复制链接

克隆策略

In [22]:

# #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()
# # df = m11.data_1.read()['data']
# # print(df[df['date']=='2021-01-26'])
# # print(df[df['date']=='2021-01-27'])

# # 计算n日涨幅
# def zhangfu(data, timeperiod=13):          
#     adj_close = data['close']- data['close'].shift(timeperiod)             
#     return adj_close

# # 计算动量
# def barAdjMon(data, timeperiod=2):          
#     adj_close = (data['close'] + data['high'] + data['low']) / 3               
#     return np.log(adj_close / adj_close.shift(timeperiod))

# def del_main(start_date_input,end_date_input):
#     instruments = ['510330.HOF','161017.ZOF','159949.ZOF']
#     df = DataSource("bar1d_CN_FUND").read(start_date=start_date_input,instruments = instruments, end_date=end_date_input)
#     groups = df.groupby(df['instrument'])
#     df_expend = pd.DataFrame()
#     for x in instruments:
#         tp = groups.get_group(x)
#         tp = tp.sort_values(by=['date'],na_position='first')
#         tp['pre_close'] = tp['close'].shift(1)
#         print(tp.head(2))
#         df_expend = df_expend.append(tp)
#     #df_159949 = groups.get_group('159949.ZOF')
#     df_expend.sort_values(['date'],na_position='first',inplace=True)
#     df_expend = df_expend.reset_index()
#     df_expend.drop('index',axis= 1,inplace = True)
    
#     #计算其他特征
#     df_expend['mom_20'] = barAdjMon(df_expend,timeperiod=20)
#     df_expend['mom_20'] = df_expend['mom_20'].fillna(value=0.0) #列向前填充
#     # 涨幅因子
#     df_expend['zhangfu'] = zhangfu(df_expend,timeperiod=13)
#     df_expend['zhangfu'] = df_expend['zhangfu'].fillna(value=0.0) #列向前填充
#     return df_expend

# # 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 bigquant_run(input_1, input_2, input_3,start_date_input,end_date_input,pre_start_date,pre_end_date):
#     # 示例代码如下。在这里编写您的代码
#     # 读取数据  默认会返回全部证券代码数据, 通过指定参数 instruments 可以读取到指定的证券代码数据
#     df_expend = del_main(start_date_input,end_date_input)
#     data_1 = DataSource.write_df(df_expend)
#     data_2 = DataSource.write_df(df_expend)
#     df_pre = del_main(pre_start_date,pre_end_date)
#     data_3 = DataSource.write_df(df_pre)
#     return Outputs(data_1=data_1, data_2=data_2, data_3=data_3)

In [23]:

#m18.data.read().tail(24)
# num = m18.data.read().isna().sum()
# print(type(num))
# print(num.index[0])
# for i in range(len(num)):
#     if num[i] > 10:
#         print(num.index[i])
# import empyrical
# returns = result.get('m21').read_raw_perf()['returns'].tolist()
# sharp_ratio = empyrical.sharpe_ratio(np.array(returns),0.03/252)
!pip install featuretools

---------------------------------------------------------------------------
BQInputRejected                           Traceback (most recent call last)
BQInputRejected: 编译错误，11: 抱歉，"get_ipython" 是保留关键字，请尝试其他名字

In [18]:

# 本代码由可视化策略环境自动生成 2022年7月23日 15:28
# 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 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

from scipy import nanstd
from sklearn import preprocessing
import math
import numpy as np
def print_debug(**kwargs):
    if True:
        for k,v in kwargs.items():
            print(k,":")
            print(v)
            
# 计算n日涨幅
def zhangfu(data, timeperiod=13):          
    adj_close = data['pre_close']- data['pre_close'].shift(timeperiod)             
    return adj_close
def rank_swing_volatility(data,timeperiod=5):
    return nanstd((data['pre_high']-data['pre_low'])/data['pre_close'], timeperiod)*sqrt(200)*100
# 计算动量
def barAdjMon(data, timeperiod=2):          
    adj_close = (data['pre_close'] + data['pre_high'] + data['pre_low']) / 3               
    return np.log(adj_close / adj_close.shift(timeperiod))

def del_main(start_date_input,end_date_input,instruments):
    #instruments = ['510330.HOF','161017.ZOF','159949.ZOF']
    df = DataSource("bar1d_CN_FUND").read(start_date=start_date_input,instruments = instruments, end_date=end_date_input)
    groups = df.groupby(df['instrument'])
    df_expend = pd.DataFrame()
    for x in instruments:
        #分组排序后重新设置索引
        tp = groups.get_group(x)
        tp = tp.sort_values(by=['date'],na_position='first')

        tp = tp.reset_index() 
        tp.drop('index',axis= 1,inplace = True) 
        tp = tp.reset_index() 
        print_debug(tp_index=tp.index)
        # 基础特征列表
        tp['open_0'] = tp['open']
        tp['high_0'] = tp['high']
        tp['low_0'] = tp['low']
        tp['close_0'] = tp['close']
        tp['volume_0'] = tp['volume']
        tp['pre_close'] = tp['close'].shift(1)
        tp['std_pre_close'] = preprocessing.scale(tp['pre_close'].values)
        tp['pre_high'] = tp['high'].shift(1)
        tp['std_pre_high'] = preprocessing.scale(tp['pre_high'].values)
        tp['pre_low'] = tp['low'].shift(1)
        tp['std_pre_low'] = preprocessing.scale(tp['pre_low'].values)
        tp['pre_open'] = tp['open'].shift(1)
        tp['std_pre_open'] = preprocessing.scale(tp['pre_open'].values)
        tp['pre_volume'] = tp['volume'].shift(1)
        tp['std_pre_volume'] = preprocessing.scale(tp['pre_volume'].values)
        tp['pre_amount'] = tp['amount'].shift(1)
        tp['std_pre_amount'] = preprocessing.scale(tp['pre_amount'].values)
        #计算其他特征
        #tp['alpha_001_my'] = (rank(ts_argmax(signedpower(where(((tp['close_0']/shift(tp['close_0'],1)-1) < 0), std((tp['close_0']/shift(tp['close_0'],1)-1), 20), tp['close_0']), 2), 5)) -0.5)
        #20日动量
        tp['mom_20'] = barAdjMon(tp,timeperiod=20)
        tp['std_mom_20'] = preprocessing.scale(tp['mom_20'].values)
        #13日涨幅
        tp['zhangfu'] = zhangfu(tp,timeperiod=13)
        tp['std_zhangfu'] = preprocessing.scale(tp['zhangfu'].values)
        # std ln pre open
        tp['std_ln_pre_open'] = preprocessing.scale(np.log(tp['pre_open']))
        print(tp.head(2))
        df_expend = df_expend.append(tp)
    #df_159949 = groups.get_group('159949.ZOF')
    df_expend.sort_values(['date'],na_position='first',inplace=True)
    df_expend = df_expend.reset_index()
    df_expend.drop('index',axis= 1,inplace = True)
    # 异常数据处理
    #df_expend = df_expend.fillna(value=0.0) #列向前填充
#     # 波动率因子
#     df_expend['rank_swing_volatility_5'] = rank_swing_volatility(df_expend,5)
#     df_expend['rank_swing_volatility_5'] = df_expend['rank_swing_volatility_5'].fillna(value=0.0) #列向前填充
    return df_expend

# 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,pre_start_date,pre_end_date):
    pre_start_date = input_1.read()['start_date']
    pre_end_date = input_1.read()['end_date']
    instruments = input_1.read()['instruments']
    # 示例代码如下。在这里编写您的代码
    # 读取数据  默认会返回全部证券代码数据, 通过指定参数 instruments 可以读取到指定的证券代码数据
    df_expend = del_main(start_date_input,end_date_input,instruments)
    data_1 = DataSource.write_df(df_expend)
    data_2 = DataSource.write_df(df_expend)
    print('pre_start_date,pre_end_date',pre_start_date,pre_end_date)
    df_pre = del_main(pre_start_date,pre_end_date,instruments)
    data_3 = DataSource.write_df(df_pre)
    return Outputs(data_1=data_1, data_2=data_2, data_3=data_3)

# 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_1):
    df = input_1.read_df()
    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 del_dirty_data(df):
    # 异常数据处理
    num = df.isna().sum()
    for i in range(len(num)):
        if num[i] > 10:
            print('!!!!!!!!!含有大量脏数据',num.index[i],num[i])
        if num[i] > 100:
            print(num.index[i],num[i])
            df = df.drop([str(num.index[i])],axis = 1)
    # 删除值全为nan的列
    df = df.dropna(axis = 1,how = 'all')
    # 删除任意含有nan的行
    #df = df.dropna()
    df = df.fillna(value=0.0) #列向前填充  
    return df
def m1_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    df1 = input_1.read()
    df1 = del_dirty_data(df1)
    data_1 = DataSource.write_df(df1)
    
    df2 = input_2.read()
    df2 = del_dirty_data(df2)
    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 m1_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 m17_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(input_3.read())
    train_df = input_1.read()
    predict_df = input_2.read()
    features = input_3.read()
    data_1 = input_1
    data_2 = input_2
    for i in features:
        print(i)
    
    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 m17_post_run_bigquant_run(outputs):
    return outputs

def m9_get_self_transfuns_list_code_bigquant_run():
    select_self_transfuns_list = ["add","subtract","multiply","divide"]
    return select_self_transfuns_list 

# 可选内置函数包括：
# add multiply subtract divide
# mod diff percentile negate absolute
# cum_count cum_max cum_min cum_mean等

def m9_user_defined_transfuns_code_bigquant_run():
    global close_1_func
    def close_1(column): 
        column = pd.Series(column)
        n = 1
        return column.shift(n)
    close_1_func = make_trans_primitive(function = close_1, input_types=[Numeric], return_type=Numeric)

def m9_get_user_defined_transfuns_list_code_bigquant_run():
    select_user_defined_transfuns_list = [close_1_func]
    return select_user_defined_transfuns_list 

# 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('初始化函数开始：')
    #print('context.options',context.options)
    # 加载预测数据
    context.ranker_prediction = context.options.get('data').read()['data']
    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=0.0003, 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 = 1.01
    context.hold_days = context.param["hold_days"]
    #print('初始化函数结束')

# 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

    context.subscribe(context.instruments)

    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

import math
# 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)
    #print('data',data)
    try:
        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
        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
                #print('卖出order target percent',context.symbol(stock))
                #print('卖出结果',context.order_target_percent(context.symbol(stock), 0))
                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
        print('买入列表',stock_to_buy)
        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:
                cash = int(math.floor(cash))
                #print('买入order_value',context.symbol(instrument),' cash ',cash)
                #print(context.order_value(context.symbol(instrument), cash))
                context.order_value(context.symbol(instrument), cash)
    except Exception as e:
        print('抛出异常',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

# 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 deal_result_data(df):
    
    return df
def m12_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(input_1)
    print(input_1.read())
    data_1 = input_1
    data_2 = input_1
#     df1 = input_1.read_raw_perf()
#     df1 = deal_result_data(df1)
#     data_1 = DataSource.write_df(df1)
    
#     df2 = input_2.read()
#     df2 = deal_result_data(df2)
#     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 m12_post_run_bigquant_run(outputs):
    return outputs


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

# rank_swing_volatility_5 = nanstd((high-low)/pre_close, 5)*sqrt(200)*100
# alpha_001 = (rank(ts_argmax(signedpower(where(((close_0/shift(close_0,1)-1) < 0), std((close_0/shift(close_0,1)-1), 20), close_0), 2), 5)) -0.5)
# shift(close_0,5)/close_0

# mom_20
# zhangfu
# ln_pre_high = log(pre_high)
#ln_pre_open = nanstd(log(pre_open))
# std_ln_pre_open
# delta(close_0, 3)
pre_close
pre_low
pre_volume
pre_amount

high
open
close
amount
volume
# std_mom_20
# std_zhangfu
# std_pre_high
# std_pre_close
# std_pre_open
# std_pre_low
# std_pre_volume
# std_pre_amount

# ln_open = log(open_0)
""",

    '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": 1,
    "hold_days": 1 
}""",
    'm14.output_ports': '',

    'm4': 'M.instruments.v2',
    'm4.start_date': '2021-06-01',
    'm4.end_date': T.live_run_param('trading_date', '2022-06-01'),
    'm4.market': 'CN_FUND',
    'm4.instrument_list': """510330.HOF
161017.ZOF
159949.ZOF""",
    'm4.max_count': 0,

    'm2': 'M.cached.v3',
    'm2.input_1': T.Graph.OutputPort('m4.data'),
    'm2.run': m2_run_bigquant_run,
    'm2.post_run': m2_post_run_bigquant_run,
    'm2.input_ports': '',
    'm2.params': """{"start_date_input":"2020-06-01",
"end_date_input":"2021-05-01",
"pre_start_date":"2021-06-01",
"pre_end_date":"2022-06-01"}""",
    'm2.output_ports': '',
    'm2.m_cached': False,

