复制链接

克隆策略

大盘风控功能¶

版本v1.0

在开发策略时，经常需要根据大盘指数计算相关技术指标来进行仓位风险控制。

本策略以上证指数5日累计涨幅作为风险控制指标，如果5日累计涨幅小于-4%，则执行清仓止损。

功能实现步骤：

1、新建AI可视化模板策略

2、在回测/模拟模块m19的属性栏中进入“数据准备函数”代码框，在函数体中计算上证指数000001.HIX在回测起止时间段内的5日涨幅指标，同时计算风控信号risk指标保存在context.benckmark_risk变量中：

3、在回测/模拟模块m19的属性栏中进入“主函数”代码框，在函数体中最前端获取当日的风控信号benckmark_risk指标, 如果满足风控条件则将持仓全部卖出后通过return语句返回，结束当天交易实现风险控制功能。

In [8]:

# 本代码由可视化策略环境自动生成 2022年4月12日 13:01
# 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):
    # 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 = 5
    # 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 = 0.5
    context.options['hold_days'] = 10

# 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):
    #获取当日日期
    today = data.current_dt.strftime('%Y-%m-%d')
    stock_hold_now = [equity.symbol for equity in context.portfolio.positions ]
    #大盘风控模块，读取风控数据    
    benckmark_risk=context.benckmark_risk[today]
    context.symbol
    #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 stock_hold_now:
            context.order_target(symbol(instrument), 0)
        print(today,'大盘风控止损触发,全仓卖出')
        return
 
    # 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: e 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('rank order for sell %s' % instruments)
        for instrument in instruments:
            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)])
    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 m19_prepare_bigquant_run(context):
    #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=50)).strftime('%Y-%m-%d') 
    df=DataSource('bar1d_index_CN_STOCK_A').read(start_date=start_date,end_date=context.end_date,fields=['close'])
    benckmark_data=df[df.instrument=='000300.HIX']
    #计算上证指数5日涨幅
    benckmark_data['ret5']=benckmark_data['close']/benckmark_data['close'].shift(5)-1
    #计算大盘风控条件，如果5日涨幅小于-4%则设置风险状态risk为1，否则为0
    benckmark_data['risk'] = np.where(benckmark_data['ret5']<-0.04,1,0)
    #修改日期格式为字符串(便于在handle中使用字符串日期索引来查看每日的风险状态)
    benckmark_data['date']=benckmark_data['date'].apply(lambda x:x.strftime('%Y-%m-%d'))
    #设置日期为索引
    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['risk']



g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2015-01-01',
    'm1.end_date': '2018-01-01',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.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)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.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
ta_wma_5_0
mean(volume_0,90)
fs_net_cash_flow_0/fs_paicl_up_capital_0
mean(volume_0,5)
fs_net_cash_flow_ttm_0
pb_lf_0
fs_operating_revenue_ttm_0/(fs_total_liability_0+fs_total_equity_0)
beta_gem_30_0
""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 0,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m3.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': False,
    'm16.remove_extra_columns': False,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m2.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm6': 'M.filter_delist_stock.v4',
    'm6.input_1': T.Graph.OutputPort('m7.data'),

    'm11': 'M.filtet_st_stock.v2',
    'm11.input_1': T.Graph.OutputPort('m6.data_1'),

    'm5': 'M.dropnan.v2',
    'm5.input_data': T.Graph.OutputPort('m11.data_1'),

    'm4': 'M.stock_ranker_train.v6',
    'm4.training_ds': T.Graph.OutputPort('m5.data'),
    'm4.features': T.Graph.OutputPort('m3.data'),
    'm4.learning_algorithm': '排序',
    'm4.number_of_leaves': 30,
    'm4.minimum_docs_per_leaf': 1000,
    'm4.number_of_trees': 20,
    'm4.learning_rate': 0.1,
    'm4.max_bins': 1023,
    'm4.feature_fraction': 1,
    'm4.data_row_fraction': 1,
    'm4.plot_charts': True,
    'm4.ndcg_discount_base': 1,
    'm4.m_lazy_run': False,

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2018-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2020-12-31'),
    'm9.market': 'CN_STOCK_A',
    'm9.instrument_list': '',
    'm9.max_count': 0,

    'm17': 'M.general_feature_extractor.v7',
    'm17.instruments': T.Graph.OutputPort('m9.data'),
    'm17.features': T.Graph.OutputPort('m3.data'),
    'm17.start_date': '',
    'm17.end_date': '',
    'm17.before_start_days': 60,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m17.data'),
    'm18.features': T.Graph.OutputPort('m3.data'),
    'm18.date_col': 'date',
    'm18.instrument_col': 'instrument',
    'm18.drop_na': False,
    'm18.remove_extra_columns': False,

    'm12': 'M.filter_delist_stock.v4',
    'm12.input_1': T.Graph.OutputPort('m18.data'),

    'm13': 'M.filtet_st_stock.v2',
    'm13.input_1': T.Graph.OutputPort('m12.data_1'),

    'm10': 'M.dropnan.v2',
    'm10.input_data': T.Graph.OutputPort('m13.data_1'),

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m4.model'),
    'm8.data': T.Graph.OutputPort('m10.data'),
    'm8.m_lazy_run': False,

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m8.predictions'),
    'm19.start_date': '2020-01-01',
    'm19.end_date': '2021-12-31',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.prepare': m19_prepare_bigquant_run,
    'm19.volume_limit': 0.025,
    'm19.order_price_field_buy': 'open',
    'm19.order_price_field_sell': 'close',
    'm19.capital_base': 1000000,
    'm19.auto_cancel_non_tradable_orders': True,
    'm19.data_frequency': 'daily',
    'm19.price_type': '后复权',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '000300.HIX',
})

# g.run({})


def m14_run_bigquant_run(
    bq_graph,
    inputs,
    trading_days_market='CN', # 使用那个市场的交易日历, TODO
    train_instruments_mid='m1', # 训练数据 证券代码列表 模块id
    test_instruments_mid='m9', # 测试数据 证券代码列表 模块id
    predict_mid='m8', # 预测 模块id
    trade_mid='m19', # 回测 模块id
    start_date='2014-01-01', # 数据开始日期
    end_date=T.live_run_param('trading_date', '2017-01-01'), # 数据结束日期
    train_update_days=250, # 更新周期，按交易日计算，每多少天更新一次
    train_update_days_for_live=None, #模拟实盘模式下的更新周期，按交易日计算，每多少天更新一次。如果需要在模拟实盘阶段使用不同的模型更新周期，可以设置这个参数
    train_data_min_days=250, # 最小数据天数，按交易日计算，所以第一个滚动的结束日期是 从开始日期到开始日期+最小数据天数
    train_data_max_days=250, # 最大数据天数，按交易日计算，0，表示没有限制，否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期
    rolling_count_for_live=1, #实盘模式下滚动次数，模拟实盘模式下，取最后多少次滚动。一般在模拟实盘模式下，只用到最后一次滚动训练的模型，这里可以设置为1；如果你的滚动训练数据时间段很短，以至于期间可能没有训练数据，这里可以设置大一点。0表示没有限制
):
    def merge_datasources(input_1):
        df_list = [ds[0].read_df().set_index('date').loc[ds[1]:].reset_index() for ds in input_1]
        df = pd.concat(df_list)
        instrument_data = {
            'start_date': df['date'].min().strftime('%Y-%m-%d'),
            'end_date': df['date'].max().strftime('%Y-%m-%d'),
            'instruments': list(set(df['instrument'])),
        }
        return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))

    def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):
        # 是否实盘模式
        tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])
        is_live_run = T.live_run_param('trading_date', None) is not None

        if is_live_run and train_update_days_for_live:
            train_update_days = train_update_days_for_live

        rollings = []
        train_end_date = train_data_min_days
        while train_end_date < len(tdays):
            if train_data_max_days is not None and train_data_max_days > 0:
                train_start_date = max(train_end_date - train_data_max_days, 0)
            else:
                train_start_date = 0
            rollings.append({
                'train_start_date': tdays[train_start_date].strftime('%Y-%m-%d'),
                'train_end_date': tdays[train_end_date - 1].strftime('%Y-%m-%d'),
                'test_start_date': tdays[train_end_date].strftime('%Y-%m-%d'),
                'test_end_date': tdays[min(train_end_date + train_update_days, len(tdays)) - 1].strftime('%Y-%m-%d'),
            })
            train_end_date += train_update_days

