复制链接

克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2022年7月29日 22:50
# 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'] = 5

# 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, -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)
""",
    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="""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)"""
)

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='98',
    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'
)

[2022-07-29 21:57:08.996169] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-07-29 21:57:09.017039] INFO: moduleinvoker: 命中缓存

[2022-07-29 21:57:09.019231] INFO: moduleinvoker: instruments.v2 运行完成[0.023078s].

[2022-07-29 21:57:09.038052] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-07-29 21:57:09.046600] INFO: moduleinvoker: 命中缓存

[2022-07-29 21:57:09.447683] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.409623s].

[2022-07-29 21:57:09.462772] INFO: moduleinvoker: standardlize.v8 开始运行..

[2022-07-29 21:57:09.474961] INFO: moduleinvoker: 命中缓存

[2022-07-29 21:57:09.482624] INFO: moduleinvoker: standardlize.v8 运行完成[0.019853s].

[2022-07-29 21:57:09.495495] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-07-29 21:57:09.503773] INFO: moduleinvoker: 命中缓存

[2022-07-29 21:57:09.506576] INFO: moduleinvoker: input_features.v1 运行完成[0.011119s].

[2022-07-29 21:57:09.530860] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-07-29 21:57:09.539607] INFO: moduleinvoker: 命中缓存

[2022-07-29 21:57:09.542529] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011692s].

[2022-07-29 21:57:09.580470] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-29 21:57:22.105816] INFO: derived_feature_extractor: 提取完成 mean(close_0, 5), 2.704s

[2022-07-29 21:57:24.816728] INFO: derived_feature_extractor: 提取完成 mean(low_0, 5), 2.709s

[2022-07-29 21:57:27.470125] INFO: derived_feature_extractor: 提取完成 mean(open_0, 5), 2.652s

[2022-07-29 21:57:30.166874] INFO: derived_feature_extractor: 提取完成 mean(high_0, 5), 2.695s

[2022-07-29 21:57:32.723961] INFO: derived_feature_extractor: 提取完成 mean(turn_0, 5), 2.555s

[2022-07-29 21:57:35.312150] INFO: derived_feature_extractor: 提取完成 mean(amount_0, 5), 2.586s

[2022-07-29 21:57:45.705919] INFO: derived_feature_extractor: 提取完成 mean(return_0, 5), 10.392s

[2022-07-29 21:57:48.358769] INFO: derived_feature_extractor: 提取完成 ts_max(close_0, 5), 2.650s

[2022-07-29 21:57:51.075456] INFO: derived_feature_extractor: 提取完成 ts_max(low_0, 5), 2.715s

[2022-07-29 21:57:53.669897] INFO: derived_feature_extractor: 提取完成 ts_max(open_0, 5), 2.592s

[2022-07-29 21:57:56.315826] INFO: derived_feature_extractor: 提取完成 ts_max(high_0, 5), 2.643s

[2022-07-29 21:57:58.936521] INFO: derived_feature_extractor: 提取完成 ts_max(turn_0, 5), 2.619s

[2022-07-29 21:58:01.703817] INFO: derived_feature_extractor: 提取完成 ts_max(amount_0, 5), 2.765s

[2022-07-29 21:58:04.334035] INFO: derived_feature_extractor: 提取完成 ts_max(return_0, 5), 2.628s

[2022-07-29 21:58:06.941468] INFO: derived_feature_extractor: 提取完成 ts_min(close_0, 5), 2.605s

[2022-07-29 21:58:09.627310] INFO: derived_feature_extractor: 提取完成 ts_min(low_0, 5), 2.684s

[2022-07-29 21:58:12.267487] INFO: derived_feature_extractor: 提取完成 ts_min(open_0, 5), 2.638s

[2022-07-29 21:58:14.975401] INFO: derived_feature_extractor: 提取完成 ts_min(high_0, 5), 2.706s

[2022-07-29 21:58:17.855256] INFO: derived_feature_extractor: 提取完成 ts_min(turn_0, 5), 2.878s

[2022-07-29 21:58:20.816928] INFO: derived_feature_extractor: 提取完成 ts_min(amount_0, 5), 2.960s

