复制链接

克隆策略

In [3]:

# 本代码由可视化策略环境自动生成 2023年2月28日 13:06
# 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, columns_input):
    # 示例代码如下。在这里编写您的代码
    df = input_1.read_df()
    if input_2==None:
        if columns_input==[]:
            print('请输入标准化的列名或连接输入因子列表模块')
        else:
            columns = columns_input
    else:
        columns = input_2.read_pickle()

    def standard(x):
        return (x-x.mean())/x.std()        
        
        
    for fac in columns:
        median = df[fac].median()
        std = df[fac].std()
        df[fac] = df.groupby('date')[fac].apply(standard)
        
    ds = DataSource().write_df(df)
    return Outputs(data_1=ds)
# 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

import numpy as np
import xgboost as xgb
from typing import Tuple
from sklearn.model_selection import train_test_split

#评估函数
def evalerror(preds, dtrain):
    labels = dtrain.get_label()
    # return a pair metric_name, result
    # since preds are margin(before logistic transformation, cutoff at 0)
    return 'error', float(sum(labels != (preds > 0.0))) / len(labels)

#损失函数
def gradient(predt: np.ndarray, dtrain: xgb.DMatrix) -> np.ndarray:
    '''Compute the gradient squared log error.'''
    y = dtrain.get_label()
    return (np.log1p(predt) - np.log1p(y)) / (predt + 1)

def hessian(predt: np.ndarray, dtrain: xgb.DMatrix) -> np.ndarray:
    '''Compute the hessian for squared log error.'''
    y = dtrain.get_label()
    return ((-np.log1p(predt) + np.log1p(y) + 1) /
            np.power(predt + 1, 2))

def squared_log(predt: np.ndarray,
                dtrain: xgb.DMatrix) -> Tuple[np.ndarray, np.ndarray]:
    '''Squared Log Error objective. A simplified version for RMSLE used as
    objective function.
    '''
    predt[predt < -1] = -1 + 1e-6
    grad = gradient(predt, dtrain)
    hess = hessian(predt, dtrain)
    return grad, hess

# 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 m15_run_bigquant_run(input_1, input_2, input_3):
    # 读取数据和特征
    train_data = input_1.read()
    feature = input_2.read()
    test_data = input_3.read()
    #设置训练集和验证集
    train, val = train_test_split(train_data, shuffle=False, test_size=0.3)
    #设置xgboost数据格式
    dtrain = xgb.DMatrix(train[feature], train["label"])
    dtrain.set_group(list(train.groupby('date').apply(len)))
    dtrain.feature_names = feature
    
    dval = xgb.DMatrix(val[feature], val["label"])
    dval.set_group(list(val.groupby('date').apply(len)))
    dval.feature_names = feature
    
    dtest = xgb.DMatrix(test_data[feature], label = None)
    dtest.set_group(list(test_data.groupby('date').apply(len)))
    dtest.feature_names = feature
    params = {
        'tree_method': 'hist', 
        'seed': 1994,
        'disable_default_eval_metric': 1
    }
    #指定训练数据和验证数据
    watchlist = [(dval, 'eval'), (dtrain, 'train')]
    #训练
    model = xgb.train(params=params,
              dtrain=dtrain,
              evals=watchlist,
              num_boost_round=10,
              obj=squared_log,
              feval=evalerror)
    #获取预测结果
    pred = model.predict(dtest)
    test_data['prediction'] = pred
    data = test_data[['date','instrument','prediction']].groupby('date').apply(lambda x:x.sort_values('prediction',ascending=False)).reset_index(drop=True)
    return Outputs(data_1=DataSource.write_df(data), 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 m15_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m14_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 m14_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 m14_prepare_bigquant_run(context):
    pass


m1 = M.input_features.v1(
    features="""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
"""
)

m4 = M.instruments.v2(
    start_date='2010-01-01',
    end_date='2016-01-01',
    market='CN_STOCK_A',
    instrument_list=' ',
    max_count=0
)

m7 = M.general_feature_extractor.v7(
    instruments=m4.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m3 = M.derived_feature_extractor.v3(
    input_data=m7.data,
    features=m1.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m5 = M.cached.v3(
    input_1=m3.data,
    input_2=m1.data,
    run=m5_run_bigquant_run,
    post_run=m5_post_run_bigquant_run,
    input_ports='',
    params="""{
    'columns_input': []
}""",
    output_ports='data_1'
)

m8 = M.advanced_auto_labeler.v2(
    instruments=m4.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.SHA',
    drop_na_label=True,
    cast_label_int=True,
    user_functions={}
)

m2 = M.join.v3(
    data1=m8.data,
    data2=m5.data_1,
    on='date,instrument',
    how='inner',
    sort=False
)

m6 = M.dropnan.v2(
    input_data=m2.data
)

m10 = M.instruments.v2(
    start_date='2015-01-01',
    end_date='2015-06-01',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m12 = M.general_feature_extractor.v7(
    instruments=m10.data,
    features=m1.data,
    start_date='',
    end_date='',
    before_start_days=0
)

m13 = M.derived_feature_extractor.v3(
    input_data=m12.data,
    features=m1.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m11 = M.dropnan.v1(
    input_data=m13.data
)

m9 = M.xgboost.v1(
    training_ds=m6.data,
    features=m1.data,
    predict_ds=m11.data,
    num_boost_round=10,
    objective='排序(pairwise)',
    booster='gbtree',
    max_depth=6,
    key_cols='date,instrument',
    group_col='date',
    nthread=1,
    n_gpus=-1,
    other_train_parameters={
#     "feval": evalerror,
#     "objective": squared_log
    
}
)

m15 = M.cached.v3(
    input_1=m6.data,
    input_2=m1.data,
    input_3=m11.data,
    run=m15_run_bigquant_run,
    post_run=m15_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m14 = M.trade.v4(
    instruments=m10.data,
    options_data=m15.data_1,
    start_date='',
    end_date='',
    initialize=m14_initialize_bigquant_run,
    handle_data=m14_handle_data_bigquant_run,
    prepare=m14_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.SHA'
)

---------------------------------------------------------------------------
BQInputRejected                           Traceback (most recent call last)
BQInputRejected: 编译错误，34: 抱歉，平台暂时不支持此模块：typing.Tuple