复制链接

克隆策略

In [ ]:

# <b>StockRanker多因子选股策略</b>

In [7]:

In [8]:

param_grid

Out[8]:

{'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 [7]:

def bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    #time == data.current_dt.strftime('%Y-%m-%d%H%M%S')
    now = context.now()
    print(now)
    if str(now) == '14:33:30' :
        context.order_target('000001', 0.05)
        context.order_target('110041.HCB', 0.05)

In [5]:

In [7]:

# 回测引擎：每日数据处理函数，每天执行一次
def bigquant_run(context, data):
    print(context.trading_day_index)
    try:
        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
        print("buy_cash_weights",buy_cash_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
        print("<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<")
        # 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
                if context.order_target_percent(context.symbol(stock), 0) != 0:
                    print('sell_context.symbol',context.symbol(stock))

        # 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 > 500:
                if context.order_value(context.symbol(instrument), cash) !=0:
                    print('fail_order_value',cash)            
    except Exception as e:
        print('抛出异常',e)
        logger.exception("限价单下买单失败%s,%s",context,e)

Out[7]:

{'m14.params': ['{"stock_count": 3, "hold_days": 3}',
  '{"stock_count": 4, "hold_days": 4}'],
 '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, 6)*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 [4]:

context.order_value(context.symbol('128143'), 180.22)

---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
KeyError: ('128143', '')

During handling of the above exception, another exception occurred:

SymbolNotFound                            Traceback (most recent call last)
<ipython-input-4-bc156661722d> in <module>
----> 1 context.order_value(context.symbol('128143'), 180.22)

SymbolNotFound: Symbol '128143' was not found.

In [148]:

#m7.data.read_df().columns
#m17.predictions.read_df()
#m8.predictions.read_df().head(100)
#m8.predictions.read_df().tail(100)
#m2.data_2.read_df()
#m23.data_1.read_df()
#m23.data_2.read_df()
m1.data_2.read_df()

Out[148]:

