克隆策略

In [26]:

# 本代码由可视化策略环境自动生成 2019年9月30日 17:37
# 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 = 2
    # 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([0.8,0.2])#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 = 0.98
    context.options['hold_days'] =1

# 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='2016-01-01',
    end_date='2019-01-01',
    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='conditionA=where(ta_sma_5_0>=ta_sma_10_0,1,0)'
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=8
)

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
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2019-01-01'),
    end_date=T.live_run_param('trading_date', '2019-09-27'),
    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=8
)

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
)

m10 = 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
sum(conditionA,8)"""
)

m4 = M.derived_feature_extractor.v3(
    input_data=m16.data,
    features=m10.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m4.data,
    on='date,instrument',
    how='inner',
    sort=True
)

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

m5 = M.derived_feature_extractor.v3(
    input_data=m18.data,
    features=m10.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m14 = M.dropnan.v1(
    input_data=m5.data
)

m11 = M.input_features.v1(
    features_ds=m10.data,
    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
conditionA
"""
)

m12 = M.stock_ranker.v2(
    training_ds=m13.data,
    features=m11.data,
    predict_ds=m14.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,
    slim_data=True
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m12.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=100000,
    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'
)

[2019-09-30 17:30:40.490979] INFO: bigquant: instruments.v2 开始运行..

[2019-09-30 17:30:40.556978] INFO: bigquant: 命中缓存

[2019-09-30 17:30:40.566143] INFO: bigquant: instruments.v2 运行完成[0.075128s].

[2019-09-30 17:30:40.570725] INFO: bigquant: advanced_auto_labeler.v2 开始运行..

[2019-09-30 17:30:40.667628] INFO: bigquant: 命中缓存

[2019-09-30 17:30:40.670680] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.099942s].

[2019-09-30 17:30:40.673993] INFO: bigquant: input_features.v1 开始运行..

[2019-09-30 17:30:40.717127] INFO: bigquant: 命中缓存

[2019-09-30 17:30:40.719503] INFO: bigquant: input_features.v1 运行完成[0.045485s].

[2019-09-30 17:30:40.771394] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-09-30 17:30:40.824145] INFO: bigquant: 命中缓存

[2019-09-30 17:30:40.826400] INFO: bigquant: general_feature_extractor.v7 运行完成[0.055015s].

[2019-09-30 17:30:40.829542] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-30 17:30:40.888342] INFO: bigquant: 命中缓存

[2019-09-30 17:30:40.890958] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.061402s].

[2019-09-30 17:30:40.894120] INFO: bigquant: instruments.v2 开始运行..

[2019-09-30 17:30:40.984984] INFO: bigquant: 命中缓存

[2019-09-30 17:30:40.987366] INFO: bigquant: instruments.v2 运行完成[0.093214s].

[2019-09-30 17:30:41.043945] INFO: bigquant: general_feature_extractor.v7 开始运行..

[2019-09-30 17:30:41.108652] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.112085] INFO: bigquant: general_feature_extractor.v7 运行完成[0.068139s].

[2019-09-30 17:30:41.116055] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-30 17:30:41.240066] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.245095] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.129034s].

[2019-09-30 17:30:41.255371] INFO: bigquant: input_features.v1 开始运行..

[2019-09-30 17:30:41.353969] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.356665] INFO: bigquant: input_features.v1 运行完成[0.101296s].

[2019-09-30 17:30:41.360802] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-30 17:30:41.423769] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.429285] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.068457s].

[2019-09-30 17:30:41.432686] INFO: bigquant: join.v3 开始运行..

[2019-09-30 17:30:41.496797] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.501070] INFO: bigquant: join.v3 运行完成[0.068372s].

[2019-09-30 17:30:41.505858] INFO: bigquant: dropnan.v1 开始运行..

[2019-09-30 17:30:41.552124] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.554539] INFO: bigquant: dropnan.v1 运行完成[0.048666s].

[2019-09-30 17:30:41.558479] INFO: bigquant: derived_feature_extractor.v3 开始运行..

[2019-09-30 17:30:41.614924] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.623222] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.064727s].

[2019-09-30 17:30:41.626555] INFO: bigquant: dropnan.v1 开始运行..

[2019-09-30 17:30:41.689763] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.692234] INFO: bigquant: dropnan.v1 运行完成[0.065677s].

[2019-09-30 17:30:41.696139] INFO: bigquant: input_features.v1 开始运行..

[2019-09-30 17:30:41.745126] INFO: bigquant: 命中缓存

[2019-09-30 17:30:41.751843] INFO: bigquant: input_features.v1 运行完成[0.055686s].

[2019-09-30 17:30:41.760256] INFO: bigquant: stock_ranker.v2 开始运行..

[2019-09-30 17:30:41.820933] INFO: bigquant: stock_ranker_train.v5 开始运行..

[2019-09-30 17:30:43.167619] INFO: StockRanker: 特征预处理 ..

[2019-09-30 17:30:43.681777] INFO: StockRanker: prepare data: training ..

[2019-09-30 17:31:06.861786] INFO: StockRanker训练: f895094e 准备训练: 2165954 行数

[2019-09-30 17:31:07.153569] INFO: StockRanker训练: 正在训练 ..

[2019-09-30 17:36:39.065924] INFO: bigquant: stock_ranker_train.v5 运行完成[357.244971s].

[2019-09-30 17:36:39.069042] INFO: bigquant: stock_ranker_predict.v5 开始运行..

[2019-09-30 17:36:39.871007] INFO: StockRanker预测: /y_2019 ..

[2019-09-30 17:36:42.143856] INFO: bigquant: stock_ranker_predict.v5 运行完成[3.074788s].

[2019-09-30 17:36:42.356163] INFO: bigquant: stock_ranker.v2 运行完成[360.595893s].

[2019-09-30 17:36:42.441614] INFO: bigquant: backtest.v8 开始运行..

[2019-09-30 17:36:42.445253] INFO: bigquant: biglearning backtest:V8.2.16

[2019-09-30 17:36:42.455841] INFO: bigquant: product_type:stock by specified

[2019-09-30 17:36:42.635793] INFO: bigquant: cached.v2 开始运行..

[2019-09-30 17:36:42.728700] INFO: bigquant: 命中缓存

[2019-09-30 17:36:42.731630] INFO: bigquant: cached.v2 运行完成[0.095841s].

[2019-09-30 17:36:53.459650] INFO: algo: TradingAlgorithm V1.5.9

[2019-09-30 17:36:55.459318] INFO: algo: trading transform...

[2019-09-30 17:36:57.289282] INFO: algo: handle_splits get splits [dt:2019-06-19 00:00:00+00:00] [asset:Equity(1448 [000014.SZA]), ratio:0.9926470762865836]

[2019-09-30 17:36:57.295840] INFO: Position: position stock handle split[sid:1448, orig_amount:2100, new_amount:2115.0, orig_cost:9.530002831766023, new_cost:9.46, ratio:0.9926470762865836, last_sale_price:9.450000620646046]

[2019-09-30 17:36:57.298162] INFO: Position: after split: PositionStock(asset:Equity(1448 [000014.SZA]), amount:2115.0, cost_basis:9.46, last_sale_price:9.520000457763672)

[2019-09-30 17:36:57.300262] INFO: Position: returning cash: 5.25

[2019-09-30 17:36:58.300536] INFO: Performance: Simulated 182 trading days out of 182.

[2019-09-30 17:36:58.303140] INFO: Performance: first open: 2019-01-02 09:30:00+00:00

[2019-09-30 17:36:58.305829] INFO: Performance: last close: 2019-09-27 15:00:00+00:00

[2019-09-30 17:37:13.522987] INFO: bigquant: backtest.v8 运行完成[31.081367s].

设置测试数据集，查看训练迭代过程的NDCG

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-fd256e42ba5c46beaa995f7df9dd4cfd"}/bigcharts-data-end

设置测试数据集，查看训练迭代过程的NDCG

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-cb0c6a5610ad43b8b100d932a48b8b43"}/bigcharts-data-end

收益率7.03%
年化收益率9.86%
基准收益率27.97%
阿尔法-0.16
贝塔0.79
夏普比率0.37
胜率0.45
盈亏比1.48
收益波动率28.24%
信息比率-0.06
最大回撤22.44%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-fef810ecf6c1491a83d96cbe42f4ae8e"}/bigcharts-data-end