复制链接

克隆策略

In [136]:

# 本代码由可视化策略环境自动生成 2022年6月30日 17:00
# 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 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
    
    from catboost import CatBoostRegressor

    train_df = input_1.read()
    test_df = input_2.read()
    features = input_3.read()

    group_col = "date"

    def prepare_data(df, group_col, features):
        if group_col:
            df.sort_values(group_col, inplace=True)

        data = df[features].values
        if "label" in df.columns:
            label = df["label"].values
        else:
            label = None   

        return  data,label

    train_data, train_labels = prepare_data(train_df, group_col, features)
    test_data = prepare_data(test_df, group_col, features)[0]

    model = CatBoostRegressor(iterations=10,
                              learning_rate=0.1,
                              depth=5)
    # Fit model
    model.fit(train_data, train_labels)
    # Get predictions
    preds = model.predict(test_data)

    test_df.sort_values(group_col, inplace=True)
    pred_df = pd.DataFrame(data={'prediction': preds}, index=test_df.index)
    test_df['score'] = pred_df
    
    test_df = test_df[['date','instrument','score']]
    test_df = test_df.sort_values(['date','score'], ascending=[True, False])
    test_df.index = np.arange(len(test_df)) 
     
    data_1 = DataSource.write_df(test_df)
    
    return Outputs(data_1=data_1)
# 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

# 回测引擎：初始化函数，只执行一次
def m10_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 = 6
    # 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 m10_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 m10_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2018-01-01',
    end_date='2020-12-31',
    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
)

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', '2021-01-01'),
    end_date=T.live_run_param('trading_date', '2022-03-31'),
    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
)

m4 = M.cached.v3(
    input_1=m13.data,
    input_2=m14.data,
    input_3=m3.data,
    run=m4_run_bigquant_run,
    post_run=m4_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

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='open',
    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'
)

m10 = M.trade.v4(
    instruments=m9.data,
    options_data=m4.data_1,
    start_date='',
    end_date='',
    initialize=m10_initialize_bigquant_run,
    handle_data=m10_handle_data_bigquant_run,
    prepare=m10_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=2000001,
    auto_cancel_non_tradable_orders=False,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2022-06-30 16:59:40.590132] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-06-30 16:59:40.598651] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.600904] INFO: moduleinvoker: instruments.v2 运行完成[0.010762s].

[2022-06-30 16:59:40.612140] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-06-30 16:59:40.620482] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.622363] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.01022s].

[2022-06-30 16:59:40.626953] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-06-30 16:59:40.634275] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.636211] INFO: moduleinvoker: input_features.v1 运行完成[0.009273s].

[2022-06-30 16:59:40.652969] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-06-30 16:59:40.709262] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.711671] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.058726s].

[2022-06-30 16:59:40.764052] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-06-30 16:59:40.771088] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.774132] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.01008s].

[2022-06-30 16:59:40.785176] INFO: moduleinvoker: join.v3 开始运行..

[2022-06-30 16:59:40.791614] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.793690] INFO: moduleinvoker: join.v3 运行完成[0.008516s].

[2022-06-30 16:59:40.805446] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-06-30 16:59:40.812426] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.814820] INFO: moduleinvoker: dropnan.v1 运行完成[0.009372s].

[2022-06-30 16:59:40.823378] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-06-30 16:59:40.833483] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.933253] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.109853s].

[2022-06-30 16:59:40.940241] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-06-30 16:59:40.947631] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.949805] INFO: moduleinvoker: instruments.v2 运行完成[0.009573s].

[2022-06-30 16:59:40.963385] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-06-30 16:59:40.969722] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.972084] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.008723s].

[2022-06-30 16:59:40.987494] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-06-30 16:59:40.994329] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:40.996560] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009071s].

[2022-06-30 16:59:41.014429] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-06-30 16:59:41.022393] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:41.024231] INFO: moduleinvoker: dropnan.v1 运行完成[0.00982s].

[2022-06-30 16:59:41.035567] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-06-30 16:59:41.046437] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:41.048455] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.012901s].

[2022-06-30 16:59:41.151624] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-06-30 16:59:41.160698] INFO: moduleinvoker: 命中缓存

[2022-06-30 16:59:42.681476] INFO: moduleinvoker: backtest.v8 运行完成[1.529866s].

[2022-06-30 16:59:42.684039] INFO: moduleinvoker: trade.v4 运行完成[1.627997s].

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-1ffc04562aeb4b5ca848323b4219424a"}/bigcharts-data-end

收益率25.21%
年化收益率20.71%
基准收益率-18.97%
阿尔法0.31
贝塔0.48
夏普比率0.81
胜率0.51
盈亏比1.21
收益波动率22.96%
信息比率0.1
最大回撤15.43%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-03d3dcca2be341828d9424f0e8cca2cc"}/bigcharts-data-end