克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2020年12月18日 11:22
# 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 m30_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_2.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 m30_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 m2_run_bigquant_run(input_1, input_2, input_3):

    test_data = input_2.read_pickle()
    pred_label = input_1.read_pickle()
    pred_result = pred_label.reshape(pred_label.shape[0]) 
    dt = input_3.read_df()['date'][-1*len(pred_result):]
    pred_df = pd.Series(pred_result, index=dt)
    ds = DataSource.write_df(pred_df)
    
    return Outputs(data_1=ds)

# 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 m2_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m1_initialize_bigquant_run(context):
    # 加载预测数据
    context.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))
# 回测引擎：每日数据处理函数，每天执行一次
def m1_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    try:
        prediction = context.prediction[data.current_dt.strftime('%Y-%m-%d')]
    except KeyError as e:
        return
    
    instrument = context.instruments[0]
    sid = context.symbol(instrument)
    cur_position = context.portfolio.positions[sid].amount
    
    # 交易逻辑
    if prediction > 0.5 and cur_position == 0:
        context.order_target_percent(context.symbol(instrument), 1)
        print(data.current_dt, '买入！')
        
    elif prediction < 0.5 and cur_position > 0:
        context.order_target_percent(context.symbol(instrument), 0)
        print(data.current_dt, '卖出！')
    
# 回测引擎：准备数据，只执行一次
def m1_prepare_bigquant_run(context):
    pass

# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。
def m1_before_trading_start_bigquant_run(context, data):
    pass


m3 = M.dl_layer_input.v1(
    shape='50,5',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m13 = M.dl_layer_reshape.v1(
    inputs=m3.data,
    target_shape='50,5,1',
    name=''
)

m14 = M.dl_layer_conv2d.v1(
    inputs=m13.data,
    filters=32,
    kernel_size='3,5',
    strides='1,1',
    padding='valid',
    data_format='channels_last',
    dilation_rate='1,1',
    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=''
)

m15 = M.dl_layer_reshape.v1(
    inputs=m14.data,
    target_shape='48,32',
    name=''
)

m4 = M.dl_layer_lstm.v1(
    inputs=m15.data,
    units=32,
    activation='tanh',
    recurrent_activation='hard_sigmoid',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    recurrent_initializer='Orthogonal',
    bias_initializer='Ones',
    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=''
)

m11 = M.dl_layer_dropout.v1(
    inputs=m4.data,
    rate=0.4,
    noise_shape='',
    name=''
)

m10 = M.dl_layer_dense.v1(
    inputs=m11.data,
    units=32,
    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=''
)

m12 = M.dl_layer_dropout.v1(
    inputs=m10.data,
    rate=0.8,
    noise_shape='',
    name=''
)

m9 = M.dl_layer_dense.v1(
    inputs=m12.data,
    units=1,
    activation='sigmoid',
    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=''
)

m5 = M.dl_model_init.v1(
    inputs=m3.data,
    outputs=m9.data
)

m8 = M.input_features.v1(
    features="""(close_0/close_1-1)*10
(high_0/high_1-1)*10
(low_0/low_1-1)*10
(open_0/open_1-1)*10
(volume_0/volume_1-1)*10"""
)

m24 = M.instruments.v2(
    start_date='2015-07-02',
    end_date='2017-10-30',
    market='CN_STOCK_A',
    instrument_list='600009.SHA',
    max_count=0
)

m21 = M.advanced_auto_labeler.v2(
    instruments=m24.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/develop/datasource/deprecated/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/develop/bigexpr/usage.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)
where(shift(close, -10) / close -1>0,1,0)

# 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=True,
    user_functions={}
)

m22 = M.general_feature_extractor.v7(
    instruments=m24.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m23 = M.derived_feature_extractor.v3(
    input_data=m22.data,
    features=m8.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m17 = M.join.v3(
    data1=m21.data,
    data2=m23.data,
    on='date',
    how='inner',
    sort=True
)

m19 = M.dropnan.v2(
    input_data=m17.data
)

m18 = M.standardlize.v8(
    input_1=m19.data,
    input_2=m8.data,
    columns_input=''
)

m25 = M.dl_convert_to_bin.v2(
    input_data=m18.data,
    features=m8.data,
    window_size=50,
    feature_clip=5,
    flatten=False,
    window_along_col=''
)

m30 = M.cached.v3(
    input_2=m25.data,
    run=m30_run_bigquant_run,
    post_run=m30_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m6 = M.dl_model_train.v1(
    input_model=m5.data,
    training_data=m30.data_1,
    validation_data=m30.data_2,
    optimizer='Adam',
    loss='binary_crossentropy',
    metrics='accuracy',
    batch_size=2048,
    epochs=10,
    n_gpus=0,
    verbose='1:输出进度条记录'
)

m28 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-02-11'),
    end_date=T.live_run_param('trading_date', '2019-09-01'),
    market='CN_STOCK_A',
    instrument_list='600009.SHA',
    max_count=0
)

m16 = M.general_feature_extractor.v7(
    instruments=m28.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m26 = M.derived_feature_extractor.v3(
    input_data=m16.data,
    features=m8.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m29 = M.dropnan.v2(
    input_data=m26.data
)

m20 = M.standardlize.v8(
    input_1=m29.data,
    input_2=m8.data,
    columns_input=''
)

m27 = M.dl_convert_to_bin.v2(
    input_data=m20.data,
    features=m8.data,
    window_size=50,
    feature_clip=5,
    flatten=False,
    window_along_col=''
)

m7 = M.dl_model_predict.v1(
    trained_model=m6.data,
    input_data=m27.data,
    batch_size=10240,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录'
)

m2 = M.cached.v3(
    input_1=m7.data,
    input_2=m27.data,
    input_3=m20.data,
    run=m2_run_bigquant_run,
    post_run=m2_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m1 = M.trade.v4(
    instruments=m28.data,
    options_data=m2.data_1,
    start_date='',
    end_date='',
    initialize=m1_initialize_bigquant_run,
    handle_data=m1_handle_data_bigquant_run,
    prepare=m1_prepare_bigquant_run,
    before_trading_start=m1_before_trading_start_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='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark=''
)

[2020-12-18 11:20:46.544151] INFO: moduleinvoker: dl_layer_input.v1 运行完成[2.314779s].

[2020-12-18 11:20:46.841195] INFO: moduleinvoker: dl_layer_reshape.v1 运行完成[0.287949s].

[2020-12-18 11:20:48.888344] INFO: moduleinvoker: dl_layer_conv2d.v1 运行完成[2.044115s].

[2020-12-18 11:20:48.902240] INFO: moduleinvoker: dl_layer_reshape.v1 运行完成[0.011662s].

[2020-12-18 11:20:49.077801] INFO: moduleinvoker: dl_layer_lstm.v1 运行完成[0.172813s].

[2020-12-18 11:20:49.105346] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.024793s].

[2020-12-18 11:20:49.122537] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.014702s].

[2020-12-18 11:20:49.149414] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.02511s].

[2020-12-18 11:20:49.164296] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.01324s].

[2020-12-18 11:20:49.192594] INFO: moduleinvoker: cached.v3 开始运行..

[2020-12-18 11:20:49.208524] INFO: moduleinvoker: 命中缓存

[2020-12-18 11:20:49.209386] INFO: moduleinvoker: cached.v3 运行完成[0.016793s].

[2020-12-18 11:20:49.210703] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.04428s].

[2020-12-18 11:20:49.212803] INFO: moduleinvoker: input_features.v1 开始运行..

[2020-12-18 11:20:49.219056] INFO: moduleinvoker: 命中缓存

[2020-12-18 11:20:49.219873] INFO: moduleinvoker: input_features.v1 运行完成[0.007068s].

[2020-12-18 11:20:49.221956] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-12-18 11:20:49.267509] INFO: moduleinvoker: instruments.v2 运行完成[0.045546s].

[2020-12-18 11:20:49.269883] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2020-12-18 11:20:51.237369] INFO: 自动标注(股票): 加载历史数据: 568 行

[2020-12-18 11:20:51.238648] INFO: 自动标注(股票): 开始标注 ..

[2020-12-18 11:20:51.362097] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[2.092189s].

[2020-12-18 11:20:51.370193] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-12-18 11:20:52.600394] INFO: 基础特征抽取: 年份 2015, 特征行数=185

[2020-12-18 11:20:53.505103] INFO: 基础特征抽取: 年份 2016, 特征行数=244

[2020-12-18 11:20:54.845401] INFO: 基础特征抽取: 年份 2017, 特征行数=200

[2020-12-18 11:20:54.936916] INFO: 基础特征抽取: 总行数: 629

[2020-12-18 11:20:54.940900] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[3.570696s].

[2020-12-18 11:20:54.943979] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2020-12-18 11:20:55.004791] INFO: derived_feature_extractor: 提取完成 (close_0/close_1-1)*10, 0.001s

[2020-12-18 11:20:55.007284] INFO: derived_feature_extractor: 提取完成 (high_0/high_1-1)*10, 0.001s

[2020-12-18 11:20:55.009367] INFO: derived_feature_extractor: 提取完成 (low_0/low_1-1)*10, 0.001s

[2020-12-18 11:20:55.011417] INFO: derived_feature_extractor: 提取完成 (open_0/open_1-1)*10, 0.001s

[2020-12-18 11:20:55.013568] INFO: derived_feature_extractor: 提取完成 (volume_0/volume_1-1)*10, 0.001s

[2020-12-18 11:20:55.050565] INFO: derived_feature_extractor: /y_2015, 185

[2020-12-18 11:20:55.079600] INFO: derived_feature_extractor: /y_2016, 244

[2020-12-18 11:20:55.108510] INFO: derived_feature_extractor: /y_2017, 200

[2020-12-18 11:20:55.220688] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.276692s].

[2020-12-18 11:20:55.223667] INFO: moduleinvoker: join.v3 开始运行..

[2020-12-18 11:20:55.308414] INFO: join: /y_2015, 行数=124/185, 耗时=0.026592s

[2020-12-18 11:20:55.335886] INFO: join: /y_2016, 行数=244/244, 耗时=0.026289s

[2020-12-18 11:20:55.362516] INFO: join: /y_2017, 行数=200/200, 耗时=0.025644s

[2020-12-18 11:20:55.465671] INFO: join: 最终行数: 568

[2020-12-18 11:20:55.471973] INFO: moduleinvoker: join.v3 运行完成[0.248297s].

[2020-12-18 11:20:55.474570] INFO: moduleinvoker: dropnan.v2 开始运行..

[2020-12-18 11:20:55.535055] INFO: dropnan: /y_2015, 124/124

[2020-12-18 11:20:55.560681] INFO: dropnan: /y_2016, 244/244

[2020-12-18 11:20:55.585851] INFO: dropnan: /y_2017, 200/200

[2020-12-18 11:20:55.676277] INFO: dropnan: 行数: 568/568

[2020-12-18 11:20:55.679773] INFO: moduleinvoker: dropnan.v2 运行完成[0.205192s].

[2020-12-18 11:20:55.682159] INFO: moduleinvoker: standardlize.v8 开始运行..

[2020-12-18 11:20:56.803589] INFO: moduleinvoker: standardlize.v8 运行完成[1.12141s].

[2020-12-18 11:20:56.810035] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2020-12-18 11:20:57.099374] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.289321s].

[2020-12-18 11:20:57.102722] INFO: moduleinvoker: cached.v3 开始运行..

[2020-12-18 11:20:57.280102] INFO: moduleinvoker: cached.v3 运行完成[0.17735s].

[2020-12-18 11:20:57.284476] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2020-12-18 11:20:57.499252] INFO: device_manager: 本次操作不使用GPU

[2020-12-18 11:20:57.939906] INFO: dl_model_train: 准备训练，训练样本个数：426，迭代次数：10

[2020-12-18 11:21:17.051738] INFO: dl_model_train: 训练结束，耗时：19.11s

[2020-12-18 11:21:17.142336] INFO: moduleinvoker: dl_model_train.v1 运行完成[19.857846s].

[2020-12-18 11:21:17.144153] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-12-18 11:21:17.171651] INFO: moduleinvoker: instruments.v2 运行完成[0.027491s].

[2020-12-18 11:21:17.176446] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-12-18 11:21:17.937244] INFO: 基础特征抽取: 年份 2014, 特征行数=35

[2020-12-18 11:21:18.670479] INFO: 基础特征抽取: 年份 2015, 特征行数=244

[2020-12-18 11:21:19.473496] INFO: 基础特征抽取: 年份 2016, 特征行数=244

[2020-12-18 11:21:20.350055] INFO: 基础特征抽取: 年份 2017, 特征行数=244

[2020-12-18 11:21:21.228959] INFO: 基础特征抽取: 年份 2018, 特征行数=243

[2020-12-18 11:21:22.138718] INFO: 基础特征抽取: 年份 2019, 特征行数=163

[2020-12-18 11:21:22.252207] INFO: 基础特征抽取: 总行数: 1173

[2020-12-18 11:21:22.255379] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[5.078924s].

[2020-12-18 11:21:22.257053] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2020-12-18 11:21:22.399845] INFO: derived_feature_extractor: 提取完成 (close_0/close_1-1)*10, 0.001s

[2020-12-18 11:21:22.401818] INFO: derived_feature_extractor: 提取完成 (high_0/high_1-1)*10, 0.001s

[2020-12-18 11:21:22.403551] INFO: derived_feature_extractor: 提取完成 (low_0/low_1-1)*10, 0.001s

[2020-12-18 11:21:22.405106] INFO: derived_feature_extractor: 提取完成 (open_0/open_1-1)*10, 0.001s

[2020-12-18 11:21:22.406620] INFO: derived_feature_extractor: 提取完成 (volume_0/volume_1-1)*10, 0.001s

[2020-12-18 11:21:22.466193] INFO: derived_feature_extractor: /y_2014, 35

[2020-12-18 11:21:22.517016] INFO: derived_feature_extractor: /y_2015, 244

[2020-12-18 11:21:22.558805] INFO: derived_feature_extractor: /y_2016, 244

[2020-12-18 11:21:22.588205] INFO: derived_feature_extractor: /y_2017, 244

[2020-12-18 11:21:22.617554] INFO: derived_feature_extractor: /y_2018, 243

[2020-12-18 11:21:22.659175] INFO: derived_feature_extractor: /y_2019, 163

[2020-12-18 11:21:22.852689] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.595617s].

[2020-12-18 11:21:22.854528] INFO: moduleinvoker: dropnan.v2 开始运行..

[2020-12-18 11:21:22.958154] INFO: dropnan: /y_2014, 35/35

[2020-12-18 11:21:22.994657] INFO: dropnan: /y_2015, 244/244

[2020-12-18 11:21:23.027615] INFO: dropnan: /y_2016, 244/244

[2020-12-18 11:21:23.059980] INFO: dropnan: /y_2017, 244/244

[2020-12-18 11:21:23.098134] INFO: dropnan: /y_2018, 243/243

[2020-12-18 11:21:23.129002] INFO: dropnan: /y_2019, 163/163

[2020-12-18 11:21:23.238905] INFO: dropnan: 行数: 1173/1173

[2020-12-18 11:21:23.242143] INFO: moduleinvoker: dropnan.v2 运行完成[0.387605s].

[2020-12-18 11:21:23.243620] INFO: moduleinvoker: standardlize.v8 开始运行..

[2020-12-18 11:21:25.522192] INFO: moduleinvoker: standardlize.v8 运行完成[2.278545s].

[2020-12-18 11:21:25.527698] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2020-12-18 11:21:26.090100] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.562385s].

[2020-12-18 11:21:26.092757] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2020-12-18 11:21:26.254566] INFO: device_manager: 本次操作不使用GPU

[2020-12-18 11:21:27.000282] INFO: moduleinvoker: dl_model_predict.v1 运行完成[0.907503s].

[2020-12-18 11:21:27.004037] INFO: moduleinvoker: cached.v3 开始运行..

[2020-12-18 11:21:27.085309] INFO: moduleinvoker: cached.v3 运行完成[0.081262s].

[2020-12-18 11:21:28.289678] INFO: moduleinvoker: backtest.v8 开始运行..

[2020-12-18 11:21:28.293325] INFO: backtest: biglearning backtest:V8.4.2

[2020-12-18 11:21:28.294373] INFO: backtest: product_type:stock by specified

[2020-12-18 11:21:28.621043] INFO: moduleinvoker: cached.v2 开始运行..

[2020-12-18 11:21:39.546193] INFO: backtest: 读取股票行情完成:414680

[2020-12-18 11:21:40.408465] INFO: moduleinvoker: cached.v2 运行完成[11.787411s].

[2020-12-18 11:21:40.555421] INFO: algo: TradingAlgorithm V1.6.9

[2020-12-18 11:21:40.801896] INFO: algo: trading transform...

[2020-12-18 11:21:41.088548] INFO: algo: handle_splits get splits [dt:2015-08-20 00:00:00+00:00] [asset:Equity(3 [600009.SHA]), ratio:0.9882234930992126]

[2020-12-18 11:21:41.089671] INFO: Position: position stock handle split[sid:3, orig_amount:48900, new_amount:49482.0, orig_cost:20.430083285176046, new_cost:20.1895, ratio:0.9882234930992126, last_sale_price:29.369998931884766]

[2020-12-18 11:21:41.090560] INFO: Position: after split: PositionStock(asset:Equity(3 [600009.SHA]), amount:49482.0, cost_basis:20.1895, last_sale_price:29.71999740600586)

[2020-12-18 11:21:41.091366] INFO: Position: returning cash: 21.5504

[2020-12-18 11:21:41.567291] INFO: algo: handle_splits get splits [dt:2016-08-18 00:00:00+00:00] [asset:Equity(3 [600009.SHA]), ratio:0.9852133393287659]

[2020-12-18 11:21:41.568287] INFO: Position: position stock handle split[sid:3, orig_amount:49482.0, new_amount:50224.0, orig_cost:20.1895, new_cost:19.891, ratio:0.9852133393287659, last_sale_price:28.65000343322754]

[2020-12-18 11:21:41.569152] INFO: Position: after split: PositionStock(asset:Equity(3 [600009.SHA]), amount:50224.0, cost_basis:19.891, last_sale_price:29.079999923706055)

[2020-12-18 11:21:41.569945] INFO: Position: returning cash: 18.7637

[2020-12-18 11:21:42.060829] INFO: algo: handle_splits get splits [dt:2017-08-24 00:00:00+00:00] [asset:Equity(3 [600009.SHA]), ratio:0.9882099032402039]

[2020-12-18 11:21:42.061893] INFO: Position: position stock handle split[sid:3, orig_amount:50224.0, new_amount:50823.0, orig_cost:19.891, new_cost:19.6565, ratio:0.9882099032402039, last_sale_price:36.8799934387207]

[2020-12-18 11:21:42.062779] INFO: Position: after split: PositionStock(asset:Equity(3 [600009.SHA]), amount:50823.0, cost_basis:19.6565, last_sale_price:37.31999969482422)

[2020-12-18 11:21:42.063585] INFO: Position: returning cash: 7.7658

[2020-12-18 11:21:42.557516] INFO: algo: handle_splits get splits [dt:2018-08-23 00:00:00+00:00] [asset:Equity(3 [600009.SHA]), ratio:0.9900703430175781]

[2020-12-18 11:21:42.558550] INFO: Position: position stock handle split[sid:3, orig_amount:50823.0, new_amount:51332.0, orig_cost:19.6565, new_cost:19.4613, ratio:0.9900703430175781, last_sale_price:57.83000946044922]

[2020-12-18 11:21:42.559429] INFO: Position: after split: PositionStock(asset:Equity(3 [600009.SHA]), amount:51332.0, cost_basis:19.4613, last_sale_price:58.40999984741211)

[2020-12-18 11:21:42.560236] INFO: Position: returning cash: 41.4216

[2020-12-18 11:21:43.055547] INFO: algo: handle_splits get splits [dt:2019-08-22 00:00:00+00:00] [asset:Equity(3 [600009.SHA]), ratio:0.9922354221343994]

[2020-12-18 11:21:43.056739] INFO: Position: position stock handle split[sid:3, orig_amount:51332.0, new_amount:51733.0, orig_cost:19.4613, new_cost:19.3102, ratio:0.9922354221343994, last_sale_price:84.34001159667969]

[2020-12-18 11:21:43.057626] INFO: Position: after split: PositionStock(asset:Equity(3 [600009.SHA]), amount:51733.0, cost_basis:19.3102, last_sale_price:85.0)

[2020-12-18 11:21:43.058437] INFO: Position: returning cash: 58.2171

[2020-12-18 11:21:43.073748] INFO: Performance: Simulated 1111 trading days out of 1111.

[2020-12-18 11:21:43.074634] INFO: Performance: first open: 2015-02-11 09:30:00+00:00

[2020-12-18 11:21:43.075456] INFO: Performance: last close: 2019-08-30 15:00:00+00:00

[2020-12-18 11:21:46.260567] INFO: moduleinvoker: backtest.v8 运行完成[17.970884s].

[2020-12-18 11:21:46.261822] INFO: moduleinvoker: trade.v4 运行完成[19.17281s].

[2020-12-18 11:20:49.126469] WARNING tensorflow: Large dropout rate: 0.8 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.

[2020-12-18 11:20:57.829795] WARNING tensorflow: Large dropout rate: 0.8 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.

Train on 426 samples, validate on 142 samples
Epoch 1/10
[2020-12-18 11:20:58.565044] WARNING tensorflow: Large dropout rate: 0.8 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.
[2020-12-18 11:21:00.117847] WARNING tensorflow: Large dropout rate: 0.8 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.
426/426 [==============================] - 5s 13ms/sample - loss: 0.9390 - accuracy: 0.5164 - val_loss: 0.6737 - val_accuracy: 0.5986
Epoch 2/10
[2020-12-18 11:21:16.327412] WARNING tensorflow: Method (on_train_batch_end) is slow compared to the batch update (12.360096). Check your callbacks.
426/426 [==============================] - 13s 30ms/sample - loss: 1.0467 - accuracy: 0.4671 - val_loss: 0.6741 - val_accuracy: 0.5986
Epoch 3/10
426/426 [==============================] - 0s 179us/sample - loss: 0.9981 - accuracy: 0.4930 - val_loss: 0.6745 - val_accuracy: 0.5986
Epoch 4/10
426/426 [==============================] - 0s 174us/sample - loss: 0.9390 - accuracy: 0.5117 - val_loss: 0.6746 - val_accuracy: 0.5986
Epoch 5/10
426/426 [==============================] - 0s 179us/sample - loss: 1.0413 - accuracy: 0.4789 - val_loss: 0.6745 - val_accuracy: 0.5986
Epoch 6/10
426/426 [==============================] - 0s 170us/sample - loss: 0.8943 - accuracy: 0.5047 - val_loss: 0.6741 - val_accuracy: 0.5986
Epoch 7/10
426/426 [==============================] - 0s 177us/sample - loss: 0.8734 - accuracy: 0.5399 - val_loss: 0.6739 - val_accuracy: 0.5986
Epoch 8/10
426/426 [==============================] - 0s 169us/sample - loss: 0.9566 - accuracy: 0.5141 - val_loss: 0.6738 - val_accuracy: 0.5986
Epoch 9/10
426/426 [==============================] - 0s 170us/sample - loss: 0.9005 - accuracy: 0.5352 - val_loss: 0.6737 - val_accuracy: 0.5986
Epoch 10/10
426/426 [==============================] - 0s 175us/sample - loss: 0.9195 - accuracy: 0.5023 - val_loss: 0.6736 - val_accuracy: 0.5986

[2020-12-18 11:21:26.608326] WARNING tensorflow: Large dropout rate: 0.8 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.
1173/1173 - 0s
DataSource(8a6dd21033de43afaa125d9a3b75db18T, v3)

2015-02-11 15:00:00+00:00 买入！

收益率334.9%
年化收益率39.57%
基准收益率11.52%
阿尔法0.35
贝塔0.96
夏普比率0.98
胜率1.0
盈亏比0.0
收益波动率38.83%
信息比率0.07
最大回撤40.62%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9332aa1593a94b09a9a0650dc9124aeb"}/bigcharts-data-end

In [2]:

# 方法一：手动绘制曲线
from matplotlib import pyplot as plt

train_loss = m6.data.read()["history"]["loss"]
val_loss = m6.data.read()["history"]["val_loss"]

plt.plot(train_loss, label="train")
plt.plot(val_loss, label="validation")
plt.legend()
plt.show()

<Figure size 640x480 with 1 Axes>

In [3]:

train_acc = m6.data.read()["history"]["accuracy"]
val_acc = m6.data.read()["history"]["val_accuracy"]

plt.plot(train_acc, label="train")
plt.plot(val_acc, label="validation")
plt.legend()
plt.show()