克隆策略

In [7]:

Out[7]:

TabNet在量化选股中的应用¶

TabNet: Attentive Interpretable Tabular Learning

基于Tabnet模型的量化选股方案。抽取了98个量价因子，2010到2018年为数据训练TabNet模型，并将模型的预测结果应用在2018到2021年9月的数据上进行了回测。

TabNet核心参数

input_dim: 输入的特征数
n_steps: 决策的步数，通常为{3 ~ 10}
n_d: 预测阶段的特征数，通常为{8 ~ 64}
n_a: Attentive阶段的特征数，通常为{8 ~ 64}
gamma: Attentive中注意力更新的比例，通常为{1.0 ~ 2.0}
momentum: BN层的动量，通常为{0.0 ~ 1.0}

In [8]:

# 本代码由可视化策略环境自动生成 2021年10月11日 13:40
# 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 m12_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    from sklearn.model_selection import train_test_split
    data = input_1.read()
    x_train, x_val, y_train, y_val = train_test_split(data["x"], data['y'], shuffle=False, random_state=2021)
    data_1 = DataSource.write_pickle({'x': x_train, 'y': y_train.reshape(-1, 1)})
    data_2 = DataSource.write_pickle({'x': x_val, 'y': y_val.reshape(-1, 1)})
    return Outputs(data_1=data_1, data_2=data_2, 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 m12_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 m20_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    pred_label = input_1.read_pickle()
    df = input_2.read_df()
    df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})
    df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])
    return Outputs(data_1=DataSource.write_df(df), 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 m20_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m21_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=0.001, sell_cost=0.001, 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 = 20
    # 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 = 0.2
    context.options['hold_days'] = 5

# 回测引擎：每日数据处理函数，每天执行一次
def m21_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
    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 m21_prepare_bigquant_run(context):
    pass


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2017-01-01',
    'm1.end_date': '2019-12-31',
    '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)-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))

# 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': False,

    'm17': 'M.standardlize.v8',
    'm17.input_1': T.Graph.OutputPort('m2.data'),
    'm17.columns_input': 'label',

    'm3': 'M.input_features.v1',
    'm3.features': """close_0
open_0
high_0
low_0 
amount_0
turn_0 
return_0
 
close_1
open_1
high_1
low_1
return_1
amount_1
turn_1
 
close_2
open_2
high_2
low_2
amount_2
turn_2
return_2
 
close_3
open_3
high_3
low_3
amount_3
turn_3
return_3
 
close_4
open_4
high_4
low_4
amount_4
turn_4
return_4
 
mean(close_0, 5)
mean(low_0, 5)
mean(open_0, 5)
mean(high_0, 5)
mean(turn_0, 5)
mean(amount_0, 5)
mean(return_0, 5)
 
ts_max(close_0, 5)
ts_max(low_0, 5)
ts_max(open_0, 5)
ts_max(high_0, 5)
ts_max(turn_0, 5)
ts_max(amount_0, 5)
ts_max(return_0, 5)
 
ts_min(close_0, 5)
ts_min(low_0, 5)
ts_min(open_0, 5)
ts_min(high_0, 5)
ts_min(turn_0, 5)
ts_min(amount_0, 5)
ts_min(return_0, 5) 
 
std(close_0, 5)
std(low_0, 5)
std(open_0, 5)
std(high_0, 5)
std(turn_0, 5)
std(amount_0, 5)
std(return_0, 5)
 
ts_rank(close_0, 5)
ts_rank(low_0, 5)
ts_rank(open_0, 5)
ts_rank(high_0, 5)
ts_rank(turn_0, 5)
ts_rank(amount_0, 5)
ts_rank(return_0, 5)
 
decay_linear(close_0, 5)
decay_linear(low_0, 5)
decay_linear(open_0, 5)
decay_linear(high_0, 5)
decay_linear(turn_0, 5)
decay_linear(amount_0, 5)
decay_linear(return_0, 5)
 
correlation(volume_0, return_0, 5)
correlation(volume_0, high_0, 5)
correlation(volume_0, low_0, 5)
correlation(volume_0, close_0, 5)
correlation(volume_0, open_0, 5)
correlation(volume_0, turn_0, 5)
  
correlation(return_0, high_0, 5)
correlation(return_0, low_0, 5)
correlation(return_0, close_0, 5)
correlation(return_0, open_0, 5)
correlation(return_0, turn_0, 5)
 
correlation(high_0, low_0, 5)
correlation(high_0, close_0, 5)
correlation(high_0, open_0, 5)
correlation(high_0, turn_0, 5)
 
correlation(low_0, close_0, 5)
correlation(low_0, open_0, 5)
correlation(low_0, turn_0, 5)
 
correlation(close_0, open_0, 5)
correlation(close_0, turn_0, 5)

correlation(open_0, turn_0, 5)""",

    'm6': 'M.general_feature_extractor.v7',
    'm6.instruments': T.Graph.OutputPort('m1.data'),
    'm6.features': T.Graph.OutputPort('m3.data'),
    'm6.start_date': '',
    'm6.end_date': '',
    'm6.before_start_days': 10,

    'm7': 'M.derived_feature_extractor.v3',
    'm7.input_data': T.Graph.OutputPort('m6.data'),
    'm7.features': T.Graph.OutputPort('m3.data'),
    'm7.date_col': 'date',
    'm7.instrument_col': 'instrument',
    'm7.drop_na': True,
    'm7.remove_extra_columns': False,

    'm13': 'M.standardlize.v8',
    'm13.input_1': T.Graph.OutputPort('m7.data'),
    'm13.input_2': T.Graph.OutputPort('m3.data'),
    'm13.columns_input': '[]',

    'm14': 'M.fillnan.v1',
    'm14.input_data': T.Graph.OutputPort('m13.data'),
    'm14.features': T.Graph.OutputPort('m3.data'),
    'm14.fill_value': '0.0',

    'm4': 'M.join.v3',
    'm4.data1': T.Graph.OutputPort('m17.data'),
    'm4.data2': T.Graph.OutputPort('m14.data'),
    'm4.on': 'date,instrument',
    'm4.how': 'inner',
    'm4.sort': False,

    'm10': 'M.dl_convert_to_bin.v2',
    'm10.input_data': T.Graph.OutputPort('m4.data'),
    'm10.features': T.Graph.OutputPort('m3.data'),
    'm10.window_size': 1,
    'm10.feature_clip': 3,
    'm10.flatten': True,
    'm10.window_along_col': 'instrument',

    'm12': 'M.cached.v3',
    'm12.input_1': T.Graph.OutputPort('m10.data'),
    'm12.run': m12_run_bigquant_run,
    'm12.post_run': m12_post_run_bigquant_run,
    'm12.input_ports': '',
    'm12.params': '{}',
    'm12.output_ports': '',

    'm18': 'M.dl_models_tabnet_train.v1',
    'm18.training_data': T.Graph.OutputPort('m12.data_1'),
    'm18.validation_data': T.Graph.OutputPort('m12.data_2'),
    'm18.input_dim': 98,
    'm18.n_steps': 3,
    'm18.n_d': 16,
    'm18.n_a': 16,
    'm18.gamma': 1.3,
    'm18.momentum': 0.01,
    'm18.batch_size': 20480,
    'm18.virtual_batch_size': 1280,
    'm18.epochs': 30,
    'm18.num_workers': 4,
    'm18.device_name': 'auto:自动调用GPU',
    'm18.verbose': '1:输出进度条记录',

    'm5': 'M.instruments.v2',
    'm5.start_date': '2020-01-01',
    'm5.end_date': '2020-12-01',
    'm5.market': 'CN_STOCK_A',
    'm5.instrument_list': '',
    'm5.max_count': 0,

    'm8': 'M.general_feature_extractor.v7',
    'm8.instruments': T.Graph.OutputPort('m5.data'),
    'm8.features': T.Graph.OutputPort('m3.data'),
    'm8.start_date': '',
    'm8.end_date': '',
    'm8.before_start_days': 10,

    'm9': 'M.derived_feature_extractor.v3',
    'm9.input_data': T.Graph.OutputPort('m8.data'),
    'm9.features': T.Graph.OutputPort('m3.data'),
    'm9.date_col': 'date',
    'm9.instrument_col': 'instrument',
    'm9.drop_na': True,
    'm9.remove_extra_columns': False,

    'm16': 'M.standardlize.v8',
    'm16.input_1': T.Graph.OutputPort('m9.data'),
    'm16.input_2': T.Graph.OutputPort('m3.data'),
    'm16.columns_input': '[]',

    'm15': 'M.fillnan.v1',
    'm15.input_data': T.Graph.OutputPort('m16.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.fill_value': '0.0',

    'm11': 'M.dl_convert_to_bin.v2',
    'm11.input_data': T.Graph.OutputPort('m15.data'),
    'm11.features': T.Graph.OutputPort('m3.data'),
    'm11.window_size': 1,
    'm11.feature_clip': 3,
    'm11.flatten': True,
    'm11.window_along_col': 'instrument',

    'm19': 'M.dl_models_tabnet_predict.v1',
    'm19.trained_model': T.Graph.OutputPort('m18.data'),
    'm19.input_data': T.Graph.OutputPort('m11.data'),
    'm19.m_cached': False,

    'm20': 'M.cached.v3',
    'm20.input_1': T.Graph.OutputPort('m19.data'),
    'm20.input_2': T.Graph.OutputPort('m9.data'),
    'm20.run': m20_run_bigquant_run,
    'm20.post_run': m20_post_run_bigquant_run,
    'm20.input_ports': '',
    'm20.params': '{}',
    'm20.output_ports': '',

    'm21': 'M.trade.v4',
    'm21.instruments': T.Graph.OutputPort('m5.data'),
    'm21.options_data': T.Graph.OutputPort('m20.data_1'),
    'm21.start_date': '',
    'm21.end_date': '',
    'm21.initialize': m21_initialize_bigquant_run,
    'm21.handle_data': m21_handle_data_bigquant_run,
    'm21.prepare': m21_prepare_bigquant_run,
    'm21.volume_limit': 0.025,
    'm21.order_price_field_buy': 'open',
    'm21.order_price_field_sell': 'close',
    'm21.capital_base': 1000000,
    'm21.auto_cancel_non_tradable_orders': True,
    'm21.data_frequency': 'daily',
    'm21.price_type': '后复权',
    'm21.product_type': '股票',
    'm21.plot_charts': True,
    'm21.backtest_only': False,
    'm21.benchmark': '000300.SHA',
})

# g.run({})


def m23_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='m5', # 测试数据 证券代码列表 模块id
    predict_mid='m20', # 预测 模块id
    trade_mid='m21', # 回测 模块id
    start_date='2014-01-01', # 数据开始日期
    end_date=T.live_run_param('trading_date', '2021-10-08'), # 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=750, # 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)
    
    print('=========:', len(rolling_dates), rolling_dates)
    
    # 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))
        
    print('++++++++:', len( results),  results)


    # 合并预测结果并回测
    mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].data_1, 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}


m23 = M.hyper_rolling_train.v1(
    run=m23_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2021-10-11 10:34:20.227442] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 10:34:20.234644] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.238805] INFO: moduleinvoker: instruments.v2 运行完成[0.011361s].

[2021-10-11 10:34:20.245489] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 10:34:20.252841] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.256150] INFO: moduleinvoker: input_features.v1 运行完成[0.010656s].

[2021-10-11 10:34:20.264360] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 10:34:20.270643] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.273346] INFO: moduleinvoker: instruments.v2 运行完成[0.008982s].

[2021-10-11 10:34:20.287021] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 10:34:20.298422] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.301613] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.014578s].

[2021-10-11 10:34:20.320001] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 10:34:20.326182] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.328646] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.008666s].

[2021-10-11 10:34:20.344750] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 10:34:20.351750] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.354620] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.009905s].

[2021-10-11 10:34:20.364238] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:34:20.374902] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.377417] INFO: moduleinvoker: standardlize.v8 运行完成[0.013165s].

[2021-10-11 10:34:20.388809] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 10:34:20.396164] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.398235] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009432s].

[2021-10-11 10:34:20.409246] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 10:34:20.419205] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.422390] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.013116s].

[2021-10-11 10:34:20.430466] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:34:20.437917] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.441295] INFO: moduleinvoker: standardlize.v8 运行完成[0.010814s].

[2021-10-11 10:34:20.451826] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:34:20.460955] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.463879] INFO: moduleinvoker: standardlize.v8 运行完成[0.012065s].

[2021-10-11 10:34:20.475380] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 10:34:20.485825] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.489128] INFO: moduleinvoker: fillnan.v1 运行完成[0.013726s].

[2021-10-11 10:34:20.501910] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 10:34:20.508802] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.511703] INFO: moduleinvoker: fillnan.v1 运行完成[0.009776s].

[2021-10-11 10:34:20.525293] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 10:34:20.534540] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.536846] INFO: moduleinvoker: join.v3 运行完成[0.011548s].

[2021-10-11 10:34:20.553687] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 10:34:20.564220] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.566213] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.012559s].

[2021-10-11 10:34:20.581280] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 10:34:20.588703] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.591362] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.010114s].

[2021-10-11 10:34:20.608539] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 10:34:20.620085] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:34:20.622804] INFO: moduleinvoker: cached.v3 运行完成[0.014285s].

[2021-10-11 10:34:20.630350] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 10:34:21.220952] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：424587，迭代次数：30

[2021-10-11 10:42:25.978121] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[485.347744s].

[2021-10-11 10:42:25.986128] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 10:42:26.575308] INFO: dl_models_tabnet_pred: 模型预测，样本个数：586272

[2021-10-11 10:42:39.814547] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[13.828399s].

[2021-10-11 10:42:39.829693] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 10:42:45.663536] INFO: moduleinvoker: cached.v3 运行完成[5.833823s].

[2021-10-11 10:42:45.672276] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 10:42:45.679255] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.682153] INFO: moduleinvoker: instruments.v2 运行完成[0.009886s].

[2021-10-11 10:42:45.687985] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 10:42:45.695471] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.697801] INFO: moduleinvoker: input_features.v1 运行完成[0.009791s].

[2021-10-11 10:42:45.705863] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 10:42:45.713281] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.715795] INFO: moduleinvoker: instruments.v2 运行完成[0.009891s].

[2021-10-11 10:42:45.727616] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 10:42:45.736755] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.739312] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.011707s].

[2021-10-11 10:42:45.759010] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 10:42:45.768321] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.770542] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011542s].

[2021-10-11 10:42:45.785384] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 10:42:45.793696] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.795561] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010209s].

[2021-10-11 10:42:45.804591] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:42:45.811647] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.814601] INFO: moduleinvoker: standardlize.v8 运行完成[0.010006s].

[2021-10-11 10:42:45.827183] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 10:42:45.834173] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.836986] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009793s].

[2021-10-11 10:42:45.849936] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 10:42:45.862273] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.865057] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.015115s].

[2021-10-11 10:42:45.874009] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:42:45.886359] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.889265] INFO: moduleinvoker: standardlize.v8 运行完成[0.015256s].

[2021-10-11 10:42:45.898634] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:42:45.909299] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.912270] INFO: moduleinvoker: standardlize.v8 运行完成[0.013633s].

[2021-10-11 10:42:45.925838] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 10:42:45.935874] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.940861] INFO: moduleinvoker: fillnan.v1 运行完成[0.015018s].

[2021-10-11 10:42:45.952137] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 10:42:45.960620] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.962760] INFO: moduleinvoker: fillnan.v1 运行完成[0.010619s].

[2021-10-11 10:42:45.972185] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 10:42:45.983226] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:45.985771] INFO: moduleinvoker: join.v3 运行完成[0.013571s].

[2021-10-11 10:42:46.001401] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 10:42:46.008855] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:46.011469] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.010083s].

[2021-10-11 10:42:46.027445] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 10:42:46.036369] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:42:46.038617] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.011159s].

[2021-10-11 10:42:46.053291] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 10:42:50.970068] INFO: moduleinvoker: cached.v3 运行完成[4.916776s].

[2021-10-11 10:42:50.977964] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 10:42:52.038585] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：856155，迭代次数：30

[2021-10-11 10:57:59.704145] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[908.726151s].

[2021-10-11 10:57:59.711653] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 10:58:00.302661] INFO: dl_models_tabnet_pred: 模型预测，样本个数：664722

[2021-10-11 10:58:11.539296] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[11.827627s].

[2021-10-11 10:58:11.551713] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 10:58:17.584236] INFO: moduleinvoker: cached.v3 运行完成[6.03255s].

[2021-10-11 10:58:17.591278] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 10:58:17.600201] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.601939] INFO: moduleinvoker: instruments.v2 运行完成[0.010666s].

[2021-10-11 10:58:17.606595] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 10:58:17.617328] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.619046] INFO: moduleinvoker: input_features.v1 运行完成[0.012457s].

[2021-10-11 10:58:17.624173] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 10:58:17.630625] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.632247] INFO: moduleinvoker: instruments.v2 运行完成[0.008075s].

[2021-10-11 10:58:17.641983] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 10:58:17.651288] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.653028] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.011043s].

[2021-10-11 10:58:17.667477] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 10:58:17.682118] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.684012] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.016559s].

[2021-10-11 10:58:17.696350] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 10:58:17.704005] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.705797] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.009473s].

[2021-10-11 10:58:17.711065] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:58:17.720592] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.722410] INFO: moduleinvoker: standardlize.v8 运行完成[0.011347s].

[2021-10-11 10:58:17.729829] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 10:58:17.737496] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.739507] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009676s].

[2021-10-11 10:58:17.748649] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 10:58:17.757627] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.759396] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010745s].

[2021-10-11 10:58:17.764582] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:58:17.773697] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.775413] INFO: moduleinvoker: standardlize.v8 运行完成[0.010827s].

[2021-10-11 10:58:17.780827] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 10:58:17.791113] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.792759] INFO: moduleinvoker: standardlize.v8 运行完成[0.011919s].

[2021-10-11 10:58:17.802446] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 10:58:17.810667] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.812268] INFO: moduleinvoker: fillnan.v1 运行完成[0.009824s].

[2021-10-11 10:58:17.820470] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 10:58:17.830011] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.831602] INFO: moduleinvoker: fillnan.v1 运行完成[0.011137s].

[2021-10-11 10:58:17.840506] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 10:58:17.849024] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.850968] INFO: moduleinvoker: join.v3 运行完成[0.01046s].

[2021-10-11 10:58:17.863227] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 10:58:17.871246] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.873194] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.009985s].

[2021-10-11 10:58:17.887611] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 10:58:17.894513] INFO: moduleinvoker: 命中缓存

[2021-10-11 10:58:17.896328] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.008735s].

[2021-10-11 10:58:17.907862] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 10:58:25.174755] INFO: moduleinvoker: cached.v3 运行完成[7.266873s].

[2021-10-11 10:58:25.181386] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 10:58:26.715441] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：1348422，迭代次数：30

[2021-10-11 11:21:36.165654] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[1390.984232s].

[2021-10-11 11:21:36.175619] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 11:21:37.073945] INFO: dl_models_tabnet_pred: 模型预测，样本个数：778306

[2021-10-11 11:21:53.527134] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[17.351541s].

[2021-10-11 11:21:53.545094] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 11:22:01.214553] INFO: moduleinvoker: cached.v3 运行完成[7.669536s].

[2021-10-11 11:22:01.221527] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 11:22:01.230053] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.231713] INFO: moduleinvoker: instruments.v2 运行完成[0.010192s].

[2021-10-11 11:22:01.235806] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 11:22:01.242921] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.244577] INFO: moduleinvoker: input_features.v1 运行完成[0.008775s].

[2021-10-11 11:22:01.249746] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 11:22:01.257898] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.259844] INFO: moduleinvoker: instruments.v2 运行完成[0.010111s].

[2021-10-11 11:22:01.269507] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 11:22:01.280118] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.282012] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.012506s].

[2021-10-11 11:22:01.302785] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 11:22:01.310577] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.312164] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.009415s].

[2021-10-11 11:22:01.324868] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 11:22:01.331116] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.332674] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.007825s].

[2021-10-11 11:22:01.337664] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 11:22:01.344933] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.346694] INFO: moduleinvoker: standardlize.v8 运行完成[0.00903s].

[2021-10-11 11:22:01.353884] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 11:22:01.363001] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.364779] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010896s].

[2021-10-11 11:22:01.371914] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 11:22:01.378626] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.380426] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.008518s].

[2021-10-11 11:22:01.385992] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 11:22:01.395638] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.397630] INFO: moduleinvoker: standardlize.v8 运行完成[0.011633s].

[2021-10-11 11:22:01.403294] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 11:22:01.411053] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.412936] INFO: moduleinvoker: standardlize.v8 运行完成[0.009652s].

[2021-10-11 11:22:01.421705] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 11:22:01.430679] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.432318] INFO: moduleinvoker: fillnan.v1 运行完成[0.010615s].

[2021-10-11 11:22:01.441120] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 11:22:01.449437] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.451316] INFO: moduleinvoker: fillnan.v1 运行完成[0.010204s].

[2021-10-11 11:22:01.460418] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 11:22:01.472854] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.474824] INFO: moduleinvoker: join.v3 运行完成[0.014408s].

[2021-10-11 11:22:01.490279] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 11:22:01.498890] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.500643] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.010388s].

[2021-10-11 11:22:01.514167] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 11:22:01.526021] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:22:01.527713] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.01357s].

[2021-10-11 11:22:01.539177] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 11:22:16.281975] INFO: moduleinvoker: cached.v3 运行完成[14.742767s].

[2021-10-11 11:22:16.291457] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 11:22:18.272336] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：1485870，迭代次数：30

[2021-10-11 11:42:37.322966] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[1221.031533s].

[2021-10-11 11:42:37.333529] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 11:42:38.121864] INFO: dl_models_tabnet_pred: 模型预测，样本个数：860264

[2021-10-11 11:42:51.722404] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[14.388889s].

[2021-10-11 11:42:51.735682] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 11:42:59.260580] INFO: moduleinvoker: cached.v3 运行完成[7.524904s].

[2021-10-11 11:42:59.268087] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 11:42:59.281498] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.283190] INFO: moduleinvoker: instruments.v2 运行完成[0.01511s].

[2021-10-11 11:42:59.287596] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 11:42:59.298789] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.300566] INFO: moduleinvoker: input_features.v1 运行完成[0.012974s].

[2021-10-11 11:42:59.306163] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 11:42:59.311058] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.312612] INFO: moduleinvoker: instruments.v2 运行完成[0.006455s].

[2021-10-11 11:42:59.320942] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 11:42:59.328879] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.330340] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009398s].

[2021-10-11 11:42:59.350692] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 11:42:59.358939] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.360757] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010075s].

[2021-10-11 11:42:59.373295] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 11:42:59.383008] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.384545] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011264s].

[2021-10-11 11:42:59.390289] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 11:42:59.400366] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.402085] INFO: moduleinvoker: standardlize.v8 运行完成[0.011798s].

[2021-10-11 11:42:59.409687] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 11:42:59.417314] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.418739] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009043s].

[2021-10-11 11:42:59.425571] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 11:42:59.434066] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.435665] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010091s].

[2021-10-11 11:42:59.441376] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 11:42:59.452879] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.454471] INFO: moduleinvoker: standardlize.v8 运行完成[0.013092s].

[2021-10-11 11:42:59.464941] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 11:42:59.475614] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.477260] INFO: moduleinvoker: standardlize.v8 运行完成[0.012322s].

[2021-10-11 11:42:59.486403] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 11:42:59.495728] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.497332] INFO: moduleinvoker: fillnan.v1 运行完成[0.01093s].

[2021-10-11 11:42:59.505386] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 11:42:59.516125] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.517957] INFO: moduleinvoker: fillnan.v1 运行完成[0.012571s].

[2021-10-11 11:42:59.526771] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 11:42:59.532313] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.533909] INFO: moduleinvoker: join.v3 运行完成[0.007144s].

[2021-10-11 11:42:59.546004] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 11:42:59.554622] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.556070] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.010085s].

[2021-10-11 11:42:59.568355] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 11:42:59.575652] INFO: moduleinvoker: 命中缓存

[2021-10-11 11:42:59.577050] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.008701s].

[2021-10-11 11:42:59.588480] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 11:43:08.207155] INFO: moduleinvoker: cached.v3 运行完成[8.618666s].

[2021-10-11 11:43:08.213153] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 11:43:10.231770] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：1686572，迭代次数：30

[2021-10-11 12:13:02.445684] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[1794.23252s].

[2021-10-11 12:13:02.453477] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 12:13:03.336093] INFO: dl_models_tabnet_pred: 模型预测，样本个数：922734

[2021-10-11 12:13:19.084105] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[16.63061s].

[2021-10-11 12:13:19.101698] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 12:13:28.841260] INFO: moduleinvoker: cached.v3 运行完成[9.739589s].

[2021-10-11 12:13:28.850761] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 12:13:28.860884] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:28.862901] INFO: moduleinvoker: instruments.v2 运行完成[0.012165s].

[2021-10-11 12:13:28.870470] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 12:13:28.879371] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:28.882055] INFO: moduleinvoker: input_features.v1 运行完成[0.011604s].

[2021-10-11 12:13:28.888891] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 12:13:28.897051] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:28.899477] INFO: moduleinvoker: instruments.v2 运行完成[0.010593s].

[2021-10-11 12:13:28.917485] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 12:13:28.929785] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:28.931743] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.014257s].

[2021-10-11 12:13:28.953276] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 12:13:28.966306] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:28.968803] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.015545s].

[2021-10-11 12:13:28.984387] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 12:13:28.994307] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:28.997242] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012895s].

[2021-10-11 12:13:29.006079] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 12:13:29.015720] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.018563] INFO: moduleinvoker: standardlize.v8 运行完成[0.012494s].

[2021-10-11 12:13:29.027121] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 12:13:29.037786] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.039437] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.012314s].

[2021-10-11 12:13:29.049965] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 12:13:29.058456] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.060968] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010989s].

[2021-10-11 12:13:29.067314] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 12:13:29.078668] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.081618] INFO: moduleinvoker: standardlize.v8 运行完成[0.014303s].

