复制链接

克隆策略

In [3]:

# 本代码由可视化策略环境自动生成 2022年7月30日 10:55
# 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 m10_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'])
    data_1 = DataSource.write_pickle({'x': x_train, 'y': y_train})
    data_2 = DataSource.write_pickle({'x': x_val, 'y': y_val})
    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 m10_post_run_bigquant_run(outputs):
    return outputs

from tensorflow.keras.callbacks import EarlyStopping
m5_earlystop_bigquant_run=EarlyStopping(monitor='val_mse', min_delta=0.0001, patience=5)
# 用户的自定义层需要写到字典中，比如
# {
#   "MyLayer": MyLayer
# }
m5_custom_objects_bigquant_run = {
 
}

# 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 m24_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 m24_post_run_bigquant_run(outputs):
    return outputs

# 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 = 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'] = 22

# 回测引擎：每日数据处理函数，每天执行一次
def m19_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]

    # 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):
    pass


m1 = M.instruments.v2(
    start_date='2017-01-01',
    end_date='2020-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -22) / 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)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=False
)

m29 = M.standardlize.v8(
    input_1=m2.data,
    columns_input='label'
)

m3 = M.input_features.v1(
    features="""mean(close_0, 22)
mean(low_0, 22)
mean(open_0, 22)
mean(high_0, 22)
mean(turn_0, 22)
mean(amount_0, 22)
mean(return_0, 22)
 
ts_max(close_0, 22)
ts_max(low_0, 22)
ts_max(open_0, 22)
ts_max(high_0, 22)
ts_max(turn_0, 22)
ts_max(amount_0, 22)
ts_max(return_0, 22)
 
ts_min(close_0, 22)
ts_min(low_0, 22)
ts_min(open_0, 22)
ts_min(high_0, 22)
ts_min(turn_0, 22)
ts_min(amount_0, 22)
ts_min(return_0, 22) 
 
std(close_0, 22)
std(low_0, 22)
std(open_0, 22)
std(high_0, 22)
std(turn_0, 22)
std(amount_0, 22)
std(return_0, 22)
 
ts_rank(close_0, 22)
ts_rank(low_0, 22)
ts_rank(open_0, 22)
ts_rank(high_0, 22)
ts_rank(turn_0, 22)
ts_rank(amount_0, 22)
ts_rank(return_0, 22)
 
decay_linear(close_0, 22)
decay_linear(low_0, 22)
decay_linear(open_0, 22)
decay_linear(high_0, 22)
decay_linear(turn_0, 22)
decay_linear(amount_0, 22)
decay_linear(return_0, 22)
 
correlation(volume_0, return_0, 22)
correlation(volume_0, high_0, 22)
correlation(volume_0, low_0, 22)
correlation(volume_0, close_0, 22)
correlation(volume_0, open_0, 22)
correlation(volume_0, turn_0, 22)
  
correlation(return_0, high_0, 22)
correlation(return_0, low_0, 22)
correlation(return_0, close_0, 22)
correlation(return_0, open_0, 22)
correlation(return_0, turn_0, 22)
 
correlation(high_0, low_0, 22)
correlation(high_0, close_0, 22)
correlation(high_0, open_0, 22)
correlation(high_0, turn_0, 22)
 
correlation(low_0, close_0, 22)
correlation(low_0, open_0, 22)
correlation(low_0, turn_0, 22)
 
correlation(close_0, open_0, 22)
correlation(close_0, turn_0, 22)

correlation(open_0, turn_0, 22)"""
)

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

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

m28 = M.standardlize.v8(
    input_1=m16.data,
    input_2=m3.data,
    columns_input='[]'
)

m13 = M.fillnan.v1(
    input_data=m28.data,
    features=m3.data,
    fill_value='0.0'
)

m7 = M.join.v3(
    data1=m29.data,
    data2=m13.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m26 = M.dl_convert_to_bin.v2(
    input_data=m7.data,
    features=m3.data,
    window_size=1,
    feature_clip=3,
    flatten=True,
    window_along_col='instrument'
)

m10 = M.cached.v3(
    input_1=m26.data,
    run=m10_run_bigquant_run,
    post_run=m10_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2022-01-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

