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1月19日 20:33
# 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 m10_initialize_bigquant_run(context):

    # 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))
    context.stock_max_num = 10 # 最多同时持有20只股票

# 回测引擎：每日数据处理函数，每天执行一次
def m10_handle_data_bigquant_run(context, data):
    # 回测引擎：每日数据处理函数，每天执行一次
    today = data.current_dt.strftime('%Y-%m-%d') # 日期
    # 通过positions对象，使用列表生成式的方法获取目前持仓的股票列表和对应的最新市值
    stock_hold_now = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.perf_tracker.position_tracker.positions.items()}
    hold_num=len(stock_hold_now)
    
    # 记录用于买入股票的可用现金,因为是早盘卖股票，需要记录卖出的股票市值并在买入下单前更新可用现金；
    # 如果是早盘买尾盘卖，则卖出时不需更新可用现金，因为尾盘卖出股票所得现金无法使用
    cash_for_buy = context.portfolio.cash
    
    # 获取当日符合买入/卖出条件的股票列表
    try:
        buy_stock = context.daily_stock_buy[today]  # 当日符合买入条件的股票
    except:
        buy_stock=[]
    try:
        sell_stock = context.daily_stock_sell[today]  # 当日符合卖出条件的股票
    except:
        sell_stock = []

    # 需要卖出的股票:已有持仓中符合卖出条件的股票
    stock_to_sell = [i for i in stock_hold_now if i in sell_stock]
    # 需要买入的股票:没有持仓且符合买入条件的股票
    stock_to_buy = [i for i in buy_stock if i not in stock_hold_now]
    # 卖出
    for instrument in stock_to_sell:
        # 如果该股票停牌，则没法成交。因此需要用can_trade方法检查下该股票的状态
        # 如果返回真值，则可以正常下单，否则会出错
        # 因为stock是字符串格式，我们用symbol方法将其转化成平台可以接受的形式：Equity格式
        if data.can_trade(context.symbol(instrument)):
            # order_target_percent是平台的一个下单接口，表明下单使得该股票的权重为0，即卖出全部股票，可参考回测文档
            context.order_target_percent(context.symbol(instrument), 0)
            # 因为设置的是早盘卖出早盘买入，需要根据卖出的股票更新可用现金；如果设置尾盘卖出早盘买入，则不需更新可用现金(可以删除下面的语句)
            cash_for_buy += stock_hold_now[instrument]
            hold_num-=1

    # 当日还允许买入建仓的股票数目
    stock_can_buy_num = context.stock_max_num - hold_num
    stock_to_buy_num = min(stock_can_buy_num,len(stock_to_buy))
    
    # 如果当天没有买入的股票，就返回
    if stock_to_buy_num == 0:
        return
    
    # 记录已经买入的股票数量
    buy_num = 0
    for instrument in stock_to_buy:
        # 使用当日可用现金等资金比例下单买入
        cash = cash_for_buy / stock_to_buy_num
        if data.can_trade(context.symbol(instrument)) and buy_num<stock_to_buy_num:
            # 整百下单
            current_price = data.current(context.symbol(instrument), 'price')
            amount = math.floor(cash / current_price / 100) * 100
            context.order(context.symbol(instrument), amount)
            buy_num += 1


# 回测引擎：准备数据，只执行一次
def m10_prepare_bigquant_run(context):
    # 加载预测数据
    df = context.options['data'].read_df()

    # 函数：求满足开仓条件的股票列表
    def open_pos_con(df):
        return list(df[df['buy_condition']>0].instrument)

    # 函数：求满足平仓条件的股票列表
    def close_pos_con(df):
        return list(df[df['sell_condition']>0].instrument)

    # 每日买入股票的数据框
    context.daily_stock_buy= df.groupby('date').apply(open_pos_con)
    # 每日卖出股票的数据框
    context.daily_stock_sell= df.groupby('date').apply(close_pos_con)

m1 = M.instruments.v2(
    start_date='2014-01-01',
    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.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
buy_condition = where((mean(close_0,5)>mean(close_0,10)),1,0)
sell_condition = where(mean(close_0,5)<mean(close_0,10),1,0)"""
)

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
)

m4 = M.filter_stockmarket.v2(
    input_1=m7.data,
    start='688'
)

m13 = M.dropnan.v1(
    input_data=m4.data_1
)

m6 = M.stock_ranker_train.v5(
    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,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2022-01-01'),
    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
)

m5 = M.filter_stockmarket.v2(
    input_1=m18.data,
    start='688'
)

m14 = M.dropnan.v1(
    input_data=m5.data_1
)

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

m10 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m10_initialize_bigquant_run,
    handle_data=m10_handle_data_bigquant_run,
    prepare=m10_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='open',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2022-01-19 20:30:14.279131] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-01-19 20:30:14.304439] INFO: moduleinvoker: 命中缓存

[2022-01-19 20:30:14.308904] INFO: moduleinvoker: instruments.v2 运行完成[0.029775s].

[2022-01-19 20:30:14.326872] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-01-19 20:30:14.339791] INFO: moduleinvoker: 命中缓存

[2022-01-19 20:30:14.344283] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.017426s].

[2022-01-19 20:30:14.355752] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-01-19 20:30:14.399580] INFO: moduleinvoker: input_features.v1 运行完成[0.043852s].

[2022-01-19 20:30:14.421436] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-01-19 20:30:14.431891] INFO: moduleinvoker: 命中缓存

[2022-01-19 20:30:14.434254] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012835s].

[2022-01-19 20:30:14.457909] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-01-19 20:30:26.863176] INFO: derived_feature_extractor: 提取完成 buy_condition = where((mean(close_0,5)>mean(close_0,10)),1,0), 6.227s

[2022-01-19 20:30:32.843197] INFO: derived_feature_extractor: 提取完成 sell_condition = where(mean(close_0,5)[2022-01-19 20:30:33.160701] INFO: derived_feature_extractor: /y_2013, 143272
[2022-01-19 20:30:34.169562] INFO: derived_feature_extractor: /y_2014, 569948
[2022-01-19 20:30:35.171634] INFO: derived_feature_extractor: /y_2015, 569698
[2022-01-19 20:30:36.251458] INFO: derived_feature_extractor: /y_2016, 641546
[2022-01-19 20:30:37.593276] INFO: derived_feature_extractor: /y_2017, 743233
[2022-01-19 20:30:39.082672] INFO: derived_feature_extractor: /y_2018, 816987
[2022-01-19 20:30:39.365837] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[24.907943s].
[2022-01-19 20:30:39.379565] INFO: moduleinvoker: join.v3 开始运行..
[2022-01-19 20:30:46.416430] INFO: join: /y_2013, 行数=0/143272, 耗时=1.287051s
[2022-01-19 20:30:48.725935] INFO: join: /y_2014, 行数=567874/569948, 耗时=2.306743s
[2022-01-19 20:30:50.934941] INFO: join: /y_2015, 行数=560424/569698, 耗时=2.203958s
[2022-01-19 20:30:53.374741] INFO: join: /y_2016, 行数=637469/641546, 耗时=2.435306s
[2022-01-19 20:30:56.073603] INFO: join: /y_2017, 行数=738255/743233, 耗时=2.694224s
[2022-01-19 20:30:58.748731] INFO: join: /y_2018, 行数=795755/816987, 耗时=2.669849s
[2022-01-19 20:30:58.882148] INFO: join: 最终行数: 3299777
[2022-01-19 20:30:58.900518] INFO: moduleinvoker: join.v3 运行完成[19.520947s].
[2022-01-19 20:30:58.941091] INFO: moduleinvoker: filter_stockmarket.v2 开始运行..
[2022-01-19 20:31:02.832825] INFO: moduleinvoker: filter_stockmarket.v2 运行完成[3.891738s].
[2022-01-19 20:31:02.852521] INFO: moduleinvoker: dropnan.v1 开始运行..
[2022-01-19 20:31:05.504855] INFO: dropnan: /data, 3299777/3299777
[2022-01-19 20:31:05.572748] INFO: dropnan: 行数: 3299777/3299777
[2022-01-19 20:31:05.608062] INFO: moduleinvoker: dropnan.v1 运行完成[2.755523s].
[2022-01-19 20:31:05.626581] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..
[2022-01-19 20:31:07.250122] INFO: StockRanker: 特征预处理 ..
[2022-01-19 20:31:07.279055] INFO: StockRanker: prepare data: training ..
[2022-01-19 20:31:07.344899] INFO: StockRanker: sort ..
[2022-01-19 20:31:39.326430] INFO: StockRanker训练: abe7c15c 准备训练: 3299777 行数
[2022-01-19 20:31:39.469227] ERROR: moduleinvoker: module name: stock_ranker_train, module version: v5, trackeback: ValueError: max() arg is an empty sequence

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-1-03451fce8bb6> in <module>
    164 )
    165 
--> 166 m6 = M.stock_ranker_train.v5(
    167     training_ds=m13.data,
    168     features=m3.data,

ValueError: max() arg is an empty sequence