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11月13日 16:52
# 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 m15_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df = pd.DataFrame({'data': [1, 2, 3]})
    data_1 = DataSource.write_df(df)
    data_2 = DataSource.write_pickle(df)
    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 m15_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m13_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()
#     context.ranker_prediction = context.options['data'].read_df().sort_values('pred_label',ascending=False)
#     context.ranker_prediction = context.options['data'].read_df().sort_values('classes_prob_1.0', ascending=False)


    

    # 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.hold_days = 5

# 回测引擎：每日数据处理函数，每天执行一次
def m13_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.hold_days # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.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StockRanker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StockRanker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 m13_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 m13_before_trading_start_bigquant_run(context, data):
    pass


m1 = M.instruments.v2(
    start_date='2015-01-01',
    end_date='2016-01-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m4 = 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/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)
where(shift(close,-5) / shift(open,-1)>1,1,0)

# 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))

# 将分数映射到分类，这里使用20个分类
# all_wbins(label, 20)

# 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,
    user_functions={}
)

m2 = M.input_features.v1(
    features="""
# #号开始的表示注释，注释需单独一行
# 多个特征，每行一个，可以包含基础特征和衍生特征，特征须为本平台特征
return_5
return_10
return_20
avg_amount_0/avg_amount_5
avg_amount_5/avg_amount_20
rank_avg_amount_0/rank_avg_amount_5
rank_avg_amount_5/rank_avg_amount_10
rank_return_0
rank_return_5
rank_return_10
rank_return_0/rank_return_5
rank_return_5/rank_return_10
pe_ttm_0
"""
)

m5 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m2.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m6 = M.derived_feature_extractor.v3(
    input_data=m5.data,
    features=m2.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m7 = M.join.v3(
    data1=m4.data,
    data2=m6.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m8 = M.dropnan.v2(
    input_data=m7.data
)

m15 = M.cached.v3(
    input_1=m8.data,
    run=m15_run_bigquant_run,
    post_run=m15_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m12 = M.linear_sgd_train.v2(
    training_ds=m15.data_1,
    features=m2.data,
    test_ds=m15.data_3,
    loss='auto',
    penalty='l2',
    alpha=0.0001,
    n_iter=5,
    shuffle=True,
    eta0=0.1,
    algo='classifier'
)

m3 = M.instruments.v2(
    start_date='2016-01-01',
    end_date='2017-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m9 = M.general_feature_extractor.v7(
    instruments=m3.data,
    features=m2.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m10 = M.derived_feature_extractor.v3(
    input_data=m9.data,
    features=m2.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m11 = M.dropnan.v2(
    input_data=m10.data
)

m14 = M.linear_sgd_predict.v2(
    model=m12.model,
    data=m11.data
)

m13 = M.trade.v4(
    instruments=m3.data,
    options_data=m14.predictions,
    start_date='',
    end_date='',
    initialize=m13_initialize_bigquant_run,
    handle_data=m13_handle_data_bigquant_run,
    prepare=m13_prepare_bigquant_run,
    before_trading_start=m13_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='000300.HIX'
)

[2022-11-13 16:50:14.994776] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-13 16:50:15.169911] INFO: moduleinvoker: instruments.v2 运行完成[0.175144s].

[2022-11-13 16:50:15.198004] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-11-13 16:50:17.792230] INFO: 自动标注(股票): 加载历史数据: 569698 行

[2022-11-13 16:50:17.795308] INFO: 自动标注(股票): 开始标注 ..

[2022-11-13 16:50:19.581967] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[4.383961s].

[2022-11-13 16:50:19.597583] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-11-13 16:50:19.606963] INFO: moduleinvoker: 命中缓存

[2022-11-13 16:50:19.609403] INFO: moduleinvoker: input_features.v1 运行完成[0.011845s].