[2021-10-11 12:13:29.089415] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 12:13:29.099281] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.102121] INFO: moduleinvoker: standardlize.v8 运行完成[0.012713s].

[2021-10-11 12:13:29.114769] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 12:13:29.121318] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.123364] INFO: moduleinvoker: fillnan.v1 运行完成[0.008612s].

[2021-10-11 12:13:29.133391] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 12:13:29.145708] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.147775] INFO: moduleinvoker: fillnan.v1 运行完成[0.014381s].

[2021-10-11 12:13:29.158564] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 12:13:29.164218] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.166410] INFO: moduleinvoker: join.v3 运行完成[0.007832s].

[2021-10-11 12:13:29.181698] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 12:13:29.193655] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.196156] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.014473s].

[2021-10-11 12:13:29.213084] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 12:13:29.220667] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:13:29.223213] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.010137s].

[2021-10-11 12:13:29.237280] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 12:13:39.851029] INFO: moduleinvoker: cached.v3 运行完成[10.61374s].

[2021-10-11 12:13:39.858433] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 12:13:42.347520] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：1872615，迭代次数：30

[2021-10-11 12:47:30.722848] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[2030.864316s].

[2021-10-11 12:47:30.732396] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 12:47:31.791693] INFO: dl_models_tabnet_pred: 模型预测，样本个数：994169

[2021-10-11 12:47:54.564482] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[23.832083s].

[2021-10-11 12:47:54.585601] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 12:48:04.957581] INFO: moduleinvoker: cached.v3 运行完成[10.371997s].

[2021-10-11 12:48:04.967207] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 12:48:04.977111] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:04.979239] INFO: moduleinvoker: instruments.v2 运行完成[0.012044s].

[2021-10-11 12:48:04.987946] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-11 12:48:04.996542] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:04.999680] INFO: moduleinvoker: input_features.v1 运行完成[0.01175s].

[2021-10-11 12:48:05.006982] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-11 12:48:05.013660] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.016265] INFO: moduleinvoker: instruments.v2 运行完成[0.00927s].

[2021-10-11 12:48:05.029067] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-11 12:48:05.039031] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.041159] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.012113s].

[2021-10-11 12:48:05.059230] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 12:48:05.069998] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.073049] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.013833s].

[2021-10-11 12:48:05.090466] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-11 12:48:05.102032] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.105454] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.015011s].

[2021-10-11 12:48:05.115235] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 12:48:05.122357] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.125466] INFO: moduleinvoker: standardlize.v8 运行完成[0.010233s].

[2021-10-11 12:48:05.134867] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 12:48:05.140817] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.143306] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.008441s].

[2021-10-11 12:48:05.153006] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-11 12:48:05.160950] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.163337] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010336s].

[2021-10-11 12:48:05.170866] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 12:48:05.181016] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.183482] INFO: moduleinvoker: standardlize.v8 运行完成[0.012625s].

[2021-10-11 12:48:05.192353] INFO: moduleinvoker: standardlize.v8 开始运行..

[2021-10-11 12:48:05.199538] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.201900] INFO: moduleinvoker: standardlize.v8 运行完成[0.009562s].

[2021-10-11 12:48:05.215057] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 12:48:05.225640] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.228162] INFO: moduleinvoker: fillnan.v1 运行完成[0.013116s].

[2021-10-11 12:48:05.239750] INFO: moduleinvoker: fillnan.v1 开始运行..

[2021-10-11 12:48:05.246577] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.249414] INFO: moduleinvoker: fillnan.v1 运行完成[0.009674s].

[2021-10-11 12:48:05.259634] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-11 12:48:05.266951] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.269279] INFO: moduleinvoker: join.v3 运行完成[0.009635s].

[2021-10-11 12:48:05.286243] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 12:48:05.296096] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.298819] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.012605s].

[2021-10-11 12:48:05.318204] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2021-10-11 12:48:05.325314] INFO: moduleinvoker: 命中缓存

[2021-10-11 12:48:05.327751] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.009575s].

[2021-10-11 12:48:05.343224] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 12:48:17.363628] INFO: moduleinvoker: cached.v3 运行完成[12.020407s].

[2021-10-11 12:48:17.370911] INFO: moduleinvoker: dl_models_tabnet_train.v1 开始运行..

[2021-10-11 12:48:20.349155] INFO: dl_models_tabnet_train: 准备训练，训练样本个数：2035257，迭代次数：30

[2021-10-11 13:20:28.507131] INFO: moduleinvoker: dl_models_tabnet_train.v1 运行完成[1931.136203s].

[2021-10-11 13:20:28.518379] INFO: moduleinvoker: dl_models_tabnet_predict.v1 开始运行..

[2021-10-11 13:20:29.256100] INFO: dl_models_tabnet_pred: 模型预测，样本个数：622820

[2021-10-11 13:20:44.881537] INFO: moduleinvoker: dl_models_tabnet_predict.v1 运行完成[16.363157s].

[2021-10-11 13:20:44.901043] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 13:20:50.224372] INFO: moduleinvoker: cached.v3 运行完成[5.323363s].

[2021-10-11 13:20:50.320190] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-11 13:21:00.134615] INFO: moduleinvoker: cached.v3 运行完成[9.814447s].

[2021-10-11 13:21:00.208266] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-10-11 13:21:00.214894] INFO: backtest: biglearning backtest:V8.5.0

[2021-10-11 13:21:00.216409] INFO: backtest: product_type:stock by specified

[2021-10-11 13:21:02.155352] INFO: moduleinvoker: cached.v2 开始运行..

[2021-10-11 13:21:55.927621] INFO: backtest: 读取股票行情完成:6851386

[2021-10-11 13:22:23.716930] INFO: moduleinvoker: cached.v2 运行完成[81.561572s].

[2021-10-11 13:22:36.755929] INFO: algo: TradingAlgorithm V1.8.5

[2021-10-11 13:22:42.254561] INFO: algo: trading transform...

[2021-10-11 13:25:46.530548] INFO: Performance: Simulated 1640 trading days out of 1640.

[2021-10-11 13:25:46.532372] INFO: Performance: first open: 2015-01-12 09:30:00+00:00

[2021-10-11 13:25:46.534040] INFO: Performance: last close: 2021-10-08 15:00:00+00:00

[2021-10-11 13:26:23.274805] INFO: moduleinvoker: backtest.v8 运行完成[323.066541s].

[2021-10-11 13:26:23.277051] INFO: moduleinvoker: trade.v4 运行完成[323.134653s].

[2021-10-11 13:26:23.279418] INFO: moduleinvoker: hyper_rolling_train.v1 运行完成[10323.1742s].

=========: 7 [{'train_start_date': '2014-01-02', 'train_end_date': '2015-01-09', 'test_start_date': '2015-01-12', 'test_end_date': '2016-01-18'}, {'train_start_date': '2014-01-02', 'train_end_date': '2016-01-18', 'test_start_date': '2016-01-19', 'test_end_date': '2017-01-25'}, {'train_start_date': '2014-01-02', 'train_end_date': '2017-01-25', 'test_start_date': '2017-01-26', 'test_end_date': '2018-02-01'}, {'train_start_date': '2015-01-12', 'train_end_date': '2018-02-01', 'test_start_date': '2018-02-02', 'test_end_date': '2019-02-19'}, {'train_start_date': '2016-01-19', 'train_end_date': '2019-02-19', 'test_start_date': '2019-02-20', 'test_end_date': '2020-02-28'}, {'train_start_date': '2017-01-26', 'train_end_date': '2020-02-28', 'test_start_date': '2020-03-02', 'test_end_date': '2021-03-10'}, {'train_start_date': '2018-02-02', 'train_end_date': '2021-03-10', 'test_start_date': '2021-03-11', 'test_end_date': '2021-10-08'}]

Device used : cuda

epoch 0  | loss: 1.17906 | val_0_mse: 0.99688 |  0:00:17s
epoch 1  | loss: 1.00874 | val_0_mse: 0.99498 |  0:00:33s
epoch 2  | loss: 0.99906 | val_0_mse: 0.9946  |  0:00:51s
epoch 3  | loss: 0.99718 | val_0_mse: 0.99401 |  0:01:10s
epoch 4  | loss: 0.99666 | val_0_mse: 0.99366 |  0:01:25s
epoch 5  | loss: 0.99597 | val_0_mse: 0.99377 |  0:01:42s
epoch 6  | loss: 0.99577 | val_0_mse: 0.99272 |  0:02:01s
epoch 7  | loss: 0.99535 | val_0_mse: 0.99275 |  0:02:19s
epoch 8  | loss: 0.99486 | val_0_mse: 0.99194 |  0:02:33s
epoch 9  | loss: 0.99444 | val_0_mse: 0.9917  |  0:02:51s
epoch 10 | loss: 0.99448 | val_0_mse: 0.99168 |  0:03:08s
epoch 11 | loss: 0.99425 | val_0_mse: 0.99233 |  0:03:25s
epoch 12 | loss: 0.9938  | val_0_mse: 0.99154 |  0:03:40s
epoch 13 | loss: 0.99384 | val_0_mse: 0.99177 |  0:03:58s
epoch 14 | loss: 0.99405 | val_0_mse: 0.99114 |  0:04:15s
epoch 15 | loss: 0.99376 | val_0_mse: 0.99148 |  0:04:31s
epoch 16 | loss: 0.99353 | val_0_mse: 0.99104 |  0:04:45s
epoch 17 | loss: 0.99333 | val_0_mse: 0.99094 |  0:04:59s
epoch 18 | loss: 0.99323 | val_0_mse: 0.9907  |  0:05:12s
epoch 19 | loss: 0.99288 | val_0_mse: 0.99079 |  0:05:27s
epoch 20 | loss: 0.99238 | val_0_mse: 0.99019 |  0:05:40s
epoch 21 | loss: 0.99249 | val_0_mse: 0.99033 |  0:05:54s
epoch 22 | loss: 0.99211 | val_0_mse: 0.99015 |  0:06:08s
epoch 23 | loss: 0.99232 | val_0_mse: 0.99088 |  0:06:23s
epoch 24 | loss: 0.99224 | val_0_mse: 0.98994 |  0:06:41s
epoch 25 | loss: 0.99227 | val_0_mse: 0.99055 |  0:06:58s
epoch 26 | loss: 0.99263 | val_0_mse: 0.99047 |  0:07:11s
epoch 27 | loss: 0.99223 | val_0_mse: 0.99031 |  0:07:27s
epoch 28 | loss: 0.99193 | val_0_mse: 0.98976 |  0:07:44s
epoch 29 | loss: 0.99164 | val_0_mse: 0.98961 |  0:07:58s
Stop training because you reached max_epochs = 30 with best_epoch = 29 and best_val_0_mse = 0.98961
Best weights from best epoch are automatically used!

Device used : cuda

Device used : cuda

epoch 0  | loss: 1.0803  | val_0_mse: 0.98986 |  0:00:26s
epoch 1  | loss: 0.99706 | val_0_mse: 0.98807 |  0:00:55s
epoch 2  | loss: 0.9948  | val_0_mse: 0.98618 |  0:01:22s
epoch 3  | loss: 0.99374 | val_0_mse: 0.98583 |  0:01:54s
epoch 4  | loss: 0.99328 | val_0_mse: 0.98562 |  0:02:22s
epoch 5  | loss: 0.99273 | val_0_mse: 0.9848  |  0:02:55s
epoch 6  | loss: 0.99237 | val_0_mse: 0.98496 |  0:03:22s
epoch 7  | loss: 0.99212 | val_0_mse: 0.9846  |  0:03:54s
epoch 8  | loss: 0.99153 | val_0_mse: 0.98402 |  0:04:22s
epoch 9  | loss: 0.99097 | val_0_mse: 0.98377 |  0:04:53s
epoch 10 | loss: 0.99068 | val_0_mse: 0.98378 |  0:05:19s
epoch 11 | loss: 0.99063 | val_0_mse: 0.98357 |  0:05:50s
epoch 12 | loss: 0.99015 | val_0_mse: 0.98343 |  0:06:17s
epoch 13 | loss: 0.98995 | val_0_mse: 0.98285 |  0:06:47s
epoch 14 | loss: 0.98937 | val_0_mse: 0.98239 |  0:07:17s
epoch 15 | loss: 0.98929 | val_0_mse: 0.98301 |  0:07:49s
epoch 16 | loss: 0.98901 | val_0_mse: 0.98217 |  0:08:20s
epoch 17 | loss: 0.98893 | val_0_mse: 0.98186 |  0:08:50s
epoch 18 | loss: 0.98869 | val_0_mse: 0.9818  |  0:09:24s
epoch 19 | loss: 0.988   | val_0_mse: 0.98131 |  0:09:54s
epoch 20 | loss: 0.98788 | val_0_mse: 0.98164 |  0:10:28s
epoch 21 | loss: 0.98771 | val_0_mse: 0.98265 |  0:10:56s
epoch 22 | loss: 0.98764 | val_0_mse: 0.98131 |  0:11:28s
epoch 23 | loss: 0.9873  | val_0_mse: 0.98834 |  0:11:59s
epoch 24 | loss: 0.98718 | val_0_mse: 0.98039 |  0:12:30s
epoch 25 | loss: 0.98649 | val_0_mse: 0.98046 |  0:13:02s
epoch 26 | loss: 0.98668 | val_0_mse: 0.97998 |  0:13:29s
epoch 27 | loss: 0.98667 | val_0_mse: 0.97994 |  0:13:59s
epoch 28 | loss: 0.98658 | val_0_mse: 0.98017 |  0:14:30s
epoch 29 | loss: 0.98621 | val_0_mse: 0.97969 |  0:14:55s
Stop training because you reached max_epochs = 30 with best_epoch = 29 and best_val_0_mse = 0.97969
Best weights from best epoch are automatically used!

Device used : cuda

Device used : cuda

epoch 0  | loss: 1.05855 | val_0_mse: 0.99177 |  0:00:37s
epoch 1  | loss: 0.99538 | val_0_mse: 0.98973 |  0:01:22s
epoch 2  | loss: 0.99429 | val_0_mse: 0.98913 |  0:02:08s
epoch 3  | loss: 0.99356 | val_0_mse: 0.98898 |  0:02:53s
epoch 4  | loss: 0.99314 | val_0_mse: 0.98853 |  0:03:41s
epoch 5  | loss: 0.99241 | val_0_mse: 0.98773 |  0:04:26s
epoch 6  | loss: 0.99157 | val_0_mse: 0.98643 |  0:05:11s
epoch 7  | loss: 0.99089 | val_0_mse: 0.98658 |  0:05:58s
epoch 8  | loss: 0.99066 | val_0_mse: 0.98682 |  0:06:42s
epoch 9  | loss: 0.99043 | val_0_mse: 0.98616 |  0:07:27s
epoch 10 | loss: 0.99002 | val_0_mse: 0.9854  |  0:08:21s
epoch 11 | loss: 0.98968 | val_0_mse: 0.98501 |  0:09:11s
epoch 12 | loss: 0.98925 | val_0_mse: 0.98518 |  0:09:55s
epoch 13 | loss: 0.98874 | val_0_mse: 0.98441 |  0:10:44s
epoch 14 | loss: 0.9887  | val_0_mse: 0.98474 |  0:11:28s
epoch 15 | loss: 0.98891 | val_0_mse: 0.98424 |  0:12:12s
epoch 16 | loss: 0.98831 | val_0_mse: 0.98413 |  0:13:02s
epoch 17 | loss: 0.98819 | val_0_mse: 0.98393 |  0:13:48s
epoch 18 | loss: 0.98782 | val_0_mse: 0.98383 |  0:14:36s
epoch 19 | loss: 0.98752 | val_0_mse: 0.98372 |  0:15:23s
epoch 20 | loss: 0.98728 | val_0_mse: 0.98282 |  0:16:10s
epoch 21 | loss: 0.98705 | val_0_mse: 0.98278 |  0:17:00s
epoch 22 | loss: 0.98693 | val_0_mse: 0.98339 |  0:17:45s
epoch 23 | loss: 0.98705 | val_0_mse: 0.98273 |  0:18:33s
epoch 24 | loss: 0.98688 | val_0_mse: 0.98311 |  0:19:17s
epoch 25 | loss: 0.98655 | val_0_mse: 0.98431 |  0:20:06s
epoch 26 | loss: 0.98586 | val_0_mse: 0.98203 |  0:20:47s
epoch 27 | loss: 0.9857  | val_0_mse: 0.98155 |  0:21:25s
epoch 28 | loss: 0.98523 | val_0_mse: 0.98121 |  0:22:03s
epoch 29 | loss: 0.98505 | val_0_mse: 0.9818  |  0:22:44s
Stop training because you reached max_epochs = 30 with best_epoch = 28 and best_val_0_mse = 0.98121
Best weights from best epoch are automatically used!

Device used : cuda

Device used : cuda

epoch 0  | loss: 1.04969 | val_0_mse: 0.99811 |  0:00:50s
epoch 1  | loss: 0.99651 | val_0_mse: 0.99577 |  0:01:42s
epoch 2  | loss: 0.99527 | val_0_mse: 0.99502 |  0:02:29s
epoch 3  | loss: 0.99396 | val_0_mse: 0.99405 |  0:03:19s
epoch 4  | loss: 0.99356 | val_0_mse: 0.99387 |  0:04:11s
epoch 5  | loss: 0.99313 | val_0_mse: 0.99318 |  0:05:00s
epoch 6  | loss: 0.99259 | val_0_mse: 0.99291 |  0:05:48s
epoch 7  | loss: 0.99224 | val_0_mse: 0.99246 |  0:06:39s
epoch 8  | loss: 0.99204 | val_0_mse: 0.99345 |  0:07:25s
epoch 9  | loss: 0.99227 | val_0_mse: 0.99258 |  0:08:13s
epoch 10 | loss: 0.99175 | val_0_mse: 0.99136 |  0:09:02s
epoch 11 | loss: 0.99122 | val_0_mse: 0.99135 |  0:09:49s
epoch 12 | loss: 0.99118 | val_0_mse: 0.9912  |  0:10:41s
epoch 13 | loss: 0.99086 | val_0_mse: 0.99081 |  0:11:29s
epoch 14 | loss: 0.99069 | val_0_mse: 0.99124 |  0:12:20s
epoch 15 | loss: 0.99153 | val_0_mse: 0.9919  |  0:13:12s
epoch 16 | loss: 0.99153 | val_0_mse: 0.99168 |  0:14:00s
epoch 17 | loss: 0.99084 | val_0_mse: 0.99116 |  0:14:53s
epoch 18 | loss: 0.9907  | val_0_mse: 0.9916  |  0:15:43s
epoch 19 | loss: 0.99106 | val_0_mse: 0.99151 |  0:16:37s
epoch 20 | loss: 0.99083 | val_0_mse: 0.99209 |  0:17:22s
epoch 21 | loss: 0.99084 | val_0_mse: 0.99176 |  0:18:13s
epoch 22 | loss: 0.99111 | val_0_mse: 0.99107 |  0:19:01s
epoch 23 | loss: 0.99047 | val_0_mse: 0.99082 |  0:19:54s

Early stopping occurred at epoch 23 with best_epoch = 13 and best_val_0_mse = 0.99081
Best weights from best epoch are automatically used!

Device used : cuda

Device used : cuda

epoch 0  | loss: 1.04281 | val_0_mse: 0.99568 |  0:00:46s
epoch 1  | loss: 0.99669 | val_0_mse: 0.99515 |  0:01:33s
epoch 2  | loss: 0.99539 | val_0_mse: 0.99323 |  0:02:28s
epoch 3  | loss: 0.99453 | val_0_mse: 0.99295 |  0:03:23s
epoch 4  | loss: 0.99421 | val_0_mse: 0.99241 |  0:04:22s
epoch 5  | loss: 0.99355 | val_0_mse: 0.99202 |  0:05:22s
epoch 6  | loss: 0.99322 | val_0_mse: 0.99253 |  0:06:19s
epoch 7  | loss: 0.99297 | val_0_mse: 0.99216 |  0:07:17s
epoch 8  | loss: 0.9927  | val_0_mse: 0.99172 |  0:08:15s
epoch 9  | loss: 0.99247 | val_0_mse: 0.99039 |  0:09:18s
epoch 10 | loss: 0.99199 | val_0_mse: 0.99012 |  0:10:17s
epoch 11 | loss: 0.99144 | val_0_mse: 0.99082 |  0:11:13s
epoch 12 | loss: 0.99159 | val_0_mse: 0.99064 |  0:12:19s
epoch 13 | loss: 0.99199 | val_0_mse: 0.99109 |  0:13:22s
epoch 14 | loss: 0.99191 | val_0_mse: 0.99061 |  0:14:27s
epoch 15 | loss: 0.99168 | val_0_mse: 0.98989 |  0:15:35s
epoch 16 | loss: 0.991   | val_0_mse: 0.9896  |  0:16:36s
epoch 17 | loss: 0.99037 | val_0_mse: 0.98912 |  0:17:34s
epoch 18 | loss: 0.98994 | val_0_mse: 0.98838 |  0:18:36s
epoch 19 | loss: 0.9896  | val_0_mse: 0.98826 |  0:19:36s
epoch 20 | loss: 0.98947 | val_0_mse: 0.9879  |  0:20:40s
epoch 21 | loss: 0.98909 | val_0_mse: 0.98827 |  0:21:43s
epoch 22 | loss: 0.98892 | val_0_mse: 0.98814 |  0:22:45s
epoch 23 | loss: 0.98905 | val_0_mse: 0.98819 |  0:23:49s
epoch 24 | loss: 0.98862 | val_0_mse: 0.98727 |  0:24:51s
epoch 25 | loss: 0.98824 | val_0_mse: 0.98687 |  0:25:52s
epoch 26 | loss: 0.98831 | val_0_mse: 0.98759 |  0:26:46s
epoch 27 | loss: 0.98884 | val_0_mse: 0.98809 |  0:27:36s
epoch 28 | loss: 0.98919 | val_0_mse: 0.98771 |  0:28:26s
epoch 29 | loss: 0.98838 | val_0_mse: 0.98716 |  0:29:23s
Stop training because you reached max_epochs = 30 with best_epoch = 25 and best_val_0_mse = 0.98687
Best weights from best epoch are automatically used!

Device used : cuda

Device used : cuda

epoch 0  | loss: 1.04277 | val_0_mse: 0.99359 |  0:01:05s
epoch 1  | loss: 0.9953  | val_0_mse: 0.99244 |  0:02:14s
epoch 2  | loss: 0.99455 | val_0_mse: 0.9922  |  0:03:21s
epoch 3  | loss: 0.99364 | val_0_mse: 0.99165 |  0:04:24s
epoch 4  | loss: 0.99351 | val_0_mse: 0.99219 |  0:05:34s
epoch 5  | loss: 0.99337 | val_0_mse: 0.99177 |  0:06:48s
epoch 6  | loss: 0.99259 | val_0_mse: 0.99085 |  0:08:00s
epoch 7  | loss: 0.99296 | val_0_mse: 0.99171 |  0:09:09s
epoch 8  | loss: 0.993   | val_0_mse: 0.99106 |  0:10:15s
epoch 9  | loss: 0.9925  | val_0_mse: 0.99109 |  0:11:27s
epoch 10 | loss: 0.99201 | val_0_mse: 0.99028 |  0:12:35s
epoch 11 | loss: 0.99158 | val_0_mse: 0.98988 |  0:13:41s
epoch 12 | loss: 0.99181 | val_0_mse: 0.99084 |  0:14:51s
epoch 13 | loss: 0.99258 | val_0_mse: 0.99085 |  0:15:59s
epoch 14 | loss: 0.99196 | val_0_mse: 0.9902  |  0:17:05s
epoch 15 | loss: 0.99152 | val_0_mse: 0.98986 |  0:18:16s
epoch 16 | loss: 0.99118 | val_0_mse: 0.98973 |  0:19:19s
epoch 17 | loss: 0.99099 | val_0_mse: 0.9899  |  0:20:26s
epoch 18 | loss: 0.99111 | val_0_mse: 0.99037 |  0:21:30s
epoch 19 | loss: 0.99097 | val_0_mse: 0.98957 |  0:22:37s
epoch 20 | loss: 0.99095 | val_0_mse: 0.99017 |  0:23:42s
epoch 21 | loss: 0.99115 | val_0_mse: 0.98952 |  0:24:46s
epoch 22 | loss: 0.99106 | val_0_mse: 0.98986 |  0:25:46s
epoch 23 | loss: 0.99078 | val_0_mse: 0.99022 |  0:26:38s
epoch 24 | loss: 0.99164 | val_0_mse: 0.98978 |  0:27:31s
epoch 25 | loss: 0.99126 | val_0_mse: 0.98969 |  0:28:42s
epoch 26 | loss: 0.99093 | val_0_mse: 0.98943 |  0:29:50s
epoch 27 | loss: 0.99103 | val_0_mse: 0.99027 |  0:30:59s
epoch 28 | loss: 0.99161 | val_0_mse: 0.98995 |  0:32:08s
epoch 29 | loss: 0.99151 | val_0_mse: 0.99026 |  0:33:17s
Stop training because you reached max_epochs = 30 with best_epoch = 26 and best_val_0_mse = 0.98943
Best weights from best epoch are automatically used!

