复制链接

克隆策略

In [10]:

# 本代码由可视化策略环境自动生成 2021年12月29日 22:44
# 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 m5_run_bigquant_run(input_1, input_2, input_3):
    # 原始输入
    min5_df = input_1.read_df()
    #min5_df = DataSource("bar5m_CN_STOCK_A").read(start_date=conf.start_date,end_date=conf.end_date,fields = ['date','instument','open'])
    min5_df =min5_df.rename(columns={'date':'datetime'})
    buy_time="9:45"
    close_time="14:45"
    min5_df_buy_1=min5_df.set_index("datetime").between_time(buy_time, buy_time)
    min5_df_close_1=min5_df.set_index("datetime").between_time(close_time, close_time)
    min5_df_buy_1['buy_price']= min5_df_buy_1['open'].shift(-1)
    min5_df_close_1['sell_price']= min5_df_close_1['open'].shift(-1)
    min5_df_buy=min5_df_buy_1.rename(columns={'open':'open_buy'})
    min5_df_close=min5_df_close_1.rename(columns={'open':'open_close'})
    min5_df_buy['date'] = min5_df_buy.index.floor('D')
    min5_df_close['date'] = min5_df_buy.index.floor('D')
    # 合并老&新因子
    min5_df_final = pd.merge(min5_df_buy,min5_df_close,on=['date','instrument'])   
    # 输出
    data_1 = DataSource.write_df(min5_df_final)
    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 m5_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

    class FixedPriceSlippage(SlippageModel):
        def process_order(self, data, order, bar_volume=0, trigger_check_price=0):
            if order.limit is None:
                price_field = self._price_field_buy if order.amount > 0 else self._price_field_sell
                price = data.current(order.asset, price_field)
            else:
                price = order.limit
            # 返回希望成交的价格和数量
            return (price, order.amount)
    # 如果未限价，设置滑点范围为最低价到最高价，即未限价时按照开盘价买入、收盘价卖出
    context.fix_slippage = FixedPriceSlippage(price_field_buy='open', price_field_sell='close')
    context.set_slippage(us_equities=context.fix_slippage) # us是universe的简写，如果是期货，需要传入us_future


# 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, limit_price=sell_price)
            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, limit_price=buy_price)

# 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='2021-09-01',
    end_date='2021-11-01',
    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/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=10,
    minimum_docs_per_leaf=100,
    number_of_trees=1,
    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', '2021-11-01'),
    end_date=T.live_run_param('trading_date', '2021-12-01'),
    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=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.use_datasource.v1(
    datasource_id='bar5m_CN_STOCK_A',
    start_date='2021-11-01',
    end_date='2021-12-01'
)

m5 = M.cached.v3(
    input_1=m4.data,
    run=m5_run_bigquant_run,
    post_run=m5_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m10 = M.join.v3(
    data1=m5.data_1,
    data2=m8.predictions,
    on='date,instrument',
    how='inner',
    sort=False
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m10.data,
    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'
)

[2021-12-29 22:25:02.611464] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-12-29 22:25:02.623294] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.625210] INFO: moduleinvoker: instruments.v2 运行完成[0.013751s].

[2021-12-29 22:25:02.637235] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-12-29 22:25:02.646735] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.648641] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.011415s].

[2021-12-29 22:25:02.653742] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-12-29 22:25:02.664570] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.666964] INFO: moduleinvoker: input_features.v1 运行完成[0.013227s].

[2021-12-29 22:25:02.707605] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-12-29 22:25:02.716279] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.718426] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.010851s].

[2021-12-29 22:25:02.726684] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-29 22:25:02.736015] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.737785] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.0111s].

[2021-12-29 22:25:02.747651] INFO: moduleinvoker: join.v3 开始运行..

[2021-12-29 22:25:02.757522] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.760266] INFO: moduleinvoker: join.v3 运行完成[0.012586s].

[2021-12-29 22:25:02.772851] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-12-29 22:25:02.784468] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.786198] INFO: moduleinvoker: dropnan.v1 运行完成[0.013358s].

[2021-12-29 22:25:02.794450] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2021-12-29 22:25:02.808503] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.977349] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[0.182899s].

[2021-12-29 22:25:02.982710] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-12-29 22:25:02.995476] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:02.997922] INFO: moduleinvoker: instruments.v2 运行完成[0.01517s].

[2021-12-29 22:25:03.012317] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-12-29 22:25:03.021575] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.024437] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012139s].

[2021-12-29 22:25:03.033564] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-29 22:25:03.041781] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.043557] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009999s].

[2021-12-29 22:25:03.053908] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-12-29 22:25:03.062447] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.064489] INFO: moduleinvoker: dropnan.v1 运行完成[0.010567s].

[2021-12-29 22:25:03.073542] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2021-12-29 22:25:03.086872] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.088561] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.015021s].

[2021-12-29 22:25:03.093568] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2021-12-29 22:25:03.104020] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.105968] INFO: moduleinvoker: use_datasource.v1 运行完成[0.012396s].

[2021-12-29 22:25:03.120826] INFO: moduleinvoker: cached.v3 开始运行..

[2021-12-29 22:25:03.144229] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.146039] INFO: moduleinvoker: cached.v3 运行完成[0.025232s].

[2021-12-29 22:25:03.155336] INFO: moduleinvoker: join.v3 开始运行..

[2021-12-29 22:25:03.166508] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.169360] INFO: moduleinvoker: join.v3 运行完成[0.01402s].

[2021-12-29 22:25:03.224427] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-12-29 22:25:03.229943] INFO: backtest: biglearning backtest:V8.6.1

[2021-12-29 22:25:03.231512] INFO: backtest: product_type:stock by specified

[2021-12-29 22:25:03.316699] INFO: moduleinvoker: cached.v2 开始运行..

[2021-12-29 22:25:03.325373] INFO: moduleinvoker: 命中缓存

[2021-12-29 22:25:03.327403] INFO: moduleinvoker: cached.v2 运行完成[0.010725s].

[2021-12-29 22:25:04.693135] INFO: algo: TradingAlgorithm V1.8.6

[2021-12-29 22:25:05.109240] INFO: algo: trading transform...

[2021-12-29 22:25:05.375060] ERROR: moduleinvoker: module name: backtest, module version: v8, trackeback: NameError: name 'buy_price' is not defined

[2021-12-29 22:25:05.384631] ERROR: moduleinvoker: module name: trade, module version: v4, trackeback: NameError: name 'buy_price' is not defined

设置测试数据集，查看训练迭代过程的NDCG

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-b462ef6b9d744ff39fa07dd26366cbc5"}/bigcharts-data-end

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-10-e379e5f2ea39> in <module>
    258 )
    259 
--> 260 m19 = M.trade.v4(
    261     instruments=m9.data,
    262     options_data=m10.data,

<ipython-input-10-e379e5f2ea39> in m19_handle_data_bigquant_run(context, data)
     97             cash = max_cash_per_instrument - positions.get(instrument, 0)
     98         if cash > 0:
---> 99             context.order_value(context.symbol(instrument), cash, limit_price=buy_price)
    100 
    101 # 回测引擎：准备数据，只执行一次

NameError: name 'buy_price' is not defined

In [13]:

m10.data.read().head()

Out[13]:

	date	instrument	score	position	amount_x	close_x	high_x	low_x	open_buy	volume_x	buy_price	amount_y	close_y	high_y	low_y	open_close	volume_y	sell_price
0	2021-11-01	000001.SZA	0.082747	1	76851311.0	19.129999	19.25	19.07	19.150000	4014540.0	19.379999	18878675.0	19.420000	19.430000	19.389999	19.420000	972400.0	18.150000
1	2021-11-01	000002.SZA	0.082747	2	111043109.0	18.240000	18.34	18.16	18.219999	6078600.0	18.209999	23786960.0	18.190001	18.200001	18.180000	18.180000	1307928.0	17.610001
2	2021-11-01	000004.SZA	0.082747	3	719044.0	16.620001	16.67	16.58	16.660000	43300.0	16.879999	367520.0	16.850000	16.870001	16.840000	16.870001	21800.0	16.469999
3	2021-11-01	000005.SZA	0.082747	4	520617.0	2.180000	2.18	2.16	2.170000	240200.0	2.120000	188401.0	2.170000	2.170000	2.160000	2.170000	87100.0	2.070000
4	2021-11-01	000006.SZA	0.082747	5	219267.0	4.160000	4.16	4.14	4.150000	52800.0	4.160000	101243.0	4.180000	4.190000	4.180000	4.180000	24200.0	4.070000