[2022-07-29 21:58:23.556021] INFO: derived_feature_extractor: 提取完成 ts_min(return_0, 5), 2.737s

[2022-07-29 21:58:26.234132] INFO: derived_feature_extractor: 提取完成 std(close_0, 5), 2.676s

[2022-07-29 21:58:28.871182] INFO: derived_feature_extractor: 提取完成 std(low_0, 5), 2.635s

[2022-07-29 21:58:31.585098] INFO: derived_feature_extractor: 提取完成 std(open_0, 5), 2.712s

[2022-07-29 21:58:34.212590] INFO: derived_feature_extractor: 提取完成 std(high_0, 5), 2.625s

[2022-07-29 21:58:37.053986] INFO: derived_feature_extractor: 提取完成 std(turn_0, 5), 2.839s

[2022-07-29 21:58:39.688781] INFO: derived_feature_extractor: 提取完成 std(amount_0, 5), 2.633s

[2022-07-29 21:58:42.323786] INFO: derived_feature_extractor: 提取完成 std(return_0, 5), 2.632s

[2022-07-29 21:58:53.826877] INFO: derived_feature_extractor: 提取完成 ts_rank(close_0, 5), 11.500s

[2022-07-29 21:59:05.041963] INFO: derived_feature_extractor: 提取完成 ts_rank(low_0, 5), 11.213s

[2022-07-29 21:59:16.417057] INFO: derived_feature_extractor: 提取完成 ts_rank(open_0, 5), 11.373s

[2022-07-29 21:59:28.479752] INFO: derived_feature_extractor: 提取完成 ts_rank(high_0, 5), 12.060s

[2022-07-29 21:59:44.334389] INFO: derived_feature_extractor: 提取完成 ts_rank(turn_0, 5), 15.851s

[2022-07-29 21:59:55.619413] INFO: derived_feature_extractor: 提取完成 ts_rank(amount_0, 5), 11.283s

[2022-07-29 22:00:07.156456] INFO: derived_feature_extractor: 提取完成 ts_rank(return_0, 5), 11.535s

[2022-07-29 22:00:14.670056] INFO: derived_feature_extractor: 提取完成 decay_linear(close_0, 5), 7.511s

[2022-07-29 22:00:21.911064] INFO: derived_feature_extractor: 提取完成 decay_linear(low_0, 5), 7.238s

[2022-07-29 22:00:29.874954] INFO: derived_feature_extractor: 提取完成 decay_linear(open_0, 5), 7.962s

[2022-07-29 22:00:38.109357] INFO: derived_feature_extractor: 提取完成 decay_linear(high_0, 5), 8.231s

[2022-07-29 22:00:45.526605] INFO: derived_feature_extractor: 提取完成 decay_linear(turn_0, 5), 7.415s

[2022-07-29 22:00:52.653122] INFO: derived_feature_extractor: 提取完成 decay_linear(amount_0, 5), 7.124s

[2022-07-29 22:00:59.976967] INFO: derived_feature_extractor: 提取完成 decay_linear(return_0, 5), 7.322s

[2022-07-29 22:01:32.349788] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, return_0, 5), 32.370s

[2022-07-29 22:02:05.240523] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, high_0, 5), 32.889s

[2022-07-29 22:02:40.288194] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, low_0, 5), 35.046s

[2022-07-29 22:03:12.590059] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, close_0, 5), 32.298s

[2022-07-29 22:03:46.191561] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, open_0, 5), 33.600s

[2022-07-29 22:04:21.747468] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, turn_0, 5), 35.554s

[2022-07-29 22:04:56.097903] INFO: derived_feature_extractor: 提取完成 correlation(return_0, high_0, 5), 34.349s

[2022-07-29 22:05:32.813181] INFO: derived_feature_extractor: 提取完成 correlation(return_0, low_0, 5), 36.713s

[2022-07-29 22:06:11.446374] INFO: derived_feature_extractor: 提取完成 correlation(return_0, close_0, 5), 38.631s

[2022-07-29 22:06:44.997348] INFO: derived_feature_extractor: 提取完成 correlation(return_0, open_0, 5), 33.549s