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

m25 = M.standardlize.v8(
    input_1=m18.data,
    input_2=m3.data,
    columns_input='[]'
)

m14 = M.fillnan.v1(
    input_data=m25.data,
    features=m3.data,
    fill_value='0.0'
)

m27 = M.dl_convert_to_bin.v2(
    input_data=m14.data,
    features=m3.data,
    window_size=1,
    feature_clip=3,
    flatten=True,
    window_along_col='instrument'
)

m6 = M.dl_layer_input.v1(
    shape='63',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m8 = M.dl_layer_dense.v1(
    inputs=m6.data,
    units=256,
    activation='relu',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m21 = M.dl_layer_dropout.v1(
    inputs=m8.data,
    rate=0.1,
    noise_shape='',
    name=''
)

m20 = M.dl_layer_dense.v1(
    inputs=m21.data,
    units=128,
    activation='relu',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m22 = M.dl_layer_dropout.v1(
    inputs=m20.data,
    rate=0.1,
    noise_shape='',
    name=''
)

m23 = M.dl_layer_dense.v1(
    inputs=m22.data,
    units=1,
    activation='linear',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m4 = M.dl_model_init.v1(
    inputs=m6.data,
    outputs=m23.data
)

m5 = M.dl_model_train.v1(
    input_model=m4.data,
    training_data=m10.data_1,
    validation_data=m10.data_2,
    optimizer='Adam',
    loss='mean_squared_error',
    metrics='mse',
    batch_size=1024,
    epochs=30,
    earlystop=m5_earlystop_bigquant_run,
    custom_objects=m5_custom_objects_bigquant_run,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录',
    m_cached=False
)

m11 = M.dl_model_predict.v1(
    trained_model=m5.data,
    input_data=m27.data,
    batch_size=1024,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录'
)

m24 = M.cached.v3(
    input_1=m11.data,
    input_2=m18.data,
    run=m24_run_bigquant_run,
    post_run=m24_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m24.data_1,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.SHA'
)

[2022-07-30 10:08:10.035976] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-07-30 10:08:10.598000] INFO: moduleinvoker: 命中缓存

[2022-07-30 10:08:10.610958] INFO: moduleinvoker: instruments.v2 运行完成[0.580056s].

[2022-07-30 10:08:10.636822] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-07-30 10:08:10.646180] INFO: moduleinvoker: 命中缓存

[2022-07-30 10:08:10.657084] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.02027s].

[2022-07-30 10:08:10.676878] INFO: moduleinvoker: standardlize.v8 开始运行..

[2022-07-30 10:08:10.686966] INFO: moduleinvoker: 命中缓存

[2022-07-30 10:08:10.692688] INFO: moduleinvoker: standardlize.v8 运行完成[0.015809s].

[2022-07-30 10:08:10.713399] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-07-30 10:08:10.803582] INFO: moduleinvoker: input_features.v1 运行完成[0.090212s].

[2022-07-30 10:08:10.851606] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-07-30 10:08:17.853041] INFO: 基础特征抽取: 年份 2017, 特征行数=743233

[2022-07-30 10:08:20.434688] INFO: 基础特征抽取: 年份 2018, 特征行数=816987

[2022-07-30 10:08:23.047524] INFO: 基础特征抽取: 年份 2019, 特征行数=884867

[2022-07-30 10:08:25.748869] INFO: 基础特征抽取: 年份 2020, 特征行数=945961

[2022-07-30 10:08:25.935547] INFO: 基础特征抽取: 总行数: 3391048

[2022-07-30 10:08:25.948294] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[15.09631s].

[2022-07-30 10:08:25.960470] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-30 10:08:34.957499] INFO: derived_feature_extractor: 提取完成 mean(close_0, 22), 2.803s

[2022-07-30 10:08:37.266044] INFO: derived_feature_extractor: 提取完成 mean(low_0, 22), 2.307s

[2022-07-30 10:08:39.608982] INFO: derived_feature_extractor: 提取完成 mean(open_0, 22), 2.341s

[2022-07-30 10:08:41.851397] INFO: derived_feature_extractor: 提取完成 mean(high_0, 22), 2.241s

[2022-07-30 10:08:44.177421] INFO: derived_feature_extractor: 提取完成 mean(turn_0, 22), 2.324s

[2022-07-30 10:08:46.476841] INFO: derived_feature_extractor: 提取完成 mean(amount_0, 22), 2.298s

[2022-07-30 10:08:48.749323] INFO: derived_feature_extractor: 提取完成 mean(return_0, 22), 2.271s

[2022-07-30 10:08:51.076340] INFO: derived_feature_extractor: 提取完成 ts_max(close_0, 22), 2.325s

[2022-07-30 10:08:53.638312] INFO: derived_feature_extractor: 提取完成 ts_max(low_0, 22), 2.560s

[2022-07-30 10:08:56.125980] INFO: derived_feature_extractor: 提取完成 ts_max(open_0, 22), 2.486s

[2022-07-30 10:08:58.582810] INFO: derived_feature_extractor: 提取完成 ts_max(high_0, 22), 2.454s

[2022-07-30 10:09:01.027552] INFO: derived_feature_extractor: 提取完成 ts_max(turn_0, 22), 2.443s

[2022-07-30 10:09:03.773708] INFO: derived_feature_extractor: 提取完成 ts_max(amount_0, 22), 2.745s

[2022-07-30 10:09:06.539088] INFO: derived_feature_extractor: 提取完成 ts_max(return_0, 22), 2.764s

[2022-07-30 10:09:09.155942] INFO: derived_feature_extractor: 提取完成 ts_min(close_0, 22), 2.615s

[2022-07-30 10:09:11.674287] INFO: derived_feature_extractor: 提取完成 ts_min(low_0, 22), 2.517s

[2022-07-30 10:09:14.226750] INFO: derived_feature_extractor: 提取完成 ts_min(open_0, 22), 2.551s

[2022-07-30 10:09:16.685193] INFO: derived_feature_extractor: 提取完成 ts_min(high_0, 22), 2.457s

[2022-07-30 10:09:19.206524] INFO: derived_feature_extractor: 提取完成 ts_min(turn_0, 22), 2.520s

[2022-07-30 10:09:21.682700] INFO: derived_feature_extractor: 提取完成 ts_min(amount_0, 22), 2.474s

[2022-07-30 10:09:24.135379] INFO: derived_feature_extractor: 提取完成 ts_min(return_0, 22), 2.451s

[2022-07-30 10:09:26.512024] INFO: derived_feature_extractor: 提取完成 std(close_0, 22), 2.375s

[2022-07-30 10:09:28.854849] INFO: derived_feature_extractor: 提取完成 std(low_0, 22), 2.341s

[2022-07-30 10:09:31.337106] INFO: derived_feature_extractor: 提取完成 std(open_0, 22), 2.480s

[2022-07-30 10:09:33.746720] INFO: derived_feature_extractor: 提取完成 std(high_0, 22), 2.407s

[2022-07-30 10:09:36.203796] INFO: derived_feature_extractor: 提取完成 std(turn_0, 22), 2.455s

[2022-07-30 10:09:38.663421] INFO: derived_feature_extractor: 提取完成 std(amount_0, 22), 2.458s

[2022-07-30 10:09:41.070015] INFO: derived_feature_extractor: 提取完成 std(return_0, 22), 2.405s

[2022-07-30 10:09:53.151149] INFO: derived_feature_extractor: 提取完成 ts_rank(close_0, 22), 12.079s

[2022-07-30 10:10:05.101098] INFO: derived_feature_extractor: 提取完成 ts_rank(low_0, 22), 11.947s

[2022-07-30 10:10:17.343391] INFO: derived_feature_extractor: 提取完成 ts_rank(open_0, 22), 12.240s

[2022-07-30 10:10:29.635479] INFO: derived_feature_extractor: 提取完成 ts_rank(high_0, 22), 12.290s

[2022-07-30 10:10:42.621691] INFO: derived_feature_extractor: 提取完成 ts_rank(turn_0, 22), 12.984s

[2022-07-30 10:10:54.641460] INFO: derived_feature_extractor: 提取完成 ts_rank(amount_0, 22), 12.018s

[2022-07-30 10:11:06.866351] INFO: derived_feature_extractor: 提取完成 ts_rank(return_0, 22), 12.223s

[2022-07-30 10:11:22.778670] INFO: derived_feature_extractor: 提取完成 decay_linear(close_0, 22), 15.910s

[2022-07-30 10:11:30.441891] INFO: derived_feature_extractor: 提取完成 decay_linear(low_0, 22), 7.661s

[2022-07-30 10:11:37.698035] INFO: derived_feature_extractor: 提取完成 decay_linear(open_0, 22), 7.254s

[2022-07-30 10:11:44.520243] INFO: derived_feature_extractor: 提取完成 decay_linear(high_0, 22), 6.820s

[2022-07-30 10:11:51.643756] INFO: derived_feature_extractor: 提取完成 decay_linear(turn_0, 22), 7.122s

[2022-07-30 10:11:58.531019] INFO: derived_feature_extractor: 提取完成 decay_linear(amount_0, 22), 6.885s

[2022-07-30 10:12:06.151263] INFO: derived_feature_extractor: 提取完成 decay_linear(return_0, 22), 7.618s

[2022-07-30 10:13:04.235996] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, return_0, 22), 58.083s

[2022-07-30 10:13:39.100207] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, high_0, 22), 34.862s

[2022-07-30 10:14:10.181767] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, low_0, 22), 31.079s

[2022-07-30 10:14:40.480214] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, close_0, 22), 30.296s

[2022-07-30 10:15:08.714724] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, open_0, 22), 28.232s

[2022-07-30 10:15:38.196053] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, turn_0, 22), 29.479s

[2022-07-30 10:16:09.526394] INFO: derived_feature_extractor: 提取完成 correlation(return_0, high_0, 22), 31.329s

[2022-07-30 10:16:39.125790] INFO: derived_feature_extractor: 提取完成 correlation(return_0, low_0, 22), 29.597s

[2022-07-30 10:17:09.104325] INFO: derived_feature_extractor: 提取完成 correlation(return_0, close_0, 22), 29.977s

[2022-07-30 10:17:40.887353] INFO: derived_feature_extractor: 提取完成 correlation(return_0, open_0, 22), 31.781s

[2022-07-30 10:18:10.426276] INFO: derived_feature_extractor: 提取完成 correlation(return_0, turn_0, 22), 29.537s

[2022-07-30 10:18:41.382182] INFO: derived_feature_extractor: 提取完成 correlation(high_0, low_0, 22), 30.954s

[2022-07-30 10:19:12.559797] INFO: derived_feature_extractor: 提取完成 correlation(high_0, close_0, 22), 31.175s

[2022-07-30 10:19:41.917543] INFO: derived_feature_extractor: 提取完成 correlation(high_0, open_0, 22), 29.356s

[2022-07-30 10:20:15.729971] INFO: derived_feature_extractor: 提取完成 correlation(high_0, turn_0, 22), 33.811s

[2022-07-30 10:20:48.466862] INFO: derived_feature_extractor: 提取完成 correlation(low_0, close_0, 22), 32.735s

[2022-07-30 10:21:22.452726] INFO: derived_feature_extractor: 提取完成 correlation(low_0, open_0, 22), 33.984s

[2022-07-30 10:21:54.847369] INFO: derived_feature_extractor: 提取完成 correlation(low_0, turn_0, 22), 32.392s

[2022-07-30 10:22:27.206232] INFO: derived_feature_extractor: 提取完成 correlation(close_0, open_0, 22), 32.356s

[2022-07-30 10:23:01.137310] INFO: derived_feature_extractor: 提取完成 correlation(close_0, turn_0, 22), 33.928s

[2022-07-30 10:23:35.159059] INFO: derived_feature_extractor: 提取完成 correlation(open_0, turn_0, 22), 34.020s

[2022-07-30 10:23:53.280110] INFO: derived_feature_extractor: /y_2017, 743233

[2022-07-30 10:23:57.787757] INFO: derived_feature_extractor: /y_2018, 816987

[2022-07-30 10:24:02.744781] INFO: derived_feature_extractor: /y_2019, 884867

[2022-07-30 10:24:08.092599] INFO: derived_feature_extractor: /y_2020, 945961

[2022-07-30 10:24:11.618189] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[945.65771s].

[2022-07-30 10:24:11.625267] INFO: moduleinvoker: standardlize.v8 开始运行..

[2022-07-30 10:29:04.675955] INFO: moduleinvoker: standardlize.v8 运行完成[293.050662s].

[2022-07-30 10:29:04.686598] INFO: moduleinvoker: fillnan.v1 开始运行..

[2022-07-30 10:29:25.567686] INFO: moduleinvoker: fillnan.v1 运行完成[20.881081s].

[2022-07-30 10:29:25.582229] INFO: moduleinvoker: join.v3 开始运行..

[2022-07-30 10:30:14.784415] INFO: join: /data, 行数=3201371/3302750, 耗时=43.99291s

[2022-07-30 10:30:15.003613] INFO: join: 最终行数: 3201371

[2022-07-30 10:30:15.027344] INFO: moduleinvoker: join.v3 运行完成[49.445112s].

[2022-07-30 10:30:15.049562] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2022-07-30 10:30:36.441399] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[21.391889s].

[2022-07-30 10:30:36.458514] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-30 10:30:46.636901] INFO: moduleinvoker: cached.v3 运行完成[10.178389s].

[2022-07-30 10:30:46.643583] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-07-30 10:30:46.649192] INFO: moduleinvoker: 命中缓存

[2022-07-30 10:30:46.650835] INFO: moduleinvoker: instruments.v2 运行完成[0.007256s].

[2022-07-30 10:30:46.668038] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-07-30 10:30:49.656259] INFO: 基础特征抽取: 年份 2021, 特征行数=1061527

[2022-07-30 10:30:51.667899] INFO: 基础特征抽取: 年份 2022, 特征行数=0

[2022-07-30 10:30:51.725202] INFO: 基础特征抽取: 总行数: 1061527

[2022-07-30 10:30:51.731706] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[5.063666s].

[2022-07-30 10:30:51.742117] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-30 10:30:54.266346] INFO: derived_feature_extractor: 提取完成 mean(close_0, 22), 0.732s

[2022-07-30 10:30:54.973234] INFO: derived_feature_extractor: 提取完成 mean(low_0, 22), 0.705s

[2022-07-30 10:30:55.727857] INFO: derived_feature_extractor: 提取完成 mean(open_0, 22), 0.753s

[2022-07-30 10:30:56.453619] INFO: derived_feature_extractor: 提取完成 mean(high_0, 22), 0.723s

[2022-07-30 10:30:57.244719] INFO: derived_feature_extractor: 提取完成 mean(turn_0, 22), 0.789s

[2022-07-30 10:30:58.046412] INFO: derived_feature_extractor: 提取完成 mean(amount_0, 22), 0.800s

[2022-07-30 10:30:58.834674] INFO: derived_feature_extractor: 提取完成 mean(return_0, 22), 0.786s

[2022-07-30 10:30:59.569107] INFO: derived_feature_extractor: 提取完成 ts_max(close_0, 22), 0.733s

[2022-07-30 10:31:00.357371] INFO: derived_feature_extractor: 提取完成 ts_max(low_0, 22), 0.787s

[2022-07-30 10:31:01.083688] INFO: derived_feature_extractor: 提取完成 ts_max(open_0, 22), 0.724s

[2022-07-30 10:31:01.826705] INFO: derived_feature_extractor: 提取完成 ts_max(high_0, 22), 0.741s

[2022-07-30 10:31:02.563204] INFO: derived_feature_extractor: 提取完成 ts_max(turn_0, 22), 0.735s

[2022-07-30 10:31:03.290684] INFO: derived_feature_extractor: 提取完成 ts_max(amount_0, 22), 0.726s

[2022-07-30 10:31:04.122766] INFO: derived_feature_extractor: 提取完成 ts_max(return_0, 22), 0.830s

[2022-07-30 10:31:04.877400] INFO: derived_feature_extractor: 提取完成 ts_min(close_0, 22), 0.753s

[2022-07-30 10:31:05.625458] INFO: derived_feature_extractor: 提取完成 ts_min(low_0, 22), 0.746s

[2022-07-30 10:31:06.383260] INFO: derived_feature_extractor: 提取完成 ts_min(open_0, 22), 0.756s

[2022-07-30 10:31:07.140790] INFO: derived_feature_extractor: 提取完成 ts_min(high_0, 22), 0.756s

[2022-07-30 10:31:07.967400] INFO: derived_feature_extractor: 提取完成 ts_min(turn_0, 22), 0.825s

[2022-07-30 10:31:08.732318] INFO: derived_feature_extractor: 提取完成 ts_min(amount_0, 22), 0.763s

[2022-07-30 10:31:09.468188] INFO: derived_feature_extractor: 提取完成 ts_min(return_0, 22), 0.734s

[2022-07-30 10:31:10.199419] INFO: derived_feature_extractor: 提取完成 std(close_0, 22), 0.729s

[2022-07-30 10:31:10.946662] INFO: derived_feature_extractor: 提取完成 std(low_0, 22), 0.746s

[2022-07-30 10:31:11.656045] INFO: derived_feature_extractor: 提取完成 std(open_0, 22), 0.708s

[2022-07-30 10:31:12.406233] INFO: derived_feature_extractor: 提取完成 std(high_0, 22), 0.748s

[2022-07-30 10:31:13.137790] INFO: derived_feature_extractor: 提取完成 std(turn_0, 22), 0.730s

[2022-07-30 10:31:13.846391] INFO: derived_feature_extractor: 提取完成 std(amount_0, 22), 0.706s

[2022-07-30 10:31:14.573519] INFO: derived_feature_extractor: 提取完成 std(return_0, 22), 0.726s

[2022-07-30 10:31:18.039473] INFO: derived_feature_extractor: 提取完成 ts_rank(close_0, 22), 3.464s

[2022-07-30 10:31:21.477343] INFO: derived_feature_extractor: 提取完成 ts_rank(low_0, 22), 3.436s

[2022-07-30 10:31:24.883613] INFO: derived_feature_extractor: 提取完成 ts_rank(open_0, 22), 3.405s

[2022-07-30 10:31:28.362487] INFO: derived_feature_extractor: 提取完成 ts_rank(high_0, 22), 3.477s

[2022-07-30 10:31:31.886745] INFO: derived_feature_extractor: 提取完成 ts_rank(turn_0, 22), 3.523s

[2022-07-30 10:31:35.697355] INFO: derived_feature_extractor: 提取完成 ts_rank(amount_0, 22), 3.809s

[2022-07-30 10:31:39.207500] INFO: derived_feature_extractor: 提取完成 ts_rank(return_0, 22), 3.508s

[2022-07-30 10:31:41.248548] INFO: derived_feature_extractor: 提取完成 decay_linear(close_0, 22), 2.039s

[2022-07-30 10:31:43.571951] INFO: derived_feature_extractor: 提取完成 decay_linear(low_0, 22), 2.321s

[2022-07-30 10:31:45.841993] INFO: derived_feature_extractor: 提取完成 decay_linear(open_0, 22), 2.268s

[2022-07-30 10:31:48.066158] INFO: derived_feature_extractor: 提取完成 decay_linear(high_0, 22), 2.222s

[2022-07-30 10:31:50.090092] INFO: derived_feature_extractor: 提取完成 decay_linear(turn_0, 22), 2.022s

[2022-07-30 10:31:52.010387] INFO: derived_feature_extractor: 提取完成 decay_linear(amount_0, 22), 1.919s

[2022-07-30 10:31:53.878293] INFO: derived_feature_extractor: 提取完成 decay_linear(return_0, 22), 1.866s

[2022-07-30 10:32:23.484067] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, return_0, 22), 29.604s

[2022-07-30 10:32:54.972992] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, high_0, 22), 31.487s

[2022-07-30 10:33:26.577682] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, low_0, 22), 31.603s

[2022-07-30 10:33:54.950886] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, close_0, 22), 28.372s

[2022-07-30 10:34:25.524025] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, open_0, 22), 30.571s

[2022-07-30 10:34:57.362471] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, turn_0, 22), 31.837s

[2022-07-30 10:35:28.847454] INFO: derived_feature_extractor: 提取完成 correlation(return_0, high_0, 22), 31.483s

[2022-07-30 10:36:00.824988] INFO: derived_feature_extractor: 提取完成 correlation(return_0, low_0, 22), 31.976s

[2022-07-30 10:36:33.379861] INFO: derived_feature_extractor: 提取完成 correlation(return_0, close_0, 22), 32.553s

[2022-07-30 10:37:05.775889] INFO: derived_feature_extractor: 提取完成 correlation(return_0, open_0, 22), 32.394s

[2022-07-30 10:37:38.996816] INFO: derived_feature_extractor: 提取完成 correlation(return_0, turn_0, 22), 33.219s

[2022-07-30 10:38:11.384643] INFO: derived_feature_extractor: 提取完成 correlation(high_0, low_0, 22), 32.386s

[2022-07-30 10:38:44.933520] INFO: derived_feature_extractor: 提取完成 correlation(high_0, close_0, 22), 33.547s

[2022-07-30 10:39:17.780000] INFO: derived_feature_extractor: 提取完成 correlation(high_0, open_0, 22), 32.844s

[2022-07-30 10:39:50.009841] INFO: derived_feature_extractor: 提取完成 correlation(high_0, turn_0, 22), 32.228s

[2022-07-30 10:40:27.162244] INFO: derived_feature_extractor: 提取完成 correlation(low_0, close_0, 22), 37.150s

[2022-07-30 10:40:59.516711] INFO: derived_feature_extractor: 提取完成 correlation(low_0, open_0, 22), 32.353s

[2022-07-30 10:41:30.567267] INFO: derived_feature_extractor: 提取完成 correlation(low_0, turn_0, 22), 31.049s

[2022-07-30 10:42:00.856617] INFO: derived_feature_extractor: 提取完成 correlation(close_0, open_0, 22), 30.288s

[2022-07-30 10:42:32.358948] INFO: derived_feature_extractor: 提取完成 correlation(close_0, turn_0, 22), 31.500s

[2022-07-30 10:43:04.086607] INFO: derived_feature_extractor: 提取完成 correlation(open_0, turn_0, 22), 31.726s

[2022-07-30 10:43:06.854267] INFO: derived_feature_extractor: /y_2021, 1061527

[2022-07-30 10:43:11.275498] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[739.533372s].

[2022-07-30 10:43:11.282205] INFO: moduleinvoker: standardlize.v8 开始运行..

[2022-07-30 10:44:21.280156] INFO: moduleinvoker: standardlize.v8 运行完成[69.997935s].

[2022-07-30 10:44:21.290506] INFO: moduleinvoker: fillnan.v1 开始运行..

[2022-07-30 10:44:28.420970] INFO: moduleinvoker: fillnan.v1 运行完成[7.130449s].

[2022-07-30 10:44:28.438970] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2022-07-30 10:44:33.214724] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[4.775753s].

[2022-07-30 10:44:33.242632] INFO: moduleinvoker: dl_layer_input.v1 运行完成[0.018331s].

[2022-07-30 10:44:33.330666] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.07764s].

[2022-07-30 10:44:33.353702] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.014238s].

[2022-07-30 10:44:33.377539] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.016758s].

[2022-07-30 10:44:33.388630] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.004441s].

[2022-07-30 10:44:33.408707] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.013255s].

[2022-07-30 10:44:33.447680] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-30 10:44:33.481427] INFO: moduleinvoker: cached.v3 运行完成[0.033746s].

[2022-07-30 10:44:33.483955] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.068688s].

[2022-07-30 10:44:33.488299] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2022-07-30 10:44:36.090799] INFO: dl_model_train: 准备训练，训练样本个数：2401028，迭代次数：30

[2022-07-30 10:53:41.850584] INFO: dl_model_train: 训练结束，耗时：545.76s

[2022-07-30 10:53:41.891338] INFO: moduleinvoker: dl_model_train.v1 运行完成[548.403024s].

[2022-07-30 10:53:41.897010] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2022-07-30 10:53:44.992254] INFO: moduleinvoker: dl_model_predict.v1 运行完成[3.09525s].

[2022-07-30 10:53:45.005913] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-30 10:53:49.657557] INFO: moduleinvoker: cached.v3 运行完成[4.651657s].

[2022-07-30 10:53:49.732349] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-07-30 10:53:49.738407] INFO: backtest: biglearning backtest:V8.6.2

[2022-07-30 10:53:49.740291] INFO: backtest: product_type:stock by specified

[2022-07-30 10:53:49.891307] INFO: moduleinvoker: cached.v2 开始运行..

[2022-07-30 10:53:49.901610] INFO: moduleinvoker: 命中缓存

[2022-07-30 10:53:49.904048] INFO: moduleinvoker: cached.v2 运行完成[0.012763s].

[2022-07-30 10:53:52.122352] INFO: algo: TradingAlgorithm V1.8.8

[2022-07-30 10:53:52.923332] INFO: algo: trading transform...

[2022-07-30 10:54:04.243855] INFO: Performance: Simulated 243 trading days out of 243.

[2022-07-30 10:54:04.245468] INFO: Performance: first open: 2021-01-04 09:30:00+00:00

[2022-07-30 10:54:04.246672] INFO: Performance: last close: 2021-12-31 15:00:00+00:00

[2022-07-30 10:54:08.481409] INFO: moduleinvoker: backtest.v8 运行完成[18.749019s].

[2022-07-30 10:54:08.483788] INFO: moduleinvoker: trade.v4 运行完成[18.817526s].

Epoch 1/30
2345/2345 - 23s - loss: 0.9694 - mse: 0.9694 - val_loss: 0.9622 - val_mse: 0.9622
Epoch 2/30
2345/2345 - 18s - loss: 0.9618 - mse: 0.9618 - val_loss: 0.9551 - val_mse: 0.9551
Epoch 3/30
2345/2345 - 18s - loss: 0.9575 - mse: 0.9575 - val_loss: 0.9512 - val_mse: 0.9512
Epoch 4/30
2345/2345 - 19s - loss: 0.9537 - mse: 0.9537 - val_loss: 0.9471 - val_mse: 0.9471
Epoch 5/30
2345/2345 - 19s - loss: 0.9502 - mse: 0.9502 - val_loss: 0.9437 - val_mse: 0.9437
Epoch 6/30
2345/2345 - 18s - loss: 0.9470 - mse: 0.9470 - val_loss: 0.9410 - val_mse: 0.9410
Epoch 7/30
2345/2345 - 18s - loss: 0.9444 - mse: 0.9444 - val_loss: 0.9385 - val_mse: 0.9385
Epoch 8/30
2345/2345 - 19s - loss: 0.9416 - mse: 0.9416 - val_loss: 0.9366 - val_mse: 0.9366
Epoch 9/30
2345/2345 - 19s - loss: 0.9391 - mse: 0.9391 - val_loss: 0.9338 - val_mse: 0.9338
Epoch 10/30
2345/2345 - 19s - loss: 0.9365 - mse: 0.9365 - val_loss: 0.9322 - val_mse: 0.9322
Epoch 11/30
2345/2345 - 18s - loss: 0.9337 - mse: 0.9337 - val_loss: 0.9306 - val_mse: 0.9306
Epoch 12/30
2345/2345 - 18s - loss: 0.9316 - mse: 0.9316 - val_loss: 0.9280 - val_mse: 0.9280
Epoch 13/30
2345/2345 - 18s - loss: 0.9299 - mse: 0.9299 - val_loss: 0.9249 - val_mse: 0.9249
Epoch 14/30
2345/2345 - 18s - loss: 0.9274 - mse: 0.9274 - val_loss: 0.9237 - val_mse: 0.9237
Epoch 15/30
2345/2345 - 18s - loss: 0.9254 - mse: 0.9254 - val_loss: 0.9213 - val_mse: 0.9213
Epoch 16/30
2345/2345 - 18s - loss: 0.9239 - mse: 0.9239 - val_loss: 0.9213 - val_mse: 0.9213
Epoch 17/30
2345/2345 - 18s - loss: 0.9222 - mse: 0.9222 - val_loss: 0.9173 - val_mse: 0.9173
Epoch 18/30
2345/2345 - 18s - loss: 0.9205 - mse: 0.9205 - val_loss: 0.9160 - val_mse: 0.9160
Epoch 19/30
2345/2345 - 18s - loss: 0.9196 - mse: 0.9196 - val_loss: 0.9158 - val_mse: 0.9158
Epoch 20/30
2345/2345 - 18s - loss: 0.9180 - mse: 0.9180 - val_loss: 0.9142 - val_mse: 0.9142
Epoch 21/30
2345/2345 - 17s - loss: 0.9163 - mse: 0.9163 - val_loss: 0.9139 - val_mse: 0.9139
Epoch 22/30
2345/2345 - 18s - loss: 0.9150 - mse: 0.9150 - val_loss: 0.9111 - val_mse: 0.9111
Epoch 23/30
2345/2345 - 18s - loss: 0.9139 - mse: 0.9139 - val_loss: 0.9119 - val_mse: 0.9119
Epoch 24/30
2345/2345 - 18s - loss: 0.9125 - mse: 0.9125 - val_loss: 0.9100 - val_mse: 0.9100
Epoch 25/30
2345/2345 - 18s - loss: 0.9114 - mse: 0.9114 - val_loss: 0.9090 - val_mse: 0.9090
Epoch 26/30
2345/2345 - 18s - loss: 0.9107 - mse: 0.9107 - val_loss: 0.9079 - val_mse: 0.9079
Epoch 27/30
2345/2345 - 18s - loss: 0.9091 - mse: 0.9091 - val_loss: 0.9080 - val_mse: 0.9080
Epoch 28/30
2345/2345 - 18s - loss: 0.9081 - mse: 0.9081 - val_loss: 0.9063 - val_mse: 0.9063
Epoch 29/30
2345/2345 - 18s - loss: 0.9072 - mse: 0.9072 - val_loss: 0.9056 - val_mse: 0.9056
Epoch 30/30
2345/2345 - 17s - loss: 0.9065 - mse: 0.9065 - val_loss: 0.9037 - val_mse: 0.9037

941/941 - 2s
DataSource(fe22061fe33949a4a616c89f36a49a74T)

收益率29.34%
年化收益率30.58%
基准收益率-5.2%
阿尔法0.33
贝塔0.4
夏普比率1.22
胜率0.54
盈亏比1.57
收益波动率21.36%
信息比率0.09
最大回撤11.12%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-a2d4e5f5211148a8a7adb69ff443bd62"}/bigcharts-data-end