[2022-11-13 16:50:19.636620] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-13 16:50:21.410899] INFO: 基础特征抽取: 年份 2014, 特征行数=141569

[2022-11-13 16:50:25.247130] INFO: 基础特征抽取: 年份 2015, 特征行数=569698

[2022-11-13 16:50:26.291792] INFO: 基础特征抽取: 年份 2016, 特征行数=0

[2022-11-13 16:50:26.422644] INFO: 基础特征抽取: 总行数: 711267

[2022-11-13 16:50:26.430069] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[6.793454s].

[2022-11-13 16:50:26.449307] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-13 16:50:28.520042] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.004s

[2022-11-13 16:50:28.528033] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.006s

[2022-11-13 16:50:28.534857] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.005s

[2022-11-13 16:50:28.539014] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.003s

[2022-11-13 16:50:28.564532] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.024s

[2022-11-13 16:50:28.570065] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.003s

[2022-11-13 16:50:29.119560] INFO: derived_feature_extractor: /y_2014, 141569

[2022-11-13 16:50:30.932462] INFO: derived_feature_extractor: /y_2015, 569698

[2022-11-13 16:50:31.518889] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[5.069556s].

[2022-11-13 16:50:31.535069] INFO: moduleinvoker: join.v3 开始运行..

[2022-11-13 16:50:33.761397] INFO: join: /y_2014, 行数=0/141569, 耗时=0.577109s

[2022-11-13 16:50:36.377686] INFO: join: /y_2015, 行数=560635/569698, 耗时=2.609886s

[2022-11-13 16:50:36.448172] INFO: join: 最终行数: 560635

[2022-11-13 16:50:36.460935] INFO: moduleinvoker: join.v3 运行完成[4.925859s].

[2022-11-13 16:50:36.492548] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-11-13 16:50:36.759681] INFO: dropnan: /y_2014, 0/0

[2022-11-13 16:50:39.257250] INFO: dropnan: /y_2015, 558339/560635

[2022-11-13 16:50:39.349735] INFO: dropnan: 行数: 558339/560635

[2022-11-13 16:50:39.358674] INFO: moduleinvoker: dropnan.v2 运行完成[2.866131s].

[2022-11-13 16:50:39.380839] INFO: moduleinvoker: cached.v3 开始运行..

[2022-11-13 16:50:39.497722] INFO: moduleinvoker: cached.v3 运行完成[0.116905s].

[2022-11-13 16:50:39.522409] INFO: moduleinvoker: linear_sgd_train.v2 开始运行..

[2022-11-13 16:50:39.575758] ERROR: linear_sgd_train: 部分特征没有在数据中，执行失败

[2022-11-13 16:50:39.579269] ERROR: moduleinvoker: module name: linear_sgd_train, module version: v2, trackeback: KeyError: "None of [Index(['return_5', 'return_10', 'return_20', 'avg_amount_0/avg_amount_5',
       'avg_amount_5/avg_amount_20', 'rank_avg_amount_0/rank_avg_amount_5',
       'rank_avg_amount_5/rank_avg_amount_10', 'rank_return_0',
       'rank_return_5', 'rank_return_10', 'rank_return_0/rank_return_5',
       'rank_return_5/rank_return_10', 'pe_ttm_0'],
      dtype='object')] are in the [columns]"

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-1-43e86a72ab21> in <module>
    181 )
    182 
--> 183 m12 = M.linear_sgd_train.v2(
    184     training_ds=m15.data_1,
    185     features=m2.data,

KeyError: "None of [Index(['return_5', 'return_10', 'return_20', 'avg_amount_0/avg_amount_5',\n       'avg_amount_5/avg_amount_20', 'rank_avg_amount_0/rank_avg_amount_5',\n       'rank_avg_amount_5/rank_avg_amount_10', 'rank_return_0',\n       'rank_return_5', 'rank_return_10', 'rank_return_0/rank_return_5',\n       'rank_return_5/rank_return_10', 'pe_ttm_0'],\n      dtype='object')] are in the [columns]"