复制链接

克隆策略

In [2]:

# 本代码由可视化策略环境自动生成 2022年9月19日 20:05
# 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。


def ts_delay(df,f,d):
    return df[f].shift(d)
def ts_std(df,f,d):
    return df[f].rolling(d).std()
def ts_mean(df,f,d):
    return df[f].rolling(d).mean()
def beta(df,d):
    benchmark = ['000300.SHA']  # 以沪深300为基准计算beta值
    benchmark_df=D.history_data(benchmark,fields=['close'],start_date='2015-01-01',end_date='2020-01-01')
    df["close_pct"]=df['close'].pct_change()
    benchmark_df["close_pct"]=benchmark_df['close'].pct_change()
    return (df['close_pct'].rolling(d).cov(benchmark_df['close_pct']))/benchmark_df['close_pct'].rolling(d).var()
m17_user_functions_bigquant_run = {
    'beta':beta,
    'ts_delay':ts_delay,
    'ts_mean':ts_mean,
    'ts_std':ts_std,
}
def ts_delay(df,f,d):
    return df[f].shift(d)
def ts_std(df,f,d):
    return df[f].rolling(d).std()
def ts_mean(df,f,d):
    return df[f].rolling(d).mean()
def beta(df,d):
    benchmark = ['000300.SHA']  # 以沪深300为基准计算beta值
    benchmark_df=D.history_data(benchmark,fields=['close'],start_date='2020-11-01',end_date='2021-12-31')
    df["close_pct"]=df['close'].pct_change()
    benchmark_df["close_pct"]=benchmark_df['close'].pct_change()
    return (df['close_pct'].rolling(d).cov(benchmark_df['close_pct']))/benchmark_df['close_pct'].rolling(d).var()
m21_user_functions_bigquant_run = {
    'beta':beta,
    'ts_delay':ts_delay,
    'ts_mean':ts_mean,
    'ts_std':ts_std,
}
# 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 m26_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df_train = input_1.read_df()
    features = input_2.read_pickle()
    df_test = input_3.read_df()
    from sklearn.preprocessing import MinMaxScaler
    scaler=MinMaxScaler()
    df_train[features]=scaler.fit_transform(df_train[features])
    df_test[features]=scaler.transform(df_test[features])
    return Outputs(data_1=DataSource.write_df(df_train), data_2=input_2, data_3=DataSource.write_df(df_test))

# 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 m26_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 m24_run_bigquant_run(input_1=None, input_2=None, input_3=None):
    from sklearn.metrics import balanced_accuracy_score,accuracy_score
    # 示例代码如下。在这里编写您的代码
    if input_1!=None:
        df1 = input_1.read_df()
        print(df1.head())
        print('RandomForest BCA: ',balanced_accuracy_score(df1['label'],df1['pred_label']))
    if input_2!=None:
        df2 = input_2.read_df()
        print(df2.head())
        print('LogisticRegression BCA: ',balanced_accuracy_score(df2['label'],df2['pred_label']))
    if input_3!=None:
        df3 = input_3.read_df()
        print(df3.head())
        print('SVC BCA: ',balanced_accuracy_score(df3['label'],df3['pred_label']))
    return Outputs(data_1=input_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 m24_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')]
    today=data.current_dt.strftime('%Y-%m-%d')
    benckmark_risk=ranker_prediction[ranker_prediction.instrument=='000001.HIX']
    stock_hold_now = [equity.symbol for equity in context.portfolio.positions ]
    # 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()}
    if len(benckmark_risk)>0:
        if benckmark_risk.classes_prob_True.iloc[0] < 0.3:
            cash_for_sell*=3
    # 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 m14_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2005-01-01',
    end_date='2016-01-01',
    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/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.input_features.v1(
    features_ds=m3.data,
    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