	remain_size	instrument	equ_trading_code	conversion_chg_pct	date	conversion_price	name_x	trading_code	trigger_cond_item_desc	conversion_chg_pct_week	...	high	low	deal_number	volume	amount	accrued_interest	yield_to_maturity	vwap	gross_close	net_close
0	2.450000	128143.ZCB	002931.SZA	0.010510	2021-06-30	12.730000	锋龙转债	128143	nan	-0.037720	...	113.370003	110.880997	2376	159034	1.779515e+07	0.238356	NaN	111.894997	112.300003	112.061646
1	13.999382	128141.ZCB	002034.SZA	-0.005866	2021-06-30	15.970000	旺能转债	128141	在本次发行的可转债转股期内，当下述两种情形的任意一种出现时，公司有权决定\n按照债券面值加当...	0.000536	...	111.059998	110.033997	1018	141360	1.565561e+07	0.161096	NaN	110.750000	110.165001	110.003906
2	1.665203	123042.ZCB	300619.SZA	-0.018182	2021-06-30	24.379999	银河转债	123042	在本次发行的可转债转股期内，如果公司股票连续三十个交易日中至少有\n十五个交易日的收盘价不低...	-0.028078	...	137.770004	134.100006	17070	1268620	1.714824e+08	0.368219	NaN	135.171997	135.000000	134.631775
3	4.998169	123082.ZCB	300016.SZA	0.004045	2021-06-30	8.810000	北陆转债	123082	在本次发行的可转债转股期内，当下述情形的任意一种出现时，公司有权决定按照债\n券面值加当期应...	-0.022396	...	111.377998	110.599998	1103	153957	1.707730e+07	0.282192	NaN	110.922997	110.958000	110.675812
4	10.248929	123113.ZCB	300791.SZA	-0.000897	2021-06-30	56.919998	仙乐转债	123113	nan	0.038048	...	125.000000	120.300003	3372	191166	2.338253e+07	0.080000	NaN	122.315002	122.500000	122.419998
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
361	0.411376	113580.HCB	603665.SHA	-0.008848	2021-06-30	15.510000	康隆转债	113580	2）有条件赎回条款\n在本次发行的可转债转股期内，如果公司 A 股股票连续三十个交易日中至\...	-0.039733	...	252.000000	247.960007	2085	94110	2.346723e+07	0.151233	NaN	249.360001	248.690002	248.538773
362	5.438477	128075.ZCB	002406.SZA	-0.010150	2021-06-30	5.540000	远东转债	128075	转股期内，当下述两种情形的任意一种出现时，公司有权决定按照债券面值\n加当期应计利息的价格赎...	0.001107	...	120.599998	117.879997	2340	292623	3.465271e+07	0.461918	NaN	118.420998	118.489998	118.028084
363	4.797715	128066.ZCB	002811.SZA	0.004884	2021-06-30	9.270000	亚泰转债	128066	在本次发行的可转换公司债券转股期内，当下述两种情形的任意一种出现时，公司董事会有权决定按照债...	0.005050	...	103.500000	101.862999	1107	79185	8.131397e+06	0.246575	NaN	102.689003	103.499001	103.252426
364	6.028369	128037.ZCB	002542.SZA	0.006359	2021-06-30	3.130000	岩土转债	128037	转股期内，当下述两种情形的任意一种出现时，公司有权决定按照债券面值加当期应计利息的价格赎回全...	0.034069	...	108.169998	107.001999	2461	178113	1.921180e+07	0.443836	NaN	107.862999	107.780998	107.337166
365	6.827154	128074.ZCB	002174.SZA	-0.013923	2021-06-30	16.969999	游族转债	128074	在本次发行的可转换公司债券转股期内，当下述两种情形的任意一种出现时，公司董事会有权决定按照债...	0.000685	...	118.779999	116.860001	4179	353840	4.174239e+07	0.461918	NaN	117.970001	116.860001	116.398079

366 rows × 33 columns

In [34]:

# 本代码由可视化策略环境自动生成 2022年6月9日 02:06
# 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,start_date_input,end_date_input):
    # 示例代码如下。在这里编写您的代码
    df = DataSource("bar1d_CN_CONBOND").read(start_date=start_date_input, end_date=end_date_input)
    df1 = DataSource("market_performance_CN_CONBOND").read(start_date=start_date_input, end_date=end_date_input)
    df2 = df.drop(['close'],axis = 1)
    df3 = pd.merge(df1,df2,on=['date','instrument'],how='inner')
    data_1 = DataSource.write_df(df3)
    data_2 = DataSource.write_df(df3)
    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

# 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 m1_run_bigquant_run(input_1, input_2, input_3,start_date_input,end_date_input):
    # 示例代码如下。在这里编写您的代码
    df = DataSource("bar1d_CN_CONBOND").read(start_date=start_date_input, end_date=end_date_input)
    df1 = DataSource("market_performance_CN_CONBOND").read(start_date=start_date_input, end_date=end_date_input)
    df2 = df.drop(['close'],axis = 1)
    df3 = pd.merge(df1,df2,on=['date','instrument'],how='inner')
    data_1 = DataSource.write_df(df3)
    data_2 = DataSource.write_df(df3)
    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 m1_post_run_bigquant_run(outputs):
    return outputs

def del_input(input_1):
    df = input_1.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 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
    print('m11.input1',input_1)
    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('当前日期data.current_dt',data.current_dt)
    try:
        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
        print("buy_cash_weights",buy_cash_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
        print("<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<")
        # 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
                if context.order_target_percent(context.symbol(stock), 0) != 0:
                    print('sell_context.symbol',context.symbol(stock))

        # 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 > 500:
                if context.order_value(context.symbol(instrument), cash) !=0:
                    print('fail_order_value',cash)            
    except Exception as e:
        print('抛出异常',e)
        logger.exception("限价单下买单失败%s,%s",context,e)
                        
# 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': """{"start_date_input":"2017-06-01",
"end_date_input":"2019-11-01"}""",
    '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': {},

    '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": 4,
    "hold_days": 5 
}""",
    'm14.output_ports': '',

    'm1': 'M.cached.v3',
    'm1.run': m1_run_bigquant_run,
    'm1.post_run': m1_post_run_bigquant_run,
    'm1.input_ports': '',
    'm1.params': """{"start_date_input":"2021-01-05",
"end_date_input":"2021-06-19"}""",
    'm1.output_ports': '',

    'm23': 'M.cached.v3',
    'm23.input_1': T.Graph.OutputPort('m2.data_2'),
    'm23.input_2': T.Graph.OutputPort('m1.data_2'),
    '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,

    'm16': 'M.derived_feature_extractor.v3',
    'm16.input_data': T.Graph.OutputPort('m23.data_1'),
    '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': 20,
    '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,

    'm17': 'M.svr.v1',
    'm17.training_ds': T.Graph.OutputPort('m7.data'),
    'm17.C': 1,
    'm17.kernel': 'rbf',
    'm17.degree': 3,
    'm17.gamma': -1,
    'm17.coef0': 0,
    'm17.tol': 0.001,
    'm17.key_cols': 'date,instrument',
    'm17.other_train_parameters': {},

    'm18': 'M.derived_feature_extractor.v3',
    'm18.input_data': T.Graph.OutputPort('m23.data_2'),
    '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.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m18.data'),
    'm8.m_lazy_run': False,

    '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': '',

    'm12': 'M.trade_data_generation.v1',
    'm12.input': T.Graph.OutputPort('m1.data_2'),
    'm12.category': 'CN_STOCK',
    'm12.m_cached': False,

    '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': True,
    'm21.show_debug_info': True,
    'm21.backtest_only': False,
})

# g.run({})


def m9_param_grid_builder_bigquant_run():
    import itertools
    param_grid = {}
    
    period_list = [5,6,120] 
    
    # 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
)

[2022-06-09 02:03:23.652638] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-06-09 02:03:23.663044] INFO: moduleinvoker: 命中缓存

[2022-06-09 02:03:23.665280] INFO: moduleinvoker: input_features.v1 运行完成[0.012652s].

[2022-06-09 02:03:23.719983] INFO: moduleinvoker: cached.v3 开始运行..

[2022-06-09 02:03:23.737398] INFO: moduleinvoker: 命中缓存

[2022-06-09 02:03:23.739872] INFO: moduleinvoker: cached.v3 运行完成[0.019903s].

[2022-06-09 02:03:23.766262] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-06-09 02:03:23.779617] INFO: moduleinvoker: 命中缓存

[2022-06-09 02:03:23.782660] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.016399s].

[2022-06-09 02:03:23.816837] INFO: moduleinvoker: cached.v3 开始运行..

[2022-06-09 02:03:23.833683] INFO: moduleinvoker: 命中缓存

[2022-06-09 02:03:23.835928] INFO: moduleinvoker: cached.v3 运行完成[0.019114s].

[2022-06-09 02:03:23.858697] INFO: moduleinvoker: cached.v3 开始运行..

[2022-06-09 02:03:25.793639] INFO: moduleinvoker: cached.v3 运行完成[1.934939s].

[2022-06-09 02:03:25.840357] INFO: moduleinvoker: cached.v3 开始运行..

[2022-06-09 02:03:26.865931] INFO: moduleinvoker: cached.v3 运行完成[1.025567s].

[2022-06-09 02:03:26.971192] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-06-09 02:03:27.286229] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.002s

[2022-06-09 02:03:27.309971] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.022s

[2022-06-09 02:03:27.641434] INFO: derived_feature_extractor: /data, 5920

[2022-06-09 02:03:27.789218] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.818007s].

[2022-06-09 02:03:27.840242] INFO: moduleinvoker: join.v3 开始运行..

[2022-06-09 02:03:29.559664] INFO: join: /data, 行数=5789/5920, 耗时=0.2663s

[2022-06-09 02:03:29.639314] INFO: join: 最终行数: 5789

[2022-06-09 02:03:29.661203] INFO: moduleinvoker: join.v3 运行完成[1.820951s].

[2022-06-09 02:03:29.680432] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-06-09 02:03:30.100587] INFO: StockRanker: 特征预处理 ..

[2022-06-09 02:03:30.186308] INFO: StockRanker: prepare data: training ..

[2022-06-09 02:03:30.376648] INFO: StockRanker训练: 4d555bea 准备训练: 5789 行数

[2022-06-09 02:03:30.378530] INFO: StockRanker训练: AI模型训练，将在5789*3=1.74万数据上对模型训练进行20轮迭代训练。预计将需要1～2分钟。请耐心等待。

[2022-06-09 02:03:30.719126] INFO: StockRanker训练: 正在训练 ..

[2022-06-09 02:03:30.772107] INFO: StockRanker训练: 任务状态: Pending

[2022-06-09 02:03:40.860842] INFO: StockRanker训练: 任务状态: Running

[2022-06-09 02:04:51.300688] INFO: StockRanker训练: 00:01:03.0855830, finished iteration 1

[2022-06-09 02:04:51.302978] INFO: StockRanker训练: 00:01:03.0925699, finished iteration 2

[2022-06-09 02:04:51.305105] INFO: StockRanker训练: 00:01:03.0991693, finished iteration 3

[2022-06-09 02:04:51.308245] INFO: StockRanker训练: 00:01:03.1034466, finished iteration 4

[2022-06-09 02:04:51.310570] INFO: StockRanker训练: 00:01:03.1093820, finished iteration 5

[2022-06-09 02:04:51.313173] INFO: StockRanker训练: 00:01:03.1142383, finished iteration 6

[2022-06-09 02:04:51.315491] INFO: StockRanker训练: 00:01:03.1182250, finished iteration 7

[2022-06-09 02:04:51.317796] INFO: StockRanker训练: 00:01:03.1230293, finished iteration 8

[2022-06-09 02:04:51.320139] INFO: StockRanker训练: 00:01:03.1270318, finished iteration 9

[2022-06-09 02:04:51.322890] INFO: StockRanker训练: 00:01:03.1319969, finished iteration 10

[2022-06-09 02:04:51.325204] INFO: StockRanker训练: 00:01:03.1359423, finished iteration 11

[2022-06-09 02:04:51.327554] INFO: StockRanker训练: 00:01:03.1407969, finished iteration 12

[2022-06-09 02:04:51.329875] INFO: StockRanker训练: 00:01:03.1468267, finished iteration 13

[2022-06-09 02:04:51.332149] INFO: StockRanker训练: 00:01:03.1506804, finished iteration 14

[2022-06-09 02:04:51.333923] INFO: StockRanker训练: 00:01:03.1550199, finished iteration 15

[2022-06-09 02:04:51.335717] INFO: StockRanker训练: 00:01:03.1613675, finished iteration 16

[2022-06-09 02:04:51.337713] INFO: StockRanker训练: 00:01:03.1654143, finished iteration 17

[2022-06-09 02:04:51.340386] INFO: StockRanker训练: 00:01:03.1691966, finished iteration 18

[2022-06-09 02:04:51.342975] INFO: StockRanker训练: 00:01:03.1735812, finished iteration 19

[2022-06-09 02:04:51.345404] INFO: StockRanker训练: 00:01:03.1774650, finished iteration 20

[2022-06-09 02:04:51.347764] INFO: StockRanker训练: 任务状态: Succeeded

[2022-06-09 02:04:51.765171] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[82.084686s].

[2022-06-09 02:04:51.784634] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-06-09 02:04:51.983026] INFO: derived_feature_extractor: 提取完成 double_low = close + bond_prem_ratio, 0.001s

[2022-06-09 02:04:52.043499] INFO: derived_feature_extractor: 提取完成 rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100, 0.050s

[2022-06-09 02:04:52.183033] INFO: derived_feature_extractor: /data, 1090

[2022-06-09 02:04:52.309583] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.524934s].

[2022-06-09 02:04:52.327256] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2022-06-09 02:04:54.804713] INFO: StockRanker预测: /data ..

[2022-06-09 02:04:57.487162] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[5.159926s].

[2022-06-09 02:04:57.574737] INFO: moduleinvoker: cached.v3 开始运行..

[2022-06-09 02:04:57.824484] INFO: moduleinvoker: cached.v3 运行完成[0.249754s].

[2022-06-09 02:04:57.861379] INFO: moduleinvoker: trade_data_generation.v1 开始运行..

[2022-06-09 02:04:58.389214] INFO: moduleinvoker: trade_data_generation.v1 运行完成[0.527773s].

[2022-06-09 02:04:58.441336] INFO: moduleinvoker: hfbacktest.v1 开始运行..

[2022-06-09 02:04:58.449068] INFO: hfbacktest: passed-in daily_data_ds:None

[2022-06-09 02:04:58.451774] INFO: hfbacktest: passed-in minute_data_ds:None

[2022-06-09 02:04:58.454301] INFO: hfbacktest: passed-in tick_data_ds:None

[2022-06-09 02:04:58.457135] INFO: hfbacktest: passed-in each_data_ds:None

[2022-06-09 02:04:58.459244] INFO: hfbacktest: passed-in dominant_data_ds:None

[2022-06-09 02:04:58.462020] INFO: hfbacktest: passed-in benchmark_data_ds:None

[2022-06-09 02:04:58.464165] INFO: hfbacktest: passed-in trading_calendar_ds:None

[2022-06-09 02:04:58.465976] INFO: hfbacktest: biglearning V1.4.12

[2022-06-09 02:04:58.468176] INFO: hfbacktest: bigtrader v1.9.6 2022-05-31

[2022-06-09 02:04:58.505140] INFO: hfbacktest: strategy callbacks:{'on_init': , 'on_stop': , 'on_start': , 'handle_data': , 'handle_tick': , 'handle_trade': , 'handle_order': }

[2022-06-09 02:04:58.525414] INFO: hfbacktest: begin reading history data, 2021-01-05 00:00:00~2021-06-18, disable_cache:False, replay_bdb:1

[2022-06-09 02:04:58.530345] INFO: hfbacktest: reading benchmark data 2021-01-04 00:00:00~2021-06-18...

[2022-06-09 02:04:58.553731] INFO: moduleinvoker: cached.v2 开始运行..

[2022-06-09 02:04:58.870579] INFO: moduleinvoker: cached.v2 运行完成[0.316837s].

[2022-06-09 02:04:58.948305] INFO: hfbacktest: reading daily data 2019-12-30 00:00:00~2021-06-18...

[2022-06-09 02:04:58.965901] INFO: moduleinvoker: cached.v2 开始运行..

[2022-06-09 02:04:59.622066] INFO: moduleinvoker: cached.v2 运行完成[0.656166s].

[2022-06-09 02:04:59.813749] INFO: hfbacktest: cached_benchmark_ds:DataSource(f63ba34eaf314976b64f5817a4abc723T)

[2022-06-09 02:04:59.816396] INFO: hfbacktest: cached_daily_ds:DataSource(45146679a6474d93b77ce953c9a9cdb5T)

[2022-06-09 02:04:59.819948] INFO: hfbacktest: cached_minute_ds:None

[2022-06-09 02:04:59.822261] INFO: hfbacktest: cached_tick_ds:None

[2022-06-09 02:04:59.826862] INFO: hfbacktest: cached_each_ds:None

[2022-06-09 02:04:59.829109] INFO: hfbacktest: dominant_data_ds:None

[2022-06-09 02:04:59.833270] INFO: hfbacktest: read history data done, call run_backtest()

[2022-06-09 02:05:00.695860] ERROR: moduleinvoker: module name: hfbacktest, module version: v1, trackeback: OverflowError: cannot convert float infinity to integer

[2022-06-09 02:05:00.704919] ERROR: moduleinvoker: module name: hftrade, module version: v2, trackeback: OverflowError: cannot convert float infinity to integer

Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name_x', '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', 'pre_close', 'name_y', 'open', 'high',
       'low', 'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close'],
      dtype='object')
Index(['remain_size', 'instrument', 'equ_trading_code', 'conversion_chg_pct',
       'date', 'conversion_price', 'name_x', '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', 'pre_close', 'name_y', 'open', 'high',
       'low', 'deal_number', 'volume', 'amount', 'accrued_interest',
       'yield_to_maturity', 'vwap', 'gross_close', 'net_close'],
      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-7aa45343a63249dba66034a0d74ee20d"}/bigcharts-data-end

m11.input1 DataSource(83dd1fb9684f4182820a856f3ca5fa51T)

2022-06-09 02:04:59.885616 init history datas... 
2022-06-09 02:04:59.887284 init history datas done. 
2022-06-09 02:04:59.898661 run_backtest() capital_base:1000000, frequency:1d, product_type:conbond, date:2021-01-05 ~ 2021-06-18 
2022-06-09 02:04:59.899024 run_backtest() running... 
2022-06-09 02:04:59.909265 initial contracts len=0 
2022-06-09 02:04:59.909509 backtest inited. 
{'data': DataSource(8213727976684dfd8d12c5149872ed59T)}
           date  instrument     score  position
0    2021-01-05  110047.HCB  0.688259         1
1    2021-01-05  110033.HCB  0.316944         2
2    2021-01-05  128042.ZCB  0.048017         3
3    2021-01-05  128129.ZCB -0.094199         4
4    2021-01-05  128040.ZCB -0.120563         5
...         ...         ...       ...       ...
1085 2021-06-18  110066.HCB -0.136418         6
1086 2021-06-18  123081.ZCB -0.199051         7
1087 2021-06-18  127005.ZCB -0.263547         8
1088 2021-06-18  123034.ZCB -0.359593         9
1089 2021-06-18  127013.ZCB -0.379047        10

[1090 rows x 4 columns]
2022-06-09 02:04:59.989247 backtest transforming 1d, bars=1... 
2022-06-09 02:04:59.989551 transform start_trading_day=2021-01-05 00:00:00, simulation period=2021-01-05 ~ 2021-06-18 
2022-06-09 02:04:59.989588 transform source=None, before_start_days=8 
2022-06-09 02:04:59.989621 transform replay_func=<cyfunction BacktestEngine.transform.<locals>.replay_bars_dt at 0x7fc6a8d34040> 
当前日期data.current_dt 2021-01-05 15:00:00
处理data BarDatas(current_dt:2021-01-05 15:00:00)
buy_cash_weights [0.39038004999210163, 0.2463023887407299, 0.19519002499605081, 0.16812753627111746]
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
当前日期data.current_dt 2021-01-06 15:00:00
处理data BarDatas(current_dt:2021-01-06 15:00:00)
当前日期data.current_dt 2021-01-07 15:00:00
处理data BarDatas(current_dt:2021-01-07 15:00:00)
当前日期data.current_dt 2021-01-08 15:00:00
处理data BarDatas(current_dt:2021-01-08 15:00:00)
当前日期data.current_dt 2021-01-11 15:00:00
处理data BarDatas(current_dt:2021-01-11 15:00:00)
当前日期data.current_dt 2021-01-12 15:00:00
处理data BarDatas(current_dt:2021-01-12 15:00:00)
buy_cash_weights [0.39038004999210163, 0.2463023887407299, 0.19519002499605081, 0.16812753627111746]
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
2022-06-09 02:05:00.340651 market open send order=OrderReq(bkt000,110065.HCB,'1','0',0,124.9499,U,0,strategy,2021-01-12 15:00:00) failed err=-108,委托数量错误 
2022-06-09 02:05:00.341229 market open send order=OrderReq(bkt000,110034.HCB,'1','0',0,112.29,U,0,strategy,2021-01-12 15:00:00) failed err=-108,委托数量错误 
2022-06-09 02:05:00.341647 market open send order=OrderReq(bkt000,110051.HCB,'1','0',0,123.0199,U,0,strategy,2021-01-12 15:00:00) failed err=-108,委托数量错误 
2022-06-09 02:05:00.342076 market open send order=OrderReq(bkt000,110056.HCB,'1','0',0,107.3,U,0,strategy,2021-01-12 15:00:00) failed err=-108,委托数量错误 
当前日期data.current_dt 2021-01-13 15:00:00
处理data BarDatas(current_dt:2021-01-13 15:00:00)
当前日期data.current_dt 2021-01-14 15:00:00
处理data BarDatas(current_dt:2021-01-14 15:00:00)
当前日期data.current_dt 2021-01-15 15:00:00
处理data BarDatas(current_dt:2021-01-15 15:00:00)
当前日期data.current_dt 2021-01-18 15:00:00
处理data BarDatas(current_dt:2021-01-18 15:00:00)
当前日期data.current_dt 2021-01-19 15:00:00
处理data BarDatas(current_dt:2021-01-19 15:00:00)
buy_cash_weights [0.39038004999210163, 0.2463023887407299, 0.19519002499605081, 0.16812753627111746]
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
当前日期data.current_dt 2021-01-20 15:00:00
处理data BarDatas(current_dt:2021-01-20 15:00:00)
当前日期data.current_dt 2021-01-21 15:00:00
处理data BarDatas(current_dt:2021-01-21 15:00:00)
当前日期data.current_dt 2021-01-22 15:00:00
处理data BarDatas(current_dt:2021-01-22 15:00:00)
当前日期data.current_dt 2021-01-25 15:00:00
处理data BarDatas(current_dt:2021-01-25 15:00:00)
当前日期data.current_dt 2021-01-26 15:00:00
处理data BarDatas(current_dt:2021-01-26 15:00:00)
buy_cash_weights [0.39038004999210163, 0.2463023887407299, 0.19519002499605081, 0.16812753627111746]
<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
2022-06-09 02:05:00.693207 market open send order=OrderReq(bkt000,110047.HCB,'1','0',0,105.18,U,0,strategy,2021-01-26 15:00:00) failed err=-108,委托数量错误 
2022-06-09 02:05:00.695059 strategy strategy exception:Traceback (most recent call last):
  File "bigtrader/strategy/engine.py", line 714, in bigtrader2.bigtrader.strategy.engine.StrategyEngine._call_strategy_func
  File "bigtrader/strategy/strategy_base.py", line 2161, in bigtrader2.bigtrader.strategy.strategy_base.StrategyBase.call_handle_market_open
  File "bigtrader/finance/account_engine.py", line 2456, in bigtrader2.bigtrader.finance.account_engine.AccountEngine.send_order
  File "bigtrader/finance/account_engine.py", line 2354, in bigtrader2.bigtrader.finance.account_engine.AccountEngine._check_order_cash_or_adjust
OverflowError: cannot convert float infinity to integer

---------------------------------------------------------------------------
OverflowError                             Traceback (most recent call last)
<ipython-input-34-d140a6185c27> in <module>
    323 )
    324 
--> 325 m21 = M.hftrade.v2(
    326     instruments=m12.instrument_list,
    327     options_data=m11.data_1,

OverflowError: cannot convert float infinity to integer