克隆策略

In [2]:

# 本代码由可视化策略环境自动生成 2020年5月6日 10:20
# 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({'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 = 5
    # 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='2014-01-01',
    end_date='2017-12-31',
    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)
where(label>0.5, NaN, label)
where(label<-0.5, NaN, label)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=False
)

m3 = M.input_features.v1(
    features="""# #号开始的表示注释
# 多个特征，每行一个，可以包含基础特征和衍生特征
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
"""
)

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
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m13 = M.dl_convert_to_bin.v2(
    input_data=m7.data,
    features=m3.data,
    window_size=1,
    feature_clip=5,
    flatten=True,
    window_along_col='instrument'
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2018-01-01'),
    end_date=T.live_run_param('trading_date', '2018-12-31'),
    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
)

m14 = M.dl_convert_to_bin.v2(
    input_data=m18.data,
    features=m3.data,
    window_size=1,
    feature_clip=5,
    flatten=True,
    window_along_col='instrument'
)

m6 = M.dl_layer_input.v1(
    shape='59',
    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=0.9,
    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=''
)

m23 = M.dl_layer_dense.v1(
    inputs=m20.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=m13.data,
    optimizer='Adam',
    loss='mean_squared_error',
    metrics='mse',
    batch_size=10240,
    epochs=2,
    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=m14.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'
)

[2020-05-06 10:17:49.021399] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-05-06 10:17:49.063255] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.064591] INFO: moduleinvoker: instruments.v2 运行完成[0.04323s].

[2020-05-06 10:17:49.076058] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2020-05-06 10:17:49.082022] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.085781] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009749s].

[2020-05-06 10:17:49.091239] INFO: moduleinvoker: input_features.v1 开始运行..

[2020-05-06 10:17:49.100110] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.101021] INFO: moduleinvoker: input_features.v1 运行完成[0.009782s].

[2020-05-06 10:17:49.131143] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-05-06 10:17:49.157319] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.158395] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.02726s].

[2020-05-06 10:17:49.165417] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2020-05-06 10:17:49.171619] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.172477] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.007069s].

[2020-05-06 10:17:49.175475] INFO: moduleinvoker: join.v3 开始运行..

[2020-05-06 10:17:49.182400] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.183193] INFO: moduleinvoker: join.v3 运行完成[0.007716s].

[2020-05-06 10:17:49.194040] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2020-05-06 10:17:49.201534] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.202391] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.008353s].

[2020-05-06 10:17:49.203749] INFO: moduleinvoker: instruments.v2 开始运行..

[2020-05-06 10:17:49.243351] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.244418] INFO: moduleinvoker: instruments.v2 运行完成[0.040656s].

[2020-05-06 10:17:49.256693] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2020-05-06 10:17:49.270477] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.271521] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.014836s].

[2020-05-06 10:17:49.273036] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2020-05-06 10:17:49.278261] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.279090] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.00605s].

[2020-05-06 10:17:49.302564] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2020-05-06 10:17:49.327530] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:17:49.328653] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.026096s].

[2020-05-06 10:17:54.583029] INFO: moduleinvoker: dl_layer_input.v1 运行完成[5.245192s].

[2020-05-06 10:17:54.642505] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.054454s].

[2020-05-06 10:17:54.686006] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.037161s].

[2020-05-06 10:17:54.701433] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.013617s].

[2020-05-06 10:17:54.714786] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.011625s].

[2020-05-06 10:17:54.749478] INFO: moduleinvoker: cached.v3 开始运行..

[2020-05-06 10:17:54.786460] INFO: moduleinvoker: cached.v3 运行完成[0.036975s].

[2020-05-06 10:17:54.789557] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.068571s].

[2020-05-06 10:17:54.802241] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2020-05-06 10:17:54.828595] INFO: device_manager: 没有gpu资源，将使用cpu计算

[2020-05-06 10:17:54.900442] INFO: device_manager: 本次操作不使用GPU

[2020-05-06 10:17:58.643332] INFO: dl_model_train: 准备训练，训练样本个数：2158451，迭代次数：2

[2020-05-06 10:19:30.724939] INFO: dl_model_train: 训练结束，耗时：92.08s

[2020-05-06 10:19:30.931975] INFO: moduleinvoker: dl_model_train.v1 运行完成[96.129731s].

[2020-05-06 10:19:30.937232] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2020-05-06 10:19:31.025633] INFO: device_manager: 没有gpu资源，将使用cpu计算

[2020-05-06 10:19:31.030032] INFO: device_manager: 本次操作不使用GPU

[2020-05-06 10:19:34.349889] INFO: moduleinvoker: dl_model_predict.v1 运行完成[3.412629s].

[2020-05-06 10:19:34.354494] INFO: moduleinvoker: cached.v3 开始运行..

[2020-05-06 10:19:35.530896] INFO: moduleinvoker: cached.v3 运行完成[1.176386s].

[2020-05-06 10:19:36.548210] INFO: moduleinvoker: backtest.v8 开始运行..

[2020-05-06 10:19:36.552393] INFO: backtest: biglearning backtest:V8.3.4

[2020-05-06 10:19:36.553796] INFO: backtest: product_type:stock by specified

[2020-05-06 10:19:36.680245] INFO: moduleinvoker: cached.v2 开始运行..

[2020-05-06 10:19:36.690734] INFO: moduleinvoker: 命中缓存

[2020-05-06 10:19:36.692422] INFO: moduleinvoker: cached.v2 运行完成[0.012181s].

[2020-05-06 10:19:37.903622] INFO: algo: TradingAlgorithm V1.6.7

[2020-05-06 10:19:38.747428] INFO: algo: trading transform...

[2020-05-06 10:19:41.732875] INFO: Performance: Simulated 243 trading days out of 243.

[2020-05-06 10:19:41.734082] INFO: Performance: first open: 2018-01-02 09:30:00+00:00

[2020-05-06 10:19:41.735093] INFO: Performance: last close: 2018-12-28 15:00:00+00:00

[2020-05-06 10:19:46.798129] INFO: moduleinvoker: backtest.v8 运行完成[10.249919s].

[2020-05-06 10:19:46.800084] INFO: moduleinvoker: trade.v4 运行完成[11.255499s].

[2020-05-06 10:17:54.653316] WARNING tensorflow: Large dropout rate: 0.9 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.

[2020-05-06 10:17:54.966648] WARNING tensorflow: Large dropout rate: 0.9 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.

Train on 2158451 samples
Epoch 1/2
[2020-05-06 10:18:00.545717] WARNING tensorflow: Large dropout rate: 0.9 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.
[2020-05-06 10:18:00.980135] WARNING tensorflow: Large dropout rate: 0.9 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.
2158451/2158451 - 46s - loss: 0.0111 - mse: 0.0111
Epoch 2/2
2158451/2158451 - 44s - loss: 0.0054 - mse: 0.0054

[2020-05-06 10:19:31.078054] WARNING tensorflow: Large dropout rate: 0.9 (>0.5). In TensorFlow 2.x, dropout() uses dropout rate instead of keep_prob. Please ensure that this is intended.
428066/428066 - 3s
DataSource(341a261240494f4499cec873760ab184T, v3)

收益率-45.54%
年化收益率-46.75%
基准收益率-25.31%
阿尔法-0.49
贝塔0.47
夏普比率-2.72
胜率0.43
盈亏比0.7
收益波动率23.24%
信息比率-0.09
最大回撤45.78%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-aa7ffa212bb044488fef6c509d101226"}/bigcharts-data-end