复制链接

克隆策略

In [1]:

import copy
import time
from datetime import timedelta

import torch
import torch.nn as nn
from torch.utils.data import TensorDataset, DataLoader, Dataset
from sklearn.model_selection import train_test_split

from bigmodels.models.base import BaseModel
from bigmodels.datasets.dataset import PredictDataset, TensorDataset

In [2]:

class GATModel(BaseModel):
    def __init__(self, d_feat=6, hidden_size=64, num_layers=2, dropout=0.0, base_model="GRU"):
        super().__init__()

        if base_model == "GRU":
            self.rnn = nn.GRU(
                input_size=d_feat,
                hidden_size=hidden_size,
                num_layers=num_layers,
                batch_first=True,
                dropout=dropout,
            )
        elif base_model == "LSTM":
            self.rnn = nn.LSTM(
                input_size=d_feat,
                hidden_size=hidden_size,
                num_layers=num_layers,
                batch_first=True,
                dropout=dropout,
            )
        else:
            raise ValueError("unknown base model name `%s`" % base_model)

        self.hidden_size = hidden_size
        self.d_feat = d_feat
        self.transformation = nn.Linear(self.hidden_size, self.hidden_size)
        self.a = nn.Parameter(torch.randn(self.hidden_size * 2, 1))
        self.a.requires_grad = True
        self.fc = nn.Linear(self.hidden_size, self.hidden_size)
        self.fc_out = nn.Linear(hidden_size, 1)
        self.leaky_relu = nn.LeakyReLU()
        self.softmax = nn.Softmax(dim=1)

    def cal_attention(self, x, y):
        x = self.transformation(x)
        y = self.transformation(y)

        sample_num = x.shape[0]
        dim = x.shape[1]
        e_x = x.expand(sample_num, sample_num, dim)
        e_y = torch.transpose(e_x, 0, 1)
        attention_in = torch.cat((e_x, e_y), 2).view(-1, dim * 2)
        self.a_t = torch.t(self.a)
        attention_out = self.a_t.mm(torch.t(attention_in)).view(sample_num, sample_num)
        attention_out = self.leaky_relu(attention_out)
        att_weight = self.softmax(attention_out)
        return att_weight

    def forward(self, x):
        out, _ = self.rnn(x)
        hidden = out[:, -1, :]
        att_weight = self.cal_attention(hidden, hidden)
        hidden = att_weight.mm(hidden) + hidden
        hidden = self.fc(hidden)
        hidden = self.leaky_relu(hidden)
        return self.fc_out(hidden).squeeze()

In [6]:

# 本代码由可视化策略环境自动生成 2022年8月12日 22:45
# 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 m33_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 sklearn.model_selection import train_test_split
    # train data
    train_data = input_1.read()
    x_train, x_val, y_train, y_val = train_test_split(train_data["x"], train_data['y'], shuffle=True, random_state=2021)
    # val data
    test_data = input_2.read()
    x_test = test_data["x"]
    
    model = GATModel(d_feat=7, hidden_size=64, num_layers=2, dropout=0.1, base_model="GRU")
    opt = torch.optim.Adam(model.parameters(), lr=1e-3)
    loss = nn.MSELoss()
    model.compile(optimizer=opt, loss=loss, device="cuda:0")
    model.fit(x_train, y_train, validation_data=(x_val, y_val), batch_size=64, epochs=10, verbose=1, num_workers=2)
    
    # model.fit(train_data["x"], train_data['y'], batch_size=1024, epochs=2, verbose=1, num_workers=2)
    output = model.predict(x_test)
    
    data_1 = DataSource.write_pickle(output)
    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 m33_post_run_bigquant_run(outputs):
    return 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 m41_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    pred_label = input_1.read_pickle()
    
    df = input_2.read_df()
    df = pd.DataFrame({'pred_label':pred_label[:], 'instrument':df.instrument, 'date':df.date})
    df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])
    return Outputs(data_1=DataSource.write_df(df), 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 m41_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m1_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.hold_days = 5

# 回测引擎：每日数据处理函数，每天执行一次
def m1_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.hold_days # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.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StockRanker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StockRanker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 m1_prepare_bigquant_run(context):
    pass

# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。
def m1_before_trading_start_bigquant_run(context, data):
    pass


m22 = M.instruments.v2(
    start_date='2020-01-01',
    end_date='2021-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=50
)

m23 = M.advanced_auto_labeler.v2(
    instruments=m22.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, -2) / shift(open, -1) - 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))

# 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=False
)

m5 = M.standardlize.v9(
    input_1=m23.data,
    standard_func='ZScoreNorm',
    columns_input='label'
)

m24 = M.input_features.v1(
    features="""mean(close_0, 5)
mean(low_0, 5)
mean(open_0, 5)
mean(high_0, 5)
mean(turn_0, 5)
mean(amount_0, 5)
mean(return_0, 5)
 
# ts_max(close_0, 5)
# ts_max(low_0, 5)
# ts_max(open_0, 5)
# ts_max(high_0, 5)
# ts_max(turn_0, 5)
# ts_max(amount_0, 5)
# ts_max(return_0, 5)
 
# ts_min(close_0, 5)
# ts_min(low_0, 5)
# ts_min(open_0, 5)
# ts_min(high_0, 5)
# ts_min(turn_0, 5)
# ts_min(amount_0, 5)
# ts_min(return_0, 5) 
 
# std(close_0, 5)
# std(low_0, 5)
# std(open_0, 5)
# std(high_0, 5)
# std(turn_0, 5)
# std(amount_0, 5)
# std(return_0, 5)
 
# ts_rank(close_0, 5)
# ts_rank(low_0, 5)
# ts_rank(open_0, 5)
# ts_rank(high_0, 5)
# ts_rank(turn_0, 5)
# ts_rank(amount_0, 5)
# ts_rank(return_0, 5)
 
# decay_linear(close_0, 5)
# decay_linear(low_0, 5)
# decay_linear(open_0, 5)
# decay_linear(high_0, 5)
# decay_linear(turn_0, 5)
# decay_linear(amount_0, 5)
# decay_linear(return_0, 5)
 
# correlation(volume_0, return_0, 5)
# correlation(volume_0, high_0, 5)
# correlation(volume_0, low_0, 5)
# correlation(volume_0, close_0, 5)
# correlation(volume_0, open_0, 5)
# correlation(volume_0, turn_0, 5)
  
# correlation(return_0, high_0, 5)
# correlation(return_0, low_0, 5)
# correlation(return_0, close_0, 5)
# correlation(return_0, open_0, 5)
# correlation(return_0, turn_0, 5)
 
# correlation(high_0, low_0, 5)
# correlation(high_0, close_0, 5)
# correlation(high_0, open_0, 5)
# correlation(high_0, turn_0, 5)
 
# correlation(low_0, close_0, 5)
# correlation(low_0, open_0, 5)
# correlation(low_0, turn_0, 5)
 
# correlation(close_0, open_0, 5)
# correlation(close_0, turn_0, 5)
# correlation(open_0, turn_0, 5)"""
)

m27 = M.general_feature_extractor.v7(
    instruments=m22.data,
    features=m24.data,
    start_date='',
    end_date='',
    before_start_days=10
)

m3 = M.chinaa_stock_filter.v1(
    input_data=m27.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m28 = M.derived_feature_extractor.v3(
    input_data=m3.data,
    features=m24.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m7 = M.standardlize.v9(
    input_1=m28.data,
    standard_func='ZScoreNorm',
    columns_input=''
)

m35 = M.fillnan.v1(
    input_data=m7.data,
    features=m24.data,
    fill_value='0.0'
)

m25 = M.join.v3(
    data1=m5.data,
    data2=m35.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m2 = M.dl_convert_to_bin.v2(
    input_data=m25.data,
    features=m24.data,
    window_size=20,
    feature_clip=3,
    flatten=False,
    window_along_col='instrument'
)

m26 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2022-01-01'),
    end_date=T.live_run_param('trading_date', '2022-08-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m29 = M.general_feature_extractor.v7(
    instruments=m26.data,
    features=m24.data,
    start_date='',
    end_date='',
    before_start_days=10
)

m4 = M.chinaa_stock_filter.v1(
    input_data=m29.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m30 = M.derived_feature_extractor.v3(
    input_data=m4.data,
    features=m24.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False
)

m36 = M.fillnan.v1(
    input_data=m30.data,
    features=m24.data,
    fill_value='0.0'
)

m32 = M.dl_convert_to_bin.v2(
    input_data=m36.data,
    features=m24.data,
    window_size=20,
    feature_clip=3,
    flatten=False,
    window_along_col='instrument'
)

m33 = M.cached.v3(
    input_1=m2.data,
    input_2=m32.data,
    run=m33_run_bigquant_run,
    post_run=m33_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m41 = M.cached.v3(
    input_1=m33.data_1,
    input_2=m30.data,
    run=m41_run_bigquant_run,
    post_run=m41_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports='',
    m_cached=False
)

m1 = M.trade.v4(
    instruments=m26.data,
    options_data=m41.data_1,
    start_date='',
    end_date='',
    initialize=m1_initialize_bigquant_run,
    handle_data=m1_handle_data_bigquant_run,
    prepare=m1_prepare_bigquant_run,
    before_trading_start=m1_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='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2022-08-12 22:40:57.721692] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-08-12 22:40:57.742772] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.745137] INFO: moduleinvoker: instruments.v2 运行完成[0.023436s].

[2022-08-12 22:40:57.757579] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-08-12 22:40:57.765040] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.767269] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009689s].

[2022-08-12 22:40:57.775325] INFO: moduleinvoker: standardlize.v9 开始运行..

[2022-08-12 22:40:57.785362] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.787326] INFO: moduleinvoker: standardlize.v9 运行完成[0.012006s].

[2022-08-12 22:40:57.792625] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-08-12 22:40:57.798962] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.800843] INFO: moduleinvoker: input_features.v1 运行完成[0.008173s].

[2022-08-12 22:40:57.816895] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-08-12 22:40:57.826480] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.828184] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.011311s].

[2022-08-12 22:40:57.845403] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2022-08-12 22:40:57.862843] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.865907] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[0.020503s].

[2022-08-12 22:40:57.883566] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-08-12 22:40:57.904448] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.906766] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.023219s].

[2022-08-12 22:40:57.922262] INFO: moduleinvoker: standardlize.v9 开始运行..

[2022-08-12 22:40:57.929465] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.931955] INFO: moduleinvoker: standardlize.v9 运行完成[0.009691s].

[2022-08-12 22:40:57.950644] INFO: moduleinvoker: fillnan.v1 开始运行..

[2022-08-12 22:40:57.958449] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.960925] INFO: moduleinvoker: fillnan.v1 运行完成[0.010288s].

[2022-08-12 22:40:57.979890] INFO: moduleinvoker: join.v3 开始运行..

[2022-08-12 22:40:57.991672] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:57.994710] INFO: moduleinvoker: join.v3 运行完成[0.014817s].

[2022-08-12 22:40:58.026879] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2022-08-12 22:40:58.034673] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.037255] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.01042s].

[2022-08-12 22:40:58.055887] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-08-12 22:40:58.063462] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.065923] INFO: moduleinvoker: instruments.v2 运行完成[0.010035s].

[2022-08-12 22:40:58.083998] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-08-12 22:40:58.094276] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.096767] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01282s].

[2022-08-12 22:40:58.106740] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2022-08-12 22:40:58.113319] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.115046] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[0.008308s].

[2022-08-12 22:40:58.124660] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-08-12 22:40:58.137134] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.139985] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.01531s].

[2022-08-12 22:40:58.163774] INFO: moduleinvoker: fillnan.v1 开始运行..

[2022-08-12 22:40:58.180367] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.182991] INFO: moduleinvoker: fillnan.v1 运行完成[0.019215s].

[2022-08-12 22:40:58.200027] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2022-08-12 22:40:58.207201] INFO: moduleinvoker: 命中缓存

[2022-08-12 22:40:58.209360] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[0.009351s].

[2022-08-12 22:40:58.226588] INFO: moduleinvoker: cached.v3 开始运行..

[2022-08-12 22:41:46.364544] INFO: moduleinvoker: cached.v3 运行完成[48.137948s].

[2022-08-12 22:41:46.380701] INFO: moduleinvoker: cached.v3 开始运行..

[2022-08-12 22:41:47.673124] INFO: moduleinvoker: cached.v3 运行完成[1.292425s].

[2022-08-12 22:41:51.994525] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-08-12 22:41:52.000421] INFO: backtest: biglearning backtest:V8.6.2

[2022-08-12 22:41:52.002181] INFO: backtest: product_type:stock by specified

[2022-08-12 22:41:52.160111] INFO: moduleinvoker: cached.v2 开始运行..

[2022-08-12 22:41:57.752360] INFO: backtest: 读取股票行情完成:1910526

[2022-08-12 22:41:59.626205] INFO: moduleinvoker: cached.v2 运行完成[7.466103s].

[2022-08-12 22:42:01.608836] INFO: algo: TradingAlgorithm V1.8.8

[2022-08-12 22:42:02.333832] INFO: algo: trading transform...

[2022-08-12 22:42:04.864989] INFO: algo: handle_splits get splits [dt:2022-06-08 00:00:00+00:00] [asset:Equity(216 [600015.SHA]), ratio:0.9371534585952759]

[2022-08-12 22:42:04.866751] INFO: Position: position stock handle split[sid:216, orig_amount:8300, new_amount:8856.0, orig_cost:5.389999895252912, new_cost:5.0513, ratio:0.9371534585952759, last_sale_price:5.070000171661377]

[2022-08-12 22:42:04.867991] INFO: Position: after split: PositionStock(asset:Equity(216 [600015.SHA]), amount:8856.0, cost_basis:5.0513, last_sale_price:5.409999847412109)

[2022-08-12 22:42:04.869066] INFO: Position: returning cash: 3.0781

[2022-08-12 22:42:05.053373] INFO: algo: handle_splits get splits [dt:2022-06-17 00:00:00+00:00] [asset:Equity(1878 [601808.SHA]), ratio:0.9901641607284546]

[2022-08-12 22:42:05.055654] INFO: Position: position stock handle split[sid:1878, orig_amount:2600, new_amount:2625.0, orig_cost:15.640001335193405, new_cost:15.4862, ratio:0.9901641607284546, last_sale_price:15.100003242492676]

[2022-08-12 22:42:05.057634] INFO: Position: after split: PositionStock(asset:Equity(1878 [601808.SHA]), amount:2625.0, cost_basis:15.4862, last_sale_price:15.25)

[2022-08-12 22:42:05.059371] INFO: Position: returning cash: 12.4909

[2022-08-12 22:42:05.178394] INFO: algo: handle_splits get splits [dt:2022-06-24 00:00:00+00:00] [asset:Equity(2100 [600016.SHA]), ratio:0.9465648531913757]

[2022-08-12 22:42:05.180943] INFO: Position: position stock handle split[sid:2100, orig_amount:11600, new_amount:12254.0, orig_cost:3.899999862316263, new_cost:3.6916, ratio:0.9465648531913757, last_sale_price:3.7200000286102295]

[2022-08-12 22:42:05.183440] INFO: Position: after split: PositionStock(asset:Equity(2100 [600016.SHA]), amount:12254.0, cost_basis:3.6916, last_sale_price:3.930000066757202)

[2022-08-12 22:42:05.186069] INFO: Position: returning cash: 3.1216

[2022-08-12 22:42:05.542056] INFO: algo: handle_splits get splits [dt:2022-07-15 00:00:00+00:00] [asset:Equity(2433 [601988.SHA]), ratio:0.9318886995315552]

[2022-08-12 22:42:05.543742] INFO: Position: position stock handle split[sid:2433, orig_amount:65800, new_amount:70609.0, orig_cost:3.100820476585074, new_cost:2.8896, ratio:0.9318886995315552, last_sale_price:3.010000228881836]

[2022-08-12 22:42:05.545168] INFO: Position: after split: PositionStock(asset:Equity(2433 [601988.SHA]), amount:70609.0, cost_basis:2.8896, last_sale_price:3.2299997806549072)

[2022-08-12 22:42:05.546831] INFO: Position: returning cash: 0.8747

[2022-08-12 22:42:05.726834] INFO: algo: handle_splits get splits [dt:2022-07-29 00:00:00+00:00] [asset:Equity(4282 [601816.SHA]), ratio:0.9894955158233643]

[2022-08-12 22:42:05.728750] INFO: Position: position stock handle split[sid:4282, orig_amount:43900, new_amount:44366.0, orig_cost:4.8415719943163555, new_cost:4.7907, ratio:0.9894955158233643, last_sale_price:4.709998607635498]

[2022-08-12 22:42:05.730347] INFO: Position: after split: PositionStock(asset:Equity(4282 [601816.SHA]), amount:44366.0, cost_basis:4.7907, last_sale_price:4.759999752044678)

[2022-08-12 22:42:05.731792] INFO: Position: returning cash: 0.1997

[2022-08-12 22:42:05.777252] INFO: Performance: Simulated 139 trading days out of 139.

[2022-08-12 22:42:05.778992] INFO: Performance: first open: 2022-01-04 09:30:00+00:00

[2022-08-12 22:42:05.780404] INFO: Performance: last close: 2022-08-01 15:00:00+00:00

[2022-08-12 22:42:10.179755] INFO: moduleinvoker: backtest.v8 运行完成[18.185236s].

[2022-08-12 22:42:10.182077] INFO: moduleinvoker: trade.v4 运行完成[22.4894s].

epoch 0   |  train_loss 0.97197|  vall_loss 0.97242|  0:00:04s
epoch 1   |  train_loss 0.97166|  vall_loss 0.96965|  0:00:09s
epoch 2   |  train_loss 0.97148|  vall_loss 0.96694|  0:00:14s
epoch 3   |  train_loss 0.97132|  vall_loss 0.96963|  0:00:19s
epoch 4   |  train_loss 0.96987|  vall_loss 0.96628|  0:00:23s
epoch 5   |  train_loss 0.97063|  vall_loss 0.96766|  0:00:27s
epoch 6   |  train_loss 0.97023|  vall_loss 0.96606|  0:00:31s
epoch 7   |  train_loss 0.96970|  vall_loss 0.96546|  0:00:34s
epoch 8   |  train_loss 0.97047|  vall_loss 0.96575|  0:00:37s
epoch 9   |  train_loss 0.97098|  vall_loss 0.96461|  0:00:40s

收益率3.19%
年化收益率5.86%
基准收益率-15.22%
阿尔法0.15
贝塔0.36
夏普比率0.29
胜率0.52
盈亏比1.2
收益波动率11.91%
信息比率0.13
最大回撤7.8%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-ab8c12621c2d41f289edee01d77d5923"}/bigcharts-data-end

In [ ]: