复制链接

克隆策略

In [25]:

# 本代码由可视化策略环境自动生成 2023年1月29日 09:16
# 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'] = 0

# 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):
    today = data.current_dt.strftime('%Y-%m-%d')
    # 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_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])

    # 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()}

    #------------------------------------------止损模块START--------------------------------------------
    
    # 新建当日止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
    stoploss_stock = []
    stopwin_stock = []
    equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
    if len(equities) > 0:
        for i in equities.keys():
            stock_market_price = data.current(context.symbol(i), 'price')  # 最新市场价格
            stock_market_today_high = data.current(context.symbol(i), 'high') #今日最高价      
            stock_market_today_close = data.current(context.symbol(i), 'close') #今日收盘价
            last_sale_date = equities[i].last_sale_date   # 上次交易日期
            last_cost_price = equities[i].cost_basis # 上次交易金额
            delta_days = data.current_dt - last_sale_date  
            hold_days = delta_days.days # 持仓天数
            # 建仓以来的最高价
            highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
            # 建仓以来的收盘价的最高价
            highclose_price_since_buy = data.history(context.symbol(i), 'close', hold_days, '1d').max()
            # 确定止损位置
            stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.05
            
            # 确定止盈位置
            stopwin_line = last_cost_price * 1.1
            # 最高收益
            high_return = (highclose_price_since_buy-last_cost_price)/last_cost_price
            #record('止损位置', stoploss_line)
            # 如果价格下穿止损位置
            if stock_market_price < stoploss_line:
                # print("止损股票：", i)
                # print('日期:',today,'最高价:',highest_price_since_buy)
                # print('日期:',today,'止损价:',stoploss_line)
                # print('日期:',today,'当前价:',stock_market_price)
                # print('日期:',today,'建仓价:',last_cost_price)
                context.order_target(context.symbol(i), 0)
                stoploss_stock.append(i)
                    
            #elif stock_market_price > stopwin_line:
            #    context.order_target(context.symbol(i), 0)
            #    stopwin_stock.append(i)
            #    stock_now = stock_now -1
    #if len(stoploss_stock)>0:
    #    print('日期：', today, '股票：', stoploss_stock, '出现跟踪止损状况')
    #if len(stopwin_stock)>0:
    #    print('日期：', today, '股票：', stopwin_stock, '出现跟踪止盈状况')
    
    #-------------------------------------------止损模块END--------------------------------------------- 
    
    # 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 equities.keys():
            if not instrument in buy_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
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    for i, instrument in enumerate(buy_instruments):
        if not instrument in positions:
            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='2021-06-01',
    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
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2022-09-07'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m24 = M.input_features.v1(
    features="""market_cap_0
ff1=(close_0-close_30)/close_30 > 1.25"""
)

m3 = M.input_features.v1(
    features_ds=m24.data,
    features='list_days_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.chinaa_stock_filter.v1(
    input_data=m18.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

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

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
)

m4 = M.chinaa_stock_filter.v1(
    input_data=m16.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m4.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=m24.data,
    test_ds=m13.data,
    learning_algorithm='排序',
    number_of_leaves=10,
    minimum_docs_per_leaf=20,
    number_of_trees=14,
    learning_rate=0.1,
    max_bins=100,
    feature_fraction=1,
    data_row_fraction=1,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

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'
)

[2023-01-29 09:11:53.386137] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-29 09:11:53.612221] INFO: moduleinvoker: instruments.v2 运行完成[0.22608s].

[2023-01-29 09:11:53.622270] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-01-29 09:11:54.270723] INFO: 自动标注(股票): 加载历史数据: 653770 行

[2023-01-29 09:11:54.272390] INFO: 自动标注(股票): 开始标注 ..

[2023-01-29 09:11:54.940078] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[1.317802s].

[2023-01-29 09:11:54.946558] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-01-29 09:11:54.961528] INFO: moduleinvoker: 命中缓存

[2023-01-29 09:11:54.963542] INFO: moduleinvoker: instruments.v2 运行完成[0.016996s].

[2023-01-29 09:11:54.967953] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-01-29 09:11:54.975128] INFO: moduleinvoker: 命中缓存

[2023-01-29 09:11:54.976843] INFO: moduleinvoker: input_features.v1 运行完成[0.008888s].

[2023-01-29 09:11:54.981091] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-01-29 09:11:54.989749] INFO: moduleinvoker: 命中缓存

[2023-01-29 09:11:54.991509] INFO: moduleinvoker: input_features.v1 运行完成[0.010434s].

[2023-01-29 09:11:55.007164] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-29 09:11:55.017938] INFO: moduleinvoker: 命中缓存

[2023-01-29 09:11:55.020044] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012901s].

[2023-01-29 09:11:55.027668] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-29 09:11:55.033931] INFO: moduleinvoker: 命中缓存

[2023-01-29 09:11:55.035337] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.007666s].

[2023-01-29 09:11:55.043542] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2023-01-29 09:11:56.366959] INFO: A股股票过滤: 过滤 /y_2020, 167622/0/243745

[2023-01-29 09:12:01.134574] INFO: A股股票过滤: 过滤 /y_2021, 706124/0/1061527

[2023-01-29 09:12:04.624414] INFO: A股股票过滤: 过滤 /y_2022, 496834/0/792817

[2023-01-29 09:12:04.629764] INFO: A股股票过滤: 过滤完成, 1370580 + 0

[2023-01-29 09:12:04.648738] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[9.605174s].

[2023-01-29 09:12:04.658498] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-29 09:12:05.086160] INFO: dropnan: /y_2020, 166115/167622

[2023-01-29 09:12:06.159533] INFO: dropnan: /y_2021, 702214/706124

[2023-01-29 09:12:07.025947] INFO: dropnan: /y_2022, 495406/496834

[2023-01-29 09:12:07.116580] INFO: dropnan: 行数: 1363735/1370580

[2023-01-29 09:12:07.123506] INFO: moduleinvoker: dropnan.v1 运行完成[2.465s].

[2023-01-29 09:12:07.138369] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-01-29 09:12:09.009027] INFO: 基础特征抽取: 年份 2021, 特征行数=907922

[2023-01-29 09:12:09.056247] INFO: 基础特征抽取: 总行数: 907922

[2023-01-29 09:12:09.063647] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[1.925295s].

[2023-01-29 09:12:09.071284] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-01-29 09:12:10.440300] INFO: derived_feature_extractor: 提取完成 ff1=(close_0-close_30)/close_30 > 1.25, 0.005s

[2023-01-29 09:12:11.637481] INFO: derived_feature_extractor: /y_2021, 907922

[2023-01-29 09:12:11.865314] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[2.794011s].

[2023-01-29 09:12:11.876526] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2023-01-29 09:12:16.094226] INFO: A股股票过滤: 过滤 /y_2021, 601528/0/907922

[2023-01-29 09:12:16.096921] INFO: A股股票过滤: 过滤完成, 601528 + 0

[2023-01-29 09:12:16.115965] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[4.239439s].

[2023-01-29 09:12:16.125174] INFO: moduleinvoker: join.v3 开始运行..

[2023-01-29 09:12:18.445400] INFO: join: /y_2021, 行数=414216/601528, 耗时=1.294851s

[2023-01-29 09:12:18.503157] INFO: join: 最终行数: 414216

[2023-01-29 09:12:18.512658] INFO: moduleinvoker: join.v3 运行完成[2.387482s].

[2023-01-29 09:12:18.521589] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-01-29 09:12:19.337010] INFO: dropnan: /y_2021, 412453/414216

[2023-01-29 09:12:19.382759] INFO: dropnan: 行数: 412453/414216

[2023-01-29 09:12:19.388919] INFO: moduleinvoker: dropnan.v1 运行完成[0.867333s].

[2023-01-29 09:12:19.396428] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2023-01-29 09:12:20.723690] INFO: StockRanker: 特征预处理 ..

[2023-01-29 09:12:20.793469] INFO: StockRanker: prepare data: training ..

[2023-01-29 09:12:20.840977] INFO: StockRanker: sort ..

[2023-01-29 09:12:24.517839] INFO: StockRanker: prepare data: test ..

[2023-01-29 09:12:24.563196] INFO: StockRanker: sort ..

[2023-01-29 09:12:28.031308] INFO: StockRanker训练: fa141ffe 准备训练: 412453 行数, test: 412453 rows

[2023-01-29 09:12:28.033205] INFO: StockRanker训练: AI模型训练，将在412453*2=82.49万数据上对模型训练进行14轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2023-01-29 09:12:28.314889] INFO: StockRanker训练: 正在训练 ..

[2023-01-29 09:12:28.360949] INFO: StockRanker训练: 任务状态: Pending

[2023-01-29 09:12:38.405645] INFO: StockRanker训练: 任务状态: Running

[2023-01-29 09:13:48.807736] INFO: StockRanker训练: 00:01:06.7269214, finished iteration 1

[2023-01-29 09:13:48.809441] INFO: StockRanker训练: 00:01:11.9752177, finished iteration 2

[2023-01-29 09:13:58.847963] INFO: StockRanker训练: 00:01:17.1423938, finished iteration 3

[2023-01-29 09:13:58.849614] INFO: StockRanker训练: 00:01:22.4615095, finished iteration 4

[2023-01-29 09:14:08.889122] INFO: StockRanker训练: 00:01:27.8940745, finished iteration 5

[2023-01-29 09:14:08.890735] INFO: StockRanker训练: 00:01:33.3027356, finished iteration 6

[2023-01-29 09:14:18.929368] INFO: StockRanker训练: 00:01:38.6395128, finished iteration 7

[2023-01-29 09:14:18.930985] INFO: StockRanker训练: 00:01:44.1342064, finished iteration 8

[2023-01-29 09:14:28.973103] INFO: StockRanker训练: 00:01:49.3644646, finished iteration 9

[2023-01-29 09:14:28.974680] INFO: StockRanker训练: 00:01:54.8036579, finished iteration 10

[2023-01-29 09:14:39.023011] INFO: StockRanker训练: 00:02:00.1765548, finished iteration 11

[2023-01-29 09:14:39.024650] INFO: StockRanker训练: 00:02:05.5792515, finished iteration 12

[2023-01-29 09:14:49.062233] INFO: StockRanker训练: 00:02:11.1931981, finished iteration 13

[2023-01-29 09:14:49.063821] INFO: StockRanker训练: 00:02:16.5951875, finished iteration 14

[2023-01-29 09:14:59.101967] INFO: StockRanker训练: 任务状态: Succeeded

[2023-01-29 09:14:59.380269] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[159.983826s].

[2023-01-29 09:14:59.389826] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-01-29 09:14:59.724473] INFO: StockRanker预测: /y_2020 ..

[2023-01-29 09:15:00.800965] INFO: StockRanker预测: /y_2021 ..

[2023-01-29 09:15:01.898622] INFO: StockRanker预测: /y_2022 ..

[2023-01-29 09:15:03.514611] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[4.124761s].

[2023-01-29 09:15:03.562230] INFO: moduleinvoker: backtest.v8 开始运行..

[2023-01-29 09:15:03.567274] INFO: backtest: biglearning backtest:V8.6.3

[2023-01-29 09:15:03.568716] INFO: backtest: product_type:stock by specified

[2023-01-29 09:15:03.640187] INFO: moduleinvoker: cached.v2 开始运行..

[2023-01-29 09:15:03.648403] INFO: moduleinvoker: 命中缓存

[2023-01-29 09:15:03.650940] INFO: moduleinvoker: cached.v2 运行完成[0.010774s].

[2023-01-29 09:15:17.085884] INFO: backtest: algo history_data=DataSource(0e01ce00f0644d36a590db362ff2669aT)

[2023-01-29 09:15:17.087656] INFO: algo: TradingAlgorithm V1.8.9

[2023-01-29 09:15:19.838649] INFO: algo: trading transform...

[2023-01-29 09:15:31.252983] INFO: Performance: Simulated 409 trading days out of 409.

[2023-01-29 09:15:31.255080] INFO: Performance: first open: 2021-01-04 09:30:00+00:00

[2023-01-29 09:15:31.256810] INFO: Performance: last close: 2022-09-07 15:00:00+00:00

[2023-01-29 09:15:35.352421] INFO: moduleinvoker: backtest.v8 运行完成[31.790109s].

[2023-01-29 09:15:35.355477] INFO: moduleinvoker: trade.v4 运行完成[31.833347s].

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-03cd56d689654d8fabef22a5afc19ccb"}/bigcharts-data-end

收益率28.78%
年化收益率16.86%
基准收益率-22.19%
阿尔法0.21
贝塔0.29
夏普比率0.76
胜率0.53
盈亏比1.2
收益波动率19.15%
信息比率0.08
最大回撤14.27%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-dea318cfdfd24001a4889cc4eab120c0"}/bigcharts-data-end

In [ ]: