克隆策略

基于随机森林模型的智能选股策略¶

n_estimators (int) – 树的个数，个数越多，则模型越复杂，计算速度越慢。
max_features (str) – 最多考虑特征个数，新建节点时，最多考虑的特征个数。
max_depth (int) – 每棵树的最大深度，数值大拟合能力强，数值小泛化能力强。
min_samples_leaf (int) – 每个叶子节点最少样本数，数值大泛化能力强，数值小拟合能力强。
n_jobs (int) – 并行度，同时使用多少个进程进行计算，最多是4。

In [2]:

# 本代码由可视化策略环境自动生成 2021年10月29日 14:58
# 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 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.portfolio.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.portfolio.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities)])))

        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='2010-01-01',
    end_date='2015-01-01',
    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/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
)

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
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
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

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

m13 = M.dropnan.v1(
    input_data=m7.data
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-01-01'),
    end_date=T.live_run_param('trading_date', '2017-01-01'),
    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=90
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m14 = M.dropnan.v1(
    input_data=m18.data
)

m4 = M.random_forest_regressor.v1(
    training_ds=m13.data,
    features=m3.data,
    predict_ds=m14.data,
    iterations=10,
    feature_fraction=0.8,
    max_depth=30,
    min_samples_per_leaf=200,
    key_cols='date,instrument',
    workers=1,
    random_state=0,
    other_train_parameters={}
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m4.predictions,
    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='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.SHA'
)

[2021-10-29 14:24:19.332552] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-29 14:24:19.353004] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.354902] INFO: moduleinvoker: instruments.v2 运行完成[0.022369s].

[2021-10-29 14:24:19.362901] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-29 14:24:19.368684] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.370104] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.007205s].

[2021-10-29 14:24:19.373709] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-29 14:24:19.380342] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.381692] INFO: moduleinvoker: input_features.v1 运行完成[0.007985s].

[2021-10-29 14:24:19.391712] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-29 14:24:19.401155] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.402584] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010873s].

[2021-10-29 14:24:19.408747] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 14:24:19.413150] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.414388] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.00564s].

[2021-10-29 14:24:19.421502] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-29 14:24:19.427844] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.429186] INFO: moduleinvoker: join.v3 运行完成[0.007683s].

[2021-10-29 14:24:19.436837] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-10-29 14:24:19.445174] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.448011] INFO: moduleinvoker: dropnan.v1 运行完成[0.011172s].

[2021-10-29 14:24:19.452706] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-29 14:24:19.459335] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.460647] INFO: moduleinvoker: instruments.v2 运行完成[0.007941s].

[2021-10-29 14:24:19.470765] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-29 14:24:19.480542] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.481980] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011218s].

[2021-10-29 14:24:19.493148] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 14:24:19.498540] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.500149] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.007005s].

[2021-10-29 14:24:19.513107] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-10-29 14:24:19.523873] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:24:19.525539] INFO: moduleinvoker: dropnan.v1 运行完成[0.012436s].

[2021-10-29 14:24:19.534307] INFO: moduleinvoker: random_forest_regressor.v1 开始运行..

[2021-10-29 14:42:03.812330] INFO: moduleinvoker: random_forest_regressor.v1 运行完成[1064.27801s].

[2021-10-29 14:42:06.315574] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-10-29 14:42:06.403910] INFO: backtest: biglearning backtest:V8.5.0

[2021-10-29 14:42:06.511556] INFO: backtest: product_type:stock by specified

[2021-10-29 14:42:09.392060] INFO: moduleinvoker: cached.v2 开始运行..

[2021-10-29 14:42:09.403687] INFO: moduleinvoker: 命中缓存

[2021-10-29 14:42:09.503750] INFO: moduleinvoker: cached.v2 运行完成[0.111716s].

[2021-10-29 14:42:28.611878] INFO: algo: TradingAlgorithm V1.8.5

[2021-10-29 14:42:33.915672] INFO: algo: trading transform...

[2021-10-29 14:42:41.510445] INFO: algo: handle_splits get splits [dt:2015-04-13 00:00:00+00:00] [asset:Equity(453 [000001.SZA]), ratio:0.8262626528739929]

[2021-10-29 14:42:41.513856] INFO: Position: position stock handle split[sid:453, orig_amount:14300, new_amount:17306.0, orig_cost:15.49195831894589, new_cost:12.8004, ratio:0.8262626528739929, last_sale_price:16.360000610351562]

[2021-10-29 14:42:41.603329] INFO: Position: after split: PositionStock(asset:Equity(453 [000001.SZA]), amount:17306.0, cost_basis:12.8004, last_sale_price:19.799999237060547)

[2021-10-29 14:42:41.617431] INFO: Position: returning cash: 13.8309

[2021-10-29 14:42:46.298679] INFO: algo: handle_splits get splits [dt:2015-06-19 00:00:00+00:00] [asset:Equity(3333 [000006.SZA]), ratio:0.9930635690689087]

[2021-10-29 14:42:46.300638] INFO: Position: position stock handle split[sid:3333, orig_amount:3000, new_amount:3020.0, orig_cost:17.309999470901975, new_cost:17.1899, ratio:0.9930635690689087, last_sale_price:17.17999839782715]

[2021-10-29 14:42:46.302379] INFO: Position: after split: PositionStock(asset:Equity(3333 [000006.SZA]), amount:3020.0, cost_basis:17.1899, last_sale_price:17.299999237060547)

[2021-10-29 14:42:46.303899] INFO: Position: returning cash: 16.4008

[2021-10-29 14:42:48.094520] INFO: algo: handle_splits get splits [dt:2015-07-21 00:00:00+00:00] [asset:Equity(2045 [000002.SZA]), ratio:0.9674267172813416]

[2021-10-29 14:42:48.096284] INFO: Position: position stock handle split[sid:2045, orig_amount:9500, new_amount:9819.0, orig_cost:14.871052511561242, new_cost:14.3867, ratio:0.9674267172813416, last_sale_price:14.850000381469727]

[2021-10-29 14:42:48.099881] INFO: Position: after split: PositionStock(asset:Equity(2045 [000002.SZA]), amount:9819.0, cost_basis:14.3867, last_sale_price:15.350000381469727)

[2021-10-29 14:42:48.102837] INFO: Position: returning cash: 12.8489

[2021-10-29 14:43:13.903182] INFO: algo: handle_splits get splits [dt:2016-06-16 00:00:00+00:00] [asset:Equity(453 [000001.SZA]), ratio:0.820881187915802]

[2021-10-29 14:43:13.904969] INFO: Position: position stock handle split[sid:453, orig_amount:11300, new_amount:13765.0, orig_cost:10.330000015937184, new_cost:8.4797, ratio:0.820881187915802, last_sale_price:8.569999694824219]

[2021-10-29 14:43:13.906304] INFO: Position: after split: PositionStock(asset:Equity(453 [000001.SZA]), amount:13765.0, cost_basis:8.4797, last_sale_price:10.440000534057617)

[2021-10-29 14:43:13.907534] INFO: Position: returning cash: 5.9555

[2021-10-29 14:43:14.095657] INFO: algo: handle_splits get splits [dt:2016-06-17 00:00:00+00:00] [asset:Equity(3333 [000006.SZA]), ratio:0.983146071434021]

[2021-10-29 14:43:14.097536] INFO: Position: position stock handle split[sid:3333, orig_amount:6600, new_amount:6713.0, orig_cost:7.190000315766434, new_cost:7.0688, ratio:0.983146071434021, last_sale_price:7.0]

[2021-10-29 14:43:14.098916] INFO: Position: after split: PositionStock(asset:Equity(3333 [000006.SZA]), amount:6713.0, cost_basis:7.0688, last_sale_price:7.119999885559082)

[2021-10-29 14:43:14.100120] INFO: Position: returning cash: 0.9998

[2021-10-29 14:43:16.006905] INFO: algo: handle_splits get splits [dt:2016-07-29 00:00:00+00:00] [asset:Equity(2045 [000002.SZA]), ratio:0.9598214626312256]

[2021-10-29 14:43:16.008626] INFO: Position: position stock handle split[sid:2045, orig_amount:13300, new_amount:13856.0, orig_cost:17.62954796663877, new_cost:16.9212, ratio:0.9598214626312256, last_sale_price:17.19999885559082]

[2021-10-29 14:43:16.010132] INFO: Position: after split: PositionStock(asset:Equity(2045 [000002.SZA]), amount:13856.0, cost_basis:16.9212, last_sale_price:17.919998168945312)

[2021-10-29 14:43:16.011449] INFO: Position: returning cash: 12.7915

[2021-10-29 14:43:19.221814] INFO: Performance: Simulated 488 trading days out of 488.

[2021-10-29 14:43:19.223429] INFO: Performance: first open: 2015-01-05 09:30:00+00:00

[2021-10-29 14:43:19.224695] INFO: Performance: last close: 2016-12-30 15:00:00+00:00

[2021-10-29 14:43:24.020409] INFO: moduleinvoker: backtest.v8 运行完成[77.704841s].

[2021-10-29 14:43:24.022584] INFO: moduleinvoker: trade.v4 运行完成[79.830361s].

收益率26.19%
年化收益率12.76%
基准收益率-6.33%
阿尔法0.14
贝塔0.67
夏普比率0.48
胜率0.55
盈亏比0.95
收益波动率25.52%
信息比率0.05
最大回撤30.13%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-5243797e60da459d84d2b314438dee2d"}/bigcharts-data-end