开始运行..
[2021-10-29 09:59:46.584866] INFO: moduleinvoker: sort.v4 运行完成[2.786611s].
[2021-10-29 09:59:48.754437] INFO: moduleinvoker: backtest.v8 开始运行..
[2021-10-29 09:59:48.761379] INFO: backtest: biglearning backtest:V8.5.0
[2021-10-29 09:59:48.763255] INFO: backtest: product_type:stock by specified
[2021-10-29 09:59:48.848055] INFO: moduleinvoker: cached.v2 开始运行..
[2021-10-29 09:59:54.285147] INFO: backtest: 读取股票行情完成:1913508
[2021-10-29 09:59:58.499536] INFO: moduleinvoker: cached.v2 运行完成[9.651447s].
[2021-10-29 10:00:00.686365] INFO: algo: TradingAlgorithm V1.8.5
[2021-10-29 10:00:01.690563] INFO: algo: trading transform...
[2021-10-29 10:01:54.647396] INFO: Performance: Simulated 192 trading days out of 192.
[2021-10-29 10:01:54.648883] INFO: Performance: first open: 2021-01-04 09:30:00+00:00
[2021-10-29 10:01:54.649966] INFO: Performance: last close: 2021-10-21 15:00:00+00:00
[2021-10-29 10:01:59.649431] INFO: moduleinvoker: backtest.v8 运行完成[130.895s].
[2021-10-29 10:01:59.651156] INFO: moduleinvoker: trade.v4 运行完成[133.045937s].

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-046b042286ab422f95a20461b89b0871"}/bigcharts-data-end

列： ['date', 'instrument', 'price_limit_status_0']
/y_2021: 818576

列： ['date', 'bm_0']
/data: 258

在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
2021-02-24 大盘风控止损触发,全仓卖出
2021-02-25 大盘风控止损触发,全仓卖出
2021-02-26 大盘风控止损触发,全仓卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
2021-03-08 大盘风控止损触发,全仓卖出
2021-03-09 大盘风控止损触发,全仓卖出
2021-03-10 大盘风控止损触发,全仓卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
在这处理止损第二天开盘卖出
2021-07-27 大盘风控止损触发,全仓卖出
2021-07-28 大盘风控止损触发,全仓卖出
2021-07-29 大盘风控止损触发,全仓卖出
2021-07-30 大盘风控止损触发,全仓卖出

收益率26.82%
年化收益率36.6%
基准收益率-5.44%
阿尔法0.42
贝塔0.35
夏普比率1.12
胜率0.5
盈亏比1.32
收益波动率29.0%
信息比率0.08
最大回撤14.34%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-14d47802412a49f39a836aff77ce0e84"}/bigcharts-data-end