复制链接

克隆策略

StockRanker多因子选股策略¶

In [ ]:

# 本代码由可视化策略环境自动生成 2023年5月6日 22:57
# 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 = 1
    context.options['hold_days'] = 1

# 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')]

    # 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.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.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        # print('rank order for sell %s' % instruments)
        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 m4_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2021-05-01',
    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)
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.SHA',
    drop_na_label=True,
    cast_label_int=True
)

m3 = M.input_features.v1(
    features="""ta_willr_14_0
rank_return_10/rank_return_30
avg_turn_15/turn_0
ta_rsi_14_0
market_cap_0
turn_5/avg_turn_10
swing_volatility_10_0/swing_volatility_60_0
rank_amount_10/rank_amount_30
rank_amount_5/rank_amount_20
rank_return_10
rank_return_20
rank_return_5/rank_return_20
rank_avg_turn_5
rank_volatility_5_0
ma_2_slope_0 = np.gradient(ta_ma(close_0,2))
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=250
)

m5 = M.chinaa_stock_filter.v1(
    input_data=m15.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
)

m16 = M.derived_feature_extractor.v3(
    input_data=m5.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', '2021-05-02'),
    end_date=T.live_run_param('trading_date', '2023-05-05'),
    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=250
)

m10 = M.chinaa_stock_filter.v1(
    input_data=m17.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
)

m18 = M.derived_feature_extractor.v3(
    input_data=m10.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.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=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2023-05-06 22:35:40.703938] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-05-06 22:35:40.712668] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.715300] INFO: moduleinvoker: instruments.v2 运行完成[0.011357s].

[2023-05-06 22:35:40.726014] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-05-06 22:35:40.733109] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.735467] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009462s].

[2023-05-06 22:35:40.741438] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-05-06 22:35:40.747828] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.749832] INFO: moduleinvoker: input_features.v1 运行完成[0.008412s].

[2023-05-06 22:35:40.768054] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-05-06 22:35:40.774042] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.776358] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.008312s].

[2023-05-06 22:35:40.786029] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2023-05-06 22:35:40.791108] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.792696] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[0.006678s].

[2023-05-06 22:35:40.808733] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-05-06 22:35:40.814708] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.816791] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.008066s].

[2023-05-06 22:35:40.826244] INFO: moduleinvoker: join.v3 开始运行..

[2023-05-06 22:35:40.832532] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:35:40.834730] INFO: moduleinvoker: join.v3 运行完成[0.00857s].

[2023-05-06 22:35:40.844285] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-05-06 22:35:43.340854] INFO: dropnan: /y_2009, 0/0

[2023-05-06 22:35:44.733577] INFO: dropnan: /y_2010, 393319/413404

[2023-05-06 22:35:46.458693] INFO: dropnan: /y_2011, 475240/493050

[2023-05-06 22:35:48.358296] INFO: dropnan: /y_2012, 536685/547433

[2023-05-06 22:35:50.372751] INFO: dropnan: /y_2013, 545905/546006

[2023-05-06 22:35:52.462005] INFO: dropnan: /y_2014, 546415/552100

[2023-05-06 22:35:54.556932] INFO: dropnan: /y_2015, 537439/548093

[2023-05-06 22:35:56.841307] INFO: dropnan: /y_2016, 617579/626525

[2023-05-06 22:35:59.371203] INFO: dropnan: /y_2017, 702499/725993

[2023-05-06 22:36:02.173859] INFO: dropnan: /y_2018, 790114/797473

[2023-05-06 22:36:05.324391] INFO: dropnan: /y_2019, 843373/849985

[2023-05-06 22:36:08.549986] INFO: dropnan: /y_2020, 852821/865644

[2023-05-06 22:36:09.553761] INFO: dropnan: /y_2021, 271497/276598

[2023-05-06 22:36:09.690250] INFO: dropnan: 行数: 7112886/7242304

[2023-05-06 22:36:09.701884] INFO: moduleinvoker: dropnan.v1 运行完成[28.857592s].

[2023-05-06 22:36:09.709960] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2023-05-06 22:36:32.782699] INFO: StockRanker: 特征预处理 ..

[2023-05-06 22:36:47.936423] INFO: StockRanker: prepare data: training ..

[2023-05-06 22:37:03.667812] INFO: StockRanker: sort ..

[2023-05-06 22:38:50.501698] INFO: StockRanker训练: 57a783a4 准备训练: 7112886 行数

[2023-05-06 22:38:50.503487] INFO: StockRanker训练: AI模型训练，将在7112886*15=10669.33万数据上对模型训练进行20轮迭代训练。预计将需要31～63分钟。请耐心等待。

[2023-05-06 22:38:50.766225] INFO: StockRanker训练: 正在训练 ..

[2023-05-06 22:38:50.824662] INFO: StockRanker训练: 任务状态: Pending

[2023-05-06 22:39:00.871463] INFO: StockRanker训练: 任务状态: Running

[2023-05-06 22:41:01.396258] INFO: StockRanker训练: 00:01:56.8584533, finished iteration 1

[2023-05-06 22:41:51.655919] INFO: StockRanker训练: 00:02:51.2604504, finished iteration 2

[2023-05-06 22:42:41.899024] INFO: StockRanker训练: 00:03:45.8702116, finished iteration 3

[2023-05-06 22:43:42.219248] INFO: StockRanker训练: 00:04:37.8389518, finished iteration 4

[2023-05-06 22:44:32.528493] INFO: StockRanker训练: 00:05:30.4670325, finished iteration 5

[2023-05-06 22:45:22.771609] INFO: StockRanker训练: 00:06:18.0529282, finished iteration 6

[2023-05-06 22:46:03.008774] INFO: StockRanker训练: 00:07:04.3006534, finished iteration 7

[2023-05-06 22:46:53.272391] INFO: StockRanker训练: 00:07:51.3421713, finished iteration 8

[2023-05-06 22:47:33.447862] INFO: StockRanker训练: 00:08:36.9998985, finished iteration 9

[2023-05-06 22:48:23.687689] INFO: StockRanker训练: 00:09:24.2741151, finished iteration 10

[2023-05-06 22:49:13.945174] INFO: StockRanker训练: 00:10:12.0413379, finished iteration 11

[2023-05-06 22:49:54.200561] INFO: StockRanker训练: 00:10:58.8023138, finished iteration 12

[2023-05-06 22:50:44.439273] INFO: StockRanker训练: 00:11:45.7704196, finished iteration 13

[2023-05-06 22:51:34.731238] INFO: StockRanker训练: 00:12:32.8219980, finished iteration 14

[2023-05-06 22:52:25.066259] INFO: StockRanker训练: 00:13:20.3252035, finished iteration 15

[2023-05-06 22:53:05.321216] INFO: StockRanker训练: 00:14:08.4830413, finished iteration 16

[2023-05-06 22:53:55.545672] INFO: StockRanker训练: 00:14:57.5024252, finished iteration 17

[2023-05-06 22:54:45.791784] INFO: StockRanker训练: 00:15:47.0162151, finished iteration 18

[2023-05-06 22:55:36.011620] INFO: StockRanker训练: 00:16:36.3356121, finished iteration 19

[2023-05-06 22:56:26.221384] INFO: StockRanker训练: 00:17:26.3562813, finished iteration 20

[2023-05-06 22:56:26.223205] INFO: StockRanker训练: 任务状态: Succeeded

[2023-05-06 22:56:26.501087] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[1216.791141s].

[2023-05-06 22:56:26.507211] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-05-06 22:56:26.512765] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:56:26.514810] INFO: moduleinvoker: instruments.v2 运行完成[0.007621s].

[2023-05-06 22:56:26.528288] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-05-06 22:56:26.537725] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:56:26.540755] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012456s].

[2023-05-06 22:56:26.552595] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2023-05-06 22:56:26.559706] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:56:26.562329] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[0.009728s].

[2023-05-06 22:56:26.572060] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-05-06 22:56:26.579899] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:56:26.582225] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.010166s].

[2023-05-06 22:56:26.592665] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-05-06 22:56:26.601376] INFO: moduleinvoker: 命中缓存

[2023-05-06 22:56:26.603888] INFO: moduleinvoker: dropnan.v1 运行完成[0.011224s].

[2023-05-06 22:56:26.624791] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-05-06 22:56:28.248379] INFO: StockRanker预测: /y_2020 ..

[2023-05-06 22:56:30.686704] INFO: StockRanker预测: /y_2021 ..

[2023-05-06 22:56:34.245454] INFO: StockRanker预测: /y_2022 ..

[2023-05-06 22:56:36.413124] INFO: StockRanker预测: /y_2023 ..

[2023-05-06 22:56:40.442196] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[13.817381s].

[2023-05-06 22:56:44.216146] INFO: moduleinvoker: backtest.v8 开始运行..

[2023-05-06 22:56:44.225389] INFO: backtest: biglearning backtest:V8.6.3

[2023-05-06 22:56:44.228160] INFO: backtest: product_type:stock by specified

[2023-05-06 22:56:44.321327] INFO: moduleinvoker: cached.v2 开始运行..

[2023-05-06 22:56:56.500444] INFO: backtest: 读取股票行情完成:3684934

[2023-05-06 22:57:00.342752] INFO: moduleinvoker: cached.v2 运行完成[16.021429s].

[2023-05-06 22:57:18.944833] INFO: backtest: algo history_data=DataSource(6bcfe29488ef4da1a9574944c852b9b5T)

[2023-05-06 22:57:18.947034] INFO: algo: TradingAlgorithm V1.8.9

[2023-05-06 22:57:24.534858] INFO: algo: trading transform...

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-df69bfaf41a441b19235c748465809b0"}/bigcharts-data-end