复制链接

克隆策略

In [3]:

m4.data_1.read()

Out[3]:

	avg_amount_0	avg_amount_20	avg_amount_5	date	instrument	pe_ttm_0	rank_avg_amount_0	rank_avg_amount_10	rank_avg_amount_5	rank_return_0	...	rank_return_5	return_10	return_20	return_5	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_5/rank_return_10
2737833	4.565388e+09	4.074674e+09	3.743381e+09	2015-01-05	000001.SZA	9.518270	0.989312	0.987548	0.985831	0.471569	...	0.933018	1.042969	1.222901	1.138593	1.219589	0.918695	1.003531	0.998261	0.505423	1.121259
2737834	3.453446e+09	4.016539e+09	3.837692e+09	2015-01-06	000001.SZA	9.375674	0.985458	0.987543	0.986684	0.128743	...	0.878007	1.059772	1.130372	1.074200	0.899876	0.955472	0.998757	0.999130	0.146630	1.019451
2737835	2.634796e+09	3.840188e+09	3.672543e+09	2015-01-07	000001.SZA	9.197430	0.982074	0.987141	0.987580	0.144686	...	0.701243	1.032000	1.065382	1.025166	0.717431	0.956345	0.994425	1.000445	0.206328	0.906371
2737836	2.128003e+09	3.661347e+09	3.363223e+09	2015-01-08	000001.SZA	8.888472	0.981624	0.986695	0.986296	0.088034	...	0.369640	0.975228	0.982272	1.002681	0.632727	0.918575	0.995264	0.999595	0.238162	1.798039
2737837	3.835378e+09	3.558131e+09	3.396205e+09	2015-01-09	000001.SZA	8.959770	0.988884	0.987119	0.986746	0.861907	...	0.122108	1.022373	1.099927	0.972903	1.129313	0.954491	1.002166	0.999623	7.058563	0.265289
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
8401647	3.836166e+06	5.469703e+06	3.143269e+06	2021-12-27	872925.BJA	40.479881	0.008793	0.007326	0.005805	0.416988	...	0.245214	0.903573	0.856735	0.950634	1.220438	0.574669	1.514611	0.792410	1.700508	2.447394
8401648	3.458513e+06	5.094640e+06	3.427296e+06	2021-12-28	872925.BJA	41.540573	0.005787	0.006680	0.006022	0.836122	...	0.235269	0.908861	0.922484	0.974661	1.009108	0.672726	0.960979	0.901478	3.553900	2.708802
8401649	9.780547e+06	5.351129e+06	4.480491e+06	2021-12-29	872925.BJA	43.777672	0.035569	0.007533	0.007734	0.970002	...	0.885616	0.965136	0.965958	1.055323	2.182918	0.837298	4.599255	1.026583	1.095285	2.672971
8401650	5.446816e+07	7.791803e+06	1.304077e+07	2021-12-30	872925.BJA	51.279659	0.357892	0.013557	0.038866	0.997428	...	0.989471	1.191842	1.140223	1.225346	4.176760	1.673652	9.208317	2.866847	1.008041	1.017285
8401651	3.764307e+07	9.450522e+06	1.906012e+07	2021-12-31	872925.BJA	48.811138	0.244216	0.025183	0.081992	0.017784	...	0.970999	1.150978	1.103313	1.163678	1.974965	2.016833	2.978539	3.255847	0.018316	1.021352

3218732 rows × 21 columns

In [2]:

# 本代码由可视化策略环境自动生成 2023年4月7日 14:22
# 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。
 
# 显式导入 BigQuant 相关 SDK 模块
from bigdatasource.api import DataSource
from biglearning.api import M
from biglearning.api import tools as T
from biglearning.module2.common.data import Outputs

# 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 m4_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df = input_1.read()
    df = df[(df.date.between("2015-01-01", "2016-12-31")) | (df.date.between("2020-01-01", "2021-12-31"))]
    data_1 = DataSource.write_df(df)
    return Outputs(data_1=data_1, 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 m4_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()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities)])))

        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 m19_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2022-12-31',
    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
)

m4 = M.cached.v3(
    input_1=m16.data,
    run=m4_run_bigquant_run,
    post_run=m4_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m4.data_1,
    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', '2021-01-01'),
    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
)

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'
)

[2023-04-07 14:21:59.502145] INFO moduleinvoker: instruments.v2 开始运行..
[2023-04-07 14:21:59.515661] INFO moduleinvoker: 命中缓存
[2023-04-07 14:21:59.519075] INFO moduleinvoker: instruments.v2 运行完成[0.016961s].
[2023-04-07 14:21:59.527818] INFO moduleinvoker: input_features.v1 开始运行..
[2023-04-07 14:21:59.535756] INFO moduleinvoker: 命中缓存
[2023-04-07 14:21:59.538087] INFO moduleinvoker: input_features.v1 运行完成[0.010314s].
[2023-04-07 14:21:59.556992] INFO moduleinvoker: general_feature_extractor.v7 开始运行..
[2023-04-07 14:21:59.568499] INFO moduleinvoker: 命中缓存
[2023-04-07 14:21:59.570493] INFO moduleinvoker: general_feature_extractor.v7 运行完成[0.013595s].
[2023-04-07 14:21:59.580702] INFO moduleinvoker: derived_feature_extractor.v3 开始运行..
[2023-04-07 14:21:59.591289] INFO moduleinvoker: 命中缓存
[2023-04-07 14:21:59.593908] INFO moduleinvoker: derived_feature_extractor.v3 运行完成[0.013212s].
[2023-04-07 14:21:59.617648] INFO moduleinvoker: cached.v3 开始运行..
[2023-04-07 14:22:28.293128] INFO moduleinvoker: cached.v3 运行完成[28.675486s].