复制链接

克隆策略

In [29]:

# 本代码由可视化策略环境自动生成 2022年11月6日 21:43
# 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。


# 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().sort_values('pred_label',ascending=False)
#     context.ranker_prediction = context.options['data'].read_df().sort_values('pred_label',ascending=False)
    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',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='2011-01-01',
    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
)

m3 = M.instruments.v2(
    start_date='2016-01-01',
    end_date='2018-01-01',
    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
)

m12 = M.stock_ranker.v2(
    training_ds=m8.data,
    features=m2.data,
    predict_ds=m11.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    data_row_fraction=1,
    ndcg_discount_base=1,
    slim_data=True
)

m13 = M.trade.v4(
    instruments=m3.data,
    options_data=m12.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'
)

[2022-11-06 21:39:37.774210] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-06 21:39:37.799709] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.802595] INFO: moduleinvoker: instruments.v2 运行完成[0.028387s].

[2022-11-06 21:39:37.819790] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-11-06 21:39:37.833450] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.836579] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.016779s].

[2022-11-06 21:39:37.847763] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-11-06 21:39:37.855689] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.858359] INFO: moduleinvoker: input_features.v1 运行完成[0.010607s].

[2022-11-06 21:39:37.878175] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-06 21:39:37.890725] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.893552] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.015403s].

[2022-11-06 21:39:37.904720] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-06 21:39:37.916170] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.919229] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.014517s].

[2022-11-06 21:39:37.933003] INFO: moduleinvoker: join.v3 开始运行..

[2022-11-06 21:39:37.954022] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.957726] INFO: moduleinvoker: join.v3 运行完成[0.024691s].

[2022-11-06 21:39:37.974610] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-11-06 21:39:37.987570] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:37.990815] INFO: moduleinvoker: dropnan.v2 运行完成[0.0162s].

[2022-11-06 21:39:38.009034] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-06 21:39:38.021993] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:38.026645] INFO: moduleinvoker: instruments.v2 运行完成[0.017615s].

[2022-11-06 21:39:38.054315] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-06 21:39:38.062834] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:38.064893] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010615s].

[2022-11-06 21:39:38.073900] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-06 21:39:38.084229] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:38.087255] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.013349s].

[2022-11-06 21:39:38.101874] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-11-06 21:39:38.110351] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:38.112536] INFO: moduleinvoker: dropnan.v2 运行完成[0.010668s].

[2022-11-06 21:39:38.159617] INFO: moduleinvoker: stock_ranker.v2 开始运行..

[2022-11-06 21:39:38.190160] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-11-06 21:39:38.200589] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:39:38.392707] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.202538s].

[2022-11-06 21:39:38.407045] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-11-06 21:39:43.432251] INFO: StockRanker预测: /y_2015 ..

[2022-11-06 21:39:47.973156] INFO: StockRanker预测: /y_2016 ..

[2022-11-06 21:39:54.406709] INFO: StockRanker预测: /y_2017 ..

[2022-11-06 21:40:02.228235] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[23.821178s].

[2022-11-06 21:40:02.357014] INFO: moduleinvoker: stock_ranker.v2 运行完成[24.197393s].

[2022-11-06 21:40:02.431334] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-11-06 21:40:02.440075] INFO: backtest: biglearning backtest:V8.6.3

[2022-11-06 21:40:02.445481] INFO: backtest: product_type:stock by specified

[2022-11-06 21:40:02.855356] INFO: moduleinvoker: cached.v2 开始运行..

[2022-11-06 21:40:02.868630] INFO: moduleinvoker: 命中缓存

[2022-11-06 21:40:02.871062] INFO: moduleinvoker: cached.v2 运行完成[0.015727s].

[2022-11-06 21:40:19.475722] INFO: backtest: algo history_data=DataSource(30dd559ef9304bccbc4399f62e3b1cbcT)

[2022-11-06 21:40:19.478447] INFO: algo: TradingAlgorithm V1.8.8

[2022-11-06 21:40:25.243163] ERROR: moduleinvoker: module name: backtest, module version: v8, trackeback: KeyError: 'pred_label'

[2022-11-06 21:40:25.249995] ERROR: moduleinvoker: module name: trade, module version: v4, trackeback: KeyError: 'pred_label'

设置评估测试数据集，查看训练曲线
[视频教程]StockRanker训练曲线

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-e06cc4e44d644814b1e995be92e6db5a"}/bigcharts-data-end

设置评估测试数据集，查看训练曲线
[视频教程]StockRanker训练曲线

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-bfe79a389f184764aa1c15f9155475fc"}/bigcharts-data-end

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-29-695b9c0b8042> in <module>
    205 )
    206 
--> 207 m13 = M.trade.v4(
    208     instruments=m3.data,
    209     options_data=m12.predictions,

<ipython-input-29-695b9c0b8042> in m13_initialize_bigquant_run(context)
      8 #     context.ranker_prediction = context.options['data'].read_df().sort_values('pred_label',ascending=False)
      9 #     context.ranker_prediction = context.options['data'].read_df().sort_values('pred_label',ascending=False)
---> 10     context.ranker_prediction = context.options['data'].read_df().sort_values('pred_label',ascending=False)
     11 #     context.ranker_prediction = context.options['data'].read_df().sort_values('classes_prob_1',ascending=False)
     12 #

KeyError: 'pred_label'