复制链接

克隆策略

In [2]:

# 本代码由可视化策略环境自动生成 2022年3月29日 14:49
# 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。


# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m28_run_bigquant_run(input_1, input_2, input_3):
    # 分别读取两个模型的数据
    df1 = input_1.read().rename(columns={'score':'score1','position':'position1'})
    df2 = input_2.read().rename(columns={'score':'score2','position':'position2'})
    
    #合并重新计算得分
    df = pd.merge(left=df1,right=df2,on=['date','instrument'],how='inner')
    df['score'] = df.score1
    #排序
    df = df.groupby('date').apply(lambda x:x.sort_values('score',ascending=False)).reset_index(drop=True)

    return Outputs(data_1=DataSource.write_df(df), data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m28_post_run_bigquant_run(outputs):
    return outputs

# 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()}
        #按照score2卖出股票
        df_sell = ranker_prediction[ranker_prediction.instrument.isin(equities)].sort_values('score2')
        instruments = df_sell.instrument.unique()
        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)])
#     print(data.current_dt.strftime('%Y-%m-%d'),buy_instruments)
    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='2018-01-01',
    end_date='2020-12-31',
    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
"""
)

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.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', '2021-12-31'),
    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
)

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

m4 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2020-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m5 = M.advanced_auto_labeler.v2(
    instruments=m4.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
)

m10 = 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
fs_net_profit_ttm_0
"""
)

m24 = M.general_feature_extractor.v7(
    instruments=m4.data,
    features=m10.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m25 = M.derived_feature_extractor.v3(
    input_data=m24.data,
    features=m10.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m12 = M.join.v3(
    data1=m5.data,
    data2=m25.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m22 = M.dropnan.v1(
    input_data=m12.data
)

m11 = M.stock_ranker_train.v5(
    training_ds=m22.data,
    features=m10.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
)

m21 = M.instruments.v2(
    start_date='2021-01-01',
    end_date='2021-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m26 = M.general_feature_extractor.v7(
    instruments=m21.data,
    features=m10.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m27 = M.derived_feature_extractor.v3(
    input_data=m26.data,
    features=m10.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m23 = M.dropnan.v1(
    input_data=m27.data
)

m20 = M.stock_ranker_predict.v5(
    model=m11.model,
    data=m23.data,
    m_lazy_run=False
)

m28 = M.cached.v3(
    input_1=m8.predictions,
    input_2=m20.predictions,
    run=m28_run_bigquant_run,
    post_run=m28_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m28.data_1,
    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'
)

[2022-03-29 13:56:52.480781] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-03-29 13:56:52.651838] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.654245] INFO: moduleinvoker: instruments.v2 运行完成[0.173484s].

[2022-03-29 13:56:52.665742] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-03-29 13:56:52.678184] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.681827] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.016058s].

[2022-03-29 13:56:52.689215] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-03-29 13:56:52.699702] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.701773] INFO: moduleinvoker: input_features.v1 运行完成[0.01262s].

[2022-03-29 13:56:52.721977] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-03-29 13:56:52.743584] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.745698] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.023753s].

[2022-03-29 13:56:52.756179] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-03-29 13:56:52.764781] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.766586] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010412s].

[2022-03-29 13:56:52.777317] INFO: moduleinvoker: join.v3 开始运行..

[2022-03-29 13:56:52.786028] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.787831] INFO: moduleinvoker: join.v3 运行完成[0.010516s].

[2022-03-29 13:56:52.800834] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-03-29 13:56:52.809644] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:52.811961] INFO: moduleinvoker: dropnan.v1 运行完成[0.011138s].

[2022-03-29 13:56:52.825059] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2022-03-29 13:56:52.847331] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.009998] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[0.184934s].

[2022-03-29 13:56:53.016834] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-03-29 13:56:53.027193] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.029630] INFO: moduleinvoker: instruments.v2 运行完成[0.012805s].

[2022-03-29 13:56:53.048284] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-03-29 13:56:53.060099] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.062411] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.014142s].

[2022-03-29 13:56:53.072023] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-03-29 13:56:53.084731] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.087045] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.015005s].

[2022-03-29 13:56:53.097530] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-03-29 13:56:53.107295] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.109858] INFO: moduleinvoker: dropnan.v1 运行完成[0.012291s].

[2022-03-29 13:56:53.124508] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-03-29 13:56:53.140540] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.144100] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.019565s].

[2022-03-29 13:56:53.149710] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-03-29 13:56:53.156131] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.157474] INFO: moduleinvoker: instruments.v2 运行完成[0.007764s].

[2022-03-29 13:56:53.166011] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-03-29 13:56:53.171899] INFO: moduleinvoker: 命中缓存

[2022-03-29 13:56:53.173218] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.007208s].

[2022-03-29 13:56:53.176731] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-03-29 13:56:53.219036] INFO: moduleinvoker: input_features.v1 运行完成[0.042289s].

[2022-03-29 13:56:53.237846] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-03-29 13:56:55.483462] INFO: 基础特征抽取: 年份 2017, 特征行数=193398

[2022-03-29 13:56:59.266368] INFO: 基础特征抽取: 年份 2018, 特征行数=816987

[2022-03-29 13:57:02.908635] INFO: 基础特征抽取: 年份 2019, 特征行数=884867

[2022-03-29 13:57:06.756151] INFO: 基础特征抽取: 年份 2020, 特征行数=945961

[2022-03-29 13:57:06.943607] INFO: 基础特征抽取: 总行数: 2841213

[2022-03-29 13:57:06.954796] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[13.716971s].

[2022-03-29 13:57:06.962680] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-03-29 13:57:12.763174] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.008s

[2022-03-29 13:57:12.772258] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.008s

[2022-03-29 13:57:12.778270] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.005s

[2022-03-29 13:57:12.783978] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.004s

[2022-03-29 13:57:12.789681] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.004s

[2022-03-29 13:57:12.795598] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.004s

[2022-03-29 13:57:13.441544] INFO: derived_feature_extractor: /y_2017, 193398

[2022-03-29 13:57:15.171173] INFO: derived_feature_extractor: /y_2018, 816987

[2022-03-29 13:57:17.362935] INFO: derived_feature_extractor: /y_2019, 884867

[2022-03-29 13:57:19.733879] INFO: derived_feature_extractor: /y_2020, 945961

[2022-03-29 13:57:20.592729] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[13.630028s].

[2022-03-29 13:57:20.607251] INFO: moduleinvoker: join.v3 开始运行..

[2022-03-29 13:57:26.366970] INFO: join: /y_2017, 行数=0/193398, 耗时=1.216723s

[2022-03-29 13:57:29.734982] INFO: join: /y_2018, 行数=813508/816987, 耗时=3.365157s

[2022-03-29 13:57:33.295104] INFO: join: /y_2019, 行数=881288/884867, 耗时=3.552853s

[2022-03-29 13:57:37.156246] INFO: join: /y_2020, 行数=919362/945961, 耗时=3.853361s

[2022-03-29 13:57:37.312554] INFO: join: 最终行数: 2614158

[2022-03-29 13:57:37.336050] INFO: moduleinvoker: join.v3 运行完成[16.728801s].

[2022-03-29 13:57:37.344764] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-03-29 13:57:37.451236] INFO: dropnan: /y_2017, 0/0

[2022-03-29 13:57:39.138287] INFO: dropnan: /y_2018, 786396/813508

[2022-03-29 13:57:40.635813] INFO: dropnan: /y_2019, 838085/881288

[2022-03-29 13:57:42.232292] INFO: dropnan: /y_2020, 855171/919362

[2022-03-29 13:57:42.361225] INFO: dropnan: 行数: 2479652/2614158

[2022-03-29 13:57:42.373935] INFO: moduleinvoker: dropnan.v1 运行完成[5.029166s].

[2022-03-29 13:57:42.397632] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2022-03-29 13:57:45.312485] INFO: StockRanker: 特征预处理 ..

[2022-03-29 13:57:49.005760] INFO: StockRanker: prepare data: training ..

[2022-03-29 13:57:52.712137] INFO: StockRanker: sort ..

[2022-03-29 13:58:22.071269] INFO: StockRanker训练: 25c71496 准备训练: 2479652 行数

[2022-03-29 13:58:22.386552] INFO: StockRanker训练: 正在训练 ..

[2022-03-29 14:06:54.241269] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[551.843633s].

[2022-03-29 14:06:54.247422] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-03-29 14:06:54.266907] INFO: moduleinvoker: 命中缓存

[2022-03-29 14:06:54.269023] INFO: moduleinvoker: instruments.v2 运行完成[0.021616s].

[2022-03-29 14:06:54.290210] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-03-29 14:06:56.917998] INFO: 基础特征抽取: 年份 2020, 特征行数=243745

[2022-03-29 14:07:01.539406] INFO: 基础特征抽取: 年份 2021, 特征行数=1061527

[2022-03-29 14:07:01.639713] INFO: 基础特征抽取: 总行数: 1305272

[2022-03-29 14:07:01.648557] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[7.358359s].

[2022-03-29 14:07:01.658914] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-03-29 14:07:04.238004] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.004s

[2022-03-29 14:07:04.243897] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_20, 0.004s

[2022-03-29 14:07:04.248197] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_0/rank_avg_amount_5, 0.003s

[2022-03-29 14:07:04.252300] INFO: derived_feature_extractor: 提取完成 rank_avg_amount_5/rank_avg_amount_10, 0.003s

[2022-03-29 14:07:04.256352] INFO: derived_feature_extractor: 提取完成 rank_return_0/rank_return_5, 0.003s

[2022-03-29 14:07:04.260335] INFO: derived_feature_extractor: 提取完成 rank_return_5/rank_return_10, 0.002s

[2022-03-29 14:07:04.888655] INFO: derived_feature_extractor: /y_2020, 243745

[2022-03-29 14:07:07.090443] INFO: derived_feature_extractor: /y_2021, 1061527

[2022-03-29 14:07:07.980075] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[6.321159s].

[2022-03-29 14:07:07.990571] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-03-29 14:07:08.419641] INFO: dropnan: /y_2020, 218004/243745

[2022-03-29 14:07:09.962234] INFO: dropnan: /y_2021, 900960/1061527

[2022-03-29 14:07:10.057643] INFO: dropnan: 行数: 1118964/1305272

[2022-03-29 14:07:10.070809] INFO: moduleinvoker: dropnan.v1 运行完成[2.080234s].

[2022-03-29 14:07:10.080434] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-03-29 14:07:10.414419] INFO: StockRanker预测: /y_2020 ..

[2022-03-29 14:07:11.475446] INFO: StockRanker预测: /y_2021 ..

[2022-03-29 14:07:14.525460] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[4.445026s].

[2022-03-29 14:07:14.542789] INFO: moduleinvoker: cached.v3 开始运行..

[2022-03-29 14:07:17.229048] INFO: moduleinvoker: cached.v3 运行完成[2.686267s].

[2022-03-29 14:07:18.981357] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-03-29 14:07:18.986999] INFO: backtest: biglearning backtest:V8.6.2

[2022-03-29 14:07:18.988552] INFO: backtest: product_type:stock by specified

[2022-03-29 14:07:19.057082] INFO: moduleinvoker: cached.v2 开始运行..

[2022-03-29 14:07:19.067654] INFO: moduleinvoker: 命中缓存

[2022-03-29 14:07:19.069417] INFO: moduleinvoker: cached.v2 运行完成[0.012352s].

[2022-03-29 14:07:21.353862] INFO: algo: TradingAlgorithm V1.8.7

[2022-03-29 14:07:22.473814] INFO: algo: trading transform...

[2022-03-29 14:07:25.961850] INFO: algo: handle_splits get splits [dt:2021-05-21 00:00:00+00:00] [asset:Equity(4096 [688060.SHA]), ratio:0.9935547709465027]

[2022-03-29 14:07:25.963780] INFO: Position: position stock handle split[sid:4096, orig_amount:1300, new_amount:1308.0, orig_cost:57.84038339888179, new_cost:57.4676, ratio:0.9935547709465027, last_sale_price:57.03997802734375]

[2022-03-29 14:07:25.965529] INFO: Position: after split: PositionStock(asset:Equity(4096 [688060.SHA]), amount:1308.0, cost_basis:57.4676, last_sale_price:57.40999984741211)

[2022-03-29 14:07:25.966981] INFO: Position: returning cash: 24.7069

[2022-03-29 14:07:26.024994] INFO: algo: handle_splits get splits [dt:2021-05-25 00:00:00+00:00] [asset:Equity(1684 [300342.SZA]), ratio:0.9861623644828796]

[2022-03-29 14:07:26.026985] INFO: Position: position stock handle split[sid:1684, orig_amount:2600, new_amount:2636.0, orig_cost:10.900000766396237, new_cost:10.7492, ratio:0.9861623644828796, last_sale_price:10.690001487731934]

[2022-03-29 14:07:26.028332] INFO: Position: after split: PositionStock(asset:Equity(1684 [300342.SZA]), amount:2636.0, cost_basis:10.7492, last_sale_price:10.840001106262207)

[2022-03-29 14:07:26.029494] INFO: Position: returning cash: 5.1599

[2022-03-29 14:07:26.121752] INFO: algo: handle_splits get splits [dt:2021-05-28 00:00:00+00:00] [asset:Equity(3344 [300462.SZA]), ratio:0.9876540899276733]

[2022-03-29 14:07:26.123386] INFO: Position: position stock handle split[sid:3344, orig_amount:15000, new_amount:15187.0, orig_cost:11.580004781748176, new_cost:11.437, ratio:0.9876540899276733, last_sale_price:11.999998092651367]

[2022-03-29 14:07:26.124782] INFO: Position: after split: PositionStock(asset:Equity(3344 [300462.SZA]), amount:15187.0, cost_basis:11.437, last_sale_price:12.15000057220459)

[2022-03-29 14:07:26.125885] INFO: Position: returning cash: 6.0426

[2022-03-29 14:07:26.275653] INFO: algo: handle_splits get splits [dt:2021-06-04 00:00:00+00:00] [asset:Equity(2127 [300107.SZA]), ratio:0.9817518591880798]

[2022-03-29 14:07:26.333354] INFO: algo: handle_splits get splits [dt:2021-06-08 00:00:00+00:00] [asset:Equity(591 [300833.SZA]), ratio:0.9923853874206543]

[2022-03-29 14:07:26.335002] INFO: algo: handle_splits get splits [dt:2021-06-08 00:00:00+00:00] [asset:Equity(1557 [002730.SZA]), ratio:0.9940072894096375]

[2022-03-29 14:07:26.630472] INFO: algo: handle_splits get splits [dt:2021-06-24 00:00:00+00:00] [asset:Equity(243 [300165.SZA]), ratio:0.9979838132858276]

[2022-03-29 14:07:26.632106] INFO: Position: position stock handle split[sid:243, orig_amount:8400, new_amount:8416.0, orig_cost:5.040000305177693, new_cost:5.0298, ratio:0.9979838132858276, last_sale_price:4.950000286102295]

[2022-03-29 14:07:26.633470] INFO: Position: after split: PositionStock(asset:Equity(243 [300165.SZA]), amount:8416.0, cost_basis:5.0298, last_sale_price:4.960000514984131)

[2022-03-29 14:07:26.634781] INFO: Position: returning cash: 4.8024

[2022-03-29 14:07:30.351415] INFO: Performance: Simulated 243 trading days out of 243.

[2022-03-29 14:07:30.352928] INFO: Performance: first open: 2021-01-04 09:30:00+00:00

[2022-03-29 14:07:30.354321] INFO: Performance: last close: 2021-12-31 15:00:00+00:00

[2022-03-29 14:07:33.928777] INFO: moduleinvoker: backtest.v8 运行完成[14.947415s].

[2022-03-29 14:07:33.930407] INFO: moduleinvoker: trade.v4 运行完成[16.691377s].

设置测试数据集，查看训练迭代过程的NDCG

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-85f2aad68eac421d831237db4899186f"}/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-8178acc2fad842b7bb969d18d2c08a13"}/bigcharts-data-end

收益率61.72%
年化收益率64.62%
基准收益率-5.2%
阿尔法0.7
贝塔0.37
夏普比率1.92
胜率0.52
盈亏比1.42
收益波动率26.28%
信息比率0.13
最大回撤12.74%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-cbf1952c063744ac8b7ad20707a31375"}/bigcharts-data-end