Device used : cuda

Device used : cuda

epoch 0  | loss: 1.03356 | val_0_mse: 0.99151 |  0:01:12s
epoch 1  | loss: 0.99349 | val_0_mse: 0.99174 |  0:02:27s
epoch 2  | loss: 0.99309 | val_0_mse: 0.99197 |  0:03:43s
epoch 3  | loss: 0.99297 | val_0_mse: 0.99182 |  0:04:57s
epoch 4  | loss: 0.99276 | val_0_mse: 0.99115 |  0:06:10s
epoch 5  | loss: 0.99221 | val_0_mse: 0.99065 |  0:07:22s
epoch 6  | loss: 0.99182 | val_0_mse: 0.99067 |  0:08:42s
epoch 7  | loss: 0.99149 | val_0_mse: 0.99052 |  0:09:55s
epoch 8  | loss: 0.99162 | val_0_mse: 0.99051 |  0:11:07s
epoch 9  | loss: 0.99122 | val_0_mse: 0.99046 |  0:12:25s
epoch 10 | loss: 0.99126 | val_0_mse: 0.99043 |  0:13:38s
epoch 11 | loss: 0.99128 | val_0_mse: 0.99032 |  0:14:53s
epoch 12 | loss: 0.99149 | val_0_mse: 0.99083 |  0:16:07s
epoch 13 | loss: 0.99174 | val_0_mse: 0.99063 |  0:17:23s
epoch 14 | loss: 0.99139 | val_0_mse: 0.99121 |  0:18:34s
epoch 15 | loss: 0.99137 | val_0_mse: 0.99019 |  0:19:43s
epoch 16 | loss: 0.99148 | val_0_mse: 0.99059 |  0:20:59s
epoch 17 | loss: 0.99157 | val_0_mse: 0.99068 |  0:22:02s
epoch 18 | loss: 0.99168 | val_0_mse: 0.99063 |  0:23:04s
epoch 19 | loss: 0.99182 | val_0_mse: 0.99073 |  0:24:06s
epoch 20 | loss: 0.99181 | val_0_mse: 0.99063 |  0:25:22s
epoch 21 | loss: 0.99191 | val_0_mse: 0.99161 |  0:26:31s
epoch 22 | loss: 0.99167 | val_0_mse: 0.99044 |  0:27:43s
epoch 23 | loss: 0.9916  | val_0_mse: 0.99065 |  0:28:59s
epoch 24 | loss: 0.99184 | val_0_mse: 0.99042 |  0:30:12s
epoch 25 | loss: 0.99189 | val_0_mse: 0.99097 |  0:31:30s

Early stopping occurred at epoch 25 with best_epoch = 15 and best_val_0_mse = 0.99019
Best weights from best epoch are automatically used!

Device used : cuda

++++++++: 7 [{'m1': {'version': 'v3', 'data': DataSource(68241c363eb24493ad10071c3ac32243T)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(07687271c4434de190c8a7e939cf6b44T), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(3b813c49cb56448a83011000121dd77eT)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(aed725224fb8446ea7ae455a9bcdaa18T)}, 'm7': {'version': 'v3', 'data': DataSource(05c6ea69f48a4bdd99e267290fd1177cT)}, 'm13': {'version': 'v3', 'data': DataSource(0ab434fa4ac044f68eebea4c2f1e6fa2T)}, 'm14': {'version': 'v3', 'data': DataSource(7cc1b59c2f614d129f7227c6b8855490T)}, 'm4': {'version': 'v3', 'data': DataSource(487b8ca11e7d48f0b3821cab692f0adaT), 'rows': 566116}, 'm10': {'version': 'v3', 'data': DataSource(4417778d5cb04c7393a71c44e4b9a78cT)}, 'm12': {'version': 'v3', 'data_1': DataSource(b3549480699749c8b04fb5ad5d08c1cdT), 'data_2': DataSource(f078da3883994ac2a992815d846e8159T), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(0e785dd8f73a4df5b0a6b7add3d6df09T)}, 'm5': {'version': 'v3', 'data': DataSource(55dfc437f42c4344a1cbaaaa93554a85T)}, 'm8': {'version': 'v3', 'data': DataSource(8c00872ffb114f59a6944fc98fe4dc50T)}, 'm9': {'version': 'v3', 'data': DataSource(2b7564f990e34d9c8a6b7afe5d57bcf4T)}, 'm16': {'version': 'v3', 'data': DataSource(0851cbc826d44770b02bf7458aebc807T)}, 'm15': {'version': 'v3', 'data': DataSource(144e22288ba04da4b08a3b75b0f5238bT)}, 'm11': {'version': 'v3', 'data': DataSource(afc4efab90164a1d91d90a4ce81ec54dT)}, 'm19': {'version': 'v3', 'data': DataSource(4bb5392733a44b3d9fa5660906c8c46fT)}, 'm20': {'version': 'v3', 'data_1': DataSource(a83d2cefc5f74f399bf9fd7dbbc904a7T), 'data_2': None, 'data_3': None}}, {'m1': {'version': 'v3', 'data': DataSource(6764f54e10af4db3ae79934152ca0f4aT)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(dc215323d944416485bcedcdbc5e22a3T), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(9834c15003784c5dbe935d10cadeafc7T)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(dd96e8ddefa449a5aca032726f30a591T)}, 'm7': {'version': 'v3', 'data': DataSource(0d2a60a0ad654ced8e45b8dfcb66ee22T)}, 'm13': {'version': 'v3', 'data': DataSource(c0b454ad5c6c487cab6e0ecfea1b7004T)}, 'm14': {'version': 'v3', 'data': DataSource(0dd7cba56ec04f4da074b0fdb9fbdb5eT)}, 'm4': {'version': 'v3', 'data': DataSource(4975e14163804fa0b708b2384fc5594dT), 'rows': 1141540}, 'm10': {'version': 'v3', 'data': DataSource(d4c2485dd5de41959c7e6cbea17ce1ceT)}, 'm12': {'version': 'v3', 'data_1': DataSource(e1a78946399f4b30abd82cb1841ca619T), 'data_2': DataSource(2be23289368b4835b9cab5861e4d54a0T), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(9ff6a613e1154e0e809563652f7a2f67T)}, 'm5': {'version': 'v3', 'data': DataSource(8fc2f2637aa64d0aa40358baab1ffc81T)}, 'm8': {'version': 'v3', 'data': DataSource(f23f304bd7ac4c2e96df4adf4c39d410T)}, 'm9': {'version': 'v3', 'data': DataSource(0a78723f5d3547eb9d0c02d84eb9f277T)}, 'm16': {'version': 'v3', 'data': DataSource(4c9784372a164c0c82765d60d6f3b5f2T)}, 'm15': {'version': 'v3', 'data': DataSource(3bc7660a50064d1eb6a13247460c627bT)}, 'm11': {'version': 'v3', 'data': DataSource(889dee009d744733b3d16e2b8c1359d8T)}, 'm19': {'version': 'v3', 'data': DataSource(077c44be68474f2f9f8cb79687b3d040T)}, 'm20': {'version': 'v3', 'data_1': DataSource(427cee2a3db9408c9b5eaf0f4c283fb4T), 'data_2': None, 'data_3': None}}, {'m1': {'version': 'v3', 'data': DataSource(c5214ee8cc7242b1a8820afe89d2b9eaT)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(5a55a1d2d2fd4805bbf98d84b1c70fd7T), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(184382a45e52447ba677e8c5c83a9c42T)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(49e5f9ab814145ccb9521c4029f0d641T)}, 'm7': {'version': 'v3', 'data': DataSource(a270d6cf1e1f463c89323d1ab47a4cc2T)}, 'm13': {'version': 'v3', 'data': DataSource(67d0038e409140e49466421794c089fbT)}, 'm14': {'version': 'v3', 'data': DataSource(40430d19efb14794be1921bdcabf9b0dT)}, 'm4': {'version': 'v3', 'data': DataSource(446063f5c0c64b9783018d8342ab2e08T), 'rows': 1797897}, 'm10': {'version': 'v3', 'data': DataSource(4e5336dcb6344f399017c1b7010e14c9T)}, 'm12': {'version': 'v3', 'data_1': DataSource(0604f63da4764d66838b16e9d8bad16cT), 'data_2': DataSource(d5c6c87eb306461da8d6d668d425b0c2T), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(11c2b95b99b24492b3adefcc1b16c7fcT)}, 'm5': {'version': 'v3', 'data': DataSource(d8d57f3bdcb549bb9723902250a74236T)}, 'm8': {'version': 'v3', 'data': DataSource(8d7c292f90414c5bbdd714473d2cc230T)}, 'm9': {'version': 'v3', 'data': DataSource(a4d58ed1d48b4138b6e8a1925bb8eca7T)}, 'm16': {'version': 'v3', 'data': DataSource(bc59bc0b0d564f0c85e62e53a9069fa9T)}, 'm15': {'version': 'v3', 'data': DataSource(bfd711bdbafc42dc85db9c474e4fd823T)}, 'm11': {'version': 'v3', 'data': DataSource(ac8e200cae8742128bfa1ef75f4cbc74T)}, 'm19': {'version': 'v3', 'data': DataSource(53c5afd8d892493fb705bec27a7670b9T)}, 'm20': {'version': 'v3', 'data_1': DataSource(b96c346559074f9c96559c39109937bcT), 'data_2': None, 'data_3': None}}, {'m1': {'version': 'v3', 'data': DataSource(be58a1d632914170b97ecaf845954443T)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(10749d1cb3ee4747bb33f3d51e91c360T), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(4479649d148242e3b08187b4902ebe30T)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(d08172a096564eb3a6a1954e911f7c01T)}, 'm7': {'version': 'v3', 'data': DataSource(f68bcfc6f800442a9379a2408f70fbabT)}, 'm13': {'version': 'v3', 'data': DataSource(424f93b8da8f49c0a934f1325468e9deT)}, 'm14': {'version': 'v3', 'data': DataSource(c504229778504fcea2b5d13b015bf376T)}, 'm4': {'version': 'v3', 'data': DataSource(2c3e4402a134465eada1674f723b5828T), 'rows': 1981161}, 'm10': {'version': 'v3', 'data': DataSource(85560df344194c78a366e34a3e1166d1T)}, 'm12': {'version': 'v3', 'data_1': DataSource(8baf0f9cf2024bc79e49cfe42b9b1674T), 'data_2': DataSource(733c282718484f00b1a1c98a698521dbT), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(da9400e858e24413a7ef1836da1051e8T)}, 'm5': {'version': 'v3', 'data': DataSource(47cffbea080d4efeb799ca0c85494591T)}, 'm8': {'version': 'v3', 'data': DataSource(7ef6d342eb05495a869d64a20368b12fT)}, 'm9': {'version': 'v3', 'data': DataSource(0081046a65274befbd8808386e84cf07T)}, 'm16': {'version': 'v3', 'data': DataSource(f854361cb2394624b01ebc7e34a0a426T)}, 'm15': {'version': 'v3', 'data': DataSource(668dceab15e3407eb8067bf199a10341T)}, 'm11': {'version': 'v3', 'data': DataSource(392af57f1f154cbd94ad906bb8cfd554T)}, 'm19': {'version': 'v3', 'data': DataSource(8f3c39c78e0f42cabfc53115adfcd34bT)}, 'm20': {'version': 'v3', 'data_1': DataSource(cdeec7bee11344208c72c166efa41447T), 'data_2': None, 'data_3': None}}, {'m1': {'version': 'v3', 'data': DataSource(949bd164c7f446189b53c4b84adc6a3dT)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(2dad080ace644086843a0bfef2173195T), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(1dd0c69aaee347509614a0901fd27163T)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(af9b87add46b4df499e305b1d318e3feT)}, 'm7': {'version': 'v3', 'data': DataSource(d235251865f546c2bb4aaec7e754f844T)}, 'm13': {'version': 'v3', 'data': DataSource(fdd15e81316b4942aa78e9290df1d70eT)}, 'm14': {'version': 'v3', 'data': DataSource(e966c94f7e6e4f98bbfd26a43f4008deT)}, 'm4': {'version': 'v3', 'data': DataSource(323150161df04097a47cbd685aeedc68T), 'rows': 2248763}, 'm10': {'version': 'v3', 'data': DataSource(c4fbafe9dc53444394bf38974845a4c1T)}, 'm12': {'version': 'v3', 'data_1': DataSource(db79f7cf8b5d42f38608fe10c375eb77T), 'data_2': DataSource(e81fc157c2404c5da8481c0c22a648e5T), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(3c831e5c55b04dfeacaeefe15237e047T)}, 'm5': {'version': 'v3', 'data': DataSource(d173fe56f32049dc852031782df6b9ecT)}, 'm8': {'version': 'v3', 'data': DataSource(6d850e68d4404d88a805cb4aed1f0562T)}, 'm9': {'version': 'v3', 'data': DataSource(4d69d6e8ffce48e7bd127e0ebbd51f8aT)}, 'm16': {'version': 'v3', 'data': DataSource(0f1e1c1a798846dd8af14c58b498b489T)}, 'm15': {'version': 'v3', 'data': DataSource(f64336fd81184579a0da257a1665aca2T)}, 'm11': {'version': 'v3', 'data': DataSource(009fb83ce1db4c58931d024fb7e0c354T)}, 'm19': {'version': 'v3', 'data': DataSource(c1794cd0ecc14541ac61dc721ef690feT)}, 'm20': {'version': 'v3', 'data_1': DataSource(a02325a94a194fed85df5658212e3323T), 'data_2': None, 'data_3': None}}, {'m1': {'version': 'v3', 'data': DataSource(efcffce5551846c191742f9df88ac35aT)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(52b6fe1b1c374706b8789edfd27c95c3T), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(b6caa0dc0b424db09194ba197035a422T)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(bdaf158b26ce4cdd8d0e5b56107ab552T)}, 'm7': {'version': 'v3', 'data': DataSource(021635067f0440afaf92dcb10d6ded79T)}, 'm13': {'version': 'v3', 'data': DataSource(ef24dded70f34273837d4731e12c019dT)}, 'm14': {'version': 'v3', 'data': DataSource(e4c3c2c0f9434f5e89b37c852a301aaeT)}, 'm4': {'version': 'v3', 'data': DataSource(e7e4b3c9f35b457bb9d61d587e81eff7T), 'rows': 2496821}, 'm10': {'version': 'v3', 'data': DataSource(a0358fcac82c4c9c9fab413a2c802f84T)}, 'm12': {'version': 'v3', 'data_1': DataSource(ee415aeedc2844a19133adc786c064f6T), 'data_2': DataSource(7289e73797dd4e19889daea531c34c95T), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(18b307e3a3b74e91a6c70962ae16fa0bT)}, 'm5': {'version': 'v3', 'data': DataSource(eda90ea93b4d494e92e6a561e888b92dT)}, 'm8': {'version': 'v3', 'data': DataSource(d8d52f0a0c1042c5b46aa3791d185fbcT)}, 'm9': {'version': 'v3', 'data': DataSource(311c0868124f47a6b2b04d1fa6841d5cT)}, 'm16': {'version': 'v3', 'data': DataSource(c2d4c402839844c599b783725e8edaaeT)}, 'm15': {'version': 'v3', 'data': DataSource(40aa467f69d149668fcb3c426d3819a8T)}, 'm11': {'version': 'v3', 'data': DataSource(b08f70790d304c6d825d74b41853187fT)}, 'm19': {'version': 'v3', 'data': DataSource(956b268c1c7b452eb23c864aad4efbaaT)}, 'm20': {'version': 'v3', 'data_1': DataSource(7781f514ba184b12bbeb810ac1232eddT), 'data_2': None, 'data_3': None}}, {'m1': {'version': 'v3', 'data': DataSource(65c31817e9f8478b82d74b7b555918a2T)}, 'm2': {'version': 'v3', 'cast_label_int': False, 'data': DataSource(af2305ba05b44d62991dfb713a52222eT), 'plot_label_counts': <bound method plot_label_counts of {...}>}, 'm17': {'version': 'v3', 'data': DataSource(4d9862db5ff74c2888ec5beedf6ba7bfT)}, 'm3': {'version': 'v3', 'data': DataSource(d959f1c34b7c48ebafc615a565b36afaT)}, 'm6': {'version': 'v3', 'data': DataSource(d0c9b9a2ffde4c598a50562ea1f91b8fT)}, 'm7': {'version': 'v3', 'data': DataSource(8c0b2aec1e2d47cbb9e26107217b8913T)}, 'm13': {'version': 'v3', 'data': DataSource(ed9eaf7e985d4633892f8037c6d9c67fT)}, 'm14': {'version': 'v3', 'data': DataSource(5893545664f14b5e90a3b289644c3578T)}, 'm4': {'version': 'v3', 'data': DataSource(2fc213398d1a493698eca41b451c1317T), 'rows': 2713676}, 'm10': {'version': 'v3', 'data': DataSource(5c5793a069af46e286fd979eb9248a25T)}, 'm12': {'version': 'v3', 'data_1': DataSource(6ac295b77ed145b0ba293779f3a622f8T), 'data_2': DataSource(5f390f00a9b54c5199b52bb392a301d2T), 'data_3': None}, 'm18': {'version': 'v3', 'data': DataSource(f63a72dbbd8047389d65fdea0b706581T)}, 'm5': {'version': 'v3', 'data': DataSource(825828a4aff24dacaa7f865a9a575a00T)}, 'm8': {'version': 'v3', 'data': DataSource(fd4d1fa600e342caabef8066a6322d14T)}, 'm9': {'version': 'v3', 'data': DataSource(2eff61c64b9b475c8357f5d595815469T)}, 'm16': {'version': 'v3', 'data': DataSource(aeecc098b835403e8ce552ea7b3256abT)}, 'm15': {'version': 'v3', 'data': DataSource(431c731855564f4090efaee9523e5d68T)}, 'm11': {'version': 'v3', 'data': DataSource(de15534726b944c1a7e2862467472208T)}, 'm19': {'version': 'v3', 'data': DataSource(cd185363b9494ccf80ef0298a867c141T)}, 'm20': {'version': 'v3', 'data_1': DataSource(886a826a37004f52a1f3058e0e452598T), 'data_2': None, 'data_3': None}}]

收益率387.81%
年化收益率27.57%
基准收益率39.0%
阿尔法0.25
贝塔0.9
夏普比率0.83
胜率0.56
盈亏比1.02
收益波动率31.92%
信息比率0.06
最大回撤55.22%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-1eb4e82158a046928183665543e3b620"}/bigcharts-data-end