# 未来2天的 收益
day_return_2=(shift(close_0, -2)-shift(open_0, -1))/shift(open_0, -1)
# 未来3天的 收益
day_return_3=(shift(close_0, -3)-shift(open_0, -1))/shift(open_0, -1)
# 未来5天的 收益
day_return_5=(shift(close_0, -5)-shift(open_0, -1))/shift(open_0, -1)"""
)

m10 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m15.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m11 = M.derived_feature_extractor.v3(
    input_data=m10.data,
    features=m15.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m5 = M.join.v3(
    data1=m2.data,
    data2=m11.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m8 = M.dropnan.v1(
    input_data=m5.data
)

m4 = M.stock_ranker_train.v5(
    training_ds=m8.data,
    features=m3.data,
    test_ds=m8.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,
    m_lazy_run=False
)

m7 = M.instruments.v2(
    start_date='2021-01-01',
    end_date='2021-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m12 = M.general_feature_extractor.v7(
    instruments=m7.data,
    features=m15.data,
    start_date='',
    end_date='',
    before_start_days=90
)

m13 = M.derived_feature_extractor.v3(
    input_data=m12.data,
    features=m15.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m9 = M.dropnan.v1(
    input_data=m13.data
)

m6 = M.stock_ranker_predict.v5(
    model=m4.model,
    data=m9.data,
    m_lazy_run=False
)

m16 = M.use_datasource.v1(
    datasource_id='bar1d_index_CN_STOCK_A',
    start_date='2015-01-01',
    end_date='2020-01-01'
)

m18 = M.filter.v3(
    input_data=m16.data,
    expr='instrument==\'000001.HIX\'',
    output_left_data=False
)

m19 = M.input_features.v1(
    features="""volume=volume
#close 衍生特征
close
ma_10=ts_mean('close',10)
ma_20=ts_mean('close',20)
ma_50=ts_mean('close',50)
#return 衍生特征
return_1=close/ts_delay('close',1)
return_5=close/ts_delay('close',5)
return_10=close/ts_delay('close',10)
return_20=close/ts_delay('close',20)
return_1/return_5
return_5/return_10
return_10/return_20
# Beta
beta_10=beta(10)
beta_20=beta(20)
beta_50=beta(50)
label = close-ts_delay('close',-10)<0
"""
)

m17 = M.derived_feature_extractor.v3(
    input_data=m18.data,
    features=m19.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=False,
    user_functions=m17_user_functions_bigquant_run
)

m20 = M.use_datasource.v1(
    datasource_id='bar1d_index_CN_STOCK_A',
    start_date='2020-11-01',
    end_date='2021-12-31'
)

m22 = M.filter.v3(
    input_data=m20.data,
    expr='instrument==\'000001.HIX\'',
    output_left_data=False
)

m21 = M.derived_feature_extractor.v3(
    input_data=m22.data,
    features=m19.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=True,
    remove_extra_columns=True,
    user_functions=m21_user_functions_bigquant_run
)

m23 = M.dropnan.v2(
    input_data=m21.data
)

m27 = M.input_features.v1(
    features="""volume
#close 衍生特征
close
ma_10
ma_20
ma_50
#return 衍生特征
return_1
return_5
return_10
return_20
return_1/return_5
return_5/return_10
return_10/return_20
# Beta
beta_10
beta_20
beta_50
"""
)

m26 = M.cached.v3(
    input_1=m17.data,
    input_2=m27.data,
    input_3=m23.data,
    run=m26_run_bigquant_run,
    post_run=m26_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m25 = M.random_forest_classifier.v1(
    training_ds=m26.data_1,
    features=m26.data_2,
    predict_ds=m26.data_3,
    iterations=1000,
    feature_fraction=1,
    max_depth=30,
    min_samples_per_leaf=10,
    key_cols='date,instrument',
    workers=1,
    random_state=0,
    other_train_parameters={}
)

m24 = M.cached.v3(
    input_1=m25.predictions,
    run=m24_run_bigquant_run,
    post_run=m24_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports='',
    m_cached=False
)

m28 = M.concat.v3(
    input_data_1=m6.predictions,
    input_data_2=m24.data_1
)

m14 = M.trade.v4(
    instruments=m7.data,
    options_data=m28.data,
    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='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2022-09-19 20:04:23.391821] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-09-19 20:04:23.400728] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.402760] INFO: moduleinvoker: instruments.v2 运行完成[0.010964s].

[2022-09-19 20:04:23.418349] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2022-09-19 20:04:23.425299] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.427856] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009513s].

[2022-09-19 20:04:23.432485] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-09-19 20:04:23.438305] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.439538] INFO: moduleinvoker: input_features.v1 运行完成[0.007058s].

[2022-09-19 20:04:23.443349] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-09-19 20:04:23.448470] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.449660] INFO: moduleinvoker: input_features.v1 运行完成[0.006314s].

[2022-09-19 20:04:23.469380] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-09-19 20:04:23.480030] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.481530] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012168s].

[2022-09-19 20:04:23.493040] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-09-19 20:04:23.500359] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.504194] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.011105s].

[2022-09-19 20:04:23.522630] INFO: moduleinvoker: join.v3 开始运行..

[2022-09-19 20:04:23.530439] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.532581] INFO: moduleinvoker: join.v3 运行完成[0.009928s].

[2022-09-19 20:04:23.542678] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-09-19 20:04:23.549394] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.550776] INFO: moduleinvoker: dropnan.v1 运行完成[0.0081s].

[2022-09-19 20:04:23.558792] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2022-09-19 20:04:23.573534] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.694578] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[0.135763s].

[2022-09-19 20:04:23.703773] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-09-19 20:04:23.711014] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.714460] INFO: moduleinvoker: instruments.v2 运行完成[0.010697s].

[2022-09-19 20:04:23.733947] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-09-19 20:04:23.741329] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.743035] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.00911s].

[2022-09-19 20:04:23.751899] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-09-19 20:04:23.758941] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.761019] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009125s].

[2022-09-19 20:04:23.785709] INFO: moduleinvoker: dropnan.v1 开始运行..

[2022-09-19 20:04:23.793579] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.797635] INFO: moduleinvoker: dropnan.v1 运行完成[0.011959s].

[2022-09-19 20:04:23.813018] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-09-19 20:04:23.826690] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.828848] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.015836s].

[2022-09-19 20:04:23.835144] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-09-19 20:04:23.841443] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.843269] INFO: moduleinvoker: use_datasource.v1 运行完成[0.00813s].

[2022-09-19 20:04:23.852309] INFO: moduleinvoker: filter.v3 开始运行..

[2022-09-19 20:04:23.857727] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.859017] INFO: moduleinvoker: filter.v3 运行完成[0.006712s].

[2022-09-19 20:04:23.862654] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-09-19 20:04:23.867339] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.868553] INFO: moduleinvoker: input_features.v1 运行完成[0.005902s].

[2022-09-19 20:04:23.879457] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-09-19 20:04:23.897001] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.900753] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.0213s].

[2022-09-19 20:04:23.911585] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-09-19 20:04:23.922396] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.924113] INFO: moduleinvoker: use_datasource.v1 运行完成[0.012563s].

[2022-09-19 20:04:23.933065] INFO: moduleinvoker: filter.v3 开始运行..

[2022-09-19 20:04:23.943364] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:23.945426] INFO: moduleinvoker: filter.v3 运行完成[0.012356s].

[2022-09-19 20:04:23.956489] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-09-19 20:04:24.029279] INFO: derived_feature_extractor: 提取完成 volume=volume, 0.000s

[2022-09-19 20:04:24.033297] INFO: derived_feature_extractor: 提取完成 ma_10=ts_mean('close',10), 0.002s

[2022-09-19 20:04:24.036249] INFO: derived_feature_extractor: 提取完成 ma_20=ts_mean('close',20), 0.001s

[2022-09-19 20:04:24.038640] INFO: derived_feature_extractor: 提取完成 ma_50=ts_mean('close',50), 0.001s

[2022-09-19 20:04:24.041234] INFO: derived_feature_extractor: 提取完成 return_1=close/ts_delay('close',1), 0.001s

[2022-09-19 20:04:24.043412] INFO: derived_feature_extractor: 提取完成 return_5=close/ts_delay('close',5), 0.001s

[2022-09-19 20:04:24.045566] INFO: derived_feature_extractor: 提取完成 return_10=close/ts_delay('close',10), 0.001s

[2022-09-19 20:04:24.047742] INFO: derived_feature_extractor: 提取完成 return_20=close/ts_delay('close',20), 0.001s

[2022-09-19 20:04:24.050107] INFO: derived_feature_extractor: 提取完成 return_1/return_5, 0.001s

[2022-09-19 20:04:24.052532] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.001s

[2022-09-19 20:04:24.054882] INFO: derived_feature_extractor: 提取完成 return_10/return_20, 0.001s

[2022-09-19 20:04:25.015102] INFO: derived_feature_extractor: 提取完成 beta_10=beta(10), 0.959s

[2022-09-19 20:04:25.909909] INFO: derived_feature_extractor: 提取完成 beta_20=beta(20), 0.893s

[2022-09-19 20:04:26.797908] INFO: derived_feature_extractor: 提取完成 beta_50=beta(50), 0.884s

[2022-09-19 20:04:26.805076] INFO: derived_feature_extractor: 提取完成 label = close-ts_delay('close',-10)<0, 0.003s

[2022-09-19 20:04:26.900569] INFO: derived_feature_extractor: /data, 287

[2022-09-19 20:04:26.993170] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[3.036652s].

[2022-09-19 20:04:27.010832] INFO: moduleinvoker: dropnan.v2 开始运行..

[2022-09-19 20:04:27.117135] INFO: dropnan: /data, 237/237

[2022-09-19 20:04:27.180072] INFO: dropnan: 行数: 237/237

[2022-09-19 20:04:27.186198] INFO: moduleinvoker: dropnan.v2 运行完成[0.175346s].

[2022-09-19 20:04:27.198444] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-09-19 20:04:27.206454] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:27.209845] INFO: moduleinvoker: input_features.v1 运行完成[0.01142s].

[2022-09-19 20:04:27.227103] INFO: moduleinvoker: cached.v3 开始运行..

[2022-09-19 20:04:27.481586] INFO: moduleinvoker: cached.v3 运行完成[0.254488s].

[2022-09-19 20:04:27.492809] INFO: moduleinvoker: random_forest_classifier.v1 开始运行..

[2022-09-19 20:04:31.806645] INFO: moduleinvoker: random_forest_classifier.v1 运行完成[4.313821s].

[2022-09-19 20:04:31.825130] INFO: moduleinvoker: cached.v3 开始运行..

[2022-09-19 20:04:31.863826] INFO: moduleinvoker: cached.v3 运行完成[0.038705s].

[2022-09-19 20:04:31.879122] INFO: moduleinvoker: concat.v3 开始运行..

[2022-09-19 20:04:32.159703] INFO: concat: 合并: /data, 行数=1266240

[2022-09-19 20:04:32.191842] INFO: concat: 合并: /data, 行数=237

[2022-09-19 20:04:33.094858] INFO: moduleinvoker: concat.v3 运行完成[1.215705s].

[2022-09-19 20:04:33.160154] INFO: moduleinvoker: backtest.v8 开始运行..

[2022-09-19 20:04:33.164803] INFO: backtest: biglearning backtest:V8.6.3

[2022-09-19 20:04:33.166626] INFO: backtest: product_type:stock by specified

[2022-09-19 20:04:33.406333] INFO: moduleinvoker: cached.v2 开始运行..

[2022-09-19 20:04:33.418327] INFO: moduleinvoker: 命中缓存

[2022-09-19 20:04:33.420835] INFO: moduleinvoker: cached.v2 运行完成[0.01449s].

[2022-09-19 20:04:45.518153] INFO: backtest: algo history_data=DataSource(f55f4d02ef3945779e65cae2d440741dT)

[2022-09-19 20:04:45.520412] INFO: algo: TradingAlgorithm V1.8.8

[2022-09-19 20:04:51.149807] INFO: algo: trading transform...

[2022-09-19 20:04:53.308191] WARNING: Performance: maybe_close_position no price for asset:Equity(3567 [600086.SHA]), field:price, dt:2021-03-17 15:00:00+00:00

[2022-09-19 20:04:53.945840] WARNING: Performance: maybe_close_position no price for asset:Equity(614 [000662.SZA]), field:price, dt:2021-04-12 15:00:00+00:00

[2022-09-19 20:04:55.327495] INFO: algo: handle_splits get splits [dt:2021-06-11 00:00:00+00:00] [asset:Equity(4842 [002679.SZA]), ratio:0.9986478090286255]

[2022-09-19 20:04:55.330746] INFO: Position: position stock handle split[sid:4842, orig_amount:3300, new_amount:3304.0, orig_cost:21.590000164433643, new_cost:21.5608, ratio:0.9986478090286255, last_sale_price:22.159996032714844]

[2022-09-19 20:04:55.332275] INFO: Position: after split: PositionStock(asset:Equity(4842 [002679.SZA]), amount:3304.0, cost_basis:21.5608, last_sale_price:22.190000534057617)

[2022-09-19 20:04:55.333391] INFO: Position: returning cash: 10.3769

[2022-09-19 20:04:55.481021] INFO: algo: handle_splits get splits [dt:2021-06-18 00:00:00+00:00] [asset:Equity(5547 [603223.SHA]), ratio:0.9948556423187256]

[2022-09-19 20:04:56.175630] WARNING: Performance: maybe_close_position no price for asset:Equity(2304 [002711.SZA]), field:price, dt:2021-07-15 15:00:00+00:00

[2022-09-19 20:04:56.617858] WARNING: Performance: maybe_close_position no price for asset:Equity(970 [600614.SHA]), field:price, dt:2021-07-21 15:00:00+00:00

[2022-09-19 20:04:56.619991] WARNING: Performance: maybe_close_position no price for asset:Equity(2189 [600634.SHA]), field:price, dt:2021-07-21 15:00:00+00:00

[2022-09-19 20:05:00.298654] INFO: algo: handle_splits get splits [dt:2021-12-27 00:00:00+00:00] [asset:Equity(4351 [831445.BJA]), ratio:0.9913643002510071]

[2022-09-19 20:05:00.302727] INFO: Position: position stock handle split[sid:4351, orig_amount:3800, new_amount:3833.0, orig_cost:22.400066674034942, new_cost:22.2066, ratio:0.9913643002510071, last_sale_price:17.219999313354492]

[2022-09-19 20:05:00.305610] INFO: Position: after split: PositionStock(asset:Equity(4351 [831445.BJA]), amount:3833.0, cost_basis:22.2066, last_sale_price:17.3700008392334)

[2022-09-19 20:05:00.307021] INFO: Position: returning cash: 1.7481

[2022-09-19 20:05:00.426978] INFO: Performance: Simulated 243 trading days out of 243.

[2022-09-19 20:05:00.428812] INFO: Performance: first open: 2021-01-04 09:30:00+00:00

[2022-09-19 20:05:00.430290] INFO: Performance: last close: 2021-12-31 15:00:00+00:00

[2022-09-19 20:05:06.590723] INFO: moduleinvoker: backtest.v8 运行完成[33.430541s].

[2022-09-19 20:05:06.594351] INFO: moduleinvoker: trade.v4 运行完成[33.485586s].

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-6a14457a4c8041ac9945ec374ac41af9"}/bigcharts-data-end

    pred_label  classes_prob_False  classes_prob_True       date  instrument  \
50       False            0.633125           0.366875 2021-01-12  000001.HIX   
51       False            0.680768           0.319232 2021-01-13  000001.HIX   
52       False            0.696769           0.303231 2021-01-14  000001.HIX   
53       False            0.697397           0.302603 2021-01-15  000001.HIX   
54       False            0.703993           0.296007 2021-01-18  000001.HIX   

    label  
50      0  
51      0  
52      0  
53      0  
54      0  
RandomForest BCA:  0.5

收益率175.55%
年化收益率186.09%
基准收益率-5.2%
阿尔法1.94
贝塔0.31
夏普比率3.95
胜率0.58
盈亏比1.43
收益波动率26.83%
信息比率0.24
最大回撤10.78%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-9e4d9d0f970d48ee88a89f44e33adb99"}/bigcharts-data-end