克隆策略

In [5]:

# 本代码由可视化策略环境自动生成 2021年10月29日 11:26
# 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 m6_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 = input_1.read_df()
    ins = m1.data.read_pickle()['instruments']
    start = m1.data.read_pickle()['start_date']
    end = m1.data.read_pickle()['end_date']
    
    df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])
    df_final = pd.merge(df,df1,on=['date','instrument'])
    df_final = df_final[df_final['instrument'].str.startswith("688") == False]
    df_final = df_final[df_final['instrument'].str.startswith("3") == False]

    df_final = df_final[df_final["st_status_0"] == 0]
    df_final = df_final[df_final['rank_turn_0'] >= 0.9]
    df_final = df_final[df_final['rank_amount_0'] >= 0.85]
    print("用于训练的样本总个数为",len(df_final))
    print(df_final.iloc[0])
    data_1 = DataSource.write_df(df_final)
    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 m6_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 m8_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 = input_1.read_df()
    ins = m9.data.read_pickle()['instruments']
    start = m9.data.read_pickle()['start_date']
    end = m9.data.read_pickle()['end_date']
    
    df1 = D.features(ins,start,end,fields=['rank_turn_0','rank_amount_0','st_status_0'])
    df_final = pd.merge(df,df1,on=['date','instrument'])
    df_final = df_final[df_final['instrument'].str.startswith("688") == False]
    df_final = df_final[df_final['instrument'].str.startswith("3") == False]

    df_final = df_final[df_final["st_status_0"] == 0]
    df_final = df_final[df_final['rank_turn_0'] >= 0.9]
    df_final = df_final[df_final['rank_amount_0'] >= 0.85]
    print("用于回测的样本总个数为",len(df_final))
    data_1 = DataSource.write_df(df_final)
    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 m8_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 = 4
    # 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 = [1 / stock_count 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 = 1
    context.options['hold_days'] = 1

# 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()}
        tmp = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        instruments = equities
#         # print('rank order for sell %s' % instruments)
        for instrument in instruments:
#             if instrument in tmp:
#                 print("涨停,不卖出",instrument)
#                 continue
            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


g = T.Graph({

    'm1': 'M.instruments.v2',
    'm1.start_date': '2010-01-01',
    'm1.end_date': '2015-1-01',
    'm1.market': 'CN_STOCK_A',
    'm1.instrument_list': '',
    'm1.max_count': 0,

    'm2': 'M.advanced_auto_labeler.v2',
    'm2.instruments': T.Graph.OutputPort('m1.data'),
    'm2.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)

# 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)
""",
    'm2.start_date': '',
    'm2.end_date': '',
    'm2.benchmark': '000300.SHA',
    'm2.drop_na_label': True,
    'm2.cast_label_int': True,

    'm3': 'M.input_features.v1',
    'm3.features': """return_5
return_10
return_20
avg_amount_5/avg_amount_10
return_5/return_10
ta_cci_14_0
turn_5/avg_turn_10
avg_amount_0/avg_amount_5
swing_volatility_5_0/swing_volatility_60_0
amount_10/amount_30
rank_volatility_10_0
return_0
ta_ema_5_0/close_0
close_0/low_0
ta_ema_20_0/close_0
open_0/close_1
high_1/close_0
ta_ema_30_0/close_0
ta_rsi(close_0, 6)
amount_0/amount_1
# return_1""",

    'm15': 'M.general_feature_extractor.v7',
    'm15.instruments': T.Graph.OutputPort('m1.data'),
    'm15.features': T.Graph.OutputPort('m3.data'),
    'm15.start_date': '',
    'm15.end_date': '',
    'm15.before_start_days': 0,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m15.data'),
    'm16.features': T.Graph.OutputPort('m3.data'),
    'm16.date_col': 'date',
    'm16.instrument_col': 'instrument',
    'm16.drop_na': False,
    'm16.remove_extra_columns': False,

    'm7': 'M.join.v3',
    'm7.data1': T.Graph.OutputPort('m2.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm6': 'M.cached.v3',
    'm6.input_1': T.Graph.OutputPort('m7.data'),
    'm6.run': m6_run_bigquant_run,
    'm6.post_run': m6_post_run_bigquant_run,
    'm6.input_ports': '',
    'm6.params': '{}',
    'm6.output_ports': '',

    'm4': 'M.dropnan.v2',
    'm4.input_data': T.Graph.OutputPort('m6.data_1'),

    'm9': 'M.instruments.v2',
    'm9.start_date': T.live_run_param('trading_date', '2015-01-01'),
    'm9.end_date': T.live_run_param('trading_date', '2021-08-20'),
    'm9.market': 'CN_STOCK_A',
    'm9.instrument_list': '',
    'm9.max_count': 0,

    'm17': 'M.general_feature_extractor.v7',
    'm17.instruments': T.Graph.OutputPort('m9.data'),
    'm17.features': T.Graph.OutputPort('m3.data'),
    'm17.start_date': '',
    'm17.end_date': '',
    'm17.before_start_days': 90,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m17.data'),
    'm18.features': T.Graph.OutputPort('m3.data'),
    'm18.date_col': 'date',
    'm18.instrument_col': 'instrument',
    'm18.drop_na': False,
    'm18.remove_extra_columns': False,

    'm8': 'M.cached.v3',
    'm8.input_1': T.Graph.OutputPort('m18.data'),
    'm8.run': m8_run_bigquant_run,
    'm8.post_run': m8_post_run_bigquant_run,
    'm8.input_ports': '',
    'm8.params': '{}',
    'm8.output_ports': '',

    'm5': 'M.dropnan.v2',
    'm5.input_data': T.Graph.OutputPort('m8.data_1'),

    'm10': 'M.lightgbm.v2',
    'm10.training_ds': T.Graph.OutputPort('m4.data'),
    'm10.features': T.Graph.OutputPort('m3.data'),
    'm10.predict_ds': T.Graph.OutputPort('m5.data'),
    'm10.num_boost_round': 79,
    'm10.objective': '排序(ndcg)',
    'm10.num_class': 1,
    'm10.num_leaves': 60,
    'm10.learning_rate': 0.1,
    'm10.min_data_in_leaf': 900,
    'm10.max_bin': 1023,
    'm10.key_cols': 'date,instrument',
    'm10.group_col': 'date',
    'm10.random_seed': 101,
    'm10.other_train_parameters': {'n_jobs':4,'label_gain':','.join([str(x) for x in range(20)]),"max_position":29,"eval_at":"1,3,5,10"},

    'm19': 'M.trade.v4',
    'm19.instruments': T.Graph.OutputPort('m9.data'),
    'm19.options_data': T.Graph.OutputPort('m10.predictions'),
    'm19.start_date': '',
    'm19.end_date': '',
    'm19.initialize': m19_initialize_bigquant_run,
    'm19.handle_data': m19_handle_data_bigquant_run,
    'm19.prepare': m19_prepare_bigquant_run,
    'm19.volume_limit': 0.025,
    'm19.order_price_field_buy': 'open',
    'm19.order_price_field_sell': 'open',
    'm19.capital_base': 12000,
    'm19.auto_cancel_non_tradable_orders': True,
    'm19.data_frequency': 'daily',
    'm19.price_type': '真实价格',
    'm19.product_type': '股票',
    'm19.plot_charts': True,
    'm19.backtest_only': False,
    'm19.benchmark': '000300.SHA',
})

# g.run({})


def m11_run_bigquant_run(
    bq_graph,
    inputs,
    trading_days_market='CN', # 使用那个市场的交易日历, TODO
    train_instruments_mid='m1', # 训练数据 证券代码列表 模块id
    test_instruments_mid='m9', # 测试数据 证券代码列表 模块id
    predict_mid='m10', # 预测 模块id
    trade_mid='m19', # 回测 模块id
    start_date='2015-01-01', # 数据开始日期
    end_date=T.live_run_param('trading_date', '2021-01-01'), # 数据结束日期
    train_update_days=250, # 更新周期，按交易日计算，每多少天更新一次
    train_update_days_for_live=None, #模拟实盘模式下的更新周期，按交易日计算，每多少天更新一次。如果需要在模拟实盘阶段使用不同的模型更新周期，可以设置这个参数
    train_data_min_days=250, # 最小数据天数，按交易日计算，所以第一个滚动的结束日期是 从开始日期到开始日期+最小数据天数
    train_data_max_days=250, # 最大数据天数，按交易日计算，0，表示没有限制，否则每一个滚动的开始日期=max(此滚动的结束日期-最大数据天数, 开始日期
    rolling_count_for_live=1, #实盘模式下滚动次数，模拟实盘模式下，取最后多少次滚动。一般在模拟实盘模式下，只用到最后一次滚动训练的模型，这里可以设置为1；如果你的滚动训练数据时间段很短，以至于期间可能没有训练数据，这里可以设置大一点。0表示没有限制
):
    def merge_datasources(input_1):
        df_list = [ds[0].read_df().set_index('date').loc[ds[1]:].reset_index() for ds in input_1]
        df = pd.concat(df_list)
        instrument_data = {
            'start_date': df['date'].min().strftime('%Y-%m-%d'),
            'end_date': df['date'].max().strftime('%Y-%m-%d'),
            'instruments': list(set(df['instrument'])),
        }
        return Outputs(data=DataSource.write_df(df), instrument_data=DataSource.write_pickle(instrument_data))

    def gen_rolling_dates(trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live):
        # 是否实盘模式
        tdays = list(D.trading_days(market=trading_days_market, start_date=start_date, end_date=end_date)['date'])
        is_live_run = T.live_run_param('trading_date', None) is not None

        if is_live_run and train_update_days_for_live:
            train_update_days = train_update_days_for_live

        rollings = []
        train_end_date = train_data_min_days
        while train_end_date < len(tdays):
            if train_data_max_days is not None and train_data_max_days > 0:
                train_start_date = max(train_end_date - train_data_max_days, 0)
            else:
                train_start_date = 0
            rollings.append({
                'train_start_date': tdays[train_start_date].strftime('%Y-%m-%d'),
                'train_end_date': tdays[train_end_date - 1].strftime('%Y-%m-%d'),
                'test_start_date': tdays[train_end_date].strftime('%Y-%m-%d'),
                'test_end_date': tdays[min(train_end_date + train_update_days, len(tdays)) - 1].strftime('%Y-%m-%d'),
            })
            train_end_date += train_update_days

        if not rollings:
            raise Exception('没有滚动需要执行，请检查配置')

        if is_live_run and rolling_count_for_live:
            rollings = rollings[-rolling_count_for_live:]

        return rollings

    g = bq_graph

    rolling_dates = gen_rolling_dates(
        trading_days_market, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)

    # 训练和预测
    results = []
    for rolling in rolling_dates:
        parameters = {}
        # 先禁用回测
        parameters[trade_mid + '.__enabled__'] = False
        parameters[train_instruments_mid + '.start_date'] = rolling['train_start_date']
        parameters[train_instruments_mid + '.end_date'] = rolling['train_end_date']
        parameters[test_instruments_mid + '.start_date'] = rolling['test_start_date']
        parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']
        # print('------ rolling_train:', parameters)
        results.append(g.run(parameters))

    # 合并预测结果并回测
    mx = M.cached.v3(run=merge_datasources, input_1=[[result[predict_mid].predictions, result[test_instruments_mid].data.read_pickle()['start_date']] for result in results])
    parameters = {}
    parameters['*.__enabled__'] = False
    parameters[trade_mid + '.__enabled__'] = True
    parameters[trade_mid + '.instruments'] = mx.instrument_data
    parameters[trade_mid + '.options_data'] = mx.data

    trade = g.run(parameters)

    return {'rollings': results, 'trade': trade}


m11 = M.hyper_rolling_train.v1(
    run=m11_run_bigquant_run,
    run_now=True,
    bq_graph=g
)

[2021-10-29 11:21:57.733172] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-29 11:21:57.812574] INFO: moduleinvoker: instruments.v2 运行完成[0.079403s].

[2021-10-29 11:21:57.816973] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-10-29 11:21:57.828563] INFO: moduleinvoker: 命中缓存

[2021-10-29 11:21:57.830440] INFO: moduleinvoker: input_features.v1 运行完成[0.013528s].

[2021-10-29 11:21:57.835380] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-10-29 11:21:57.909874] INFO: moduleinvoker: instruments.v2 运行完成[0.074467s].

[2021-10-29 11:21:57.922075] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-10-29 11:21:58.558345] INFO: 自动标注(股票): 加载历史数据: 584988 行

[2021-10-29 11:21:58.560461] INFO: 自动标注(股票): 开始标注 ..

[2021-10-29 11:21:59.502369] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[1.580298s].

[2021-10-29 11:21:59.519134] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-29 11:22:09.921251] INFO: 基础特征抽取: 年份 2015, 特征行数=569698

[2021-10-29 11:22:15.175592] INFO: 基础特征抽取: 年份 2016, 特征行数=15290

[2021-10-29 11:22:15.341892] INFO: 基础特征抽取: 总行数: 584988

[2021-10-29 11:22:15.346943] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[15.827852s].

[2021-10-29 11:22:15.359968] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-10-29 11:22:21.552077] INFO: 基础特征抽取: 年份 2015, 特征行数=139170

[2021-10-29 11:22:33.412009] INFO: 基础特征抽取: 年份 2016, 特征行数=641546

[2021-10-29 11:22:38.323270] INFO: 基础特征抽取: 年份 2017, 特征行数=34165

[2021-10-29 11:22:38.417577] INFO: 基础特征抽取: 总行数: 814881

[2021-10-29 11:22:38.423919] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[23.063958s].

[2021-10-29 11:22:38.431230] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 11:22:39.994972] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_10, 0.003s

[2021-10-29 11:22:39.998751] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.002s

[2021-10-29 11:22:40.001981] INFO: derived_feature_extractor: 提取完成 turn_5/avg_turn_10, 0.002s

[2021-10-29 11:22:40.005531] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.002s

[2021-10-29 11:22:40.008642] INFO: derived_feature_extractor: 提取完成 swing_volatility_5_0/swing_volatility_60_0, 0.002s

[2021-10-29 11:22:40.012277] INFO: derived_feature_extractor: 提取完成 amount_10/amount_30, 0.003s

[2021-10-29 11:22:40.015402] INFO: derived_feature_extractor: 提取完成 ta_ema_5_0/close_0, 0.002s

[2021-10-29 11:22:40.018419] INFO: derived_feature_extractor: 提取完成 close_0/low_0, 0.002s

[2021-10-29 11:22:40.021465] INFO: derived_feature_extractor: 提取完成 ta_ema_20_0/close_0, 0.002s

[2021-10-29 11:22:40.024567] INFO: derived_feature_extractor: 提取完成 open_0/close_1, 0.002s

[2021-10-29 11:22:40.027566] INFO: derived_feature_extractor: 提取完成 high_1/close_0, 0.002s

[2021-10-29 11:22:40.030628] INFO: derived_feature_extractor: 提取完成 ta_ema_30_0/close_0, 0.002s

[2021-10-29 11:22:42.598356] INFO: derived_feature_extractor: 提取完成 ta_rsi(close_0, 6), 2.567s

[2021-10-29 11:22:42.603057] INFO: derived_feature_extractor: 提取完成 amount_0/amount_1, 0.003s

[2021-10-29 11:22:43.999377] INFO: derived_feature_extractor: /y_2015, 569698

[2021-10-29 11:22:44.991672] INFO: derived_feature_extractor: /y_2016, 15290

[2021-10-29 11:22:45.120102] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[6.68886s].

[2021-10-29 11:22:45.128529] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-10-29 11:22:47.255695] INFO: derived_feature_extractor: 提取完成 avg_amount_5/avg_amount_10, 0.004s

[2021-10-29 11:22:47.259785] INFO: derived_feature_extractor: 提取完成 return_5/return_10, 0.002s

[2021-10-29 11:22:47.263454] INFO: derived_feature_extractor: 提取完成 turn_5/avg_turn_10, 0.002s

[2021-10-29 11:22:47.267971] INFO: derived_feature_extractor: 提取完成 avg_amount_0/avg_amount_5, 0.003s

[2021-10-29 11:22:47.271673] INFO: derived_feature_extractor: 提取完成 swing_volatility_5_0/swing_volatility_60_0, 0.002s

[2021-10-29 11:22:47.279948] INFO: derived_feature_extractor: 提取完成 amount_10/amount_30, 0.007s

[2021-10-29 11:22:47.283960] INFO: derived_feature_extractor: 提取完成 ta_ema_5_0/close_0, 0.002s

[2021-10-29 11:22:47.287709] INFO: derived_feature_extractor: 提取完成 close_0/low_0, 0.002s

[2021-10-29 11:22:47.291477] INFO: derived_feature_extractor: 提取完成 ta_ema_20_0/close_0, 0.002s

[2021-10-29 11:22:47.296005] INFO: derived_feature_extractor: 提取完成 open_0/close_1, 0.003s

[2021-10-29 11:22:47.300050] INFO: derived_feature_extractor: 提取完成 high_1/close_0, 0.003s

[2021-10-29 11:22:47.304991] INFO: derived_feature_extractor: 提取完成 ta_ema_30_0/close_0, 0.003s

[2021-10-29 11:22:50.867966] INFO: derived_feature_extractor: 提取完成 ta_rsi(close_0, 6), 3.562s

[2021-10-29 11:22:50.875457] INFO: derived_feature_extractor: 提取完成 amount_0/amount_1, 0.006s

[2021-10-29 11:22:51.547944] INFO: derived_feature_extractor: /y_2015, 139170

[2021-10-29 11:22:53.330674] INFO: derived_feature_extractor: /y_2016, 641546

[2021-10-29 11:22:54.610647] INFO: derived_feature_extractor: /y_2017, 34165

[2021-10-29 11:22:54.847846] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[9.719311s].

[2021-10-29 11:22:54.855906] INFO: moduleinvoker: join.v3 开始运行..

[2021-10-29 11:22:59.837486] INFO: join: /y_2015, 行数=560123/569698, 耗时=3.903477s

[2021-10-29 11:23:00.135383] INFO: join: /y_2016, 行数=10037/15290, 耗时=0.292331s

[2021-10-29 11:23:00.260485] INFO: join: 最终行数: 570160

[2021-10-29 11:23:00.313444] INFO: moduleinvoker: join.v3 运行完成[5.457512s].

[2021-10-29 11:23:00.330094] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-29 11:23:44.295259] INFO: moduleinvoker: cached.v3 运行完成[43.965172s].

[2021-10-29 11:23:44.306667] INFO: moduleinvoker: cached.v3 开始运行..

[2021-10-29 11:24:03.370117] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: IndexError: single positional indexer is out-of-bounds

[2021-10-29 11:24:03.380486] ERROR: moduleinvoker: module name: hyper_rolling_train, module version: v1, trackeback: IndexError: single positional indexer is out-of-bounds

用于回测的样本总个数为 32402

用于训练的样本总个数为 0

---------------------------------------------------------------------------
IndexError                                Traceback (most recent call last)
<ipython-input-5-620b16fd8dbf> in <module>
    370 
    371 
--> 372 m11 = M.hyper_rolling_train.v1(
    373     run=m11_run_bigquant_run,
    374     run_now=True,

<ipython-input-5-620b16fd8dbf> in m11_run_bigquant_run(bq_graph, inputs, trading_days_market, train_instruments_mid, test_instruments_mid, predict_mid, trade_mid, start_date, end_date, train_update_days, train_update_days_for_live, train_data_min_days, train_data_max_days, rolling_count_for_live)
    355         parameters[test_instruments_mid + '.end_date'] = rolling['test_end_date']
    356         # print('------ rolling_train:', parameters)
--> 357         results.append(g.run(parameters))
    358 
    359     # 合并预测结果并回测

<ipython-input-5-620b16fd8dbf> in m6_run_bigquant_run(input_1, input_2, input_3)
     20     df_final = df_final[df_final['rank_amount_0'] >= 0.85]
     21     print("用于训练的样本总个数为",len(df_final))
---> 22     print(df_final.iloc[0])
     23     data_1 = DataSource.write_df(df_final)
     24     return Outputs(data_1=data_1, data_2=None, data_3=None)

IndexError: single positional indexer is out-of-bounds

In [ ]:

m10.feature_gains.read().sort_values('gain',ascending=False)

In [ ]: