复制链接

克隆策略

StockRanker多因子选股策略¶

In [7]:

import itertools
param_grid = {}

period_list = [5,20,60,100,120] 

# 在这里设置需要调优的参数备选
feature_list = [
'''
double_low = close + bond_prem_ratio
remain_size
rank_swing_volatility_5 = nanstd((high-low)/pre_close, {0})*sqrt(200)*100
'''.format(period) for period in period_list
]
param_grid["m14.params"] = [
    """{"stock_count": 3, "hold_days": 3}""",
    """{"stock_count": 4, "hold_days": 4}""",
    """{"stock_count": 3, "hold_days": 1}""",
    """{"stock_count": 4, "hold_days": 2}"""
]
param_grid['m3.features'] = feature_list

In [9]:

param_grid

Out[9]:

{'m14.params': ['{"stock_count": 3, "hold_days": 3}',
  '{"stock_count": 4, "hold_days": 4}',
  '{"stock_count": 3, "hold_days": 1}',
  '{"stock_count": 4, "hold_days": 2}'],
 'm3.features': ['\ndouble_low = close + bond_prem_ratio\nremain_size\nrank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100\n',
  '\ndouble_low = close + bond_prem_ratio\nremain_size\nrank_swing_volatility_5 = nanstd((high-low)/pre_close, 20)*sqrt(200)*100\n',
  '\ndouble_low = close + bond_prem_ratio\nremain_size\nrank_swing_volatility_5 = nanstd((high-low)/pre_close, 60)*sqrt(200)*100\n',
  '\ndouble_low = close + bond_prem_ratio\nremain_size\nrank_swing_volatility_5 = nanstd((high-low)/pre_close, 100)*sqrt(200)*100\n',
  '\ndouble_low = close + bond_prem_ratio\nremain_size\nrank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100\n']}

In [15]:

m21.read_raw_perf()['sharpe'].tail(1)[0]
# score = result.get('m7').read_raw_perf()['sharpe'].tail(1)[0]

Out[15]:

3.681702751663812

In [2]:

# 本代码由可视化策略环境自动生成 2022年5月30日 09:02
# 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 m2_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 = DataSource("bar1d_CN_CONBOND").read(start_date="2017-06-01", end_date="2020-06-30")
    df2 = df.drop(['close'],axis = 1)
    data_1 = DataSource.write_df(df)
    data_2 = DataSource.write_df(df2)
    return Outputs(data_1=data_1, data_2=data_2, 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 m2_post_run_bigquant_run(outputs):
    return outputs

def del_input(input):
    df = input.read_df()
    df = df.drop(["trigger_cond_item_desc",'revise_item_desc','trigger_item_desc'],axis=1)
    df = df.dropna(axis=0, how='all', thresh=None, subset=None, inplace=False)
    print(df.columns)
    #df.sort_values(by=['date','double_low'],axis=0,ascending=True,inplace = True)
    df = df.sort_index(axis = 1)
    df = df.reset_index(drop = True)
    df = df.groupby('date').head(10)
    #print(df[['double_low','date']])
    data_1 = DataSource.write_df(df)
    return data_1
# 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 m23_run_bigquant_run(input_1, input_2, input_3):
    data_1 = del_input(input_1)
    data_2 = del_input(input_2)
    return Outputs(data_1=data_1, data_2=data_2, 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 m23_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 m15_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 = DataSource("bar1d_CN_CONBOND").read(start_date="2020-06-30", end_date="2021-06-30")
    df = df.drop(['close'],axis = 1)
    data_1 = DataSource.write_df(df)
    data_2 = DataSource.write_pickle(df)
    return Outputs(data_1=data_1, data_2=data_2, 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

# 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 m13_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()
    #print(df.columns)
    #df = df1[['date','instrument','close','label']]
    #df = df.drop(["trigger_cond_item_desc",'revise_item_desc','trigger_item_desc'],axis=1)
    df = df.dropna(axis=0, how='all', thresh=None, subset=None, inplace=False)
    print(df.columns)
    df.sort_values(by=['date','double_low'],axis=0,ascending=True,inplace = True)
    df = df.sort_index(axis = 1)
    df = df.reset_index(drop = True)
    df = df.groupby('date').head(10)
    #print(df[['double_low','date']])
    data_1 = DataSource.write_df(df)
    data_2 = DataSource.write_pickle(df)
    return Outputs(data_1=data_1, data_2=data_2, 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 m13_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 m14_run_bigquant_run(input_1, input_2, input_3, stock_count, hold_days):
    # 示例代码如下。在这里编写您的代码
    param = {
        "stock_count": stock_count,
        "hold_days": hold_days
        }
    data_1 = DataSource.write_pickle(param)
    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 m14_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 m11_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()
    param = input_2.read()
    
    data = {
        "param": param,
        "data": df
    }
    data_1 = DataSource.write_pickle(data)
    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 m11_post_run_bigquant_run(outputs):
    return outputs

# 回测引擎：初始化函数，只执行一次
def m21_initialize_bigquant_run(context):
    print(context.options)
    # 加载预测数据
    context.ranker_prediction = context.options.get('data').read()['data']
    print(context.ranker_prediction)
    context.param = context.options['data'].read()["param"]
    # 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 = context.param["stock_count"]
    # 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 = 0.4
    context.hold_days = context.param["hold_days"]

# 交易引擎：每个单位时间开盘前调用一次。
def m21_before_trading_start_bigquant_run(context, data):
    # 盘前处理，订阅行情等
    pass

# 交易引擎：tick数据处理函数，每个tick执行一次
def m21_handle_tick_bigquant_run(context, tick):
    pass

# 回测引擎：每日数据处理函数，每天执行一次
def m21_handle_data_bigquant_run(context, data):
    print('处理data',data)
    context.ranker_prediction = context.options.get('data').read()['data']
    # 相隔几天（hold_days）进行一下换仓
    if context.trading_day_index % context.hold_days != 0:
        return 
    
    # 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')]
    # 目前持仓
    positions = {e: p.amount * p.last_sale_price for e, p in context.portfolio.positions.items()}
    # 权重
    buy_cash_weights = context.stock_weights
    # 今日买入股票列表
    stock_to_buy = list(ranker_prediction.instrument[:len(buy_cash_weights)])
    # 持仓上限
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument

    # 通过positions对象，使用列表生成式的方法获取目前持仓的股票列表
    stock_hold_now = [equity for equity in context.portfolio.positions ]
    # 继续持有的股票：调仓时，如果买入的股票已经存在于目前的持仓里，那么应继续持有
    no_need_to_sell = [i for i in stock_hold_now if i in stock_to_buy]
    # 需要卖出的股票
    stock_to_sell = [i for i in stock_hold_now if i not in no_need_to_sell]
  
    # 卖出
    for stock in stock_to_sell:
        # 如果该股票停牌，则没法成交。因此需要用can_trade方法检查下该股票的状态
        # 如果返回真值，则可以正常下单，否则会出错
        # 因为stock是字符串格式，我们用symbol方法将其转化成平台可以接受的形式：Equity格式
        if data.can_trade(context.symbol(stock)):
            # order_target_percent是平台的一个下单接口，表明下单使得该股票的权重为0，
            #   即卖出全部股票，可参考回测文档
            context.order_target_percent(context.symbol(stock), 0)
    
    # 如果当天没有买入的股票，就返回
    if len(stock_to_buy) == 0:
        return
    
    # 买入
    for i, instrument in enumerate(stock_to_buy):
        cash = context.portfolio.portfolio_value * 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)
# 交易引擎：成交回报处理函数，每个成交发生时执行一次
def m21_handle_trade_bigquant_run(context, trade):
    pass

# 交易引擎：委托回报处理函数，每个委托变化时执行一次
def m21_handle_order_bigquant_run(context, order):
    pass

# 交易引擎：盘后处理函数，每日盘后执行一次
def m21_after_trading_bigquant_run(context, data):
    pass


g = T.Graph({

    'm3': 'M.input_features.v1',
    'm3.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
double_low = close + bond_prem_ratio
remain_size
rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100""",

    'm2': 'M.cached.v3',
    'm2.run': m2_run_bigquant_run,
    'm2.post_run': m2_post_run_bigquant_run,
    'm2.input_ports': '',
    'm2.params': '{}',
    'm2.output_ports': '',

    'm10': 'M.auto_labeler_on_datasource.v1',
    'm10.input_data': T.Graph.OutputPort('m2.data_1'),
    'm10.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
# 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, 10)

# 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)
""",
    'm10.drop_na_label': True,
    'm10.cast_label_int': True,
    'm10.date_col': 'date',
    'm10.instrument_col': 'instrument',
    'm10.user_functions': {},

    'm1': 'M.use_datasource.v1',
    'm1.datasource_id': 'market_performance_CN_CONBOND',
    'm1.start_date': '2019-06-01',
    'm1.end_date': '2020-06-30',

    'm5': 'M.use_datasource.v1',
    'm5.datasource_id': 'market_performance_CN_CONBOND',
    'm5.start_date': '2021-05-01',
    'm5.end_date': '2021-06-30',

    'm12': 'M.trade_data_generation.v1',
    'm12.input': T.Graph.OutputPort('m5.data'),
    'm12.category': 'CN_STOCK',
    'm12.m_cached': False,

    'm23': 'M.cached.v3',
    'm23.input_1': T.Graph.OutputPort('m1.data'),
    'm23.input_2': T.Graph.OutputPort('m5.data'),
    'm23.run': m23_run_bigquant_run,
    'm23.post_run': m23_post_run_bigquant_run,
    'm23.input_ports': '',
    'm23.params': '{}',
    'm23.output_ports': '',
    'm23.m_cached': False,

    'm4': 'M.join.v3',
    'm4.data1': T.Graph.OutputPort('m2.data_2'),
    'm4.data2': T.Graph.OutputPort('m23.data_1'),
    'm4.on': 'date,instrument',
    'm4.how': 'inner',
    'm4.sort': False,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m4.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('m10.data'),
    'm7.data2': T.Graph.OutputPort('m16.data'),
    'm7.on': 'date,instrument',
    'm7.how': 'inner',
    'm7.sort': False,

    'm6': 'M.stock_ranker_train.v6',
    'm6.training_ds': T.Graph.OutputPort('m7.data'),
    'm6.features': T.Graph.OutputPort('m3.data'),
    'm6.learning_algorithm': '排序',
    'm6.number_of_leaves': 3,
    'm6.minimum_docs_per_leaf': 100,
    'm6.number_of_trees': 2,
    'm6.learning_rate': 0.1,
    'm6.max_bins': 1023,
    'm6.feature_fraction': 1,
    'm6.data_row_fraction': 1,
    'm6.plot_charts': True,
    'm6.ndcg_discount_base': 1,
    'm6.m_lazy_run': False,
    'm6.m_cached': False,

    'm15': 'M.cached.v3',
    'm15.run': m15_run_bigquant_run,
    'm15.post_run': m15_post_run_bigquant_run,
    'm15.input_ports': '',
    'm15.params': '{}',
    'm15.output_ports': '',

    'm25': 'M.join.v3',
    'm25.data1': T.Graph.OutputPort('m23.data_2'),
    'm25.data2': T.Graph.OutputPort('m15.data_1'),
    'm25.on': 'date,instrument',
    'm25.how': 'inner',
    'm25.sort': False,

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m25.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,

    'm13': 'M.cached.v3',
    'm13.input_1': T.Graph.OutputPort('m18.data'),
    'm13.run': m13_run_bigquant_run,
    'm13.post_run': m13_post_run_bigquant_run,
    'm13.input_ports': '',
    'm13.params': '{}',
    'm13.output_ports': '',
    'm13.m_cached': False,

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m13.data_1'),
    'm8.m_lazy_run': False,

    'm14': 'M.cached.v3',
    'm14.run': m14_run_bigquant_run,
    'm14.post_run': m14_post_run_bigquant_run,
    'm14.input_ports': '',
    'm14.params': """{
    "stock_count": 3,
    "hold_days": 4 
}""",
    'm14.output_ports': '',

    'm11': 'M.cached.v3',
    'm11.input_1': T.Graph.OutputPort('m8.predictions'),
    'm11.input_2': T.Graph.OutputPort('m14.data_1'),
    'm11.run': m11_run_bigquant_run,
    'm11.post_run': m11_post_run_bigquant_run,
    'm11.input_ports': '',
    'm11.params': '{}',
    'm11.output_ports': '',

    'm21': 'M.hftrade.v2',
    'm21.instruments': T.Graph.OutputPort('m12.instrument_list'),
    'm21.options_data': T.Graph.OutputPort('m11.data_1'),
    'm21.start_date': '',
    'm21.end_date': '',
    'm21.initialize': m21_initialize_bigquant_run,
    'm21.before_trading_start': m21_before_trading_start_bigquant_run,
    'm21.handle_tick': m21_handle_tick_bigquant_run,
    'm21.handle_data': m21_handle_data_bigquant_run,
    'm21.handle_trade': m21_handle_trade_bigquant_run,
    'm21.handle_order': m21_handle_order_bigquant_run,
    'm21.after_trading': m21_after_trading_bigquant_run,
    'm21.capital_base': 1000000,
    'm21.frequency': 'daily',
    'm21.price_type': '真实价格',
    'm21.product_type': '可转债',
    'm21.before_start_days': '8',
    'm21.order_price_field_buy': 'open',
    'm21.order_price_field_sell': 'close',
    'm21.benchmark': '000300.HIX',
    'm21.plot_charts': True,
    'm21.disable_cache': False,
    'm21.replay_bdb': False,
    'm21.show_debug_info': False,
    'm21.backtest_only': False,
})

# g.run({})


def m9_param_grid_builder_bigquant_run():
    import itertools
    param_grid = {}
    
    period_list = [5,120] 
    
    # 在这里设置需要调优的参数备选
    feature_list = [
    '''
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, {0})*sqrt(200)*100
    '''.format(period) for period in period_list
    ]
    param_grid["m14.params"] = [
        """{"stock_count": 3, "hold_days": 3}""",
        """{"stock_count": 4, "hold_days": 4}""",
    ]
    param_grid['m3.features'] = feature_list
    return param_grid
def m9_scoring_bigquant_run(result):
    # 评分：收益/最大回撤
    score = result.get('m21').read_raw_perf()['sharpe'].tail(1)[0]
    return {'score': score}


m9 = M.hyper_parameter_search.v1(
    param_grid_builder=m9_param_grid_builder_bigquant_run,
    scoring=m9_scoring_bigquant_run,
    search_algorithm='网格搜索',
    search_iterations=10,
    workers=1,
    worker_distributed_run=False,
    worker_silent=False,
    run_now=True,
    bq_graph=g
)

[2022-05-30 16:55:37.108370] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-30 16:55:37.115391] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.117157] INFO: moduleinvoker: input_features.v1 运行完成[0.008788s].

[2022-05-30 16:55:37.126562] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:55:37.137841] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.139402] INFO: moduleinvoker: cached.v3 运行完成[0.012851s].

[2022-05-30 16:55:37.143612] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:55:37.148949] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.150228] INFO: moduleinvoker: use_datasource.v1 运行完成[0.006618s].

[2022-05-30 16:55:37.154319] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:55:37.160402] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.161661] INFO: moduleinvoker: use_datasource.v1 运行完成[0.007343s].

[2022-05-30 16:55:37.175876] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:55:37.184492] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.185909] INFO: moduleinvoker: cached.v3 运行完成[0.010049s].

[2022-05-30 16:55:37.196071] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:55:37.202847] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.205010] INFO: moduleinvoker: cached.v3 运行完成[0.008941s].

[2022-05-30 16:55:37.213485] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-05-30 16:55:37.219766] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:55:37.221165] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.007678s].

[2022-05-30 16:55:37.229989] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:55:37.543590] INFO: moduleinvoker: cached.v3 运行完成[0.313594s].

[2022-05-30 16:55:37.551223] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-05-30 16:55:37.696350] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.145097s].

[2022-05-30 16:55:37.705743] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:55:39.952627] INFO: join: /data, 行数=2596/2620, 耗时=0.210168s

[2022-05-30 16:55:39.973971] INFO: join: 最终行数: 2596

[2022-05-30 16:55:39.987196] INFO: moduleinvoker: join.v3 运行完成[2.281458s].

[2022-05-30 16:55:39.994621] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:55:40.985726] INFO: join: /data, 行数=390/268823, 耗时=0.915845s

[2022-05-30 16:55:41.014817] INFO: join: 最终行数: 390

[2022-05-30 16:55:41.023888] INFO: moduleinvoker: join.v3 运行完成[1.029254s].

[2022-05-30 16:55:41.030718] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:55:41.099176] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:55:41.118449] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.018s

[2022-05-30 16:55:41.203961] INFO: derived_feature_extractor: /data, 2596

[2022-05-30 16:55:41.258667] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.227935s].

[2022-05-30 16:55:41.265800] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:55:41.324020] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:55:41.346451] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.021s

[2022-05-30 16:55:41.406443] INFO: derived_feature_extractor: /data, 390

[2022-05-30 16:55:41.466543] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.200719s].

[2022-05-30 16:55:41.474290] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:55:41.900311] INFO: join: /data, 行数=2531/2596, 耗时=0.086075s

[2022-05-30 16:55:41.994492] INFO: join: 最终行数: 2531

[2022-05-30 16:55:42.003780] INFO: moduleinvoker: join.v3 运行完成[0.52948s].

[2022-05-30 16:55:42.012319] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:55:42.147768] INFO: moduleinvoker: cached.v3 运行完成[0.135442s].

[2022-05-30 16:55:42.156560] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-05-30 16:55:42.229824] INFO: StockRanker: 特征预处理 ..

[2022-05-30 16:55:42.260332] INFO: StockRanker: prepare data: training ..

[2022-05-30 16:55:42.369152] INFO: StockRanker训练: 490527d4 准备训练: 2531 行数

[2022-05-30 16:55:42.370809] INFO: StockRanker训练: AI模型训练，将在2531*3=0.76万数据上对模型训练进行2轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-05-30 16:55:42.586961] INFO: StockRanker训练: 正在训练 ..

[2022-05-30 16:55:42.641765] INFO: StockRanker训练: 任务状态: Pending

[2022-05-30 16:55:52.716860] INFO: StockRanker训练: 任务状态: Running

[2022-05-30 16:56:53.030031] INFO: StockRanker训练: 00:01:02.0633654, finished iteration 1

[2022-05-30 16:56:53.031524] INFO: StockRanker训练: 00:01:02.0760436, finished iteration 2

[2022-05-30 16:56:53.032695] INFO: StockRanker训练: 任务状态: Succeeded

[2022-05-30 16:56:53.202061] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[71.045488s].

[2022-05-30 16:56:53.215372] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-05-30 16:56:53.363993] INFO: StockRanker预测: /data ..

[2022-05-30 16:56:53.451862] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.236491s].

[2022-05-30 16:56:53.462596] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:56:53.553885] INFO: moduleinvoker: cached.v3 运行完成[0.091276s].

[2022-05-30 16:56:53.582304] INFO: moduleinvoker: hfbacktest.v1 开始运行..

[2022-05-30 16:56:53.588232] INFO: hfbacktest: biglearning V1.4.11

[2022-05-30 16:56:53.589486] INFO: hfbacktest: bigtrader v1.9.6 2022-05-24

[2022-05-30 16:56:53.632990] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 16:56:53.642117] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:53.643582] INFO: moduleinvoker: cached.v2 运行完成[0.010607s].

[2022-05-30 16:56:53.702293] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 16:56:53.722307] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:53.724075] INFO: moduleinvoker: cached.v2 运行完成[0.021801s].

[2022-05-30 16:56:56.304919] INFO: hfbacktest: backtest done, raw_perf_ds:DataSource(f4187b29a15d4cda85e43be3204c5e21T)

[2022-05-30 16:56:56.775688] INFO: moduleinvoker: hfbacktest.v1 运行完成[3.193382s].

[2022-05-30 16:56:56.776990] INFO: moduleinvoker: hftrade.v2 运行完成[3.215644s].

[2022-05-30 16:56:56.828518] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-30 16:56:56.983167] INFO: moduleinvoker: input_features.v1 运行完成[0.154647s].

[2022-05-30 16:56:56.994072] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:56:57.008082] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:57.009759] INFO: moduleinvoker: cached.v3 运行完成[0.015695s].

[2022-05-30 16:56:57.014701] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:56:57.060957] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:57.062763] INFO: moduleinvoker: use_datasource.v1 运行完成[0.048062s].

[2022-05-30 16:56:57.069150] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:56:57.091738] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:57.093535] INFO: moduleinvoker: use_datasource.v1 运行完成[0.02439s].

[2022-05-30 16:56:57.104376] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:56:57.119529] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:57.121178] INFO: moduleinvoker: cached.v3 运行完成[0.016817s].

[2022-05-30 16:56:57.131631] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:56:57.138803] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:57.140158] INFO: moduleinvoker: cached.v3 运行完成[0.008535s].

[2022-05-30 16:56:57.146379] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-05-30 16:56:57.153018] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:56:57.154251] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.00787s].

[2022-05-30 16:56:57.162120] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:56:57.506801] INFO: moduleinvoker: cached.v3 运行完成[0.344649s].

[2022-05-30 16:56:57.518682] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-05-30 16:56:57.677093] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.158406s].

[2022-05-30 16:56:57.688963] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:57:00.138609] INFO: join: /data, 行数=2596/2620, 耗时=0.197362s

[2022-05-30 16:57:00.164740] INFO: join: 最终行数: 2596

[2022-05-30 16:57:00.176927] INFO: moduleinvoker: join.v3 运行完成[2.487965s].

[2022-05-30 16:57:00.184559] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:57:01.270107] INFO: join: /data, 行数=390/268823, 耗时=0.990227s

[2022-05-30 16:57:01.296375] INFO: join: 最终行数: 390

[2022-05-30 16:57:01.305070] INFO: moduleinvoker: join.v3 运行完成[1.120503s].

[2022-05-30 16:57:01.315182] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:57:01.385280] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:57:01.405170] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100, 0.018s

[2022-05-30 16:57:01.473231] INFO: derived_feature_extractor: /data, 2596

[2022-05-30 16:57:01.539958] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.224759s].

[2022-05-30 16:57:01.546585] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:57:01.622059] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.002s

[2022-05-30 16:57:01.642930] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100, 0.019s

[2022-05-30 16:57:01.715856] INFO: derived_feature_extractor: /data, 390

[2022-05-30 16:57:01.800649] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.254035s].

[2022-05-30 16:57:01.817026] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:57:02.412653] INFO: join: /data, 行数=2531/2596, 耗时=0.113564s

[2022-05-30 16:57:02.446437] INFO: join: 最终行数: 2531

[2022-05-30 16:57:02.455465] INFO: moduleinvoker: join.v3 运行完成[0.638447s].

[2022-05-30 16:57:02.464507] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:57:02.581138] INFO: moduleinvoker: cached.v3 运行完成[0.116621s].

[2022-05-30 16:57:02.588027] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-05-30 16:57:02.648601] INFO: StockRanker: 特征预处理 ..

[2022-05-30 16:57:02.670147] INFO: StockRanker: prepare data: training ..

[2022-05-30 16:57:02.754982] INFO: StockRanker训练: 78f5c598 准备训练: 2531 行数

[2022-05-30 16:57:02.756396] INFO: StockRanker训练: AI模型训练，将在2531*3=0.76万数据上对模型训练进行2轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-05-30 16:57:02.981829] INFO: StockRanker训练: 正在训练 ..

[2022-05-30 16:57:03.033033] INFO: StockRanker训练: 任务状态: Pending

[2022-05-30 16:57:13.082207] INFO: StockRanker训练: 任务状态: Running

[2022-05-30 16:58:13.357690] INFO: StockRanker训练: 00:01:01.6389805, finished iteration 1

[2022-05-30 16:58:13.359251] INFO: StockRanker训练: 00:01:01.6447730, finished iteration 2

[2022-05-30 16:58:13.360531] INFO: StockRanker训练: 任务状态: Succeeded

[2022-05-30 16:58:13.536106] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[70.948064s].

[2022-05-30 16:58:13.544783] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-05-30 16:58:13.644808] INFO: StockRanker预测: /data ..

[2022-05-30 16:58:13.713814] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.169021s].

[2022-05-30 16:58:13.724436] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:58:13.807531] INFO: moduleinvoker: cached.v3 运行完成[0.083091s].

[2022-05-30 16:58:13.833192] INFO: moduleinvoker: hfbacktest.v1 开始运行..

[2022-05-30 16:58:13.838271] INFO: hfbacktest: biglearning V1.4.11

[2022-05-30 16:58:13.839688] INFO: hfbacktest: bigtrader v1.9.6 2022-05-24

[2022-05-30 16:58:13.861466] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 16:58:13.868093] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:13.869850] INFO: moduleinvoker: cached.v2 运行完成[0.008391s].

[2022-05-30 16:58:13.922849] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 16:58:13.929451] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:13.930736] INFO: moduleinvoker: cached.v2 运行完成[0.007894s].

[2022-05-30 16:58:16.347186] INFO: hfbacktest: backtest done, raw_perf_ds:DataSource(e5ce88eca64848d89ad2ef3922119263T)

[2022-05-30 16:58:16.924516] INFO: moduleinvoker: hfbacktest.v1 运行完成[3.091338s].

[2022-05-30 16:58:16.926042] INFO: moduleinvoker: hftrade.v2 运行完成[3.111616s].

[2022-05-30 16:58:16.995960] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-30 16:58:17.029184] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:17.031131] INFO: moduleinvoker: input_features.v1 运行完成[0.035184s].

[2022-05-30 16:58:17.042418] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:58:17.058796] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:17.060697] INFO: moduleinvoker: cached.v3 运行完成[0.018289s].

[2022-05-30 16:58:17.066333] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:58:17.085795] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:17.087717] INFO: moduleinvoker: use_datasource.v1 运行完成[0.021384s].

[2022-05-30 16:58:17.092736] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:58:17.103638] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:17.105081] INFO: moduleinvoker: use_datasource.v1 运行完成[0.012345s].

[2022-05-30 16:58:17.115907] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:58:17.126539] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:17.128698] INFO: moduleinvoker: cached.v3 运行完成[0.012797s].

[2022-05-30 16:58:17.139177] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:58:17.169329] INFO: moduleinvoker: cached.v3 运行完成[0.030151s].

[2022-05-30 16:58:17.178845] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-05-30 16:58:17.185141] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:58:17.187081] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.00823s].

[2022-05-30 16:58:17.197306] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:58:17.575399] INFO: moduleinvoker: cached.v3 运行完成[0.378103s].

[2022-05-30 16:58:17.583189] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-05-30 16:58:17.763396] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.18018s].

[2022-05-30 16:58:17.772852] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:58:20.752792] INFO: join: /data, 行数=2596/2620, 耗时=0.198659s

[2022-05-30 16:58:20.807659] INFO: join: 最终行数: 2596

[2022-05-30 16:58:20.821892] INFO: moduleinvoker: join.v3 运行完成[3.049035s].

[2022-05-30 16:58:20.859057] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:58:21.816976] INFO: join: /data, 行数=390/268823, 耗时=0.880911s

[2022-05-30 16:58:21.850538] INFO: join: 最终行数: 390

[2022-05-30 16:58:21.858883] INFO: moduleinvoker: join.v3 运行完成[0.999815s].

[2022-05-30 16:58:21.873111] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:58:21.942183] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:58:21.960578] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.017s

[2022-05-30 16:58:22.029557] INFO: derived_feature_extractor: /data, 2596

[2022-05-30 16:58:22.085553] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.21244s].

[2022-05-30 16:58:22.091852] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:58:22.141773] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:58:22.161752] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.019s

[2022-05-30 16:58:22.218457] INFO: derived_feature_extractor: /data, 390

[2022-05-30 16:58:22.272762] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.180897s].

[2022-05-30 16:58:22.279956] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:58:22.751932] INFO: join: /data, 行数=2531/2596, 耗时=0.090916s

[2022-05-30 16:58:22.786373] INFO: join: 最终行数: 2531

[2022-05-30 16:58:22.794899] INFO: moduleinvoker: join.v3 运行完成[0.514923s].