        if not rollings:
            raise Exception('没有滚动需要执行，请检查配置')

        if is_live_run and rolling_count_for_live:
            rollings = rollings[-rolling_count_for_live:]

        return rollings

    g = bq_graph

    rolling_dates = gen_rolling_dates(
        trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)

    # 训练和预测
    results = []
    for rolling in rolling_dates:
        parameters = {}
        # 先禁用回测
        parameters[trade_mid + '.__enabled__'] = False
        parameters[train_instruments_mid + '.start_date'] = rolling['train_start_date']
        parameters[train_instruments_mid + '.end_date'] = rolling['train_end_date']
        parameters[test_instruments_mid + '.start_date'] = rolling['test_start_date']
        parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']
        # print('------ rolling_train:', parameters)
        results.append(g.run(parameters))

    # 合并预测结果并回测
    mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].predictions, result[test_instruments_mid].data.read_pickle()['start_date']] for result in results])
    parameters = {}
    parameters['*.__enabled__'] = False
    parameters[trade_mid + '.__enabled__'] = True
    parameters[trade_mid + '.instruments'] = mx.instrument_data
    parameters[trade_mid + '.options_data'] = mx.data

    trade = g.run(parameters)

    return {'rollings': results, 'trade': trade}


m14 = M.hyper_rolling_train.v1(
    run=m14_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2022-04-12 12:48:27.889501] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-04-12 12:48:28.009527] INFO: moduleinvoker: instruments.v2 运行完成[0.119994s].

[2022-04-12 12:48:28.020684] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-04-12 12:48:28.030547] INFO: moduleinvoker: 命中缓存

[2022-04-12 12:48:28.032415] INFO: moduleinvoker: input_features.v1 运行完成[0.011787s].

[2022-04-12 12:48:28.038722] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-04-12 12:48:28.148281] INFO: moduleinvoker: instruments.v2 运行完成[0.109543s].

[2022-04-12 12:48:28.159858] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-04-12 12:48:29.120062] INFO: 自动标注(股票): 加载历史数据: 581647 行

[2022-04-12 12:48:29.122469] INFO: 自动标注(股票): 开始标注 ..

[2022-04-12 12:48:30.133368] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[1.97349s].

[2022-04-12 12:48:30.152519] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-04-12 12:48:59.184539] INFO: 基础特征抽取: 年份 2014, 特征行数=569948

[2022-04-12 12:49:06.716442] INFO: 基础特征抽取: 年份 2015, 特征行数=11699

[2022-04-12 12:49:06.778846] INFO: 基础特征抽取: 总行数: 581647

[2022-04-12 12:49:06.785460] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[36.632947s].

[2022-04-12 12:49:06.824271] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-04-12 12:49:20.779577] INFO: 基础特征抽取: 年份 2014, 特征行数=81185

[2022-04-12 12:49:29.155472] INFO: 基础特征抽取: 年份 2015, 特征行数=569698

[2022-04-12 12:49:37.261908] INFO: 基础特征抽取: 年份 2016, 特征行数=28050

[2022-04-12 12:49:37.337307] INFO: 基础特征抽取: 总行数: 678933

[2022-04-12 12:49:37.342794] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[30.518548s].

[2022-04-12 12:49:37.359345] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-04-12 12:49:40.321435] INFO: derived_feature_extractor: 提取完成 mean(volume_0,90), 0.546s

[2022-04-12 12:49:40.326401] INFO: derived_feature_extractor: 提取完成 fs_net_cash_flow_0/fs_paicl_up_capital_0, 0.003s

[2022-04-12 12:49:40.867345] INFO: derived_feature_extractor: 提取完成 mean(volume_0,5), 0.539s

[2022-04-12 12:49:40.874615] INFO: derived_feature_extractor: 提取完成 fs_operating_revenue_ttm_0/(fs_total_liability_0+fs_total_equity_0), 0.005s

[2022-04-12 12:50:14.681334] INFO: derived_feature_extractor: /y_2014, 569948

[2022-04-12 12:50:50.850737] INFO: derived_feature_extractor: /y_2015, 11699

[2022-04-12 12:50:51.152052] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[73.792688s].

[2022-04-12 12:50:51.164471] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-04-12 12:51:19.858132] INFO: derived_feature_extractor: 提取完成 mean(volume_0,90), 0.669s

[2022-04-12 12:51:19.867881] INFO: derived_feature_extractor: 提取完成 fs_net_cash_flow_0/fs_paicl_up_capital_0, 0.006s

[2022-04-12 12:51:20.566870] INFO: derived_feature_extractor: 提取完成 mean(volume_0,5), 0.696s

[2022-04-12 12:51:20.574156] INFO: derived_feature_extractor: 提取完成 fs_operating_revenue_ttm_0/(fs_total_liability_0+fs_total_equity_0), 0.005s

[2022-04-12 12:51:43.946881] INFO: derived_feature_extractor: /y_2014, 81185

[2022-04-12 12:51:51.965232] INFO: derived_feature_extractor: /y_2015, 569698

[2022-04-12 12:51:57.299261] INFO: derived_feature_extractor: /y_2016, 28050

[2022-04-12 12:51:57.515929] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[66.351442s].

[2022-04-12 12:51:57.527867] INFO: moduleinvoker: join.v3 开始运行..

[2022-04-12 12:52:59.843423] INFO: join: /y_2014, 行数=566797/569948, 耗时=61.162724s

[2022-04-12 12:53:00.128093] INFO: join: /y_2015, 行数=0/11699, 耗时=0.269077s

[2022-04-12 12:53:00.204945] INFO: join: 最终行数: 566797

[2022-04-12 12:53:00.220303] INFO: moduleinvoker: join.v3 运行完成[62.692418s].

[2022-04-12 12:53:00.240047] INFO: moduleinvoker: filter_delist_stock.v4 开始运行..

[2022-04-12 12:53:05.140320] INFO: moduleinvoker: filter_delist_stock.v4 运行完成[4.900268s].

[2022-04-12 12:53:05.154841] INFO: moduleinvoker: filter_delist_stock.v4 开始运行..

[2022-04-12 12:53:08.224466] INFO: moduleinvoker: filter_delist_stock.v4 运行完成[3.069616s].

[2022-04-12 12:53:08.240566] INFO: moduleinvoker: filtet_st_stock.v2 开始运行..

[2022-04-12 12:53:10.840598] INFO: moduleinvoker: filtet_st_stock.v2 运行完成[2.600047s].

[2022-04-12 12:53:10.853579] INFO: moduleinvoker: filtet_st_stock.v2 开始运行..

[2022-04-12 12:53:13.101580] INFO: moduleinvoker: filtet_st_stock.v2 运行完成[2.247999s].

[2022-04-12 12:53:13.113137] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-04-12 12:53:14.194320] INFO: dropnan: /data, 423239/665614

[2022-04-12 12:53:14.259688] INFO: dropnan: 行数: 423239/665614

[2022-04-12 12:53:14.275496] INFO: moduleinvoker: dropnan.v2 运行完成[1.162362s].

[2022-04-12 12:53:14.287727] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-04-12 12:53:15.369111] INFO: dropnan: /data, 333684/554162

[2022-04-12 12:53:15.434293] INFO: dropnan: 行数: 333684/554162

[2022-04-12 12:53:15.444991] INFO: moduleinvoker: dropnan.v2 运行完成[1.15726s].

[2022-04-12 12:53:15.454692] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-04-12 12:53:15.992349] INFO: StockRanker: 特征预处理 ..

[2022-04-12 12:53:16.227302] INFO: StockRanker: prepare data: training ..

[2022-04-12 12:53:16.469394] INFO: StockRanker: sort ..

[2022-04-12 12:53:21.895895] INFO: StockRanker训练: 76b093b2 准备训练: 333684 行数

[2022-04-12 12:53:21.898114] INFO: StockRanker训练: AI模型训练，将在333684*8=266.95万数据上对模型训练进行20轮迭代训练。预计将需要2～4分钟。请耐心等待。

[2022-04-12 12:53:22.101250] INFO: StockRanker训练: 正在训练 ..

[2022-04-12 12:53:22.148298] INFO: StockRanker训练: 任务状态: Pending

[2022-04-12 12:53:32.191032] INFO: StockRanker训练: 任务状态: Running

[2022-04-12 12:54:32.488875] INFO: StockRanker训练: 00:01:04.7227457, finished iteration 1

[2022-04-12 12:54:42.550961] INFO: StockRanker训练: 00:01:07.9084359, finished iteration 2

[2022-04-12 12:54:42.553574] INFO: StockRanker训练: 00:01:11.2258711, finished iteration 3

[2022-04-12 12:54:42.555853] INFO: StockRanker训练: 00:01:14.7227632, finished iteration 4

[2022-04-12 12:54:52.605357] INFO: StockRanker训练: 00:01:18.1282642, finished iteration 5

[2022-04-12 12:54:52.607418] INFO: StockRanker训练: 00:01:21.6300447, finished iteration 6

[2022-04-12 12:54:52.609038] INFO: StockRanker训练: 00:01:25.1718903, finished iteration 7

[2022-04-12 12:55:02.666429] INFO: StockRanker训练: 00:01:28.6940991, finished iteration 8

[2022-04-12 12:55:02.668211] INFO: StockRanker训练: 00:01:32.3779005, finished iteration 9

[2022-04-12 12:55:02.669510] INFO: StockRanker训练: 00:01:36.0874253, finished iteration 10

[2022-04-12 12:55:12.716586] INFO: StockRanker训练: 00:01:39.8579849, finished iteration 11

[2022-04-12 12:55:12.718717] INFO: StockRanker训练: 00:01:43.8567205, finished iteration 12

[2022-04-12 12:55:22.758389] INFO: StockRanker训练: 00:01:47.9530599, finished iteration 13

[2022-04-12 12:55:22.760709] INFO: StockRanker训练: 00:01:52.1808940, finished iteration 14

[2022-04-12 12:55:32.807118] INFO: StockRanker训练: 00:01:56.5217537, finished iteration 15

[2022-04-12 12:55:32.809490] INFO: StockRanker训练: 00:02:00.7755698, finished iteration 16

[2022-04-12 12:55:32.812374] INFO: StockRanker训练: 00:02:04.8447397, finished iteration 17

[2022-04-12 12:55:42.858290] INFO: StockRanker训练: 00:02:08.9097666, finished iteration 18

[2022-04-12 12:55:42.860053] INFO: StockRanker训练: 00:02:12.9808948, finished iteration 19

[2022-04-12 12:56:07.131464] INFO: StockRanker训练: 任务状态: Succeeded

[2022-04-12 12:56:07.505403] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[172.05075s].

[2022-04-12 12:56:07.517539] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-04-12 12:56:07.991750] INFO: StockRanker预测: /data ..

[2022-04-12 12:56:08.985579] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[1.468023s].

[2022-04-12 12:56:08.995289] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-04-12 12:56:09.006030] INFO: moduleinvoker: 命中缓存

[2022-04-12 12:56:09.009127] INFO: moduleinvoker: instruments.v2 运行完成[0.013837s].

[2022-04-12 12:56:09.016269] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-04-12 12:56:09.025760] INFO: moduleinvoker: 命中缓存

[2022-04-12 12:56:09.028013] INFO: moduleinvoker: input_features.v1 运行完成[0.011753s].

[2022-04-12 12:56:09.035358] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-04-12 12:56:09.109248] INFO: moduleinvoker: instruments.v2 运行完成[0.073895s].

[2022-04-12 12:56:09.120866] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-04-12 12:56:09.724773] INFO: 自动标注(股票): 加载历史数据: 586049 行

[2022-04-12 12:56:09.726528] INFO: 自动标注(股票): 开始标注 ..

[2022-04-12 12:56:10.445978] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[1.3251s].

[2022-04-12 12:56:10.462263] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-04-12 12:56:16.144330] INFO: 基础特征抽取: 年份 2015, 特征行数=557999

[2022-04-12 12:56:20.528911] INFO: 基础特征抽取: 年份 2016, 特征行数=28050

[2022-04-12 12:56:20.596601] INFO: 基础特征抽取: 总行数: 586049

[2022-04-12 12:56:20.602798] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[10.140549s].

[2022-04-12 12:56:20.617729] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-04-12 12:56:24.945307] INFO: 基础特征抽取: 年份 2015, 特征行数=74873

[2022-04-12 12:56:30.557188] INFO: 基础特征抽取: 年份 2016, 特征行数=641546

[2022-04-12 12:56:30.746668] INFO: 基础特征抽取: 总行数: 716419

[2022-04-12 12:56:30.754193] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[10.136471s].

[2022-04-12 12:56:30.763047] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-04-12 12:56:32.720035] INFO: derived_feature_extractor: 提取完成 mean(volume_0,90), 0.541s

[2022-04-12 12:56:32.726590] INFO: derived_feature_extractor: 提取完成 fs_net_cash_flow_0/fs_paicl_up_capital_0, 0.003s

[2022-04-12 12:56:33.177095] INFO: derived_feature_extractor: 提取完成 mean(volume_0,5), 0.449s

[2022-04-12 12:56:33.182435] INFO: derived_feature_extractor: 提取完成 fs_operating_revenue_ttm_0/(fs_total_liability_0+fs_total_equity_0), 0.003s

[2022-04-12 12:56:34.427756] INFO: derived_feature_extractor: /y_2015, 557999

[2022-04-12 12:56:34.909939] INFO: derived_feature_extractor: /y_2016, 28050

[2022-04-12 12:56:35.048191] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[4.285127s].

[2022-04-12 12:56:35.057098] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-04-12 12:56:37.434958] INFO: derived_feature_extractor: 提取完成 mean(volume_0,90), 0.669s

[2022-04-12 12:56:37.440011] INFO: derived_feature_extractor: 提取完成 fs_net_cash_flow_0/fs_paicl_up_capital_0, 0.003s

[2022-04-12 12:56:38.144257] INFO: derived_feature_extractor: 提取完成 mean(volume_0,5), 0.702s

[2022-04-12 12:56:38.150134] INFO: derived_feature_extractor: 提取完成 fs_operating_revenue_ttm_0/(fs_total_liability_0+fs_total_equity_0), 0.004s

[2022-04-12 12:56:38.450471] INFO: derived_feature_extractor: /y_2015, 74873

[2022-04-12 12:56:39.776594] INFO: derived_feature_extractor: /y_2016, 641546

[2022-04-12 12:56:40.336556] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[5.279445s].

[2022-04-12 12:56:40.350449] INFO: moduleinvoker: join.v3 开始运行..

[2022-04-12 12:56:43.414906] INFO: join: /y_2015, 行数=547850/557999, 耗时=1.898438s

[2022-04-12 12:56:43.685234] INFO: join: /y_2016, 行数=14954/28050, 耗时=0.265325s

[2022-04-12 12:56:43.760388] INFO: join: 最终行数: 562804

[2022-04-12 12:56:43.775253] INFO: moduleinvoker: join.v3 运行完成[3.424794s].

[2022-04-12 12:56:43.794053] INFO: moduleinvoker: filter_delist_stock.v4 开始运行..

[2022-04-12 12:56:46.976859] INFO: moduleinvoker: filter_delist_stock.v4 运行完成[3.182821s].

[2022-04-12 12:56:46.988856] INFO: moduleinvoker: filter_delist_stock.v4 开始运行..

[2022-04-12 12:56:49.799680] INFO: moduleinvoker: filter_delist_stock.v4 运行完成[2.810766s].

[2022-04-12 12:56:49.816737] INFO: moduleinvoker: filtet_st_stock.v2 开始运行..

[2022-04-12 12:56:52.041570] INFO: moduleinvoker: filtet_st_stock.v2 运行完成[2.224854s].

[2022-04-12 12:56:52.052887] INFO: moduleinvoker: filtet_st_stock.v2 开始运行..

[2022-04-12 12:56:54.317684] INFO: moduleinvoker: filtet_st_stock.v2 运行完成[2.264725s].

[2022-04-12 12:56:54.329656] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-04-12 12:56:55.668979] INFO: dropnan: /data, 445156/702179

[2022-04-12 12:56:55.729904] INFO: dropnan: 行数: 445156/702179

[2022-04-12 12:56:55.742607] INFO: moduleinvoker: dropnan.v2 运行完成[1.412962s].

[2022-04-12 12:56:55.752437] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-04-12 12:56:56.706379] INFO: dropnan: /data, 316327/552334

[2022-04-12 12:56:56.772252] INFO: dropnan: 行数: 316327/552334

[2022-04-12 12:56:56.782715] INFO: moduleinvoker: dropnan.v2 运行完成[1.030268s].

[2022-04-12 12:56:56.790746] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-04-12 12:56:57.397266] INFO: StockRanker: 特征预处理 ..

[2022-04-12 12:56:57.679991] INFO: StockRanker: prepare data: training ..

[2022-04-12 12:56:57.919405] INFO: StockRanker: sort ..

[2022-04-12 12:57:02.019257] INFO: StockRanker训练: fa9c222c 准备训练: 316327 行数

[2022-04-12 12:57:02.021682] INFO: StockRanker训练: AI模型训练，将在316327*8=253.06万数据上对模型训练进行20轮迭代训练。预计将需要2～3分钟。请耐心等待。

[2022-04-12 12:57:02.204980] INFO: StockRanker训练: 正在训练 ..

[2022-04-12 12:57:02.256021] INFO: StockRanker训练: 任务状态: Pending

[2022-04-12 12:57:12.302499] INFO: StockRanker训练: 任务状态: Running

[2022-04-12 12:58:12.614390] INFO: StockRanker训练: 00:01:04.1988338, finished iteration 1

[2022-04-12 12:58:22.663431] INFO: StockRanker训练: 00:01:06.7044409, finished iteration 2

[2022-04-12 12:58:22.665152] INFO: StockRanker训练: 00:01:09.2662601, finished iteration 3

[2022-04-12 12:58:22.666682] INFO: StockRanker训练: 00:01:12.0904306, finished iteration 4

[2022-04-12 12:58:22.668273] INFO: StockRanker训练: 00:01:14.7738225, finished iteration 5

[2022-04-12 12:58:32.712829] INFO: StockRanker训练: 00:01:17.4982157, finished iteration 6

[2022-04-12 12:58:32.714719] INFO: StockRanker训练: 00:01:20.2865553, finished iteration 7

[2022-04-12 12:58:32.716279] INFO: StockRanker训练: 00:01:23.5805005, finished iteration 8

[2022-04-12 12:58:42.760477] INFO: StockRanker训练: 00:01:26.7905164, finished iteration 9

[2022-04-12 12:58:42.762212] INFO: StockRanker训练: 00:01:30.2866889, finished iteration 10

[2022-04-12 12:58:42.763832] INFO: StockRanker训练: 00:01:34.0717130, finished iteration 11

[2022-04-12 12:58:52.806965] INFO: StockRanker训练: 00:01:37.0952408, finished iteration 12

[2022-04-12 12:58:52.809216] INFO: StockRanker训练: 00:01:40.3287932, finished iteration 13

[2022-04-12 12:58:52.810945] INFO: StockRanker训练: 00:01:44.6920449, finished iteration 14

[2022-04-12 12:59:02.860911] INFO: StockRanker训练: 00:01:48.0006448, finished iteration 15

[2022-04-12 12:59:02.862948] INFO: StockRanker训练: 00:01:50.9416003, finished iteration 16

[2022-04-12 12:59:02.864722] INFO: StockRanker训练: 00:01:53.8072615, finished iteration 17

[2022-04-12 12:59:12.968457] INFO: StockRanker训练: 00:01:56.9817603, finished iteration 18

[2022-04-12 12:59:12.970653] INFO: StockRanker训练: 00:02:00.1468818, finished iteration 19

[2022-04-12 12:59:12.972372] INFO: StockRanker训练: 00:02:03.4869882, finished iteration 20

[2022-04-12 12:59:23.026158] INFO: StockRanker训练: 任务状态: Succeeded

[2022-04-12 12:59:23.173763] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[146.382998s].

[2022-04-12 12:59:23.184099] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-04-12 12:59:23.589092] INFO: StockRanker预测: /data ..

[2022-04-12 12:59:24.811905] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[1.627791s].

[2022-04-12 12:59:24.852807] INFO: moduleinvoker: cached.v3 开始运行..

[2022-04-12 12:59:26.025227] INFO: moduleinvoker: cached.v3 运行完成[1.172437s].

[2022-04-12 12:59:26.081949] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-04-12 12:59:26.088208] INFO: backtest: biglearning backtest:V8.6.2

[2022-04-12 12:59:26.184707] INFO: backtest: product_type:stock by specified

[2022-04-12 12:59:26.271777] INFO: moduleinvoker: cached.v2 开始运行..

[2022-04-12 12:59:33.338987] INFO: backtest: 读取股票行情完成:2307626

[2022-04-12 12:59:36.354284] INFO: moduleinvoker: cached.v2 运行完成[10.082529s].

[2022-04-12 12:59:38.526858] INFO: algo: TradingAlgorithm V1.8.7

[2022-04-12 12:59:39.471698] INFO: algo: trading transform...

[2022-04-12 12:59:42.603331] INFO: Performance: Simulated 486 trading days out of 486.

[2022-04-12 12:59:42.607286] INFO: Performance: first open: 2020-01-02 09:30:00+00:00

[2022-04-12 12:59:42.609257] INFO: Performance: last close: 2021-12-31 15:00:00+00:00

[2022-04-12 12:59:45.944090] INFO: moduleinvoker: backtest.v8 运行完成[19.86216s].

[2022-04-12 12:59:45.946346] INFO: moduleinvoker: trade.v4 运行完成[19.910617s].

[2022-04-12 12:59:45.948146] INFO: moduleinvoker: hyper_rolling_train.v1 运行完成[678.092558s].

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-4db52244911f435ba2710493e6dbe1fc"}/bigcharts-data-end

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-7e10d8ccc57043e7b22b8cbbf68f304f"}/bigcharts-data-end

2020-02-03 大盘风控止损触发,全仓卖出
2020-02-04 大盘风控止损触发,全仓卖出
2020-02-05 大盘风控止损触发,全仓卖出
2020-02-06 大盘风控止损触发,全仓卖出
2020-02-28 大盘风控止损触发,全仓卖出
2020-03-12 大盘风控止损触发,全仓卖出
2020-03-13 大盘风控止损触发,全仓卖出
2020-03-16 大盘风控止损触发,全仓卖出
2020-03-17 大盘风控止损触发,全仓卖出
2020-03-18 大盘风控止损触发,全仓卖出
2020-03-19 大盘风控止损触发,全仓卖出
2020-03-20 大盘风控止损触发,全仓卖出
2020-03-23 大盘风控止损触发,全仓卖出
2020-07-16 大盘风控止损触发,全仓卖出
2020-07-17 大盘风控止损触发,全仓卖出
2020-09-09 大盘风控止损触发,全仓卖出
2020-09-10 大盘风控止损触发,全仓卖出
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
2021-03-02 大盘风控止损触发,全仓卖出
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
2021-03-25 大盘风控止损触发,全仓卖出
2021-04-12 大盘风控止损触发,全仓卖出
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
2021-08-17 大盘风控止损触发,全仓卖出
2021-12-20 大盘风控止损触发,全仓卖出

收益率0.0%
年化收益率0.0%
基准收益率20.6%
阿尔法-0.03
贝塔0.0
夏普比率n/a
胜率0.0
盈亏比0.0
收益波动率0.0%
信息比率-0.04
最大回撤0.0%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-7a614fe8771e4defa2f761b7ca6a314f"}/bigcharts-data-end