以Xgboost AI模型选股为例¶

本文主要从模型训练-模型保存-模型调用三个流程完整讲解如何使用Xgboost模型进行AI策略开发

首先是训练模型¶

In [1]:

# 本代码由可视化策略环境自动生成 2022年9月7日 20:19
# 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'] = 5

    
    from zipline.finance.slippage import SlippageModel
    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 = data.current(order.asset, self._price_field_buy)
            # 返回希望成交的价格和数量
            return (price, order.amount)
    # 设置price_field,默认是开盘买入，收盘卖出
    context.fix_slippage = FixedPriceSlippage(price_field_buy='open', price_field_sell='close')
    context.set_slippage(us_equities=context.fix_slippage)    
# 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.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 m19_prepare_bigquant_run(context):
    pass

def m19_before_trading_start_bigquant_run(context, data):
# 获取股票名称 用于过滤st和退市股
    context.name_df = DataSource('instruments_CN_STOCK_A').read()
    # 获取涨跌停状态
    context.price_limit_status = DataSource('stock_status_CN_STOCK_A').read(fields=['price_limit_status'])
    
    df_price_limit_status=context.price_limit_status.set_index('date')
    today=data.current_dt.strftime('%Y-%m-%d')
    # 得到当前未完成订单
    for orders in get_open_orders().values():
        # 循环，撤销订单
        for _order in orders:
            ins=str(_order.sid.symbol)
            if data.can_trade(_order.sid):
                #判断一下如果当日涨停，则取消卖单
                if  df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status.loc[today]>2 and _order.amount<0:
                    cancel_order(_order)
                    print(today,'尾盘涨停',ins) 
    pass

m1 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2015-01-01',
    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)
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="""# #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=0
)

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
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2015-01-01'),
    end_date=T.live_run_param('trading_date', '2017-01-01'),
    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=0
)

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
)

m20 = M.xgboost.v1(
    training_ds=m13.data,
    features=m3.data,
    predict_ds=m14.data,
    num_boost_round=30,
    objective='排序(pairwise)',
    booster='gbtree',
    max_depth=6,
    key_cols='date,instrument',
    group_col='date',
    nthread=1,
    n_gpus=-1,
    other_train_parameters={}
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m20.predictions,
    start_date='',
    end_date='',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    before_trading_start=m19_before_trading_start_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.SHA'
)

[2022-09-07 20:17:39.105228] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-09-07 20:17:39.142278] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:39.145492] INFO: moduleinvoker: instruments.v2 运行完成[0.040307s].

[2022-09-07 20:17:39.190393] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-09-07 20:17:39.203822] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:40.722893] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[1.532499s].

[2022-09-07 20:17:40.751773] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-09-07 20:17:40.771543] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:40.773775] INFO: moduleinvoker: input_features.v1 运行完成[0.022032s].

[2022-09-07 20:17:40.837658] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-09-07 20:17:40.849043] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:40.851686] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.014091s].

[2022-09-07 20:17:40.889939] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-09-07 20:17:40.906323] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:40.908451] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.018516s].

[2022-09-07 20:17:40.926668] INFO: moduleinvoker: join.v3 开始运行..

[2022-09-07 20:17:40.938113] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:40.942258] INFO: moduleinvoker: join.v3 运行完成[0.015581s].

[2022-09-07 20:17:40.960026] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-09-07 20:17:40.984962] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:40.987498] INFO: moduleinvoker: dropnan.v1 运行完成[0.027484s].

[2022-09-07 20:17:41.000301] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-09-07 20:17:41.013661] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:41.016367] INFO: moduleinvoker: instruments.v2 运行完成[0.016061s].

[2022-09-07 20:17:41.044595] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-09-07 20:17:41.060467] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:41.063355] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01879s].

[2022-09-07 20:17:41.084498] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-09-07 20:17:41.094190] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:41.096985] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.012483s].

[2022-09-07 20:17:41.121940] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-09-07 20:17:41.130845] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:41.133501] INFO: moduleinvoker: dropnan.v1 运行完成[0.01156s].

[2022-09-07 20:17:41.156913] INFO: moduleinvoker: xgboost.v1 开始运行..

[2022-09-07 20:17:41.179207] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:41.186230] INFO: moduleinvoker: xgboost.v1 运行完成[0.029316s].

[2022-09-07 20:17:48.058913] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-09-07 20:17:48.067132] INFO: backtest: biglearning backtest:V8.6.3

[2022-09-07 20:17:48.069664] INFO: backtest: product_type:stock by specified

[2022-09-07 20:17:48.838174] INFO: moduleinvoker: cached.v2 开始运行..

[2022-09-07 20:17:48.857821] INFO: moduleinvoker: 命中缓存

[2022-09-07 20:17:48.859956] INFO: moduleinvoker: cached.v2 运行完成[0.021822s].

[2022-09-07 20:18:11.853619] INFO: algo: TradingAlgorithm V1.8.8

[2022-09-07 20:18:17.660228] INFO: algo: trading transform...

[2022-09-07 20:19:24.892250] ERROR: moduleinvoker: module name: backtest, module version: v8, trackeback: ValueError: The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().

[2022-09-07 20:19:24.909257] ERROR: moduleinvoker: module name: trade, module version: v4, trackeback: ValueError: The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-1-b2bd5150d7e0> in <module>
    224 )
    225 
--> 226 m19 = M.trade.v4(
    227     instruments=m9.data,
    228     options_data=m20.predictions,

<ipython-input-1-b2bd5150d7e0> in m19_before_trading_start_bigquant_run(context, data)
     92             if data.can_trade(_order.sid):
     93                 #判断一下如果当日涨停，则取消卖单
---> 94                 if  df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status.loc[today]>2 and _order.amount<0:
     95                     cancel_order(_order)
     96                     print(today,'尾盘涨停',ins)

ValueError: The truth value of a Series is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().

接下来是模型保存¶

In [ ]:

import xgboost as xgb

def prepare_data(df, features, group_col):
    if group_col:
        df.sort_values(group_col, inplace=True)
    try:
        data = df[features].values
        if 'label' in df.columns:
            label = df['label'].values
        else:
            label = None
        dm = xgb.DMatrix(data, label=label)
        if group_col:
            dm.set_group(list(df.groupby(group_col).apply(len)))
        dm.feature_names = features
        return dm
    except KeyError as e:
        log.error('部分特征没有在数据中，执行失败')
        raise e

# 保存模型 
pd.to_pickle(m20.output_model.read(), 'xgboost.csv')
model_info = pd.read_pickle('xgboost.csv') 
features = model_info['features']
parameters = model_info['parameters']
model = model_info['model']
df = m14.data.read()   # 样本外数据
group_col = 'date'
outsample_data = prepare_data(df, features, group_col)

# 预测结果
pred_label = model.predict(outsample_data)
pred_df = pd.DataFrame(
data={'prediction': pred_label}, index=df.index)

# 通过两种方式比较预测结果是否一致
a = m20.predictions.read().sort_values(['date','instrument'])  # 可视化模块的预测结果

df['pred'] = pred_df
b = df[['pred','date','instrument']]  # 源码预测结果

print(a[a['instrument'] =='600000.SHA'].head(50).head(1)) # 随便查看某只股票某天的预测数据是否一致
print(b[b['instrument'] =='600000.SHA'].head(50).head(1))

In [ ]:

# 查看保存的模型信息
model_info