LSTM滚动运行不了

a1750271086 · 2020-09-08 11:29:11 UTC

老师您好，在平台的模板策略中，我根据之前的帖子把m24模块的预测数据标签修正为’predictions’，滚动运行的预测数据接口试过填m11和m24，都不行。我这里也单独运行了m24模块，能够正确地输出‘predictions’数据，但是滚动训练就是运行不了。我也把数据缩短到很小的区间了，还是不行。能不能帮我看看呢？非常感谢

克隆策略

策略简介¶

因子：样例因子（7个）

因子是否标准化：是

标注：未来5日收益(不做离散化)

算法：LSTM

类型：回归问题

训练集：10-16年

测试集：16-19年

选股依据：根据预测值降序排序买入

持股数：30

持仓天数：5

In [26]:

# 本代码由可视化策略环境自动生成 2020年9月11日 21:41
# 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 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({'predictions':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})
    df.sort_values(['date','predictions'],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 = 3
    # 每只的股票的权重，如下的权重分配会使得靠前的股票分配多一点的资金，[0.339160, 0.213986, 0.169580, ..]
    context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.2
    context.options['hold_days'] = 1
# 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='2016-01-01',
    end_date='2019-01-01',
    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
)

m13 = M.standardlize.v8(
    input_1=m2.data,
    columns_input='label'
)

m3 = M.input_features.v1(
    features="""close_0/mean(close_0,5)
close_0/mean(close_0,10)
close_0/mean(close_0,20)
close_0/open_0
open_0/mean(close_0,5)
open_0/mean(close_0,10)
open_0/mean(close_0,20)"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=30
)

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
)

m14 = M.standardlize.v8(
    input_1=m16.data,
    input_2=m3.data,
    columns_input='[]'
)

m7 = M.join.v3(
    data1=m13.data,
    data2=m14.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m26 = M.dl_convert_to_bin.v2(
    input_data=m7.data,
    features=m3.data,
    window_size=20,
    feature_clip=7,
    flatten=False,
    window_along_col='instrument'
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2019-01-01'),
    end_date=T.live_run_param('trading_date', '2020-09-10'),
    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=30
)

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='[]'
)

m27 = M.dl_convert_to_bin.v2(
    input_data=m25.data,
    features=m3.data,
    window_size=20,
    feature_clip=7,
    flatten=False,
    window_along_col='instrument'
)

m6 = M.dl_layer_input.v1(
    shape='20,7',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m10 = M.dl_layer_lstm.v1(
    inputs=m6.data,
    units=32,
    activation='tanh',
    recurrent_activation='hard_sigmoid',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    recurrent_initializer='Orthogonal',
    bias_initializer='Zeros',
    unit_forget_bias=True,
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    recurrent_regularizer='None',
    recurrent_regularizer_l1=0,
    recurrent_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',
    recurrent_constraint='None',
    bias_constraint='None',
    dropout=0,
    recurrent_dropout=0,
    return_sequences=False,
    implementation='2',
    name=''
)

m12 = M.dl_layer_dropout.v1(
    inputs=m10.data,
    rate=0.2,
    noise_shape='',
    name=''
)

m20 = M.dl_layer_dense.v1(
    inputs=m12.data,
    units=30,
    activation='tanh',
    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=m20.data,
    rate=0.2,
    noise_shape='',
    name=''
)

m22 = M.dl_layer_dense.v1(
    inputs=m21.data,
    units=1,
    activation='tanh',
    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=''
)

m34 = M.dl_model_init.v1(
    inputs=m6.data,
    outputs=m22.data
)

m5 = M.dl_model_train.v1(
    input_model=m34.data,
    training_data=m26.data,
    validation_data=m26.data,
    optimizer='RMSprop',
    loss='mean_squared_error',
    metrics='mae',
    batch_size=256,
    epochs=5,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录'
)

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='',
    m_cached=False
)

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,
    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'
)

[2020-09-11 21:07:10.409315] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-09-11 21:07:10.489593] INFO: moduleinvoker: 命中缓存

[2020-09-11 21:07:10.493113] INFO: moduleinvoker: instruments.v2 运行完成[0.086288s].

[2020-09-11 21:07:10.499849] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2020-09-11 21:07:10.508359] INFO: moduleinvoker: 命中缓存

[2020-09-11 21:07:10.514189] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.01434s].

[2020-09-11 21:07:10.521698] INFO: moduleinvoker: standardlize.v8 开始运行..

[2020-09-11 21:07:10.527733] INFO: moduleinvoker: 命中缓存

[2020-09-11 21:07:10.528625] INFO: moduleinvoker: standardlize.v8 运行完成[0.006926s].

[2020-09-11 21:07:10.536443] INFO: moduleinvoker: input_features.v1 开始运行..

[2020-09-11 21:07:10.546735] INFO: moduleinvoker: 命中缓存

[2020-09-11 21:07:10.547592] INFO: moduleinvoker: input_features.v1 运行完成[0.011149s].

[2020-09-11 21:07:10.581049] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-09-11 21:07:14.130302] INFO: 基础特征抽取: 年份 2015, 特征行数=55212

[2020-09-11 21:07:16.047710] INFO: 基础特征抽取: 年份 2016, 特征行数=641546

[2020-09-11 21:07:19.179679] INFO: 基础特征抽取: 年份 2017, 特征行数=743233

[2020-09-11 21:07:21.670808] INFO: 基础特征抽取: 年份 2018, 特征行数=816987

[2020-09-11 21:07:23.058151] INFO: 基础特征抽取: 年份 2019, 特征行数=0

[2020-09-11 21:07:23.508774] INFO: 基础特征抽取: 总行数: 2256978

[2020-09-11 21:07:23.513158] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[12.932099s].

[2020-09-11 21:07:23.520911] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2020-09-11 21:07:30.499048] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 6.179s

[2020-09-11 21:07:34.967242] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 4.467s

[2020-09-11 21:07:37.156990] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,20), 2.189s

[2020-09-11 21:07:37.162332] INFO: derived_feature_extractor: 提取完成 close_0/open_0, 0.004s

[2020-09-11 21:07:39.096965] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,5), 1.934s

[2020-09-11 21:07:41.799701] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,10), 2.702s

[2020-09-11 21:07:47.805501] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,20), 6.005s

[2020-09-11 21:07:49.721915] INFO: derived_feature_extractor: /y_2015, 55212

[2020-09-11 21:07:49.921488] INFO: derived_feature_extractor: /y_2016, 641546

[2020-09-11 21:07:50.495169] INFO: derived_feature_extractor: /y_2017, 743233

[2020-09-11 21:07:51.232235] INFO: derived_feature_extractor: /y_2018, 816987

[2020-09-11 21:07:52.870343] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[29.349387s].

[2020-09-11 21:07:52.872795] INFO: moduleinvoker: standardlize.v8 开始运行..

[2020-09-11 21:08:01.175227] INFO: moduleinvoker: standardlize.v8 运行完成[8.302417s].

[2020-09-11 21:08:01.177186] INFO: moduleinvoker: join.v3 开始运行..

[2020-09-11 21:08:10.527362] INFO: join: /data, 行数=2159248/2189048, 耗时=8.784638s

[2020-09-11 21:08:14.510050] INFO: join: 最终行数: 2159248

[2020-09-11 21:08:14.571474] INFO: moduleinvoker: join.v3 运行完成[13.394255s].

[2020-09-11 21:08:14.579786] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2020-09-11 21:13:20.176694] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[305.596885s].

[2020-09-11 21:13:20.178814] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-09-11 21:13:20.184359] INFO: moduleinvoker: 命中缓存

[2020-09-11 21:13:20.185531] INFO: moduleinvoker: instruments.v2 运行完成[0.006714s].

[2020-09-11 21:13:20.200081] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-09-11 21:13:20.542208] INFO: 基础特征抽取: 年份 2018, 特征行数=70840

[2020-09-11 21:13:21.906729] INFO: 基础特征抽取: 年份 2019, 特征行数=884867

[2020-09-11 21:13:22.791560] INFO: 基础特征抽取: 年份 2020, 特征行数=646324

[2020-09-11 21:13:24.082072] INFO: 基础特征抽取: 总行数: 1602031

[2020-09-11 21:13:24.102125] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[3.902035s].

[2020-09-11 21:13:24.104567] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2020-09-11 21:13:26.642181] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 2.135s

[2020-09-11 21:13:28.426178] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 1.783s

[2020-09-11 21:13:30.185665] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,20), 1.758s

[2020-09-11 21:13:30.189532] INFO: derived_feature_extractor: 提取完成 close_0/open_0, 0.003s

[2020-09-11 21:13:31.972546] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,5), 1.782s

[2020-09-11 21:13:34.011220] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,10), 2.037s

[2020-09-11 21:13:35.928577] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,20), 1.916s

[2020-09-11 21:13:36.059700] INFO: derived_feature_extractor: /y_2018, 70840

[2020-09-11 21:13:36.254172] INFO: derived_feature_extractor: /y_2019, 884867

[2020-09-11 21:13:37.055617] INFO: derived_feature_extractor: /y_2020, 646324

[2020-09-11 21:13:38.330986] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[14.226406s].

[2020-09-11 21:13:38.333214] INFO: moduleinvoker: standardlize.v8 开始运行..

[2020-09-11 21:13:45.870007] INFO: moduleinvoker: standardlize.v8 运行完成[7.536773s].

[2020-09-11 21:13:45.881624] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2020-09-11 21:17:15.032921] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[209.151285s].

[2020-09-11 21:17:15.047875] INFO: moduleinvoker: dl_layer_input.v1 运行完成[0.012721s].

[2020-09-11 21:17:15.292184] INFO: moduleinvoker: dl_layer_lstm.v1 运行完成[0.241721s].

[2020-09-11 21:17:15.320086] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.026148s].

[2020-09-11 21:17:15.340729] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.01845s].

[2020-09-11 21:17:15.372200] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.029393s].

[2020-09-11 21:17:15.391247] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.016629s].

[2020-09-11 21:17:15.413913] INFO: moduleinvoker: cached.v3 开始运行..

[2020-09-11 21:17:15.641894] INFO: moduleinvoker: cached.v3 运行完成[0.227962s].

[2020-09-11 21:17:15.643615] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.250241s].

[2020-09-11 21:17:15.645778] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2020-09-11 21:17:15.821470] INFO: device_manager: 没有gpu资源，将使用cpu计算

[2020-09-11 21:17:15.825186] INFO: device_manager: 本次操作不使用GPU

[2020-09-11 21:17:20.997542] INFO: dl_model_train: 准备训练，训练样本个数：2159248，迭代次数：5

[2020-09-11 21:39:32.120986] INFO: dl_model_train: 训练结束，耗时：1331.12s

[2020-09-11 21:39:32.353242] INFO: moduleinvoker: dl_model_train.v1 运行完成[1336.70743s].

[2020-09-11 21:39:32.355560] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2020-09-11 21:39:32.572898] INFO: device_manager: 没有gpu资源，将使用cpu计算

[2020-09-11 21:39:32.575711] INFO: device_manager: 本次操作不使用GPU

[2020-09-11 21:39:56.709892] INFO: moduleinvoker: dl_model_predict.v1 运行完成[24.35431s].

[2020-09-11 21:39:56.713048] INFO: moduleinvoker: cached.v3 开始运行..

[2020-09-11 21:40:00.014652] INFO: moduleinvoker: cached.v3 运行完成[3.301561s].

[2020-09-11 21:40:00.059656] INFO: moduleinvoker: backtest.v8 开始运行..

[2020-09-11 21:40:00.063577] INFO: backtest: biglearning backtest:V8.4.2

[2020-09-11 21:40:00.064751] INFO: backtest: product_type:stock by specified

[2020-09-11 21:40:00.213113] INFO: moduleinvoker: cached.v2 开始运行..

[2020-09-11 21:40:00.223568] INFO: moduleinvoker: 命中缓存

[2020-09-11 21:40:00.224913] INFO: moduleinvoker: cached.v2 运行完成[0.011804s].

[2020-09-11 21:40:01.499108] INFO: algo: TradingAlgorithm V1.6.9

[2020-09-11 21:40:03.220242] INFO: algo: trading transform...

[2020-09-11 21:40:09.523577] INFO: Performance: Simulated 413 trading days out of 413.

[2020-09-11 21:40:09.524957] INFO: Performance: first open: 2019-01-02 09:30:00+00:00

[2020-09-11 21:40:09.526072] INFO: Performance: last close: 2020-09-10 15:00:00+00:00

[2020-09-11 21:40:17.031956] INFO: moduleinvoker: backtest.v8 运行完成[16.972301s].

[2020-09-11 21:40:17.033406] INFO: moduleinvoker: trade.v4 运行完成[17.016494s].

Train on 2159248 samples, validate on 2159248 samples
Epoch 1/5
2159248/2159248 - 293s - loss: 0.9830 - mae: 0.7088 - val_loss: 0.9802 - val_mae: 0.7098
Epoch 2/5
2159248/2159248 - 289s - loss: 0.9796 - mae: 0.7073 - val_loss: 0.9782 - val_mae: 0.7075
Epoch 3/5
2159248/2159248 - 291s - loss: 0.9782 - mae: 0.7067 - val_loss: 0.9759 - val_mae: 0.7062
Epoch 4/5
2159248/2159248 - 242s - loss: 0.9770 - mae: 0.7062 - val_loss: 0.9749 - val_mae: 0.7073
Epoch 5/5
2159248/2159248 - 214s - loss: 0.9758 - mae: 0.7058 - val_loss: 0.9742 - val_mae: 0.7049

1526171/1526171 - 21s
DataSource(5d61c9a499cb4754877eda75f97796bdT, v3)

收益率-40.66%
年化收益率-27.27%
基准收益率52.19%
阿尔法-0.43
贝塔0.48
夏普比率-1.1
胜率0.53
盈亏比0.83
收益波动率28.1%
信息比率-0.12
最大回撤67.51%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-bd318b538e17464cbc239319010ded1a"}/bigcharts-data-end

tiantianz · 2020-09-12 08:49:08 UTC

您设置的m8模块需要的参数是3维的，但m20的运算结果是2维的，可以将m8模块删掉。
参考策略