[2022-05-30 16:58:22.805628] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:58:22.958983] INFO: moduleinvoker: cached.v3 运行完成[0.153356s].

[2022-05-30 16:58:22.966834] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-05-30 16:58:23.055277] INFO: StockRanker: 特征预处理 ..

[2022-05-30 16:58:23.100959] INFO: StockRanker: prepare data: training ..

[2022-05-30 16:58:23.182693] INFO: StockRanker训练: a8df094a 准备训练: 2531 行数

[2022-05-30 16:58:23.184147] INFO: StockRanker训练: AI模型训练，将在2531*3=0.76万数据上对模型训练进行2轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-05-30 16:58:23.387604] INFO: StockRanker训练: 正在训练 ..

[2022-05-30 16:58:23.440156] INFO: StockRanker训练: 任务状态: Pending

[2022-05-30 16:58:33.519045] INFO: StockRanker训练: 任务状态: Running

[2022-05-30 16:59:33.943531] INFO: StockRanker训练: 00:01:01.5262966, finished iteration 1

[2022-05-30 16:59:33.944994] INFO: StockRanker训练: 00:01:01.5313940, finished iteration 2

[2022-05-30 16:59:43.987235] INFO: StockRanker训练: 任务状态: Succeeded

[2022-05-30 16:59:44.169301] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[81.202453s].

[2022-05-30 16:59:44.194252] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-05-30 16:59:44.312507] INFO: StockRanker预测: /data ..

[2022-05-30 16:59:44.387423] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.19315s].

[2022-05-30 16:59:44.399958] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:59:44.472620] INFO: moduleinvoker: cached.v3 运行完成[0.07266s].

[2022-05-30 16:59:44.504371] INFO: moduleinvoker: hfbacktest.v1 开始运行..

[2022-05-30 16:59:44.508928] INFO: hfbacktest: biglearning V1.4.11

[2022-05-30 16:59:44.510134] INFO: hfbacktest: bigtrader v1.9.6 2022-05-24

[2022-05-30 16:59:44.526122] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 16:59:44.532392] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:44.533612] INFO: moduleinvoker: cached.v2 运行完成[0.007489s].

[2022-05-30 16:59:44.578430] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 16:59:44.585134] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:44.586401] INFO: moduleinvoker: cached.v2 运行完成[0.007996s].

[2022-05-30 16:59:47.011347] INFO: hfbacktest: backtest done, raw_perf_ds:DataSource(09c95470d23e4e8dbeb2bbcce4e81239T)

[2022-05-30 16:59:47.507026] INFO: moduleinvoker: hfbacktest.v1 运行完成[3.002637s].

[2022-05-30 16:59:47.508724] INFO: moduleinvoker: hftrade.v2 运行完成[3.030166s].

[2022-05-30 16:59:47.560582] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-30 16:59:47.568106] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.569597] INFO: moduleinvoker: input_features.v1 运行完成[0.009023s].

[2022-05-30 16:59:47.579786] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:59:47.589210] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.590477] INFO: moduleinvoker: cached.v3 运行完成[0.010689s].

[2022-05-30 16:59:47.594934] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:59:47.604622] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.605854] INFO: moduleinvoker: use_datasource.v1 运行完成[0.010919s].

[2022-05-30 16:59:47.610120] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 16:59:47.615473] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.616695] INFO: moduleinvoker: use_datasource.v1 运行完成[0.006575s].

[2022-05-30 16:59:47.626264] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:59:47.634010] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.635210] INFO: moduleinvoker: cached.v3 运行完成[0.008946s].

[2022-05-30 16:59:47.644500] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:59:47.649911] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.651228] INFO: moduleinvoker: cached.v3 运行完成[0.006729s].

[2022-05-30 16:59:47.657694] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-05-30 16:59:47.663026] INFO: moduleinvoker: 命中缓存

[2022-05-30 16:59:47.664306] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.006611s].

[2022-05-30 16:59:47.673965] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:59:48.002717] INFO: moduleinvoker: cached.v3 运行完成[0.32874s].

[2022-05-30 16:59:48.011558] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-05-30 16:59:48.167108] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.155537s].

[2022-05-30 16:59:48.177397] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:59:50.431800] INFO: join: /data, 行数=2596/2620, 耗时=0.195471s

[2022-05-30 16:59:50.451896] INFO: join: 最终行数: 2596

[2022-05-30 16:59:50.465463] INFO: moduleinvoker: join.v3 运行完成[2.288059s].

[2022-05-30 16:59:50.475728] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:59:51.457045] INFO: join: /data, 行数=390/268823, 耗时=0.881605s

[2022-05-30 16:59:51.485066] INFO: join: 最终行数: 390

[2022-05-30 16:59:51.492497] INFO: moduleinvoker: join.v3 运行完成[1.016765s].

[2022-05-30 16:59:51.501121] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:59:51.572833] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:59:51.593925] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100, 0.020s

[2022-05-30 16:59:51.662782] INFO: derived_feature_extractor: /data, 2596

[2022-05-30 16:59:51.712938] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.2118s].

[2022-05-30 16:59:51.719893] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 16:59:51.767778] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 16:59:51.788491] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100, 0.019s

[2022-05-30 16:59:51.852514] INFO: derived_feature_extractor: /data, 390

[2022-05-30 16:59:51.922955] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.20305s].

[2022-05-30 16:59:51.930013] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 16:59:52.388684] INFO: join: /data, 行数=2531/2596, 耗时=0.087095s

[2022-05-30 16:59:52.417791] INFO: join: 最终行数: 2531

[2022-05-30 16:59:52.424969] INFO: moduleinvoker: join.v3 运行完成[0.494954s].

[2022-05-30 16:59:52.432536] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 16:59:52.540600] INFO: moduleinvoker: cached.v3 运行完成[0.108053s].

[2022-05-30 16:59:52.549756] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-05-30 16:59:52.609826] INFO: StockRanker: 特征预处理 ..

[2022-05-30 16:59:52.637284] INFO: StockRanker: prepare data: training ..

[2022-05-30 16:59:52.701921] INFO: StockRanker训练: de4396d2 准备训练: 2531 行数

[2022-05-30 16:59:52.703580] INFO: StockRanker训练: AI模型训练，将在2531*3=0.76万数据上对模型训练进行2轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-05-30 16:59:52.888856] INFO: StockRanker训练: 正在训练 ..

[2022-05-30 16:59:52.942441] INFO: StockRanker训练: 任务状态: Pending

[2022-05-30 17:00:03.009349] INFO: StockRanker训练: 任务状态: Running

[2022-05-30 17:01:03.398094] INFO: StockRanker训练: 00:01:02.0324082, finished iteration 1

[2022-05-30 17:01:03.399680] INFO: StockRanker训练: 00:01:02.0369762, finished iteration 2

[2022-05-30 17:01:03.400835] INFO: StockRanker训练: 任务状态: Succeeded

[2022-05-30 17:01:03.596283] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[71.046503s].

[2022-05-30 17:01:03.610873] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-05-30 17:01:03.695646] INFO: StockRanker预测: /data ..

[2022-05-30 17:01:03.786889] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.176005s].

[2022-05-30 17:01:03.802513] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:01:03.894801] INFO: moduleinvoker: cached.v3 运行完成[0.092283s].

[2022-05-30 17:01:03.924599] INFO: moduleinvoker: hfbacktest.v1 开始运行..

[2022-05-30 17:01:03.929688] INFO: hfbacktest: biglearning V1.4.11

[2022-05-30 17:01:03.930866] INFO: hfbacktest: bigtrader v1.9.6 2022-05-24

[2022-05-30 17:01:03.948316] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 17:01:03.955817] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:03.958222] INFO: moduleinvoker: cached.v2 运行完成[0.009916s].

[2022-05-30 17:01:04.009807] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 17:01:04.016557] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:04.018121] INFO: moduleinvoker: cached.v2 运行完成[0.008329s].

[2022-05-30 17:01:06.486149] INFO: hfbacktest: backtest done, raw_perf_ds:DataSource(45c0a5215b32481195b8647b33a867d6T)

[2022-05-30 17:01:06.967259] INFO: moduleinvoker: hfbacktest.v1 运行完成[3.042678s].

[2022-05-30 17:01:06.968487] INFO: moduleinvoker: hftrade.v2 运行完成[3.065201s].

[2022-05-30 17:01:07.015905] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-30 17:01:07.030414] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.031962] INFO: moduleinvoker: input_features.v1 运行完成[0.01607s].

[2022-05-30 17:01:07.041726] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:01:07.051081] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.052497] INFO: moduleinvoker: cached.v3 运行完成[0.010781s].

[2022-05-30 17:01:07.056609] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 17:01:07.061977] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.063288] INFO: moduleinvoker: use_datasource.v1 运行完成[0.006681s].

[2022-05-30 17:01:07.067590] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-30 17:01:07.073756] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.075237] INFO: moduleinvoker: use_datasource.v1 运行完成[0.007642s].

[2022-05-30 17:01:07.086215] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:01:07.099313] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.100820] INFO: moduleinvoker: cached.v3 运行完成[0.014604s].

[2022-05-30 17:01:07.110880] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:01:07.116858] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.118255] INFO: moduleinvoker: cached.v3 运行完成[0.007379s].

[2022-05-30 17:01:07.126205] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-05-30 17:01:07.131860] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:01:07.133180] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.006974s].

[2022-05-30 17:01:07.140905] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:01:07.533307] INFO: moduleinvoker: cached.v3 运行完成[0.392388s].

[2022-05-30 17:01:07.542158] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-05-30 17:01:07.741158] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.198981s].

[2022-05-30 17:01:07.750588] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 17:01:10.276935] INFO: join: /data, 行数=2596/2620, 耗时=0.192076s

[2022-05-30 17:01:10.314990] INFO: join: 最终行数: 2596

[2022-05-30 17:01:10.331026] INFO: moduleinvoker: join.v3 运行完成[2.580438s].

[2022-05-30 17:01:10.341658] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 17:01:11.455320] INFO: join: /data, 行数=390/268823, 耗时=1.033576s

[2022-05-30 17:01:11.507249] INFO: join: 最终行数: 390

[2022-05-30 17:01:11.517337] INFO: moduleinvoker: join.v3 运行完成[1.175677s].

[2022-05-30 17:01:11.524133] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 17:01:11.650311] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.006s

[2022-05-30 17:01:11.693805] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.041s

[2022-05-30 17:01:11.785522] INFO: derived_feature_extractor: /data, 2596

[2022-05-30 17:01:11.843112] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.318959s].

[2022-05-30 17:01:11.850254] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-30 17:01:11.918026] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-05-30 17:01:11.939208] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.019s

[2022-05-30 17:01:11.990424] INFO: derived_feature_extractor: /data, 390

[2022-05-30 17:01:12.051737] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.201471s].

[2022-05-30 17:01:12.060789] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-30 17:01:12.517503] INFO: join: /data, 行数=2531/2596, 耗时=0.089235s

[2022-05-30 17:01:12.543955] INFO: join: 最终行数: 2531

[2022-05-30 17:01:12.553838] INFO: moduleinvoker: join.v3 运行完成[0.493044s].

[2022-05-30 17:01:12.563383] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:01:12.730171] INFO: moduleinvoker: cached.v3 运行完成[0.166781s].

[2022-05-30 17:01:12.743301] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-05-30 17:01:12.830128] INFO: StockRanker: 特征预处理 ..

[2022-05-30 17:01:12.852792] INFO: StockRanker: prepare data: training ..

[2022-05-30 17:01:12.955981] INFO: StockRanker训练: 0e12b3f2 准备训练: 2531 行数

[2022-05-30 17:01:12.957936] INFO: StockRanker训练: AI模型训练，将在2531*3=0.76万数据上对模型训练进行2轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-05-30 17:01:13.185675] INFO: StockRanker训练: 正在训练 ..

[2022-05-30 17:01:13.238512] INFO: StockRanker训练: 任务状态: Pending

[2022-05-30 17:01:23.286094] INFO: StockRanker训练: 任务状态: Running

[2022-05-30 17:02:23.538445] INFO: StockRanker训练: 00:01:01.6159058, finished iteration 1

[2022-05-30 17:02:23.539878] INFO: StockRanker训练: 00:01:01.6224995, finished iteration 2

[2022-05-30 17:02:23.540876] INFO: StockRanker训练: 任务状态: Succeeded

[2022-05-30 17:02:23.727851] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[70.984551s].

[2022-05-30 17:02:23.747610] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-05-30 17:02:23.831401] INFO: StockRanker预测: /data ..

[2022-05-30 17:02:23.918151] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.170539s].

[2022-05-30 17:02:23.932575] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-30 17:02:24.012607] INFO: moduleinvoker: cached.v3 运行完成[0.080036s].

[2022-05-30 17:02:24.042401] INFO: moduleinvoker: hfbacktest.v1 开始运行..

[2022-05-30 17:02:24.048059] INFO: hfbacktest: biglearning V1.4.11

[2022-05-30 17:02:24.049494] INFO: hfbacktest: bigtrader v1.9.6 2022-05-24

[2022-05-30 17:02:24.074456] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 17:02:24.082888] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:02:24.084946] INFO: moduleinvoker: cached.v2 运行完成[0.010511s].

[2022-05-30 17:02:24.140927] INFO: moduleinvoker: cached.v2 开始运行..

[2022-05-30 17:02:24.150683] INFO: moduleinvoker: 命中缓存

[2022-05-30 17:02:24.152295] INFO: moduleinvoker: cached.v2 运行完成[0.011398s].

[2022-05-30 17:02:26.701957] INFO: hfbacktest: backtest done, raw_perf_ds:DataSource(cdb90a71836744e58dc91192f92b6b5aT)

[2022-05-30 17:02:27.201654] INFO: moduleinvoker: hfbacktest.v1 运行完成[3.159273s].

[2022-05-30 17:02:27.203275] INFO: moduleinvoker: hftrade.v2 运行完成[3.184651s].

[2022-05-30 17:02:27.205937] INFO: moduleinvoker: hyper_parameter_search.v1 运行完成[410.103484s].

Fitting 1 folds for each of 4 candidates, totalling 4 fits
[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.
[CV 1/1; 1/4] START m14.params={"stock_count": 3, "hold_days": 3}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100

Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')
Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')

Index(['instrument', 'date', 'pre_close', 'name_x', 'open', 'high', 'low',
       'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close',
       'bond_prem_ratio', 'close', 'close_equ', 'conversion_chg_pct',
       'conversion_chg_pct_week', 'conversion_price', 'equ_name',
       'equ_trading_code', 'name_y', 'pure_bond_prem_ratio', 'pure_bond_ratio',
       'redemption_price', 'remain_size', 'total_size', 'trading_code',
       'double_low', 'rank_swing_volatility_5'],
      dtype='object')

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-ed406b1d8a594a99af8002c574119959"}/bigcharts-data-end

{'data': DataSource(7a989652ccb74dbca7694ab017189a6cT)}
          date  instrument     score  position
0   2021-05-06  123096.ZCB  0.104772         1
1   2021-05-06  123084.ZCB  0.104772         2
2   2021-05-06  123050.ZCB  0.104772         3
3   2021-05-06  113530.HCB  0.104772         4
4   2021-05-06  113033.HCB  0.104199         5
..         ...         ...       ...       ...
385 2021-06-30  128143.ZCB -0.070900         6
386 2021-06-30  127021.ZCB -0.070900         7
387 2021-06-30  128141.ZCB -0.084736         8
388 2021-06-30  123042.ZCB -0.372995         9
389 2021-06-30  123043.ZCB -0.372995        10

[390 rows x 4 columns]
处理data BarDatas(current_dt:2021-05-06 15:00:00)
处理data BarDatas(current_dt:2021-05-07 15:00:00)
处理data BarDatas(current_dt:2021-05-10 15:00:00)
处理data BarDatas(current_dt:2021-05-11 15:00:00)
2022-05-30 16:56:54.091438 market open send order=OrderReq(bkt000,128096.ZCB,'1','0',0,124.956,U,0,strategy,2021-05-11 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:56:54.092452 market open send order=OrderReq(bkt000,123059.ZCB,'1','0',0,101.0,U,0,strategy,2021-05-11 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-12 15:00:00)
处理data BarDatas(current_dt:2021-05-13 15:00:00)
处理data BarDatas(current_dt:2021-05-14 15:00:00)
处理data BarDatas(current_dt:2021-05-17 15:00:00)
处理data BarDatas(current_dt:2021-05-18 15:00:00)
处理data BarDatas(current_dt:2021-05-19 15:00:00)
2022-05-30 16:56:54.255806 market open send order=OrderReq(bkt000,113600.HCB,'1','0',0,94.47,U,0,strategy,2021-05-19 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:56:54.256485 market open send order=OrderReq(bkt000,128123.ZCB,'1','0',0,104.1999,U,0,strategy,2021-05-19 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-20 15:00:00)
处理data BarDatas(current_dt:2021-05-21 15:00:00)
处理data BarDatas(current_dt:2021-05-24 15:00:00)
处理data BarDatas(current_dt:2021-05-25 15:00:00)
处理data BarDatas(current_dt:2021-05-26 15:00:00)
处理data BarDatas(current_dt:2021-05-27 15:00:00)
2022-05-30 16:56:54.405081 market open send order=OrderReq(bkt000,128097.ZCB,'1','0',0,173.388,U,0,strategy,2021-05-27 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:56:54.405638 market open send order=OrderReq(bkt000,128095.ZCB,'1','0',0,231.1999,U,0,strategy,2021-05-27 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-28 15:00:00)
处理data BarDatas(current_dt:2021-05-31 15:00:00)
处理data BarDatas(current_dt:2021-06-01 15:00:00)
处理data BarDatas(current_dt:2021-06-02 15:00:00)
处理data BarDatas(current_dt:2021-06-03 15:00:00)
处理data BarDatas(current_dt:2021-06-04 15:00:00)
2022-05-30 16:56:54.573504 market open send order=OrderReq(bkt000,113593.HCB,'1','0',0,107.8799,U,0,strategy,2021-06-04 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:56:54.574173 market open send order=OrderReq(bkt000,110055.HCB,'1','0',0,209.0399,U,0,strategy,2021-06-04 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-07 15:00:00)
处理data BarDatas(current_dt:2021-06-08 15:00:00)
处理data BarDatas(current_dt:2021-06-09 15:00:00)
处理data BarDatas(current_dt:2021-06-10 15:00:00)
处理data BarDatas(current_dt:2021-06-11 15:00:00)
处理data BarDatas(current_dt:2021-06-15 15:00:00)
2022-05-30 16:56:54.730812 market open send order=OrderReq(bkt000,128106.ZCB,'1','0',0,110.3499,U,0,strategy,2021-06-15 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:56:54.731387 market open send order=OrderReq(bkt000,113588.HCB,'1','0',0,106.8199,U,0,strategy,2021-06-15 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-16 15:00:00)
处理data BarDatas(current_dt:2021-06-17 15:00:00)
处理data BarDatas(current_dt:2021-06-18 15:00:00)
处理data BarDatas(current_dt:2021-06-21 15:00:00)
处理data BarDatas(current_dt:2021-06-22 15:00:00)
处理data BarDatas(current_dt:2021-06-23 15:00:00)
2022-05-30 16:56:54.883123 market open send order=OrderReq(bkt000,110065.HCB,'1','0',0,132.96,U,0,strategy,2021-06-23 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:56:54.883532 market open send order=OrderReq(bkt000,113598.HCB,'1','0',0,109.9199,U,0,strategy,2021-06-23 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-24 15:00:00)
处理data BarDatas(current_dt:2021-06-25 15:00:00)
处理data BarDatas(current_dt:2021-06-28 15:00:00)
处理data BarDatas(current_dt:2021-06-29 15:00:00)
处理data BarDatas(current_dt:2021-06-30 15:00:00)

收益率3.04%
年化收益率20.41%
基准收益率3.22%
阿尔法0.18
贝塔0.03
夏普比率1.89
胜率0.58
盈亏比3.26
收益波动率8.88%
信息比率0.02
最大回撤2.2%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-f627b4dbfa0c494ba4ab895b87a685b9"}/bigcharts-data-end

[CV 1/1; 1/4] END m14.params={"stock_count": 3, "hold_days": 3}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100
    ; score: (test=1.890) total time= 1.3min
[Parallel(n_jobs=1)]: Done   1 out of   1 | elapsed:  1.3min remaining:    0.0s
[CV 1/1; 2/4] START m14.params={"stock_count": 3, "hold_days": 3}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100

Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')
Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')

Index(['instrument', 'date', 'pre_close', 'name_x', 'open', 'high', 'low',
       'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close',
       'bond_prem_ratio', 'close', 'close_equ', 'conversion_chg_pct',
       'conversion_chg_pct_week', 'conversion_price', 'equ_name',
       'equ_trading_code', 'name_y', 'pure_bond_prem_ratio', 'pure_bond_ratio',
       'redemption_price', 'remain_size', 'total_size', 'trading_code',
       'double_low', 'rank_swing_volatility_5'],
      dtype='object')

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-2c05e806b7d540149fa5fbd382811016"}/bigcharts-data-end

{'data': DataSource(88a9497f1b9b42fcac015bc13286729aT)}
          date  instrument     score  position
0   2021-05-06  113013.HCB  0.236329         1
1   2021-05-06  113033.HCB  0.079207         2
2   2021-05-06  123096.ZCB  0.079207         3
3   2021-05-06  128119.ZCB  0.079207         4
4   2021-05-06  123084.ZCB  0.079207         5
..         ...         ...       ...       ...
385 2021-06-30  123113.ZCB  0.079207         6
386 2021-06-30  123043.ZCB  0.079207         7
387 2021-06-30  127021.ZCB -0.027755         8
388 2021-06-30  128141.ZCB -0.295625         9
389 2021-06-30  123042.ZCB -0.362367        10

[390 rows x 4 columns]
处理data BarDatas(current_dt:2021-05-06 15:00:00)
处理data BarDatas(current_dt:2021-05-07 15:00:00)
处理data BarDatas(current_dt:2021-05-10 15:00:00)
处理data BarDatas(current_dt:2021-05-11 15:00:00)
2022-05-30 16:58:14.230324 market open send order=OrderReq(bkt000,128120.ZCB,'1','0',0,103.0039,U,0,strategy,2021-05-11 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:58:14.231109 market open send order=OrderReq(bkt000,128096.ZCB,'1','0',0,124.956,U,0,strategy,2021-05-11 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-12 15:00:00)
处理data BarDatas(current_dt:2021-05-13 15:00:00)
处理data BarDatas(current_dt:2021-05-14 15:00:00)
处理data BarDatas(current_dt:2021-05-17 15:00:00)
处理data BarDatas(current_dt:2021-05-18 15:00:00)
处理data BarDatas(current_dt:2021-05-19 15:00:00)
2022-05-30 16:58:14.365400 market open send order=OrderReq(bkt000,113013.HCB,'1','0',0,114.66,U,0,strategy,2021-05-19 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:58:14.365768 market open send order=OrderReq(bkt000,128013.ZCB,'1','0',0,105.415,U,0,strategy,2021-05-19 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-20 15:00:00)
处理data BarDatas(current_dt:2021-05-21 15:00:00)
处理data BarDatas(current_dt:2021-05-24 15:00:00)
处理data BarDatas(current_dt:2021-05-25 15:00:00)
处理data BarDatas(current_dt:2021-05-26 15:00:00)
处理data BarDatas(current_dt:2021-05-27 15:00:00)
2022-05-30 16:58:14.500288 market open send order=OrderReq(bkt000,123085.ZCB,'1','0',0,97.4649,U,0,strategy,2021-05-27 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:58:14.500676 market open send order=OrderReq(bkt000,110034.HCB,'1','0',0,109.9899,U,0,strategy,2021-05-27 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-28 15:00:00)
处理data BarDatas(current_dt:2021-05-31 15:00:00)
处理data BarDatas(current_dt:2021-06-01 15:00:00)
处理data BarDatas(current_dt:2021-06-02 15:00:00)
处理data BarDatas(current_dt:2021-06-03 15:00:00)
处理data BarDatas(current_dt:2021-06-04 15:00:00)
2022-05-30 16:58:14.631682 market open send order=OrderReq(bkt000,113043.HCB,'1','0',0,108.98,U,0,strategy,2021-06-04 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:58:14.632018 market open send order=OrderReq(bkt000,123073.ZCB,'1','0',0,121.772,U,0,strategy,2021-06-04 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-07 15:00:00)
处理data BarDatas(current_dt:2021-06-08 15:00:00)
处理data BarDatas(current_dt:2021-06-09 15:00:00)
处理data BarDatas(current_dt:2021-06-10 15:00:00)
处理data BarDatas(current_dt:2021-06-11 15:00:00)
处理data BarDatas(current_dt:2021-06-15 15:00:00)
2022-05-30 16:58:14.770168 market open send order=OrderReq(bkt000,113610.HCB,'1','0',0,103.9899,U,0,strategy,2021-06-15 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:58:14.770537 market open send order=OrderReq(bkt000,128106.ZCB,'1','0',0,110.3499,U,0,strategy,2021-06-15 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-16 15:00:00)
处理data BarDatas(current_dt:2021-06-17 15:00:00)
处理data BarDatas(current_dt:2021-06-18 15:00:00)
处理data BarDatas(current_dt:2021-06-21 15:00:00)
处理data BarDatas(current_dt:2021-06-22 15:00:00)
处理data BarDatas(current_dt:2021-06-23 15:00:00)
2022-05-30 16:58:14.907513 market open send order=OrderReq(bkt000,110065.HCB,'1','0',0,132.96,U,0,strategy,2021-06-23 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:58:14.907857 market open send order=OrderReq(bkt000,113598.HCB,'1','0',0,109.9199,U,0,strategy,2021-06-23 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-24 15:00:00)
处理data BarDatas(current_dt:2021-06-25 15:00:00)
处理data BarDatas(current_dt:2021-06-28 15:00:00)
处理data BarDatas(current_dt:2021-06-29 15:00:00)
处理data BarDatas(current_dt:2021-06-30 15:00:00)

收益率9.67%
年化收益率77.36%
基准收益率3.22%
阿尔法0.83
贝塔-0.21
夏普比率3.3
胜率0.62
盈亏比9.36
收益波动率17.64%
信息比率0.12
最大回撤0.66%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-74cf6d69bd954e2e94e9aa8e84a4c124"}/bigcharts-data-end

[CV 1/1; 2/4] END m14.params={"stock_count": 3, "hold_days": 3}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100
    ; score: (test=3.302) total time= 1.3min
[Parallel(n_jobs=1)]: Done   2 out of   2 | elapsed:  2.7min remaining:    0.0s
[CV 1/1; 3/4] START m14.params={"stock_count": 4, "hold_days": 4}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100

Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')
Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')

Index(['instrument', 'date', 'pre_close', 'name_x', 'open', 'high', 'low',
       'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close',
       'bond_prem_ratio', 'close', 'close_equ', 'conversion_chg_pct',
       'conversion_chg_pct_week', 'conversion_price', 'equ_name',
       'equ_trading_code', 'name_y', 'pure_bond_prem_ratio', 'pure_bond_ratio',
       'redemption_price', 'remain_size', 'total_size', 'trading_code',
       'double_low', 'rank_swing_volatility_5'],
      dtype='object')

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-7f7d83177bda4b30a6ed48af05ad9f5c"}/bigcharts-data-end

{'data': DataSource(479d6093d2594a818605e6068beef944T)}
          date  instrument     score  position
0   2021-05-06  123096.ZCB  0.104772         1
1   2021-05-06  123084.ZCB  0.104772         2
2   2021-05-06  123050.ZCB  0.104772         3
3   2021-05-06  113530.HCB  0.104772         4
4   2021-05-06  113033.HCB  0.104199         5
..         ...         ...       ...       ...
385 2021-06-30  128143.ZCB -0.070900         6
386 2021-06-30  127021.ZCB -0.070900         7
387 2021-06-30  128141.ZCB -0.084736         8
388 2021-06-30  123042.ZCB -0.372995         9
389 2021-06-30  123043.ZCB -0.372995        10

[390 rows x 4 columns]
处理data BarDatas(current_dt:2021-05-06 15:00:00)
处理data BarDatas(current_dt:2021-05-07 15:00:00)
处理data BarDatas(current_dt:2021-05-10 15:00:00)
处理data BarDatas(current_dt:2021-05-11 15:00:00)
处理data BarDatas(current_dt:2021-05-12 15:00:00)
2022-05-30 16:59:44.901580 market open send order=OrderReq(bkt000,123100.ZCB,'1','0',0,112.0,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:44.901918 market open send order=OrderReq(bkt000,123068.ZCB,'1','0',0,104.7968,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:44.902207 market open send order=OrderReq(bkt000,128033.ZCB,'1','0',0,146.5,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:44.902499 market open send order=OrderReq(bkt000,128013.ZCB,'1','0',0,105.3359,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-13 15:00:00)
处理data BarDatas(current_dt:2021-05-14 15:00:00)
处理data BarDatas(current_dt:2021-05-17 15:00:00)
处理data BarDatas(current_dt:2021-05-18 15:00:00)
处理data BarDatas(current_dt:2021-05-19 15:00:00)
处理data BarDatas(current_dt:2021-05-20 15:00:00)
处理data BarDatas(current_dt:2021-05-21 15:00:00)
处理data BarDatas(current_dt:2021-05-24 15:00:00)
2022-05-30 16:59:45.069577 market open send order=OrderReq(bkt000,128106.ZCB,'1','0',0,112.022,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.069947 market open send order=OrderReq(bkt000,128082.ZCB,'1','0',0,122.0,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.070237 market open send order=OrderReq(bkt000,123007.ZCB,'1','0',0,108.3,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.070538 market open send order=OrderReq(bkt000,123105.ZCB,'1','0',0,102.0199,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-25 15:00:00)
处理data BarDatas(current_dt:2021-05-26 15:00:00)
处理data BarDatas(current_dt:2021-05-27 15:00:00)
处理data BarDatas(current_dt:2021-05-28 15:00:00)
处理data BarDatas(current_dt:2021-05-31 15:00:00)
处理data BarDatas(current_dt:2021-06-01 15:00:00)
处理data BarDatas(current_dt:2021-06-02 15:00:00)
处理data BarDatas(current_dt:2021-06-03 15:00:00)
2022-05-30 16:59:45.280712 market open send order=OrderReq(bkt000,113568.HCB,'1','0',0,109.5299,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.281083 market open send order=OrderReq(bkt000,113604.HCB,'1','0',0,110.1699,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.281679 market open send order=OrderReq(bkt000,123056.ZCB,'1','0',0,103.51,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.281982 market open send order=OrderReq(bkt000,128025.ZCB,'1','0',0,127.3639,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-04 15:00:00)
处理data BarDatas(current_dt:2021-06-07 15:00:00)
处理data BarDatas(current_dt:2021-06-08 15:00:00)
处理data BarDatas(current_dt:2021-06-09 15:00:00)
处理data BarDatas(current_dt:2021-06-10 15:00:00)
处理data BarDatas(current_dt:2021-06-11 15:00:00)
处理data BarDatas(current_dt:2021-06-15 15:00:00)
处理data BarDatas(current_dt:2021-06-16 15:00:00)
2022-05-30 16:59:45.483283 market open send order=OrderReq(bkt000,123080.ZCB,'1','0',0,107.0,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.483924 market open send order=OrderReq(bkt000,128075.ZCB,'1','0',0,117.315,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.484224 market open send order=OrderReq(bkt000,123078.ZCB,'1','0',0,115.273,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.484526 market open send order=OrderReq(bkt000,128083.ZCB,'1','0',0,103.1999,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-17 15:00:00)
处理data BarDatas(current_dt:2021-06-18 15:00:00)
处理data BarDatas(current_dt:2021-06-21 15:00:00)
处理data BarDatas(current_dt:2021-06-22 15:00:00)
处理data BarDatas(current_dt:2021-06-23 15:00:00)
处理data BarDatas(current_dt:2021-06-24 15:00:00)
处理data BarDatas(current_dt:2021-06-25 15:00:00)
处理data BarDatas(current_dt:2021-06-28 15:00:00)
2022-05-30 16:59:45.656546 market open send order=OrderReq(bkt000,127031.ZCB,'1','0',0,117.3,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
2022-05-30 16:59:45.657119 market open send order=OrderReq(bkt000,128135.ZCB,'1','0',0,114.9,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-29 15:00:00)
处理data BarDatas(current_dt:2021-06-30 15:00:00)

收益率5.41%
年化收益率38.69%
基准收益率3.22%
阿尔法0.35
贝塔0.12
夏普比率4.43
胜率0.47
盈亏比6.26
收益波动率7.09%
信息比率0.08
最大回撤1.29%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-a69218d2d52b4b4d959af6438b5822a4"}/bigcharts-data-end

[CV 1/1; 3/4] END m14.params={"stock_count": 4, "hold_days": 4}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100
    ; score: (test=4.426) total time= 1.5min
[Parallel(n_jobs=1)]: Done   3 out of   3 | elapsed:  4.2min remaining:    0.0s
[CV 1/1; 4/4] START m14.params={"stock_count": 4, "hold_days": 4}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100

Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')
Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')

Index(['instrument', 'date', 'pre_close', 'name_x', 'open', 'high', 'low',
       'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close',
       'bond_prem_ratio', 'close', 'close_equ', 'conversion_chg_pct',
       'conversion_chg_pct_week', 'conversion_price', 'equ_name',
       'equ_trading_code', 'name_y', 'pure_bond_prem_ratio', 'pure_bond_ratio',
       'redemption_price', 'remain_size', 'total_size', 'trading_code',
       'double_low', 'rank_swing_volatility_5'],
      dtype='object')

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-c7ef4cdc5d8f4abba264d29741a3ac24"}/bigcharts-data-end

{'data': DataSource(7a96e4075297483bbf4a5f9e680c67caT)}
          date  instrument     score  position
0   2021-05-06  113013.HCB  0.236329         1
1   2021-05-06  113033.HCB  0.079207         2
2   2021-05-06  123096.ZCB  0.079207         3
3   2021-05-06  128119.ZCB  0.079207         4
4   2021-05-06  123084.ZCB  0.079207         5
..         ...         ...       ...       ...
385 2021-06-30  123113.ZCB  0.079207         6
386 2021-06-30  123043.ZCB  0.079207         7
387 2021-06-30  127021.ZCB -0.027755         8
388 2021-06-30  128141.ZCB -0.295625         9
389 2021-06-30  123042.ZCB -0.362367        10

[390 rows x 4 columns]
处理data BarDatas(current_dt:2021-05-06 15:00:00)
处理data BarDatas(current_dt:2021-05-07 15:00:00)
处理data BarDatas(current_dt:2021-05-10 15:00:00)
处理data BarDatas(current_dt:2021-05-11 15:00:00)
处理data BarDatas(current_dt:2021-05-12 15:00:00)
2022-05-30 17:01:04.363019 market open send order=OrderReq(bkt000,128013.ZCB,'1','0',0,105.3359,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.363672 market open send order=OrderReq(bkt000,128081.ZCB,'1','0',0,109.857,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.364052 market open send order=OrderReq(bkt000,123100.ZCB,'1','0',0,112.0,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.364436 market open send order=OrderReq(bkt000,123068.ZCB,'1','0',0,104.7968,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-13 15:00:00)
处理data BarDatas(current_dt:2021-05-14 15:00:00)
处理data BarDatas(current_dt:2021-05-17 15:00:00)
处理data BarDatas(current_dt:2021-05-18 15:00:00)
处理data BarDatas(current_dt:2021-05-19 15:00:00)
处理data BarDatas(current_dt:2021-05-20 15:00:00)
处理data BarDatas(current_dt:2021-05-21 15:00:00)
处理data BarDatas(current_dt:2021-05-24 15:00:00)
2022-05-30 17:01:04.548068 market open send order=OrderReq(bkt000,128129.ZCB,'1','0',0,108.361,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.548428 market open send order=OrderReq(bkt000,128106.ZCB,'1','0',0,112.022,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.548816 market open send order=OrderReq(bkt000,128082.ZCB,'1','0',0,122.0,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.549097 market open send order=OrderReq(bkt000,123007.ZCB,'1','0',0,108.3,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-25 15:00:00)
处理data BarDatas(current_dt:2021-05-26 15:00:00)
处理data BarDatas(current_dt:2021-05-27 15:00:00)
处理data BarDatas(current_dt:2021-05-28 15:00:00)
处理data BarDatas(current_dt:2021-05-31 15:00:00)
处理data BarDatas(current_dt:2021-06-01 15:00:00)
处理data BarDatas(current_dt:2021-06-02 15:00:00)
处理data BarDatas(current_dt:2021-06-03 15:00:00)
2022-05-30 17:01:04.727489 market open send order=OrderReq(bkt000,113568.HCB,'1','0',0,109.5299,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.728114 market open send order=OrderReq(bkt000,113604.HCB,'1','0',0,110.1699,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.728442 market open send order=OrderReq(bkt000,113561.HCB,'1','0',0,110.0299,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.728901 market open send order=OrderReq(bkt000,123056.ZCB,'1','0',0,103.51,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-04 15:00:00)
处理data BarDatas(current_dt:2021-06-07 15:00:00)
处理data BarDatas(current_dt:2021-06-08 15:00:00)
处理data BarDatas(current_dt:2021-06-09 15:00:00)
处理data BarDatas(current_dt:2021-06-10 15:00:00)
处理data BarDatas(current_dt:2021-06-11 15:00:00)
处理data BarDatas(current_dt:2021-06-15 15:00:00)
处理data BarDatas(current_dt:2021-06-16 15:00:00)
2022-05-30 17:01:04.916973 market open send order=OrderReq(bkt000,123080.ZCB,'1','0',0,107.0,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.917351 market open send order=OrderReq(bkt000,128081.ZCB,'1','0',0,108.1999,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.917696 market open send order=OrderReq(bkt000,128075.ZCB,'1','0',0,117.315,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:04.918034 market open send order=OrderReq(bkt000,123078.ZCB,'1','0',0,115.273,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-17 15:00:00)
处理data BarDatas(current_dt:2021-06-18 15:00:00)
处理data BarDatas(current_dt:2021-06-21 15:00:00)
处理data BarDatas(current_dt:2021-06-22 15:00:00)
处理data BarDatas(current_dt:2021-06-23 15:00:00)
处理data BarDatas(current_dt:2021-06-24 15:00:00)
处理data BarDatas(current_dt:2021-06-25 15:00:00)
处理data BarDatas(current_dt:2021-06-28 15:00:00)
2022-05-30 17:01:05.098326 market open send order=OrderReq(bkt000,123084.ZCB,'1','0',0,109.9,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:05.098819 market open send order=OrderReq(bkt000,123071.ZCB,'1','0',0,116.65,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:01:05.100643 market open send order=OrderReq(bkt000,123073.ZCB,'1','0',0,116.72,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-29 15:00:00)
处理data BarDatas(current_dt:2021-06-30 15:00:00)

收益率13.02%
年化收益率113.76%
基准收益率3.22%
阿尔法1.21
贝塔-0.11
夏普比率3.83
胜率0.68
盈亏比16.79
收益波动率20.43%
信息比率0.16
最大回撤1.32%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-98ad20ef0e8049279cd4c426c71e6293"}/bigcharts-data-end

[CV 1/1; 4/4] END m14.params={"stock_count": 4, "hold_days": 4}, m3.features=
    double_low = close + bond_prem_ratio
    remain_size
    rank_swing_volatility_5 = nanstd((high-low)/pre_close, 120)*sqrt(200)*100
    ; score: (test=3.829) total time= 1.3min
[Parallel(n_jobs=1)]: Done   4 out of   4 | elapsed:  5.5min remaining:    0.0s
[Parallel(n_jobs=1)]: Done   4 out of   4 | elapsed:  5.5min finished

Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')
Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name', 'trading_code',
       'conversion_chg_pct_week', 'bond_prem_ratio', 'equ_name',
       'redemption_price', 'close_equ', 'total_size', 'pure_bond_prem_ratio',
       'pure_bond_ratio', 'close'],
      dtype='object')

Index(['instrument', 'date', 'pre_close', 'name_x', 'open', 'high', 'low',
       'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close',
       'bond_prem_ratio', 'close', 'close_equ', 'conversion_chg_pct',
       'conversion_chg_pct_week', 'conversion_price', 'equ_name',
       'equ_trading_code', 'name_y', 'pure_bond_prem_ratio', 'pure_bond_ratio',
       'redemption_price', 'remain_size', 'total_size', 'trading_code',
       'double_low', 'rank_swing_volatility_5'],
      dtype='object')

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-2a01568125744a21aa58f55ab01661f4"}/bigcharts-data-end

{'data': DataSource(fc3beb3cc2324a5a880b046eee6875ebT)}
          date  instrument     score  position
0   2021-05-06  123096.ZCB  0.104772         1
1   2021-05-06  123084.ZCB  0.104772         2
2   2021-05-06  123050.ZCB  0.104772         3
3   2021-05-06  113530.HCB  0.104772         4
4   2021-05-06  113033.HCB  0.104199         5
..         ...         ...       ...       ...
385 2021-06-30  128143.ZCB -0.070900         6
386 2021-06-30  127021.ZCB -0.070900         7
387 2021-06-30  128141.ZCB -0.084736         8
388 2021-06-30  123042.ZCB -0.372995         9
389 2021-06-30  123043.ZCB -0.372995        10

[390 rows x 4 columns]
处理data BarDatas(current_dt:2021-05-06 15:00:00)
处理data BarDatas(current_dt:2021-05-07 15:00:00)
处理data BarDatas(current_dt:2021-05-10 15:00:00)
处理data BarDatas(current_dt:2021-05-11 15:00:00)
处理data BarDatas(current_dt:2021-05-12 15:00:00)
2022-05-30 17:02:24.494349 market open send order=OrderReq(bkt000,123100.ZCB,'1','0',0,112.0,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.495066 market open send order=OrderReq(bkt000,123068.ZCB,'1','0',0,104.7968,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.496354 market open send order=OrderReq(bkt000,128033.ZCB,'1','0',0,146.5,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.496971 market open send order=OrderReq(bkt000,128013.ZCB,'1','0',0,105.3359,U,0,strategy,2021-05-12 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-13 15:00:00)
处理data BarDatas(current_dt:2021-05-14 15:00:00)
处理data BarDatas(current_dt:2021-05-17 15:00:00)
处理data BarDatas(current_dt:2021-05-18 15:00:00)
处理data BarDatas(current_dt:2021-05-19 15:00:00)
处理data BarDatas(current_dt:2021-05-20 15:00:00)
处理data BarDatas(current_dt:2021-05-21 15:00:00)
处理data BarDatas(current_dt:2021-05-24 15:00:00)
2022-05-30 17:02:24.724547 market open send order=OrderReq(bkt000,128106.ZCB,'1','0',0,112.022,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.725297 market open send order=OrderReq(bkt000,128082.ZCB,'1','0',0,122.0,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.725885 market open send order=OrderReq(bkt000,123007.ZCB,'1','0',0,108.3,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.726531 market open send order=OrderReq(bkt000,123105.ZCB,'1','0',0,102.0199,U,0,strategy,2021-05-24 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-05-25 15:00:00)
处理data BarDatas(current_dt:2021-05-26 15:00:00)
处理data BarDatas(current_dt:2021-05-27 15:00:00)
处理data BarDatas(current_dt:2021-05-28 15:00:00)
处理data BarDatas(current_dt:2021-05-31 15:00:00)
处理data BarDatas(current_dt:2021-06-01 15:00:00)
处理data BarDatas(current_dt:2021-06-02 15:00:00)
处理data BarDatas(current_dt:2021-06-03 15:00:00)
2022-05-30 17:02:24.928079 market open send order=OrderReq(bkt000,113568.HCB,'1','0',0,109.5299,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.928505 market open send order=OrderReq(bkt000,113604.HCB,'1','0',0,110.1699,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.928831 market open send order=OrderReq(bkt000,123056.ZCB,'1','0',0,103.51,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:24.929133 market open send order=OrderReq(bkt000,128025.ZCB,'1','0',0,127.3639,U,0,strategy,2021-06-03 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-04 15:00:00)
处理data BarDatas(current_dt:2021-06-07 15:00:00)
处理data BarDatas(current_dt:2021-06-08 15:00:00)
处理data BarDatas(current_dt:2021-06-09 15:00:00)
处理data BarDatas(current_dt:2021-06-10 15:00:00)
处理data BarDatas(current_dt:2021-06-11 15:00:00)
处理data BarDatas(current_dt:2021-06-15 15:00:00)
处理data BarDatas(current_dt:2021-06-16 15:00:00)
2022-05-30 17:02:25.168387 market open send order=OrderReq(bkt000,123080.ZCB,'1','0',0,107.0,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:25.168755 market open send order=OrderReq(bkt000,128075.ZCB,'1','0',0,117.315,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:25.169049 market open send order=OrderReq(bkt000,123078.ZCB,'1','0',0,115.273,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:25.169333 market open send order=OrderReq(bkt000,128083.ZCB,'1','0',0,103.1999,U,0,strategy,2021-06-16 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-17 15:00:00)
处理data BarDatas(current_dt:2021-06-18 15:00:00)
处理data BarDatas(current_dt:2021-06-21 15:00:00)
处理data BarDatas(current_dt:2021-06-22 15:00:00)
处理data BarDatas(current_dt:2021-06-23 15:00:00)
处理data BarDatas(current_dt:2021-06-24 15:00:00)
处理data BarDatas(current_dt:2021-06-25 15:00:00)
处理data BarDatas(current_dt:2021-06-28 15:00:00)
2022-05-30 17:02:25.348569 market open send order=OrderReq(bkt000,127031.ZCB,'1','0',0,117.3,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
2022-05-30 17:02:25.349231 market open send order=OrderReq(bkt000,128135.ZCB,'1','0',0,114.9,U,0,strategy,2021-06-28 15:00:00) failed err=-108,委托数量错误 
处理data BarDatas(current_dt:2021-06-29 15:00:00)
处理data BarDatas(current_dt:2021-06-30 15:00:00)

收益率5.41%
年化收益率38.69%
基准收益率3.22%
阿尔法0.35
贝塔0.12
夏普比率4.43
胜率0.47
盈亏比6.26
收益波动率7.09%
信息比率0.08
最大回撤1.29%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-b8cedec7cddd42a39eb6ee8c605e24ec"}/bigcharts-data-end