复制链接

克隆策略

In [1]:

1+1

Out[1]:

In [9]:

# 本代码由可视化策略环境自动生成 2022年2月20日 21:12
# 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 m14_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 m14_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 m14_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 m14_before_trading_start_bigquant_run(context, data):
    pass


m1 = M.instruments.v2(
    start_date='2013-01-01',
    end_date='2016-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m3 = 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)

# 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=True,
    user_functions={}
)

m2 = M.instruments.v2(
    start_date='2017-01-01',
    end_date='2018-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m4 = 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=m4.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m6 = M.derived_feature_extractor.v3(
    input_data=m5.data,
    features=m4.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m9 = M.join.v3(
    data1=m3.data,
    data2=m6.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m10 = M.dropnan.v2(
    input_data=m9.data
)

m7 = M.general_feature_extractor.v7(
    instruments=m2.data,
    features=m4.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m8 = M.derived_feature_extractor.v3(
    input_data=m7.data,
    features=m4.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m11 = M.dropnan.v2(
    input_data=m8.data
)

m12 = M.stock_ranker_train.v6(
    training_ds=m10.data,
    features=m4.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,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

m13 = M.stock_ranker_predict.v5(
    model=m12.model,
    data=m11.data,
    m_lazy_run=False
)

m14 = M.trade.v4(
    instruments=m2.data,
    options_data=m13.predictions,
    start_date='',
    end_date='',
    initialize=m14_initialize_bigquant_run,
    handle_data=m14_handle_data_bigquant_run,
    prepare=m14_prepare_bigquant_run,
    before_trading_start=m14_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'
)

[2022-02-20 20:56:42.725851] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-02-20 20:56:42.739878] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:42.744230] INFO: moduleinvoker: instruments.v2 运行完成[0.018373s].

[2022-02-20 20:56:42.789861] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-02-20 20:56:42.803791] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:42.806188] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.016346s].

[2022-02-20 20:56:42.812994] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-02-20 20:56:42.954585] INFO: moduleinvoker: instruments.v2 运行完成[0.141547s].

[2022-02-20 20:56:42.995166] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-02-20 20:56:43.006000] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:43.009070] INFO: moduleinvoker: input_features.v1 运行完成[0.013942s].

[2022-02-20 20:56:43.027048] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-02-20 20:56:43.042980] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:43.045358] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.018342s].

[2022-02-20 20:56:43.073285] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-02-20 20:56:43.085664] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:43.088366] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.015094s].

[2022-02-20 20:56:43.113316] INFO: moduleinvoker: join.v3 开始运行..

[2022-02-20 20:56:43.136066] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:43.139531] INFO: moduleinvoker: join.v3 运行完成[0.026217s].

[2022-02-20 20:56:43.192106] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-02-20 20:56:43.207937] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:56:43.210315] INFO: moduleinvoker: dropnan.v2 运行完成[0.018233s].

[2022-02-20 20:56:43.231831] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-02-20 20:56:47.068819] INFO: 基础特征抽取: 年份 2016, 特征行数=165781

[2022-02-20 20:57:29.050964] INFO: 基础特征抽取: 年份 2017, 特征行数=743233

[2022-02-20 20:58:22.414614] INFO: 基础特征抽取: 年份 2018, 特征行数=816987

[2022-02-20 20:58:22.573166] INFO: 基础特征抽取: 总行数: 1726001

[2022-02-20 20:58:22.587697] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[99.355902s].

[2022-02-20 20:58:22.611414] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-02-20 20:58:27.139266] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.010s

[2022-02-20 20:58:27.148744] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.007s

[2022-02-20 20:58:27.163007] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.011s

[2022-02-20 20:58:27.176431] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.011s

[2022-02-20 20:58:27.182919] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s

[2022-02-20 20:58:27.232194] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.048s

[2022-02-20 20:58:27.878762] INFO: derived_feature_extractor: /y_2016, 165781

[2022-02-20 20:58:29.703150] INFO: derived_feature_extractor: /y_2017, 743233

[2022-02-20 20:58:32.158765] INFO: derived_feature_extractor: /y_2018, 816987

[2022-02-20 20:58:32.927830] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[10.316454s].

[2022-02-20 20:58:32.947416] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-02-20 20:58:33.345949] INFO: dropnan: /y_2016, 163887/165781

[2022-02-20 20:58:34.687516] INFO: dropnan: /y_2017, 733820/743233

[2022-02-20 20:58:36.074135] INFO: dropnan: /y_2018, 814562/816987

[2022-02-20 20:58:36.202070] INFO: dropnan: 行数: 1712269/1726001

[2022-02-20 20:58:36.213918] INFO: moduleinvoker: dropnan.v2 运行完成[3.266507s].

[2022-02-20 20:58:36.226684] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-02-20 20:58:36.371270] INFO: moduleinvoker: 命中缓存

[2022-02-20 20:58:36.600861] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.374177s].

[2022-02-20 20:58:36.621053] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-02-20 20:58:36.938116] INFO: StockRanker预测: /y_2016 ..

[2022-02-20 20:58:37.908341] INFO: StockRanker预测: /y_2017 ..

[2022-02-20 20:58:40.120244] INFO: StockRanker预测: /y_2018 ..

[2022-02-20 20:58:46.710579] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[10.089518s].

[2022-02-20 20:58:46.809464] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-02-20 20:58:46.821279] INFO: backtest: biglearning backtest:V8.6.1

[2022-02-20 20:58:46.822883] INFO: backtest: product_type:stock by specified

[2022-02-20 20:58:47.106265] INFO: moduleinvoker: cached.v2 开始运行..

[2022-02-20 20:59:04.409324] INFO: backtest: 读取股票行情完成:2581648

[2022-02-20 20:59:10.830490] INFO: moduleinvoker: cached.v2 运行完成[23.724204s].

[2022-02-20 20:59:13.794760] INFO: algo: TradingAlgorithm V1.8.7

[2022-02-20 20:59:15.364201] INFO: algo: trading transform...

[2022-02-20 20:59:23.569458] INFO: algo: handle_splits get splits [dt:2017-05-09 00:00:00+00:00] [asset:Equity(487 [603322.SHA]), ratio:0.9979960918426514]

[2022-02-20 20:59:23.571891] INFO: Position: position stock handle split[sid:487, orig_amount:2800, new_amount:2805.0, orig_cost:62.39500160160807, new_cost:62.27, ratio:0.9979960918426514, last_sale_price:59.760005950927734]

[2022-02-20 20:59:23.575306] INFO: Position: after split: PositionStock(asset:Equity(487 [603322.SHA]), amount:2805.0, cost_basis:62.27, last_sale_price:59.880001068115234)

[2022-02-20 20:59:23.577997] INFO: Position: returning cash: 37.1832

[2022-02-20 20:59:23.961881] INFO: algo: handle_splits get splits [dt:2017-05-22 00:00:00+00:00] [asset:Equity(374 [300548.SZA]), ratio:0.9965568780899048]

[2022-02-20 20:59:23.964926] INFO: Position: position stock handle split[sid:374, orig_amount:800, new_amount:802.0, orig_cost:57.030006292308165, new_cost:56.8336, ratio:0.9965568780899048, last_sale_price:57.88002395629883]

[2022-02-20 20:59:23.967477] INFO: Position: after split: PositionStock(asset:Equity(374 [300548.SZA]), amount:802.0, cost_basis:56.8336, last_sale_price:58.08000183105469)

[2022-02-20 20:59:23.969878] INFO: Position: returning cash: 44.2212

[2022-02-20 20:59:24.188015] INFO: algo: handle_splits get splits [dt:2017-05-26 00:00:00+00:00] [asset:Equity(1839 [002797.SZA]), ratio:0.623359739780426]

[2022-02-20 20:59:24.191544] INFO: Position: position stock handle split[sid:1839, orig_amount:13100, new_amount:21015.0, orig_cost:13.686335589835526, new_cost:8.5315, ratio:0.623359739780426, last_sale_price:9.500001907348633]

[2022-02-20 20:59:24.195280] INFO: Position: after split: PositionStock(asset:Equity(1839 [002797.SZA]), amount:21015.0, cost_basis:8.5315, last_sale_price:15.239999771118164)

[2022-02-20 20:59:24.198052] INFO: Position: returning cash: 1.4488

[2022-02-20 20:59:24.421857] INFO: algo: handle_splits get splits [dt:2017-06-06 00:00:00+00:00] [asset:Equity(2289 [300387.SZA]), ratio:0.9926353096961975]

[2022-02-20 20:59:24.423372] INFO: Position: position stock handle split[sid:2289, orig_amount:2700, new_amount:2720.0, orig_cost:18.65002412471148, new_cost:18.5127, ratio:0.9926353096961975, last_sale_price:18.869997024536133]

[2022-02-20 20:59:24.424484] INFO: Position: after split: PositionStock(asset:Equity(2289 [300387.SZA]), amount:2720.0, cost_basis:18.5127, last_sale_price:19.010000228881836)

[2022-02-20 20:59:24.428706] INFO: Position: returning cash: 0.6075

[2022-02-20 20:59:25.055732] INFO: algo: handle_splits get splits [dt:2017-06-23 00:00:00+00:00] [asset:Equity(1406 [300261.SZA]), ratio:0.9955899715423584]

[2022-02-20 20:59:25.058993] INFO: Position: position stock handle split[sid:1406, orig_amount:6500, new_amount:6528.0, orig_cost:9.240005611124051, new_cost:9.1993, ratio:0.9955899715423584, last_sale_price:9.030000686645508]

[2022-02-20 20:59:25.063629] INFO: Position: after split: PositionStock(asset:Equity(1406 [300261.SZA]), amount:6528.0, cost_basis:9.1993, last_sale_price:9.069999694824219)

[2022-02-20 20:59:25.066658] INFO: Position: returning cash: 7.1532

[2022-02-20 20:59:25.571694] INFO: algo: handle_splits get splits [dt:2017-07-10 00:00:00+00:00] [asset:Equity(178 [603223.SHA]), ratio:0.9959980249404907]

[2022-02-20 20:59:25.576200] INFO: Position: position stock handle split[sid:178, orig_amount:1400, new_amount:1405.0, orig_cost:24.920010862775865, new_cost:24.8203, ratio:0.9959980249404907, last_sale_price:24.889991760253906]

[2022-02-20 20:59:25.579202] INFO: Position: after split: PositionStock(asset:Equity(178 [603223.SHA]), amount:1405.0, cost_basis:24.8203, last_sale_price:24.990001678466797)

[2022-02-20 20:59:25.582522] INFO: Position: returning cash: 15.5631

[2022-02-20 20:59:25.882237] INFO: algo: handle_splits get splits [dt:2017-07-18 00:00:00+00:00] [asset:Equity(180 [300522.SZA]), ratio:0.5523555874824524]

[2022-02-20 20:59:27.100397] INFO: algo: handle_splits get splits [dt:2017-08-24 00:00:00+00:00] [asset:Equity(3208 [300517.SZA]), ratio:0.9946913123130798]

[2022-02-20 20:59:27.103047] INFO: Position: position stock handle split[sid:3208, orig_amount:1500, new_amount:1508.0, orig_cost:24.62001206082065, new_cost:24.4893, ratio:0.9946913123130798, last_sale_price:24.359989166259766]

[2022-02-20 20:59:27.106776] INFO: Position: after split: PositionStock(asset:Equity(3208 [300517.SZA]), amount:1508.0, cost_basis:24.4893, last_sale_price:24.489999771118164)

[2022-02-20 20:59:27.108952] INFO: Position: returning cash: 0.1347

[2022-02-20 20:59:36.902673] INFO: algo: handle_splits get splits [dt:2018-07-05 00:00:00+00:00] [asset:Equity(602 [600682.SHA]), ratio:0.9931350946426392]

[2022-02-20 20:59:36.905705] INFO: Position: position stock handle split[sid:602, orig_amount:400, new_amount:402.0, orig_cost:13.579999923758576, new_cost:13.4868, ratio:0.9931350946426392, last_sale_price:13.020000457763672]

[2022-02-20 20:59:36.908270] INFO: Position: after split: PositionStock(asset:Equity(602 [600682.SHA]), amount:402.0, cost_basis:13.4868, last_sale_price:13.109999656677246)

[2022-02-20 20:59:36.910113] INFO: Position: returning cash: 9.9596

[2022-02-20 20:59:37.273747] INFO: algo: handle_splits get splits [dt:2018-07-13 00:00:00+00:00] [asset:Equity(1829 [300266.SZA]), ratio:0.6649048924446106]

[2022-02-20 20:59:37.276111] INFO: Position: position stock handle split[sid:1829, orig_amount:100, new_amount:150.0, orig_cost:7.739999771118291, new_cost:5.1464, ratio:0.6649048924446106, last_sale_price:6.2900004386901855]

[2022-02-20 20:59:37.278955] INFO: Position: after split: PositionStock(asset:Equity(1829 [300266.SZA]), amount:150.0, cost_basis:5.1464, last_sale_price:9.460000038146973)

[2022-02-20 20:59:37.282839] INFO: Position: returning cash: 2.5

[2022-02-20 20:59:39.072360] INFO: algo: handle_splits get splits [dt:2018-08-29 00:00:00+00:00] [asset:Equity(33 [600687.SHA]), ratio:0.9910112619400024]

[2022-02-20 20:59:39.076025] INFO: Position: position stock handle split[sid:33, orig_amount:100, new_amount:100.0, orig_cost:4.400000095367966, new_cost:4.3604, ratio:0.9910112619400024, last_sale_price:4.409999847412109]

[2022-02-20 20:59:39.081421] INFO: Position: after split: PositionStock(asset:Equity(33 [600687.SHA]), amount:100.0, cost_basis:4.3604, last_sale_price:4.449999809265137)

[2022-02-20 20:59:39.084185] INFO: Position: returning cash: 4.0

[2022-02-20 20:59:42.567939] INFO: Performance: Simulated 487 trading days out of 487.

[2022-02-20 20:59:42.572467] INFO: Performance: first open: 2017-01-03 09:30:00+00:00

[2022-02-20 20:59:42.575693] INFO: Performance: last close: 2018-12-28 15:00:00+00:00

[2022-02-20 20:59:53.077981] INFO: moduleinvoker: backtest.v8 运行完成[66.26852s].

[2022-02-20 20:59:53.082043] INFO: moduleinvoker: trade.v4 运行完成[66.362243s].

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-e724164270914e74afd5c1b41212418e"}/bigcharts-data-end

收益率-55.53%
年化收益率-34.25%
基准收益率-9.05%
阿尔法-0.34
贝塔0.19
夏普比率-2.55
胜率0.52
盈亏比0.64
收益波动率17.04%
信息比率-0.11
最大回撤58.03%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-2b0add5b96c34bebb987e6ce46c69b7d"}/bigcharts-data-end

In [ ]: