复制链接

克隆策略

In [1]:

# 本代码由可视化策略环境自动生成 2022年11月5日 15:32
# 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
    today = data.current_dt.strftime('%Y-%m-%d')
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == today]

    # 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()}
    
    #--------------------------START：持有固定天数卖出(不含建仓期)-----------
    current_stopdays_stock = []
    positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.portfolio.positions.items()}
    # 不是建仓期（在前hold_days属于建仓期）
    if not is_staging:
        for instrument in positions.keys():
            #使用交易天数
            dt = pd.to_datetime(D.trading_days(end_date = today).iloc[-context.options['hold_days']].values[0])
            if  pd.to_datetime(positions_lastdate[instrument].strftime('%Y-%m-%d')) <= dt and data.can_trade(context.symbol(instrument)):
                context.order_target_percent(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
    #-------------------------  END:持有固定天数卖出-----------------------
    
    # 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='2019-01-01',
    end_date='2021-12-31',
    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.HIX',
    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
"""
)

m4 = M.input_features.v1(
    features_ds=m3.data,
    features="""# _PRS250=(close_0-shift(close_0,250))/shift(close_0,250)
# PRS250=rank(_PRS250)
# _PRS120=(close_0-shift(close_0,120))/shift(close_0,120)
# PRS120=rank(_PRS120)
# t1=where(PRS250<0.1,1,0)
# t2=where(PRS120<0.1,1,0)
# flag=where(max(t1,t2)==1,1,0)

PRS10=rank(return_10)
PRS20=rank(return_20)
PRS60=rank(return_60)

t1=where(PRS10<0.1,1,0)
t2=where(PRS20<0.1,1,0)
t3=where(PRS60<0.1,1,0)
flag=where(max(t1,t2,t3)==1,1,0)

rank_fs_roe_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
)

m6 = M.stock_ranker_train.v6(
    training_ds=m13.data,
    features=m3.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
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2022-01-01'),
    end_date=T.live_run_param('trading_date', '2022-11-02'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m4.data,
    start_date='',
    end_date='',
    before_start_days=400
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m4.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m10 = M.filter.v3(
    input_data=m18.data,
    expr='flag!=1 and rank_fs_roe_ttm_0>0.1',
    output_left_data=False
)

m14 = M.dropnan.v1(
    input_data=m10.data
)

m8 = M.stock_ranker_predict.v5(
    model=m6.model,
    data=m14.data,
    m_lazy_run=False
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.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.HIX'
)

[2022-11-03 15:19:09.789098] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-03 15:19:09.811876] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:09.814850] INFO: moduleinvoker: instruments.v2 运行完成[0.025757s].

[2022-11-03 15:19:09.830532] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-11-03 15:19:09.851952] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.067077] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.236542s].

[2022-11-03 15:19:10.074398] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-11-03 15:19:10.147339] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.149897] INFO: moduleinvoker: input_features.v1 运行完成[0.075495s].

[2022-11-03 15:19:10.155690] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-11-03 15:19:10.166944] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.169021] INFO: moduleinvoker: input_features.v1 运行完成[0.013336s].

[2022-11-03 15:19:10.190927] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-03 15:19:10.201810] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.203742] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012841s].

[2022-11-03 15:19:10.213576] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-03 15:19:10.227773] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.229715] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.016121s].

[2022-11-03 15:19:10.242178] INFO: moduleinvoker: join.v3 开始运行..

[2022-11-03 15:19:10.271395] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.273697] INFO: moduleinvoker: join.v3 运行完成[0.031518s].

[2022-11-03 15:19:10.287962] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-11-03 15:19:10.302769] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.305839] INFO: moduleinvoker: dropnan.v1 运行完成[0.017876s].

[2022-11-03 15:19:10.318575] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-11-03 15:19:10.344057] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.586917] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.268344s].

[2022-11-03 15:19:10.608619] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-11-03 15:19:10.618907] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.620668] INFO: moduleinvoker: instruments.v2 运行完成[0.012051s].

[2022-11-03 15:19:10.640462] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-11-03 15:19:10.656434] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.658373] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.017938s].

[2022-11-03 15:19:10.666974] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-11-03 15:19:10.675826] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.677617] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010644s].

[2022-11-03 15:19:10.691213] INFO: moduleinvoker: filter.v3 开始运行..

[2022-11-03 15:19:10.698644] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.700889] INFO: moduleinvoker: filter.v3 运行完成[0.009679s].

[2022-11-03 15:19:10.712108] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-11-03 15:19:10.720266] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:10.722017] INFO: moduleinvoker: dropnan.v1 运行完成[0.009907s].

[2022-11-03 15:19:10.735324] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-11-03 15:19:11.993155] INFO: StockRanker预测: /y_2020 ..

[2022-11-03 15:19:13.511487] INFO: StockRanker预测: /y_2021 ..

[2022-11-03 15:19:15.343675] INFO: StockRanker预测: /y_2022 ..

[2022-11-03 15:19:17.634310] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[6.898975s].

[2022-11-03 15:19:21.634554] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-11-03 15:19:21.642654] INFO: backtest: biglearning backtest:V8.6.3

[2022-11-03 15:19:21.644663] INFO: backtest: product_type:stock by specified

[2022-11-03 15:19:21.758359] INFO: moduleinvoker: cached.v2 开始运行..

[2022-11-03 15:19:21.769445] INFO: moduleinvoker: 命中缓存

[2022-11-03 15:19:21.772215] INFO: moduleinvoker: cached.v2 运行完成[0.01386s].

[2022-11-03 15:19:32.761691] INFO: backtest: algo history_data=DataSource(e69ff7cd8ebb463f87b0b9f0aa0b4d3aT)

[2022-11-03 15:19:32.764057] INFO: algo: TradingAlgorithm V1.8.8

[2022-11-03 15:19:37.642910] INFO: algo: trading transform...

[2022-11-03 15:20:29.831298] INFO: algo: handle_splits get splits [dt:2022-05-13 00:00:00+00:00] [asset:Equity(1536 [300876.SZA]), ratio:0.9868475794792175]

[2022-11-03 15:20:29.833260] INFO: Position: position stock handle split[sid:1536, orig_amount:3600, new_amount:3647.0, orig_cost:22.5801365920691, new_cost:22.2832, ratio:0.9868475794792175, last_sale_price:22.509994506835938]

[2022-11-03 15:20:29.834868] INFO: Position: after split: PositionStock(asset:Equity(1536 [300876.SZA]), amount:3647.0, cost_basis:22.2832, last_sale_price:22.810001373291016)

[2022-11-03 15:20:29.836166] INFO: Position: returning cash: 22.0545

[2022-11-03 15:20:41.939230] INFO: algo: handle_splits get splits [dt:2022-06-08 00:00:00+00:00] [asset:Equity(5622 [300756.SZA]), ratio:0.7127549648284912]

[2022-11-03 15:20:41.941429] INFO: Position: position stock handle split[sid:5622, orig_amount:2300, new_amount:3226.0, orig_cost:19.160011695044304, new_cost:13.6564, ratio:0.7127549648284912, last_sale_price:13.96999740600586]

[2022-11-03 15:20:41.943392] INFO: Position: after split: PositionStock(asset:Equity(5622 [300756.SZA]), amount:3226.0, cost_basis:13.6564, last_sale_price:19.600000381469727)

[2022-11-03 15:20:41.944899] INFO: Position: returning cash: 12.7887

[2022-11-03 15:20:53.524252] INFO: algo: handle_splits get splits [dt:2022-07-14 00:00:00+00:00] [asset:Equity(949 [603900.SHA]), ratio:0.9943183064460754]

[2022-11-03 15:20:53.526169] INFO: Position: position stock handle split[sid:949, orig_amount:7000, new_amount:7039.0, orig_cost:7.06001617839667, new_cost:7.0199, ratio:0.9943183064460754, last_sale_price:7.000001430511475]

[2022-11-03 15:20:53.527662] INFO: Position: after split: PositionStock(asset:Equity(949 [603900.SHA]), amount:7039.0, cost_basis:7.0199, last_sale_price:7.0400004386901855)

[2022-11-03 15:20:53.528864] INFO: Position: returning cash: 6.9938

[2022-11-03 15:20:53.909684] INFO: algo: handle_splits get splits [dt:2022-07-15 00:00:00+00:00] [asset:Equity(2077 [002193.SZA]), ratio:0.9983843564987183]

[2022-11-03 15:20:53.912986] INFO: Position: position stock handle split[sid:2077, orig_amount:6400, new_amount:6410.0, orig_cost:6.150000578416294, new_cost:6.1401, ratio:0.9983843564987183, last_sale_price:6.179999351501465]

[2022-11-03 15:20:53.915928] INFO: Position: after split: PositionStock(asset:Equity(2077 [002193.SZA]), amount:6410.0, cost_basis:6.1401, last_sale_price:6.190000057220459)

[2022-11-03 15:20:53.917911] INFO: Position: returning cash: 2.2053

[2022-11-03 15:21:34.894653] INFO: Performance: Simulated 200 trading days out of 200.

[2022-11-03 15:21:34.897042] INFO: Performance: first open: 2022-01-04 09:30:00+00:00

[2022-11-03 15:21:34.899401] INFO: Performance: last close: 2022-11-02 15:00:00+00:00

[2022-11-03 15:21:38.677472] INFO: moduleinvoker: backtest.v8 运行完成[137.042937s].

[2022-11-03 15:21:38.680456] INFO: moduleinvoker: trade.v4 运行完成[141.035917s].

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-bb1b7061dfba425e91cfb677009b31f9"}/bigcharts-data-end

收益率31.36%
年化收益率41.01%
基准收益率-25.56%
阿尔法0.91
贝塔0.78
夏普比率1.27
胜率0.51
盈亏比1.27
收益波动率27.73%
信息比率0.2
最大回撤17.24%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-c579c02bfab84a7da872e1def36e17a7"}/bigcharts-data-end