[2022-07-29 22:07:22.576109] INFO: derived_feature_extractor: 提取完成 correlation(return_0, turn_0, 5), 37.577s

[2022-07-29 22:07:56.929503] INFO: derived_feature_extractor: 提取完成 correlation(high_0, low_0, 5), 34.351s

[2022-07-29 22:08:31.476638] INFO: derived_feature_extractor: 提取完成 correlation(high_0, close_0, 5), 34.545s

[2022-07-29 22:09:05.991412] INFO: derived_feature_extractor: 提取完成 correlation(high_0, open_0, 5), 34.511s

[2022-07-29 22:09:41.300823] INFO: derived_feature_extractor: 提取完成 correlation(high_0, turn_0, 5), 35.306s

[2022-07-29 22:10:15.182715] INFO: derived_feature_extractor: 提取完成 correlation(low_0, close_0, 5), 33.880s

[2022-07-29 22:10:51.087149] INFO: derived_feature_extractor: 提取完成 correlation(low_0, open_0, 5), 35.903s

[2022-07-29 22:11:25.235492] INFO: derived_feature_extractor: 提取完成 correlation(low_0, turn_0, 5), 34.146s

[2022-07-29 22:11:59.509855] INFO: derived_feature_extractor: 提取完成 correlation(close_0, open_0, 5), 34.272s

[2022-07-29 22:12:32.530305] INFO: derived_feature_extractor: 提取完成 correlation(close_0, turn_0, 5), 33.017s

[2022-07-29 22:13:04.557240] INFO: derived_feature_extractor: 提取完成 correlation(open_0, turn_0, 5), 32.025s

[2022-07-29 22:13:09.941242] INFO: derived_feature_extractor: /y_2017, 743233

[2022-07-29 22:13:15.227820] INFO: derived_feature_extractor: /y_2018, 816987

[2022-07-29 22:13:21.191467] INFO: derived_feature_extractor: /y_2019, 884867

[2022-07-29 22:13:27.963971] INFO: derived_feature_extractor: /y_2020, 945961

[2022-07-29 22:13:32.677927] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[983.097477s].

[2022-07-29 22:13:32.686649] INFO: moduleinvoker: standardlize.v8 开始运行..

[2022-07-29 22:20:58.289524] INFO: moduleinvoker: standardlize.v8 运行完成[445.602858s].

[2022-07-29 22:20:58.309880] INFO: moduleinvoker: fillnan.v1 开始运行..

[2022-07-29 22:21:35.861036] INFO: moduleinvoker: fillnan.v1 运行完成[37.551144s].

[2022-07-29 22:21:35.890473] INFO: moduleinvoker: join.v3 开始运行..

[2022-07-29 22:22:33.220130] INFO: join: /data, 行数=3337834/3372572, 耗时=51.018159s

[2022-07-29 22:22:33.547386] INFO: join: 最终行数: 3337834

[2022-07-29 22:22:33.566421] INFO: moduleinvoker: join.v3 运行完成[57.675943s].

[2022-07-29 22:22:33.615739] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2022-07-29 22:23:01.148010] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[27.532299s].

[2022-07-29 22:23:01.164220] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-29 22:23:20.265048] INFO: moduleinvoker: cached.v3 运行完成[19.100828s].

[2022-07-29 22:23:20.280919] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-07-29 22:23:20.287811] INFO: moduleinvoker: 命中缓存

[2022-07-29 22:23:20.290092] INFO: moduleinvoker: instruments.v2 运行完成[0.009185s].

[2022-07-29 22:23:20.316587] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-07-29 22:23:20.326131] INFO: moduleinvoker: 命中缓存

[2022-07-29 22:23:20.327918] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011361s].

[2022-07-29 22:23:20.335000] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-29 22:23:24.025915] INFO: derived_feature_extractor: 提取完成 mean(close_0, 5), 0.830s

[2022-07-29 22:23:24.807896] INFO: derived_feature_extractor: 提取完成 mean(low_0, 5), 0.780s

[2022-07-29 22:23:25.598449] INFO: derived_feature_extractor: 提取完成 mean(open_0, 5), 0.789s

[2022-07-29 22:23:26.318974] INFO: derived_feature_extractor: 提取完成 mean(high_0, 5), 0.719s

[2022-07-29 22:23:27.123243] INFO: derived_feature_extractor: 提取完成 mean(turn_0, 5), 0.803s

[2022-07-29 22:23:27.907157] INFO: derived_feature_extractor: 提取完成 mean(amount_0, 5), 0.782s

[2022-07-29 22:23:28.684162] INFO: derived_feature_extractor: 提取完成 mean(return_0, 5), 0.775s

[2022-07-29 22:23:29.472510] INFO: derived_feature_extractor: 提取完成 ts_max(close_0, 5), 0.786s

[2022-07-29 22:23:30.261954] INFO: derived_feature_extractor: 提取完成 ts_max(low_0, 5), 0.787s

[2022-07-29 22:23:31.111964] INFO: derived_feature_extractor: 提取完成 ts_max(open_0, 5), 0.848s

[2022-07-29 22:23:31.901377] INFO: derived_feature_extractor: 提取完成 ts_max(high_0, 5), 0.788s

[2022-07-29 22:23:32.705577] INFO: derived_feature_extractor: 提取完成 ts_max(turn_0, 5), 0.803s

[2022-07-29 22:23:33.536606] INFO: derived_feature_extractor: 提取完成 ts_max(amount_0, 5), 0.829s

[2022-07-29 22:23:34.367054] INFO: derived_feature_extractor: 提取完成 ts_max(return_0, 5), 0.829s

[2022-07-29 22:23:35.200098] INFO: derived_feature_extractor: 提取完成 ts_min(close_0, 5), 0.831s

[2022-07-29 22:23:36.048842] INFO: derived_feature_extractor: 提取完成 ts_min(low_0, 5), 0.847s

[2022-07-29 22:23:36.878945] INFO: derived_feature_extractor: 提取完成 ts_min(open_0, 5), 0.828s

[2022-07-29 22:23:37.745886] INFO: derived_feature_extractor: 提取完成 ts_min(high_0, 5), 0.865s

[2022-07-29 22:23:38.534064] INFO: derived_feature_extractor: 提取完成 ts_min(turn_0, 5), 0.786s

[2022-07-29 22:23:39.294943] INFO: derived_feature_extractor: 提取完成 ts_min(amount_0, 5), 0.759s

[2022-07-29 22:23:40.145068] INFO: derived_feature_extractor: 提取完成 ts_min(return_0, 5), 0.848s

[2022-07-29 22:23:40.989150] INFO: derived_feature_extractor: 提取完成 std(close_0, 5), 0.842s

[2022-07-29 22:23:41.849081] INFO: derived_feature_extractor: 提取完成 std(low_0, 5), 0.858s

[2022-07-29 22:23:42.726135] INFO: derived_feature_extractor: 提取完成 std(open_0, 5), 0.875s

[2022-07-29 22:23:43.575896] INFO: derived_feature_extractor: 提取完成 std(high_0, 5), 0.848s

[2022-07-29 22:23:44.414086] INFO: derived_feature_extractor: 提取完成 std(turn_0, 5), 0.836s

[2022-07-29 22:23:45.286837] INFO: derived_feature_extractor: 提取完成 std(amount_0, 5), 0.871s

[2022-07-29 22:23:46.111021] INFO: derived_feature_extractor: 提取完成 std(return_0, 5), 0.822s

[2022-07-29 22:23:49.622091] INFO: derived_feature_extractor: 提取完成 ts_rank(close_0, 5), 3.509s

[2022-07-29 22:23:53.198405] INFO: derived_feature_extractor: 提取完成 ts_rank(low_0, 5), 3.575s

[2022-07-29 22:23:56.940959] INFO: derived_feature_extractor: 提取完成 ts_rank(open_0, 5), 3.741s

[2022-07-29 22:24:00.510530] INFO: derived_feature_extractor: 提取完成 ts_rank(high_0, 5), 3.568s

[2022-07-29 22:24:04.027233] INFO: derived_feature_extractor: 提取完成 ts_rank(turn_0, 5), 3.514s

[2022-07-29 22:24:07.912109] INFO: derived_feature_extractor: 提取完成 ts_rank(amount_0, 5), 3.883s

[2022-07-29 22:24:11.809303] INFO: derived_feature_extractor: 提取完成 ts_rank(return_0, 5), 3.895s

[2022-07-29 22:24:14.166749] INFO: derived_feature_extractor: 提取完成 decay_linear(close_0, 5), 2.355s

[2022-07-29 22:24:16.666310] INFO: derived_feature_extractor: 提取完成 decay_linear(low_0, 5), 2.498s

[2022-07-29 22:24:19.203826] INFO: derived_feature_extractor: 提取完成 decay_linear(open_0, 5), 2.536s

[2022-07-29 22:24:21.543814] INFO: derived_feature_extractor: 提取完成 decay_linear(high_0, 5), 2.337s

[2022-07-29 22:24:23.735068] INFO: derived_feature_extractor: 提取完成 decay_linear(turn_0, 5), 2.190s

[2022-07-29 22:24:26.147498] INFO: derived_feature_extractor: 提取完成 decay_linear(amount_0, 5), 2.410s

[2022-07-29 22:24:28.436517] INFO: derived_feature_extractor: 提取完成 decay_linear(return_0, 5), 2.287s

[2022-07-29 22:25:02.495584] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, return_0, 5), 34.057s

[2022-07-29 22:25:37.209483] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, high_0, 5), 34.711s

[2022-07-29 22:26:11.800421] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, low_0, 5), 34.589s

[2022-07-29 22:26:45.990192] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, close_0, 5), 34.188s

[2022-07-29 22:27:18.814383] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, open_0, 5), 32.822s

[2022-07-29 22:27:53.018520] INFO: derived_feature_extractor: 提取完成 correlation(volume_0, turn_0, 5), 34.202s

[2022-07-29 22:28:27.315194] INFO: derived_feature_extractor: 提取完成 correlation(return_0, high_0, 5), 34.295s

[2022-07-29 22:29:02.412877] INFO: derived_feature_extractor: 提取完成 correlation(return_0, low_0, 5), 35.096s

[2022-07-29 22:29:36.627544] INFO: derived_feature_extractor: 提取完成 correlation(return_0, close_0, 5), 34.213s

[2022-07-29 22:30:12.007971] INFO: derived_feature_extractor: 提取完成 correlation(return_0, open_0, 5), 35.379s

[2022-07-29 22:30:50.340552] INFO: derived_feature_extractor: 提取完成 correlation(return_0, turn_0, 5), 38.331s

[2022-07-29 22:31:27.330765] INFO: derived_feature_extractor: 提取完成 correlation(high_0, low_0, 5), 36.988s

[2022-07-29 22:32:05.245459] INFO: derived_feature_extractor: 提取完成 correlation(high_0, close_0, 5), 37.913s

[2022-07-29 22:32:42.928336] INFO: derived_feature_extractor: 提取完成 correlation(high_0, open_0, 5), 37.681s

[2022-07-29 22:33:20.773585] INFO: derived_feature_extractor: 提取完成 correlation(high_0, turn_0, 5), 37.844s

[2022-07-29 22:33:58.256189] INFO: derived_feature_extractor: 提取完成 correlation(low_0, close_0, 5), 37.479s

[2022-07-29 22:34:34.845086] INFO: derived_feature_extractor: 提取完成 correlation(low_0, open_0, 5), 36.586s

[2022-07-29 22:35:10.539116] INFO: derived_feature_extractor: 提取完成 correlation(low_0, turn_0, 5), 35.692s

[2022-07-29 22:35:45.178300] INFO: derived_feature_extractor: 提取完成 correlation(close_0, open_0, 5), 34.637s

[2022-07-29 22:36:20.522046] INFO: derived_feature_extractor: 提取完成 correlation(close_0, turn_0, 5), 35.342s

[2022-07-29 22:36:55.641546] INFO: derived_feature_extractor: 提取完成 correlation(open_0, turn_0, 5), 35.117s

[2022-07-29 22:37:00.221813] INFO: derived_feature_extractor: /y_2021, 1061527

[2022-07-29 22:37:06.250323] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[825.915309s].

[2022-07-29 22:37:06.257928] INFO: moduleinvoker: standardlize.v8 开始运行..

[2022-07-29 22:39:12.704081] INFO: moduleinvoker: standardlize.v8 运行完成[126.446149s].

[2022-07-29 22:39:12.758455] INFO: moduleinvoker: fillnan.v1 开始运行..

[2022-07-29 22:39:32.137343] INFO: moduleinvoker: fillnan.v1 运行完成[19.378898s].

[2022-07-29 22:39:32.163509] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2022-07-29 22:39:40.223816] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[8.060318s].

[2022-07-29 22:39:40.257001] INFO: moduleinvoker: dl_layer_input.v1 运行完成[0.020747s].

[2022-07-29 22:39:40.330918] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.051933s].

[2022-07-29 22:39:40.346411] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.005138s].

[2022-07-29 22:39:40.366609] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.012412s].

[2022-07-29 22:39:40.393371] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.007368s].

[2022-07-29 22:39:40.414358] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.013073s].

[2022-07-29 22:39:40.456358] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-29 22:39:40.466239] INFO: moduleinvoker: 命中缓存

[2022-07-29 22:39:40.468465] INFO: moduleinvoker: cached.v3 运行完成[0.012094s].

[2022-07-29 22:39:40.473637] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.048681s].

[2022-07-29 22:39:40.497843] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2022-07-29 22:39:48.235813] INFO: dl_model_train: 准备训练，训练样本个数：2503375，迭代次数：30

[2022-07-29 22:48:27.886995] INFO: dl_model_train: 训练结束，耗时：519.65s

[2022-07-29 22:48:27.939786] INFO: moduleinvoker: dl_model_train.v1 运行完成[527.441956s].

[2022-07-29 22:48:27.949234] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2022-07-29 22:48:32.649754] INFO: moduleinvoker: dl_model_predict.v1 运行完成[4.700522s].

[2022-07-29 22:48:32.662892] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-29 22:48:39.465273] INFO: moduleinvoker: cached.v3 运行完成[6.802384s].

[2022-07-29 22:48:44.127009] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-07-29 22:48:44.132315] INFO: backtest: biglearning backtest:V8.6.2

[2022-07-29 22:48:44.133661] INFO: backtest: product_type:stock by specified

[2022-07-29 22:48:44.284782] INFO: moduleinvoker: cached.v2 开始运行..

[2022-07-29 22:48:44.295580] INFO: moduleinvoker: 命中缓存

[2022-07-29 22:48:44.298346] INFO: moduleinvoker: cached.v2 运行完成[0.013602s].

[2022-07-29 22:48:46.867055] INFO: algo: TradingAlgorithm V1.8.8

[2022-07-29 22:48:47.775413] INFO: algo: trading transform...

[2022-07-29 22:48:55.752595] WARNING: Performance: maybe_close_position no price for asset:Equity(4487 [002071.SZA]), field:price, dt:2021-05-07 15:00:00+00:00

[2022-07-29 22:49:10.992491] INFO: Performance: Simulated 243 trading days out of 243.

[2022-07-29 22:49:10.994119] INFO: Performance: first open: 2021-01-04 09:30:00+00:00

[2022-07-29 22:49:10.995574] INFO: Performance: last close: 2021-12-31 15:00:00+00:00

[2022-07-29 22:49:17.871782] INFO: moduleinvoker: backtest.v8 运行完成[33.744783s].

[2022-07-29 22:49:17.874409] INFO: moduleinvoker: trade.v4 运行完成[38.388928s].

Epoch 1/30
2445/2445 - 26s - loss: 0.9911 - mse: 0.9911 - val_loss: 0.9901 - val_mse: 0.9901
Epoch 2/30
2445/2445 - 19s - loss: 0.9874 - mse: 0.9874 - val_loss: 0.9900 - val_mse: 0.9900
Epoch 3/30
2445/2445 - 20s - loss: 0.9864 - mse: 0.9864 - val_loss: 0.9888 - val_mse: 0.9888
Epoch 4/30
2445/2445 - 19s - loss: 0.9856 - mse: 0.9856 - val_loss: 0.9887 - val_mse: 0.9887
Epoch 5/30
2445/2445 - 19s - loss: 0.9847 - mse: 0.9847 - val_loss: 0.9882 - val_mse: 0.9882
Epoch 6/30
2445/2445 - 19s - loss: 0.9841 - mse: 0.9841 - val_loss: 0.9872 - val_mse: 0.9872
Epoch 7/30
2445/2445 - 19s - loss: 0.9833 - mse: 0.9833 - val_loss: 0.9870 - val_mse: 0.9870
Epoch 8/30
2445/2445 - 19s - loss: 0.9826 - mse: 0.9826 - val_loss: 0.9866 - val_mse: 0.9866
Epoch 9/30
2445/2445 - 19s - loss: 0.9821 - mse: 0.9821 - val_loss: 0.9861 - val_mse: 0.9861
Epoch 10/30
2445/2445 - 20s - loss: 0.9816 - mse: 0.9816 - val_loss: 0.9861 - val_mse: 0.9861
Epoch 11/30
2445/2445 - 20s - loss: 0.9813 - mse: 0.9813 - val_loss: 0.9858 - val_mse: 0.9858
Epoch 12/30
2445/2445 - 20s - loss: 0.9806 - mse: 0.9806 - val_loss: 0.9858 - val_mse: 0.9858
Epoch 13/30
2445/2445 - 20s - loss: 0.9801 - mse: 0.9801 - val_loss: 0.9856 - val_mse: 0.9856
Epoch 14/30
2445/2445 - 20s - loss: 0.9797 - mse: 0.9797 - val_loss: 0.9857 - val_mse: 0.9857
Epoch 15/30
2445/2445 - 19s - loss: 0.9792 - mse: 0.9792 - val_loss: 0.9856 - val_mse: 0.9856
Epoch 16/30
2445/2445 - 20s - loss: 0.9788 - mse: 0.9788 - val_loss: 0.9853 - val_mse: 0.9853
Epoch 17/30
2445/2445 - 20s - loss: 0.9784 - mse: 0.9784 - val_loss: 0.9855 - val_mse: 0.9855
Epoch 18/30
2445/2445 - 19s - loss: 0.9779 - mse: 0.9779 - val_loss: 0.9855 - val_mse: 0.9855
Epoch 19/30
2445/2445 - 19s - loss: 0.9775 - mse: 0.9775 - val_loss: 0.9846 - val_mse: 0.9846
Epoch 20/30
2445/2445 - 19s - loss: 0.9770 - mse: 0.9770 - val_loss: 0.9845 - val_mse: 0.9845
Epoch 21/30
2445/2445 - 19s - loss: 0.9768 - mse: 0.9768 - val_loss: 0.9842 - val_mse: 0.9842
Epoch 22/30
2445/2445 - 19s - loss: 0.9762 - mse: 0.9762 - val_loss: 0.9842 - val_mse: 0.9842
Epoch 23/30
2445/2445 - 19s - loss: 0.9758 - mse: 0.9758 - val_loss: 0.9849 - val_mse: 0.9849
Epoch 24/30
2445/2445 - 19s - loss: 0.9755 - mse: 0.9755 - val_loss: 0.9843 - val_mse: 0.9843
Epoch 25/30
2445/2445 - 20s - loss: 0.9752 - mse: 0.9752 - val_loss: 0.9850 - val_mse: 0.9850
Epoch 26/30
2445/2445 - 20s - loss: 0.9747 - mse: 0.9747 - val_loss: 0.9851 - val_mse: 0.9851

1018/1018 - 2s
DataSource(490883351d8143b087e8bf947f8fb685T)

收益率53.83%
年化收益率56.3%
基准收益率-5.2%
阿尔法0.61
贝塔0.45
夏普比率1.88
胜率0.5
盈亏比1.41
收益波动率23.74%
信息比率0.13
最大回撤11.45%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9a21feea479f4484ac697e5bfa481e0b"}/bigcharts-data-end