复制链接

克隆策略

In [14]:

# 本代码由可视化策略环境自动生成 2022年11月7日 20:23
# 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()

    # 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'
)

[2022-11-07 20:22:52.772875] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-07 20:22:52.781857] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:52.784124] INFO: moduleinvoker: instruments.v2 运行完成[0.011257s].

[2022-11-07 20:22:52.799276] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-11-07 20:22:52.813859] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:52.816717] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.017475s].

[2022-11-07 20:22:52.824297] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-11-07 20:22:52.835125] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:52.838075] INFO: moduleinvoker: input_features.v1 运行完成[0.013789s].

[2022-11-07 20:22:52.928459] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-07 20:22:52.939855] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:52.942697] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01425s].

[2022-11-07 20:22:52.953600] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-07 20:22:52.972506] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:52.975543] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.021934s].

[2022-11-07 20:22:52.988650] INFO: moduleinvoker: join.v3 开始运行..

[2022-11-07 20:22:53.018629] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.021035] INFO: moduleinvoker: join.v3 运行完成[0.032387s].

[2022-11-07 20:22:53.032522] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-11-07 20:22:53.046275] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.048654] INFO: moduleinvoker: dropnan.v2 运行完成[0.016134s].

[2022-11-07 20:22:53.059441] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-07 20:22:53.070795] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.073868] INFO: moduleinvoker: instruments.v2 运行完成[0.014422s].

[2022-11-07 20:22:53.097533] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-07 20:22:53.106518] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.109423] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011904s].

[2022-11-07 20:22:53.118962] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-07 20:22:53.131851] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.134710] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.015708s].

[2022-11-07 20:22:53.145583] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-11-07 20:22:53.154355] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.156929] INFO: moduleinvoker: dropnan.v2 运行完成[0.011346s].

[2022-11-07 20:22:53.168037] INFO: moduleinvoker: stock_ranker.v2 开始运行..

[2022-11-07 20:22:53.187609] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.292608] INFO: moduleinvoker: stock_ranker.v2 运行完成[0.124555s].

[2022-11-07 20:22:53.379136] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-11-07 20:22:53.386882] INFO: backtest: biglearning backtest:V8.6.3

[2022-11-07 20:22:53.389381] INFO: backtest: product_type:stock by specified

[2022-11-07 20:22:53.554384] INFO: moduleinvoker: cached.v2 开始运行..

[2022-11-07 20:22:53.568913] INFO: moduleinvoker: 命中缓存

[2022-11-07 20:22:53.572010] INFO: moduleinvoker: cached.v2 运行完成[0.017641s].

[2022-11-07 20:23:08.558283] INFO: backtest: algo history_data=DataSource(e03d97b804eb43a69b4cf22925e1d215T)

[2022-11-07 20:23:08.561032] INFO: algo: TradingAlgorithm V1.8.8

[2022-11-07 20:23:13.274913] INFO: algo: trading transform...

[2022-11-07 20:23:16.343733] INFO: algo: handle_splits get splits [dt:2016-04-06 00:00:00+00:00] [asset:Equity(1678 [002503.SZA]), ratio:0.7680311799049377]

[2022-11-07 20:23:16.864943] INFO: algo: handle_splits get splits [dt:2016-04-21 00:00:00+00:00] [asset:Equity(1847 [300410.SZA]), ratio:0.998920738697052]

[2022-11-07 20:23:16.867663] INFO: Position: position stock handle split[sid:1847, orig_amount:2100, new_amount:2102.0, orig_cost:35.000000213273566, new_cost:34.9622, ratio:0.998920738697052, last_sale_price:37.02000427246094]

[2022-11-07 20:23:16.870582] INFO: Position: after split: PositionStock(asset:Equity(1847 [300410.SZA]), amount:2102.0, cost_basis:34.9622, last_sale_price:37.060001373291016)

[2022-11-07 20:23:16.872943] INFO: Position: returning cash: 9.9546

[2022-11-07 20:23:18.190715] INFO: algo: handle_splits get splits [dt:2016-06-06 00:00:00+00:00] [asset:Equity(2477 [000582.SZA]), ratio:0.9963370561599731]

[2022-11-07 20:23:18.192597] INFO: Position: position stock handle split[sid:2477, orig_amount:4800, new_amount:4817.0, orig_cost:17.850002311534094, new_cost:17.7846, ratio:0.9963370561599731, last_sale_price:16.31999969482422]

[2022-11-07 20:23:18.194163] INFO: Position: after split: PositionStock(asset:Equity(2477 [000582.SZA]), amount:4817.0, cost_basis:17.7846, last_sale_price:16.3799991607666)

[2022-11-07 20:23:18.195812] INFO: Position: returning cash: 10.5553

[2022-11-07 20:23:18.767717] INFO: algo: handle_splits get splits [dt:2016-06-28 00:00:00+00:00] [asset:Equity(2644 [000027.SZA]), ratio:0.9694189429283142]

[2022-11-07 20:23:19.207492] INFO: algo: handle_splits get splits [dt:2016-07-12 00:00:00+00:00] [asset:Equity(1380 [600791.SHA]), ratio:0.99717116355896]

[2022-11-07 20:23:19.209753] INFO: Position: position stock handle split[sid:1380, orig_amount:9000, new_amount:9025.0, orig_cost:6.940000840132148, new_cost:6.9204, ratio:0.99717116355896, last_sale_price:7.050000190734863]

[2022-11-07 20:23:19.211478] INFO: Position: after split: PositionStock(asset:Equity(1380 [600791.SHA]), amount:9025.0, cost_basis:6.9204, last_sale_price:7.070000171661377)

[2022-11-07 20:23:19.213122] INFO: Position: returning cash: 3.7489

[2022-11-07 20:23:27.486612] INFO: algo: handle_splits get splits [dt:2017-05-31 00:00:00+00:00] [asset:Equity(3422 [300384.SZA]), ratio:0.9931263327598572]

[2022-11-07 20:23:27.489153] INFO: Position: position stock handle split[sid:3422, orig_amount:1400, new_amount:1409.0, orig_cost:39.48002458345653, new_cost:39.2087, ratio:0.9931263327598572, last_sale_price:39.01000213623047]

[2022-11-07 20:23:27.491039] INFO: Position: after split: PositionStock(asset:Equity(3422 [300384.SZA]), amount:1409.0, cost_basis:39.2087, last_sale_price:39.279998779296875)

[2022-11-07 20:23:27.492876] INFO: Position: returning cash: 26.9067

[2022-11-07 20:23:27.802017] INFO: algo: handle_splits get splits [dt:2017-06-12 00:00:00+00:00] [asset:Equity(3687 [002275.SZA]), ratio:0.9776158332824707]

[2022-11-07 20:23:27.966347] INFO: algo: handle_splits get splits [dt:2017-06-19 00:00:00+00:00] [asset:Equity(1570 [300265.SZA]), ratio:0.9957912564277649]

[2022-11-07 20:23:27.968339] INFO: Position: position stock handle split[sid:1570, orig_amount:3800, new_amount:3816.0, orig_cost:11.18999999787672, new_cost:11.1429, ratio:0.9957912564277649, last_sale_price:11.829998970031738]

[2022-11-07 20:23:27.970084] INFO: Position: after split: PositionStock(asset:Equity(1570 [300265.SZA]), amount:3816.0, cost_basis:11.1429, last_sale_price:11.879999160766602)

[2022-11-07 20:23:27.971337] INFO: Position: returning cash: 0.7195

[2022-11-07 20:23:28.448197] INFO: algo: handle_splits get splits [dt:2017-07-06 00:00:00+00:00] [asset:Equity(2916 [603116.SHA]), ratio:0.9864495992660522]

[2022-11-07 20:23:28.451092] INFO: Position: position stock handle split[sid:2916, orig_amount:2100, new_amount:2128.0, orig_cost:18.47000286870398, new_cost:18.2197, ratio:0.9864495992660522, last_sale_price:18.199995040893555]

[2022-11-07 20:23:28.453554] INFO: Position: after split: PositionStock(asset:Equity(2916 [603116.SHA]), amount:2128.0, cost_basis:18.2197, last_sale_price:18.450000762939453)

[2022-11-07 20:23:28.455187] INFO: Position: returning cash: 15.4104

[2022-11-07 20:23:28.789614] INFO: algo: handle_splits get splits [dt:2017-07-18 00:00:00+00:00] [asset:Equity(3434 [300522.SZA]), ratio:0.5523555874824524]

[2022-11-07 20:23:28.875403] INFO: algo: handle_splits get splits [dt:2017-07-20 00:00:00+00:00] [asset:Equity(1640 [300407.SZA]), ratio:0.9987163543701172]

[2022-11-07 20:23:30.791958] INFO: algo: handle_splits get splits [dt:2017-09-29 00:00:00+00:00] [asset:Equity(3702 [601515.SHA]), ratio:0.977698564529419]

[2022-11-07 20:23:30.794394] INFO: Position: position stock handle split[sid:3702, orig_amount:3600, new_amount:3682.0, orig_cost:11.320010513498845, new_cost:11.0676, ratio:0.977698564529419, last_sale_price:10.960000991821289]

[2022-11-07 20:23:30.796087] INFO: Position: after split: PositionStock(asset:Equity(3702 [601515.SHA]), amount:3682.0, cost_basis:11.0676, last_sale_price:11.210000038146973)

[2022-11-07 20:23:30.798154] INFO: Position: returning cash: 1.2767

[2022-11-07 20:23:33.107927] INFO: Performance: Simulated 488 trading days out of 488.

[2022-11-07 20:23:33.109783] INFO: Performance: first open: 2016-01-04 09:30:00+00:00

[2022-11-07 20:23:33.111749] INFO: Performance: last close: 2017-12-29 15:00:00+00:00

[2022-11-07 20:23:41.236931] INFO: moduleinvoker: backtest.v8 运行完成[47.857808s].

[2022-11-07 20:23:41.239224] INFO: moduleinvoker: trade.v4 运行完成[47.934837s].

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-0d41b664d8f14dc9954a0470c9990970"}/bigcharts-data-end

收益率18.37%
年化收益率9.1%
基准收益率8.04%
阿尔法0.07
贝塔0.93
夏普比率0.35
胜率0.56
盈亏比0.95
收益波动率25.09%
信息比率0.02
最大回撤27.73%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9ea14df10b414baf8353e81f277f34e9"}/bigcharts-data-end