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5月13日 08:20
# 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 m4_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 = 0.5
    context.options['hold_days'] = 2

# 回测引擎：每日数据处理函数，每天执行一次
def m4_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')]
    buy_condition = 2.0
    sell_condition= 1.0

    # 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, (0.5 if is_staging else 0.75) * 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.perf_tracker.position_tracker.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StockRanker预测的排序末位淘汰
    if True:
        equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
        instruments12 = list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities )])
        position_prediction = ranker_prediction[ranker_prediction.instrument.isin(instruments12)]
        instruments = list(position_prediction.instrument[position_prediction.score <sell_condition])
        for instrument in instruments:
            context.order_target(context.symbol(instrument), 0)
            

    # 3. 生成买入订单：按StockRanker预测的排序，买入前面的stock_count只股票
    rank_buy = ranker_prediction[ranker_prediction.score>buy_condition]
    buy_instruments1 = list(rank_buy.instrument)
    buy_scores1 = list(rank_buy.score)
    buy_instruments = buy_instruments1[:np.where(len(buy_instruments1)>5,5,len(buy_instruments1))]
    buy_scores = buy_scores1[:len(buy_instruments)]
    buy_cash_weights = buy_scores/np.sum(buy_scores)
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    if any(buy_instruments):
        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)
            today_price = data.current(symbol(instrument), ['amount', 'volume'])
            buy_price =today_price['amount'] / today_price['volume']
            buy_amount = int(round(cash/(buy_price*100)))
            if buy_amount > 0: 
                context.order_lots(symbol(instrument),buy_amount)
# 回测引擎：准备数据，只执行一次
def m4_prepare_bigquant_run(context):
    pass

m1 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2018-01-01',
    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/data_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/big_expr.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)
#signedpower((shift(close, -5) / shift(open, -1)-1),log10(market_cap_float)/pe_ttm)
#where((shift(close, -3) / shift(open, -1) > 0) & (correlation(close, amount, -3)>0),correlation(close, amount, -3) ,0)
(shift(close, -10) / shift(open, -1)-1)*100
# 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, 60)

# 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="""Alpha_1=-1*rank((ts_max(high_0,20)+ts_min(low_0,20)-open_20-close_0))
Alpha_2=-1*rank((close_0-open_20)/(ts_max(high_0,20)-ts_min(low_0,20)))
Alpha_3=rank(-1*(ts_max(close_0,20)-close_0)/(ts_max(close_0,20)-ts_min(close_0,20)))

Alpha_4=rank(sum(amount_0*sign(max(open_0+close_0-high_0-low_0,close_0-open_0)/max(high_0-close_1,high_0-low_0,close_1-low_0)-0.1),20))
Alpha_5=rank(return_20)
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=120
)

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
)

m11 = M.chinaa_stock_filter.v1(
    input_data=m7.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m6 = M.dropnan.v2(
    input_data=m11.data
)

m12 = M.filter.v3(
    input_data=m6.data,
    expr='date<\'2017-01-01\'',
    output_left_data=True
)

m5 = M.features_short.v1(
    input_1=m3.data
)

m20 = M.stock_ranker_train.v6(
    training_ds=m12.data,
    features=m5.data_1,
    test_ds=m12.left_data,
    learning_algorithm='排序',
    number_of_leaves=70,
    minimum_docs_per_leaf=2400,
    number_of_trees=60,
    learning_rate=0.15,
    max_bins=800,
    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', '2018-01-02'),
    end_date=T.live_run_param('trading_date', '2020-12-01'),
    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=120
)

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
)

m13 = M.chinaa_stock_filter.v1(
    input_data=m18.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m10 = M.dropnan.v2(
    input_data=m13.data
)

m8 = M.stock_ranker_predict.v5(
    model=m20.model,
    data=m10.data,
    m_lazy_run=False
)

m4 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m4_initialize_bigquant_run,
    handle_data=m4_handle_data_bigquant_run,
    prepare=m4_prepare_bigquant_run,
    volume_limit=0,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000,
    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=''
)

[2022-03-16 08:39:43.204116] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-03-16 08:39:43.223929] INFO: moduleinvoker: 命中缓存

[2022-03-16 08:39:43.225659] INFO: moduleinvoker: instruments.v2 运行完成[0.021563s].

[2022-03-16 08:39:43.238189] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-03-16 08:39:47.148735] INFO: 自动标注(股票): 加载历史数据: 4597290 行

[2022-03-16 08:39:47.150374] INFO: 自动标注(股票): 开始标注 ..

[2022-03-16 08:39:52.369639] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[9.131431s].

[2022-03-16 08:39:52.392446] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-03-16 08:39:52.432001] INFO: moduleinvoker: input_features.v1 运行完成[0.039551s].

[2022-03-16 08:39:52.447925] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-03-16 08:39:54.166230] INFO: 基础特征抽取: 年份 2009, 特征行数=125803

[2022-03-16 08:39:56.554919] INFO: 基础特征抽取: 年份 2010, 特征行数=431567

[2022-03-16 08:39:59.283322] INFO: 基础特征抽取: 年份 2011, 特征行数=511455

[2022-03-16 08:40:02.717329] INFO: 基础特征抽取: 年份 2012, 特征行数=565675

[2022-03-16 08:40:05.815706] INFO: 基础特征抽取: 年份 2013, 特征行数=564168

[2022-03-16 08:40:09.844864] INFO: 基础特征抽取: 年份 2014, 特征行数=569948

[2022-03-16 08:40:13.300933] INFO: 基础特征抽取: 年份 2015, 特征行数=569698

[2022-03-16 08:40:16.885103] INFO: 基础特征抽取: 年份 2016, 特征行数=641546

[2022-03-16 08:40:21.285629] INFO: 基础特征抽取: 年份 2017, 特征行数=743233

[2022-03-16 08:40:24.920504] INFO: 基础特征抽取: 年份 2018, 特征行数=0

[2022-03-16 08:40:25.069603] INFO: 基础特征抽取: 总行数: 4723093

[2022-03-16 08:40:25.076983] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[32.62901s].

[2022-03-16 08:40:25.099940] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-03-16 08:40:42.843252] INFO: derived_feature_extractor: 提取完成 Alpha_1=-1*rank((ts_max(high_0,20)+ts_min(low_0,20)-open_20-close_0)), 9.347s

[2022-03-16 08:40:52.504910] INFO: derived_feature_extractor: 提取完成 Alpha_2=-1*rank((close_0-open_20)/(ts_max(high_0,20)-ts_min(low_0,20))), 9.660s

[2022-03-16 08:41:05.865090] INFO: derived_feature_extractor: 提取完成 Alpha_3=rank(-1*(ts_max(close_0,20)-close_0)/(ts_max(close_0,20)-ts_min(close_0,20))), 13.359s

[2022-03-16 08:41:11.764574] INFO: derived_feature_extractor: 提取完成 Alpha_4=rank(sum(amount_0*sign(max(open_0+close_0-high_0-low_0,close_0-open_0)/max(high_0-close_1,high_0-low_0,close_1-low_0)-0.1),20)), 5.898s

[2022-03-16 08:41:14.328854] INFO: derived_feature_extractor: 提取完成 Alpha_5=rank(return_20), 2.562s

[2022-03-16 08:41:15.116204] INFO: derived_feature_extractor: /y_2009, 125803

[2022-03-16 08:41:15.872306] INFO: derived_feature_extractor: /y_2010, 431567

[2022-03-16 08:41:16.872531] INFO: derived_feature_extractor: /y_2011, 511455

[2022-03-16 08:41:18.164668] INFO: derived_feature_extractor: /y_2012, 565675

[2022-03-16 08:41:19.352687] INFO: derived_feature_extractor: /y_2013, 564168

[2022-03-16 08:41:20.509107] INFO: derived_feature_extractor: /y_2014, 569948

[2022-03-16 08:41:21.879768] INFO: derived_feature_extractor: /y_2015, 569698

[2022-03-16 08:41:23.241927] INFO: derived_feature_extractor: /y_2016, 641546

[2022-03-16 08:41:24.742732] INFO: derived_feature_extractor: /y_2017, 743233

[2022-03-16 08:41:25.310325] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[60.210375s].

[2022-03-16 08:41:25.324727] INFO: moduleinvoker: join.v3 开始运行..

[2022-03-16 08:41:33.836381] INFO: join: /y_2009, 行数=0/125803, 耗时=1.733066s

[2022-03-16 08:41:36.226945] INFO: join: /y_2010, 行数=431019/431567, 耗时=2.388465s

[2022-03-16 08:41:38.781395] INFO: join: /y_2011, 行数=510907/511455, 耗时=2.550521s

[2022-03-16 08:41:41.541162] INFO: join: /y_2012, 行数=564567/565675, 耗时=2.755282s

[2022-03-16 08:41:44.412038] INFO: join: /y_2013, 行数=563117/564168, 耗时=2.866444s

[2022-03-16 08:41:47.338524] INFO: join: /y_2014, 行数=567859/569948, 耗时=2.922222s

[2022-03-16 08:41:50.257351] INFO: join: /y_2015, 行数=560395/569698, 耗时=2.914206s

[2022-03-16 08:41:53.244562] INFO: join: /y_2016, 行数=637411/641546, 耗时=2.981669s

[2022-03-16 08:41:56.474503] INFO: join: /y_2017, 行数=703934/743233, 耗时=3.223973s

[2022-03-16 08:41:56.636664] INFO: join: 最终行数: 4539209

[2022-03-16 08:41:56.663075] INFO: moduleinvoker: join.v3 运行完成[31.338345s].

[2022-03-16 08:41:56.678143] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2022-03-16 08:41:58.490598] INFO: A股股票过滤: 过滤 /y_2010, 413404/0/431019

[2022-03-16 08:42:00.386452] INFO: A股股票过滤: 过滤 /y_2011, 493050/0/510907

[2022-03-16 08:42:02.436330] INFO: A股股票过滤: 过滤 /y_2012, 547433/0/564567

[2022-03-16 08:42:04.416917] INFO: A股股票过滤: 过滤 /y_2013, 546006/0/563117

[2022-03-16 08:42:06.570593] INFO: A股股票过滤: 过滤 /y_2014, 552100/0/567859

[2022-03-16 08:42:08.700671] INFO: A股股票过滤: 过滤 /y_2015, 548093/0/560395

[2022-03-16 08:42:11.159741] INFO: A股股票过滤: 过滤 /y_2016, 626472/0/637411

[2022-03-16 08:42:13.879019] INFO: A股股票过滤: 过滤 /y_2017, 692317/0/703934

[2022-03-16 08:42:13.885316] INFO: A股股票过滤: 过滤完成, 4418875 + 0

[2022-03-16 08:42:13.972776] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[17.294614s].

[2022-03-16 08:42:13.997495] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-03-16 08:42:14.560985] INFO: dropnan: /y_2010, 406126/413404

[2022-03-16 08:42:15.099211] INFO: dropnan: /y_2011, 486906/493050

[2022-03-16 08:42:15.692784] INFO: dropnan: /y_2012, 543891/547433

[2022-03-16 08:42:16.291537] INFO: dropnan: /y_2013, 545871/546006

[2022-03-16 08:42:16.952406] INFO: dropnan: /y_2014, 550261/552100

[2022-03-16 08:42:17.652685] INFO: dropnan: /y_2015, 545817/548093

[2022-03-16 08:42:18.343636] INFO: dropnan: /y_2016, 624612/626472

[2022-03-16 08:42:19.068180] INFO: dropnan: /y_2017, 686805/692317

[2022-03-16 08:42:19.215375] INFO: dropnan: 行数: 4390289/4418875

[2022-03-16 08:42:19.232526] INFO: moduleinvoker: dropnan.v2 运行完成[5.23504s].

[2022-03-16 08:42:19.246334] INFO: moduleinvoker: filter.v3 开始运行..

[2022-03-16 08:42:19.282688] INFO: filter: 使用表达式 date[2022-03-16 08:42:19.788520] INFO: filter: 过滤 /y_2010, 406126/0/406126
[2022-03-16 08:42:20.379984] INFO: filter: 过滤 /y_2011, 486906/0/486906
[2022-03-16 08:42:20.948119] INFO: filter: 过滤 /y_2012, 543891/0/543891
[2022-03-16 08:42:21.510234] INFO: filter: 过滤 /y_2013, 545871/0/545871
[2022-03-16 08:42:22.152547] INFO: filter: 过滤 /y_2014, 550261/0/550261
[2022-03-16 08:42:22.795321] INFO: filter: 过滤 /y_2015, 545817/0/545817
[2022-03-16 08:42:23.600513] INFO: filter: 过滤 /y_2016, 624612/0/624612
[2022-03-16 08:42:24.343443] INFO: filter: 过滤 /y_2017, 0/686805/686805
[2022-03-16 08:42:24.395051] INFO: moduleinvoker: filter.v3 运行完成[5.1487s].
[2022-03-16 08:42:24.452618] INFO: moduleinvoker: features_short.v1 开始运行..
[2022-03-16 08:42:24.516150] INFO: moduleinvoker: features_short.v1 运行完成[0.063536s].
[2022-03-16 08:42:24.531504] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..
[2022-03-16 08:42:28.039922] INFO: StockRanker: 特征预处理 ..
[2022-03-16 08:42:30.502441] INFO: StockRanker: prepare data: training ..
[2022-03-16 08:42:32.596389] INFO: StockRanker: sort ..
[2022-03-16 08:43:10.567810] INFO: StockRanker: prepare data: test ..
[2022-03-16 08:43:10.942684] INFO: StockRanker: sort ..
[2022-03-16 08:43:17.837539] INFO: StockRanker训练: f27b3a62 准备训练: 3703484 行数, test: 686805 rows
[2022-03-16 08:43:17.839122] INFO: StockRanker训练: AI模型训练，将在3703484*5=1851.74万数据上对模型训练进行60轮迭代训练。预计将需要17～34分钟。请耐心等待。
[2022-03-16 08:43:18.055042] INFO: StockRanker训练: 正在训练 ..
[2022-03-16 08:43:18.136751] INFO: StockRanker训练: 任务状态: Pending
[2022-03-16 08:43:38.213292] INFO: StockRanker训练: 任务状态: Running
[2022-03-16 08:44:58.690620] INFO: StockRanker训练: 00:01:20.6488932, finished iteration 1
[2022-03-16 08:45:18.836490] INFO: StockRanker训练: 00:01:41.4553195, finished iteration 2
[2022-03-16 08:45:38.920380] INFO: StockRanker训练: 00:02:04.5986914, finished iteration 3
[2022-03-16 08:46:09.056404] INFO: StockRanker训练: 00:02:32.1514495, finished iteration 4
[2022-03-16 08:46:39.226909] INFO: StockRanker训练: 00:03:01.4483721, finished iteration 5
[2022-03-16 08:47:09.411071] INFO: StockRanker训练: 00:03:33.7345915, finished iteration 6
[2022-03-16 08:47:39.574335] INFO: StockRanker训练: 00:04:05.8964459, finished iteration 7
[2022-03-16 08:48:09.722232] INFO: StockRanker训练: 00:04:38.6089360, finished iteration 8
[2022-03-16 08:48:49.941164] INFO: StockRanker训练: 00:05:12.1448284, finished iteration 9
[2022-03-16 08:49:10.033044] INFO: StockRanker训练: 00:05:38.7166348, finished iteration 10
[2022-03-16 08:49:40.180504] INFO: StockRanker训练: 00:06:05.7384898, finished iteration 11
[2022-03-16 08:50:10.338036] INFO: StockRanker训练: 00:06:32.8921324, finished iteration 12
[2022-03-16 08:50:40.559877] INFO: StockRanker训练: 00:07:05.0854614, finished iteration 13
[2022-03-16 08:51:10.801808] INFO: StockRanker训练: 00:07:35.6538452, finished iteration 14
[2022-03-16 08:51:41.015053] INFO: StockRanker训练: 00:08:04.8622168, finished iteration 15
[2022-03-16 08:52:01.154928] INFO: StockRanker训练: 00:08:30.6953311, finished iteration 16
[2022-03-16 08:52:31.311358] INFO: StockRanker训练: 00:08:54.2826591, finished iteration 17
[2022-03-16 08:52:51.435562] INFO: StockRanker训练: 00:09:18.0141494, finished iteration 18
[2022-03-16 08:53:11.539451] INFO: StockRanker训练: 00:09:41.1495868, finished iteration 19
[2022-03-16 08:53:41.689806] INFO: StockRanker训练: 00:10:05.3032403, finished iteration 20
[2022-03-16 08:54:01.800594] INFO: StockRanker训练: 00:10:29.9747393, finished iteration 21
[2022-03-16 08:54:31.955192] INFO: StockRanker训练: 00:10:54.3342730, finished iteration 22
[2022-03-16 08:54:52.068553] INFO: StockRanker训练: 00:11:18.8291711, finished iteration 23
[2022-03-16 08:55:22.203703] INFO: StockRanker训练: 00:11:44.3056519, finished iteration 24
[2022-03-16 08:55:42.332955] INFO: StockRanker训练: 00:12:09.1535709, finished iteration 25
[2022-03-16 08:56:12.708633] INFO: StockRanker训练: 00:12:33.3186242, finished iteration 26
[2022-03-16 08:56:32.864088] INFO: StockRanker训练: 00:12:57.1616735, finished iteration 27
[2022-03-16 08:56:52.960378] INFO: StockRanker训练: 00:13:20.5052408, finished iteration 28
[2022-03-16 08:57:23.104359] INFO: StockRanker训练: 00:13:44.7211424, finished iteration 29
[2022-03-16 08:57:43.218179] INFO: StockRanker训练: 00:14:09.0160261, finished iteration 30
[2022-03-16 08:58:03.314580] INFO: StockRanker训练: 00:14:32.7934509, finished iteration 31
[2022-03-16 08:58:33.474095] INFO: StockRanker训练: 00:14:56.1669741, finished iteration 32
[2022-03-16 08:58:53.565957] INFO: StockRanker训练: 00:15:19.8241078, finished iteration 33
[2022-03-16 08:59:23.709836] INFO: StockRanker训练: 00:15:44.0495940, finished iteration 34
[2022-03-16 09:00:34.171156] INFO: StockRanker训练: 00:16:57.6031653, finished iteration 37
[2022-03-16 09:00:54.279765] INFO: StockRanker训练: 00:17:21.9303216, finished iteration 38
[2022-03-16 09:01:24.465137] INFO: StockRanker训练: 00:17:46.4885673, finished iteration 39
[2022-03-16 09:01:44.593547] INFO: StockRanker训练: 00:18:10.5964185, finished iteration 40
[2022-03-16 09:02:34.850614] INFO: StockRanker训练: 00:18:58.7497246, finished iteration 42
[2022-03-16 09:02:54.945930] INFO: StockRanker训练: 00:19:22.5695915, finished iteration 43
[2022-03-16 09:03:25.096958] INFO: StockRanker训练: 00:19:46.2549166, finished iteration 44
[2022-03-16 09:03:45.370846] INFO: StockRanker训练: 00:20:11.7847711, finished iteration 45
[2022-03-16 09:04:15.517937] INFO: StockRanker训练: 00:20:37.2462248, finished iteration 46
[2022-03-16 09:04:35.604639] INFO: StockRanker训练: 00:21:01.6898667, finished iteration 47
[2022-03-16 09:04:55.724511] INFO: StockRanker训练: 00:21:25.1433395, finished iteration 48
[2022-03-16 09:05:25.918623] INFO: StockRanker训练: 00:21:49.1028190, finished iteration 49
[2022-03-16 09:05:46.021767] INFO: StockRanker训练: 00:22:13.3626482, finished iteration 50
[2022-03-16 09:06:16.167801] INFO: StockRanker训练: 00:22:37.1984071, finished iteration 51
[2022-03-16 09:06:36.267939] INFO: StockRanker训练: 00:23:00.6927359, finished iteration 52
[2022-03-16 09:06:56.390965] INFO: StockRanker训练: 00:23:24.4801400, finished iteration 53
[2022-03-16 09:07:26.544786] INFO: StockRanker训练: 00:23:50.0039117, finished iteration 54
[2022-03-16 09:07:46.654820] INFO: StockRanker训练: 00:24:14.4564231, finished iteration 55
[2022-03-16 09:08:16.879834] INFO: StockRanker训练: 00:24:39.5252406, finished iteration 56
[2022-03-16 09:08:36.972606] INFO: StockRanker训练: 00:25:03.2442963, finished iteration 57
[2022-03-16 09:09:07.115827] INFO: StockRanker训练: 00:25:27.3175156, finished iteration 58
[2022-03-16 09:09:27.207195] INFO: StockRanker训练: 00:25:50.8565925, finished iteration 59
[2022-03-16 09:09:47.393196] INFO: StockRanker训练: 00:26:14.6769416, finished iteration 60
[2022-03-16 09:09:57.438907] INFO: StockRanker训练: 任务状态: Succeeded
[2022-03-16 09:09:57.742975] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[1653.211457s].
[2022-03-16 09:09:57.760359] INFO: moduleinvoker: instruments.v2 开始运行..
[2022-03-16 09:09:57.928712] INFO: moduleinvoker: instruments.v2 运行完成[0.168377s].
[2022-03-16 09:09:57.955490] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2022-03-16 09:10:01.916777] INFO: 基础特征抽取: 年份 2017, 特征行数=256263
[2022-03-16 09:10:06.788776] INFO: 基础特征抽取: 年份 2018, 特征行数=816987
[2022-03-16 09:10:12.257423] INFO: 基础特征抽取: 年份 2019, 特征行数=884867
[2022-03-16 09:10:17.693132] INFO: 基础特征抽取: 年份 2020, 特征行数=855949
[2022-03-16 09:10:17.811414] INFO: 基础特征抽取: 总行数: 2814066
[2022-03-16 09:10:17.819607] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[19.864124s].
[2022-03-16 09:10:17.827903] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2022-03-16 09:10:27.759235] INFO: derived_feature_extractor: 提取完成 Alpha_1=-1*rank((ts_max(high_0,20)+ts_min(low_0,20)-open_20-close_0)), 5.000s
[2022-03-16 09:10:32.890654] INFO: derived_feature_extractor: 提取完成 Alpha_2=-1*rank((close_0-open_20)/(ts_max(high_0,20)-ts_min(low_0,20))), 5.130s
[2022-03-16 09:10:39.629375] INFO: derived_feature_extractor: 提取完成 Alpha_3=rank(-1*(ts_max(close_0,20)-close_0)/(ts_max(close_0,20)-ts_min(close_0,20))), 6.737s
[2022-03-16 09:10:42.747872] INFO: derived_feature_extractor: 提取完成 Alpha_4=rank(sum(amount_0*sign(max(open_0+close_0-high_0-low_0,close_0-open_0)/max(high_0-close_1,high_0-low_0,close_1-low_0)-0.1),20)), 3.117s
[2022-03-16 09:10:44.187761] INFO: derived_feature_extractor: 提取完成 Alpha_5=rank(return_20), 1.438s
[2022-03-16 09:10:45.007615] INFO: derived_feature_extractor: /y_2017, 256263
[2022-03-16 09:10:46.442683] INFO: derived_feature_extractor: /y_2018, 816987
[2022-03-16 09:10:48.272506] INFO: derived_feature_extractor: /y_2019, 884867
[2022-03-16 09:10:50.087546] INFO: derived_feature_extractor: /y_2020, 855949
[2022-03-16 09:10:50.624380] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[32.796455s].
[2022-03-16 09:10:50.636217] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..
[2022-03-16 09:10:51.686371] INFO: A股股票过滤: 过滤 /y_2017, 251995/0/256263
[2022-03-16 09:10:54.503671] INFO: A股股票过滤: 过滤 /y_2018, 800233/0/816987
[2022-03-16 09:10:57.514187] INFO: A股股票过滤: 过滤 /y_2019, 852507/0/884867
[2022-03-16 09:11:00.484033] INFO: A股股票过滤: 过滤 /y_2020, 789268/0/855949
[2022-03-16 09:11:00.490928] INFO: A股股票过滤: 过滤完成, 2694003 + 0
[2022-03-16 09:11:00.554928] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[9.91872s].
[2022-03-16 09:11:00.564571] INFO: moduleinvoker: dropnan.v2 开始运行..
[2022-03-16 09:11:00.825659] INFO: dropnan: /y_2017, 188490/251995
[2022-03-16 09:11:01.389364] INFO: dropnan: /y_2018, 796836/800233
[2022-03-16 09:11:02.079539] INFO: dropnan: /y_2019, 849723/852507
[2022-03-16 09:11:02.722572] INFO: dropnan: /y_2020, 784752/789268
[2022-03-16 09:11:02.860080] INFO: dropnan: 行数: 2619801/2694003
[2022-03-16 09:11:02.871392] INFO: moduleinvoker: dropnan.v2 运行完成[2.306816s].
[2022-03-16 09:11:02.886327] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..
[2022-03-16 09:11:03.209456] INFO: StockRanker预测: /y_2017 ..
[2022-03-16 09:11:04.542307] INFO: StockRanker预测: /y_2018 ..
[2022-03-16 09:11:09.056030] INFO: StockRanker预测: /y_2019 ..
[2022-03-16 09:11:13.458520] INFO: StockRanker预测: /y_2020 ..
[2022-03-16 09:11:20.364519] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[17.478182s].
[2022-03-16 09:11:22.008018] INFO: moduleinvoker: backtest.v8 开始运行..
[2022-03-16 09:11:22.014482] INFO: backtest: biglearning backtest:V8.6.2
[2022-03-16 09:11:22.015572] INFO: backtest: product_type:stock by specified
[2022-03-16 09:11:22.105767] INFO: moduleinvoker: cached.v2 开始运行..
[2022-03-16 09:11:31.258282] INFO: backtest: 读取股票行情完成:3695596
[2022-03-16 09:11:33.810454] INFO: moduleinvoker: cached.v2 运行完成[11.70468s].
[2022-03-16 09:11:36.827297] INFO: algo: TradingAlgorithm V1.8.7
[2022-03-16 09:11:38.276218] INFO: algo: trading transform...
[2022-03-16 09:11:55.537233] INFO: Performance: Simulated 708 trading days out of 708.
[2022-03-16 09:11:55.538720] INFO: Performance: first open: 2018-01-02 09:30:00+00:00
[2022-03-16 09:11:55.539806] INFO: Performance: last close: 2020-12-01 15:00:00+00:00
[2022-03-16 09:12:06.054646] INFO: moduleinvoker: backtest.v8 运行完成[44.046621s].
[2022-03-16 09:12:06.056251] INFO: moduleinvoker: trade.v4 运行完成[45.682983s].

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-5003ebfe274d4218b9771c19826795d3"}/bigcharts-data-end

收益率186.27%
年化收益率45.41%
基准收益率25.71%
阿尔法0.39
贝塔0.61
夏普比率1.58
胜率0.54
盈亏比1.44
收益波动率23.55%
信息比率0.09
最大回撤11.94%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-d2412daf7fe14e2f8e44f5e1b470a86c"}/bigcharts-data-end