克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2019年4月11日 16:34
# 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 m2_run_bigquant_run(input_1, input_2, input_3):
    predictions = input_1.read_pickle()
    pred_result = predictions.reshape(predictions.shape[0]) 
    dt = input_2.read_df()['date']
    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：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：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='5,59',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m4 = M.dl_layer_lstm.v1(
    inputs=m3.data,
    units=32,
    activation='linear',
    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=True,
    implementation='0',
    name=''
)

m10 = M.dl_layer_dropout.v1(
    inputs=m4.data,
    rate=0.1,
    noise_shape='',
    seed=0,
    name=''
)

m25 = M.dl_layer_lstm.v1(
    inputs=m10.data,
    units=32,
    activation='sigmoid',
    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='0',
    name=''
)

m11 = M.dl_layer_dropout.v1(
    inputs=m25.data,
    rate=0.1,
    noise_shape='',
    seed=0,
    name=''
)

m9 = M.dl_layer_dense.v1(
    inputs=m11.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="""return_5-1
return_10-1
return_20-1
avg_amount_0/avg_amount_5-1
avg_amount_5/avg_amount_20-1
rank_avg_amount_0-rank_avg_amount_5
rank_avg_amount_5-rank_avg_amount_10
rank_return_0-rank_return_5
rank_return_5-rank_return_10
beta_csi300_30_0/10
beta_csi300_60_0/10
swing_volatility_5_0/swing_volatility_30_0-1
swing_volatility_30_0/swing_volatility_60_0-1
ta_atr_14_0/ta_atr_28_0-1
ta_sma_5_0/ta_sma_20_0-1
ta_sma_10_0/ta_sma_20_0-1
ta_sma_20_0/ta_sma_30_0-1
ta_sma_30_0/ta_sma_60_0-1
ta_rsi_14_0/100
ta_rsi_28_0/100
ta_cci_14_0/500
ta_cci_28_0/500
beta_industry_30_0/10
beta_industry_60_0/10
ta_sma(amount_0, 10)/ta_sma(amount_0, 20)-1
ta_sma(amount_0, 20)/ta_sma(amount_0, 30)-1
ta_sma(amount_0, 30)/ta_sma(amount_0, 60)-1
ta_sma(amount_0, 50)/ta_sma(amount_0, 100)-1
ta_sma(turn_0, 10)/ta_sma(turn_0, 20)-1
ta_sma(turn_0, 20)/ta_sma(turn_0, 30)-1
ta_sma(turn_0, 30)/ta_sma(turn_0, 60)-1
ta_sma(turn_0, 50)/ta_sma(turn_0, 100)-1
high_0/low_0-1
close_0/open_0-1
shift(close_0,1)/close_0-1
shift(close_0,2)/close_0-1
shift(close_0,3)/close_0-1
shift(close_0,4)/close_0-1
shift(close_0,5)/close_0-1
shift(close_0,10)/close_0-1
shift(close_0,20)/close_0-1
ta_sma(high_0-low_0, 5)/ta_sma(high_0-low_0, 20)-1
ta_sma(high_0-low_0, 10)/ta_sma(high_0-low_0, 20)-1
ta_sma(high_0-low_0, 20)/ta_sma(high_0-low_0, 30)-1
ta_sma(high_0-low_0, 30)/ta_sma(high_0-low_0, 60)-1
ta_sma(high_0-low_0, 50)/ta_sma(high_0-low_0, 100)-1
rank_avg_amount_5
rank_avg_turn_5
rank_volatility_5_0
rank_swing_volatility_5_0
rank_avg_mf_net_amount_5
rank_beta_industry_5_0
rank_return_5
rank_return_2
std(close_0,5)/std(close_0,20)-1
std(close_0,10)/std(close_0,20)-1
std(close_0,20)/std(close_0,30)-1
std(close_0,30)/std(close_0,60)-1
std(close_0,50)/std(close_0,100)-1"""
)

m24 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2017-03-01',
    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)
shift(close, -5) / shift(open, -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=True,
    user_functions={}
)

m16 = M.general_feature_extractor.v7(
    instruments=m24.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m22 = 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={}
)

m17 = M.join.v3(
    data1=m21.data,
    data2=m22.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m18 = M.dropnan.v1(
    input_data=m17.data
)

m13 = M.dl_convert_to_bin.v2(
    input_data=m18.data,
    features=m8.data,
    window_size=5,
    feature_clip=5,
    flatten=False,
    window_along_col='instrument'
)

m6 = M.dl_model_train.v1(
    input_model=m5.data,
    training_data=m13.data,
    optimizer='RMSprop',
    loss='mean_squared_error',
    metrics='mse',
    batch_size=512,
    epochs=10,
    n_gpus=0,
    verbose='1:输出进度条记录'
)

m23 = M.instruments.v2(
    start_date='2017-03-01',
    end_date='2019-03-01',
    market='CN_STOCK_A',
    instrument_list='600009.SHA',
    max_count=0
)

m26 = M.general_feature_extractor.v7(
    instruments=m23.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m27 = M.derived_feature_extractor.v3(
    input_data=m26.data,
    features=m8.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m19 = M.dropnan.v1(
    input_data=m27.data
)

m14 = M.dl_convert_to_bin.v2(
    input_data=m19.data,
    features=m8.data,
    window_size=5,
    feature_clip=5,
    flatten=False,
    window_along_col='instrument'
)

m7 = M.dl_model_predict.v1(
    trained_model=m6.data,
    input_data=m14.data,
    batch_size=1024,
    n_gpus=2,
    verbose='2:每个epoch输出一行记录'
)

m2 = M.cached.v3(
    input_1=m7.data,
    input_2=m19.data,
    run=m2_run_bigquant_run,
    post_run=m2_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m15 = M.use_datasource.v1(
    instruments=m23.data,
    datasource_id='bar1d_CN_STOCK_A',
    start_date='',
    end_date=''
)

m1 = M.trade.v4(
    instruments=m23.data,
    options_data=m2.data_1,
    benchmark_ds=m15.data,
    start_date='2017-04-01',
    end_date='',
    handle_data=m1_handle_data_bigquant_run,
    prepare=m1_prepare_bigquant_run,
    initialize=m1_initialize_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=''
)

[2019-04-11 16:32:47.938372] INFO: bigquant: cached.v3 开始运行..

[2019-04-11 16:32:47.975496] INFO: bigquant: 命中缓存

[2019-04-11 16:32:47.977812] INFO: bigquant: cached.v3 运行完成[0.039441s].

[2019-04-11 16:32:47.995775] INFO: bigquant: input_features.v1 开始运行..

[2019-04-11 16:32:48.003263] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.004802] INFO: bigquant: input_features.v1 运行完成[0.009037s].

[2019-04-11 16:32:48.011603] INFO: bigquant: instruments.v2 开始运行..

[2019-04-11 16:32:48.016555] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.017927] INFO: bigquant: instruments.v2 运行完成[0.006318s].

[2019-04-11 16:32:48.021802] INFO: bigquant: advanced_auto_labeler.v2 开始运行..

[2019-04-11 16:32:48.026385] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.027892] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.006083s].

[2019-04-11 16:32:48.065746] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-04-11 16:32:48.071725] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.073488] INFO: bigquant: general_feature_extractor.v7 运行完成[0.007744s].

[2019-04-11 16:32:48.078092] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-04-11 16:32:48.082644] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.083998] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.0059s].

[2019-04-11 16:32:48.087672] INFO: bigquant: join.v3 开始运行..

[2019-04-11 16:32:48.092298] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.093613] INFO: bigquant: join.v3 运行完成[0.005937s].

[2019-04-11 16:32:48.096890] INFO: bigquant: dropnan.v1 开始运行..

[2019-04-11 16:32:48.101558] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.102777] INFO: bigquant: dropnan.v1 运行完成[0.005882s].

[2019-04-11 16:32:48.111059] INFO: bigquant: dl_convert_to_bin.v2 开始运行..

[2019-04-11 16:32:48.117269] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.119318] INFO: bigquant: dl_convert_to_bin.v2 运行完成[0.00825s].

[2019-04-11 16:32:48.124233] INFO: bigquant: dl_model_train.v1 开始运行..

[2019-04-11 16:32:48.130308] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.131995] INFO: bigquant: dl_model_train.v1 运行完成[0.007762s].

[2019-04-11 16:32:48.134979] INFO: bigquant: instruments.v2 开始运行..

[2019-04-11 16:32:48.139826] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.141383] INFO: bigquant: instruments.v2 运行完成[0.006396s].

[2019-04-11 16:32:48.148293] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-04-11 16:32:48.153721] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.166448] INFO: bigquant: general_feature_extractor.v7 运行完成[0.018146s].

[2019-04-11 16:32:48.169703] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-04-11 16:32:48.175040] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.176402] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.006693s].

[2019-04-11 16:32:48.179112] INFO: bigquant: dropnan.v1 开始运行..

[2019-04-11 16:32:48.183448] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.184645] INFO: bigquant: dropnan.v1 运行完成[0.005527s].

[2019-04-11 16:32:48.189681] INFO: bigquant: dl_convert_to_bin.v2 开始运行..

[2019-04-11 16:32:48.194118] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.195349] INFO: bigquant: dl_convert_to_bin.v2 运行完成[0.005663s].

[2019-04-11 16:32:48.199588] INFO: bigquant: dl_model_predict.v1 开始运行..

[2019-04-11 16:32:48.204287] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.205686] INFO: bigquant: dl_model_predict.v1 运行完成[0.006095s].

[2019-04-11 16:32:48.210041] INFO: bigquant: cached.v3 开始运行..

[2019-04-11 16:32:48.215229] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.216755] INFO: bigquant: cached.v3 运行完成[0.006711s].

[2019-04-11 16:32:48.220389] INFO: bigquant: use_datasource.v1 开始运行..

[2019-04-11 16:32:48.225197] INFO: bigquant: 命中缓存

[2019-04-11 16:32:48.226454] INFO: bigquant: use_datasource.v1 运行完成[0.00606s].

[2019-04-11 16:32:48.311405] INFO: bigquant: backtest.v8 开始运行..

[2019-04-11 16:32:48.314311] INFO: bigquant: biglearning backtest:V8.1.11

[2019-04-11 16:32:48.316232] INFO: bigquant: product_type:stock by specified

[2019-04-11 16:32:54.230762] INFO: bigquant: 读取股票行情完成:709

[2019-04-11 16:32:54.270611] INFO: algo: TradingAlgorithm V1.4.10

[2019-04-11 16:32:54.420498] INFO: algo: trading transform...

[2019-04-11 16:32:55.589127] INFO: Performance: Simulated 466 trading days out of 466.

[2019-04-11 16:32:55.591421] INFO: Performance: first open: 2017-04-05 09:30:00+00:00

[2019-04-11 16:32:55.593743] INFO: Performance: last close: 2019-03-01 15:00:00+00:00

[2019-04-11 16:32:56.816420] INFO: bigquant: backtest.v8 运行完成[8.505003s].

Using TensorFlow backend.

DataSource(fb36dcc2a6184901a6e50f01fc42ba18, v3)

收益率48.13%
年化收益率23.67%
基准收益率102.85%
阿尔法0.05
贝塔0.37
夏普比率0.95
胜率0.71
盈亏比1.13
收益波动率21.81%
信息比率-0.05
最大回撤12.63%