    '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, -2) / shift(open, -1)

# 极值处理：用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))

# 将分数映射到分类，这里使用20个分类
all_wbins(label, 20)

# 过滤掉一字涨停的情况 (设置label为NaN，在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
    'm10.drop_na_label': True,
    'm10.cast_label_int': True,
    'm10.date_col': 'date',
    'm10.instrument_col': 'instrument',
    'm10.user_functions': {},

    'm23': 'M.cached.v3',
    'm23.input_1': T.Graph.OutputPort('m2.data_2'),
    'm23.input_2': T.Graph.OutputPort('m2.data_3'),
    '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,

    '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,

    'm1': 'M.cached.v3',
    'm1.input_1': T.Graph.OutputPort('m7.data'),
    'm1.input_2': T.Graph.OutputPort('m18.data'),
    'm1.run': m1_run_bigquant_run,
    'm1.post_run': m1_post_run_bigquant_run,
    'm1.input_ports': '',
    'm1.params': '{}',
    'm1.output_ports': '',

    'm17': 'M.cached.v3',
    'm17.input_1': T.Graph.OutputPort('m1.data_1'),
    'm17.input_2': T.Graph.OutputPort('m1.data_2'),
    'm17.input_3': T.Graph.OutputPort('m3.data'),
    'm17.run': m17_run_bigquant_run,
    'm17.post_run': m17_post_run_bigquant_run,
    'm17.input_ports': '',
    'm17.params': """{'start':0,
'end':2}""",
    'm17.output_ports': '',

    'm6': 'M.stock_ranker_train.v6',
    'm6.training_ds': T.Graph.OutputPort('m17.data_1'),
    '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,

    'm9': 'M.featuretools.v1',
    'm9.input_df': T.Graph.OutputPort('m17.data_1'),
    'm9.df_unique_id': 'date',
    'm9.time_style_variable_input': 'date',
    'm9.get_self_transfuns_list_code': m9_get_self_transfuns_list_code_bigquant_run,
    'm9.user_defined_transfuns_code': m9_user_defined_transfuns_code_bigquant_run,
    'm9.get_user_defined_transfuns_list_code': m9_get_user_defined_transfuns_list_code_bigquant_run,
    'm9.max_depth_input': 2,
    'm9.verbose_input': True,

    'm13': 'M.fearutre_auto.v2',
    'm13.input_1': T.Graph.OutputPort('m17.data_1'),
    'm13.df_unique_id': 'date',
    'm13.time_style_variable_input': 'date',
    'm13.verbose_input': True,
    'm13.trans_primitives_input': [],
    'm13.self_transfuns_list': [],
    'm13.max_depth_input': 2,
    'm13.njobs_input': 1,

    'm8': 'M.stock_ranker_predict.v5',
    'm8.model': T.Graph.OutputPort('m6.model'),
    'm8.data': T.Graph.OutputPort('m17.data_2'),
    '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': '',

    'm21': 'M.hftrade.v2',
    'm21.instruments': T.Graph.OutputPort('m4.data'),
    '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': '自动',
    'm21.before_start_days': '80',
    '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': True,
    'm21.backtest_only': False,

    'm12': 'M.cached.v3',
    'm12.input_1': T.Graph.OutputPort('m21.raw_perf'),
    'm12.run': m12_run_bigquant_run,
    'm12.post_run': m12_post_run_bigquant_run,
    'm12.input_ports': '',
    'm12.params': '{}',
    'm12.output_ports': '',

    'm15': 'M.genetic_algorithm.v1',
    'm15.instruments': T.Graph.OutputPort('m4.data'),
    'm15.feature_datas': T.Graph.OutputPort('m17.data_1'),
    'm15.base_features': T.Graph.OutputPort('m3.data'),
    'm15.all_start_date': '',
    'm15.all_end_date': '',
    'm15.short_date_range_ratio': 0.7,
    'm15.return_field': 'wap_3_vwap_buy',
    'm15.rebalance_period': 1,
    'm15.train_test_ratio': 0.75,
    'm15.train_validate_ratio': 0.75,
    'm15.mtime': 1,
    'm15.init_ind_num': 10,
    'm15.ngen': 3,
    'm15.fitness_func': 'icir',
    'm15.train_fitness': 2,
    'm15.test_fitness': 1.6,
    'm15.ir_type': 'ir',
    'm15.cxpb': 0.5,
    'm15.mutpb': 0.3,
    'm15.mutspb': 0.3,
    'm15.mutnrpb': 0.3,
    'm15.constant': '1,11',
    'm15.pool_processes_limit': 1,

    'm19': 'M.select_k_best.v9',
    'm19.start_date': '2005-01-01',
    'm19.end_date': '2015-01-01',
    'm19.score_func': 'f_classif',
    'm19.k': 60,
    'm19.if_print': True,
    'm19.feature_list': ['rank_return_0', 'rank_return_5', 'rank_return_10', 'rank_return_20', 'rank_avg_amount_0', 'rank_avg_turn_0', 'rank_avg_mf_net_amount_0', 'rank_avg_amount_5', 'rank_avg_turn_5', 'rank_avg_mf_net_amount_5', 'rank_avg_amount_10', 'rank_avg_turn_10', 'rank_avg_mf_net_amount_10', 'rank_avg_amount_0-rank_avg_amount_5', 'rank_avg_amount_5-rank_avg_amount_10', 'rank_return_0-rank_return_5', 'rank_return_5-rank_return_10', 'rank_return_10-rank_return_20', 'rank_beta_industry_5_0', 'rank_volatility_5_0', 'rank_swing_volatility_5_0', 'rank_beta_industry_10_0', 'rank_volatility_10_0', 'rank_swing_volatility_10_0', 'rank_beta_industry_30_0', 'rank_volatility_30_0', 'rank_swing_volatility_30_0', 'high_0/low_0-1', 'close_0/open_0-1', 'return_0', 'return_1', 'return_2', 'return_3', 'return_4', 'return_5', 'return_10', 'return_20', 'shift(mf_net_amount_s_0,3)', 'shift(mf_net_amount_m_0,3)', 'shift(mf_net_amount_l_0,3)', 'mf_net_amount_0', 'mf_net_amount_5', 'mf_net_amount_10', 'mf_net_amount_20', 'mf_net_amount_main_0', 'avg_amount_0/avg_amount_5', 'avg_amount_5/avg_amount_10', 'avg_amount_10/avg_amount_20', 'beta_csi300_30_0', 'beta_csi300_60_0', 'beta_industry_30_0', 'beta_industry_60_0', 'swing_volatility_5_0/swing_volatility_30_0', 'swing_volatility_30_0/swing_volatility_60_0', 'ta_atr_14_0', 'ta_atr_28_0', 'ta_rsi_14_0', 'ta_rsi_28_0', 'ta_cci_14_0', 'ta_cci_28_0', 'ta_sma_5_0/ta_sma_10_0', 'ta_sma_10_0/ta_sma_20_0', 'ta_sma_20_0/ta_sma_30_0', 'ta_sma_30_0/ta_sma_60_0', 'ta_sma(amount_0, 10)/ta_sma(amount_0, 20)', 'ta_sma(amount_0, 20)/ta_sma(amount_0, 30)', 'ta_sma(amount_0, 30)/ta_sma(amount_0, 60)', 'ta_sma(amount_0, 50)/ta_sma(amount_0, 100)', 'ta_sma(turn_0, 10)/ta_sma(turn_0, 20)', 'ta_sma(turn_0, 20)/ta_sma(turn_0, 30)', 'ta_sma(turn_0, 30)/ta_sma(turn_0, 60)', 'ta_sma(turn_0, 50)/ta_sma(turn_0, 100)', 'ta_sma(high_0-low_0, 5)/ta_sma(high_0-low_0, 20)', 'ta_sma(high_0-low_0, 10)/ta_sma(high_0-low_0, 20)', 'ta_sma(high_0-low_0, 20)/ta_sma(high_0-low_0, 30)', 'ta_sma(high_0-low_0, 30)/ta_sma(high_0-low_0, 60)', 'ta_sma(high_0-low_0, 50)/ta_sma(high_0-low_0, 100)', 'std(close_0,5)/std(close_0,10)', 'std(close_0,10)/std(close_0,20)', 'std(close_0,20)/std(close_0,30)', 'std(close_0,30)/std(close_0,60)', 'std(close_0,50)/std(close_0,100)'],
})

# g.run({})


def m5_param_grid_builder_bigquant_run():
    param_grid = {}

    # 在这里设置需要调优的参数备选
    # param_grid['m3.features'] = ['close_1/close_0', 'close_2/close_0\nclose_3/close_0']
    # param_grid['m6.number_of_trees'] = [5, 10, 20]
    param_grid["m17.params"] = [
        """{"start": 1, "end": 2}""",
        """{"start": 2, "end": 3}""",
    ]
    return param_grid

def m5_scoring_bigquant_run(result):
    score = result.get('m19').read_raw_perf()['sharpe'].tail(1)[0]

    return {'score': score}


m5 = M.hyper_parameter_search.v1(
    param_grid_builder=m5_param_grid_builder_bigquant_run,
    scoring=m5_scoring_bigquant_run,
    search_algorithm='网格搜索',
    search_iterations=10,
    workers=1,
    worker_distributed_run=True,
    worker_silent=True,
    run_now=True,
    bq_graph=g
)

[2022-07-23 15:18:41.898606] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-07-23 15:18:41.912211] INFO: moduleinvoker: 命中缓存

[2022-07-23 15:18:41.914156] INFO: moduleinvoker: input_features.v1 运行完成[0.015574s].

[2022-07-23 15:18:41.919778] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-07-23 15:18:41.928156] INFO: moduleinvoker: 命中缓存

[2022-07-23 15:18:41.930173] INFO: moduleinvoker: instruments.v2 运行完成[0.010402s].

[2022-07-23 15:18:41.958024] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-23 15:18:43.094572] INFO: moduleinvoker: cached.v3 运行完成[1.13655s].

[2022-07-23 15:18:43.107685] INFO: moduleinvoker: auto_labeler_on_datasource.v1 开始运行..

[2022-07-23 15:18:43.192582] INFO: 自动标注(任意数据源): 开始标注 ..

[2022-07-23 15:18:43.284318] INFO: moduleinvoker: auto_labeler_on_datasource.v1 运行完成[0.176638s].

[2022-07-23 15:18:43.298009] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-23 15:18:43.526467] INFO: moduleinvoker: cached.v3 运行完成[0.228475s].

[2022-07-23 15:18:43.534717] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-23 15:18:43.665740] INFO: derived_feature_extractor: /data, 675

[2022-07-23 15:18:43.740662] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.205934s].

[2022-07-23 15:18:43.756824] INFO: moduleinvoker: join.v3 开始运行..

[2022-07-23 15:18:43.891728] INFO: join: /data, 行数=669/675, 耗时=0.052326s

[2022-07-23 15:18:43.935551] INFO: join: 最终行数: 669

[2022-07-23 15:18:43.943290] INFO: moduleinvoker: join.v3 运行完成[0.186462s].

[2022-07-23 15:18:43.950457] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-23 15:18:44.097305] INFO: derived_feature_extractor: /data, 729

[2022-07-23 15:18:44.172142] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.221666s].

[2022-07-23 15:18:44.208668] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-23 15:18:44.563198] INFO: moduleinvoker: cached.v3 运行完成[0.354514s].

[2022-07-23 15:18:44.583445] INFO: moduleinvoker: cached.v3 开始运行..

[2022-07-23 15:18:45.004122] INFO: moduleinvoker: cached.v3 运行完成[0.420695s].

[2022-07-23 15:18:45.035392] INFO: moduleinvoker: fearutre_auto.v2 开始运行..

[2022-07-23 15:18:45.045908] ERROR: moduleinvoker: module name: fearutre_auto, module version: v2, trackeback: ModuleNotFoundError: No module named 'featuretools'

tp_index :
RangeIndex(start=0, stop=225, step=1)
   index  instrument       date   open   high    low  close       volume  \
0      0  159949.ZOF 2020-06-01  0.793  0.818  0.793  0.816  754511227.0   
1      1  159949.ZOF 2020-06-02  0.818  0.818  0.805  0.811  645798345.0   

         amount  adjust_factor  ...  std_pre_open   pre_volume  \
0  6.093608e+08            1.0  ...           NaN          NaN   
1  5.231684e+08            1.0  ...     -2.380893  754511227.0   

   std_pre_volume    pre_amount  std_pre_amount  mom_20  std_mom_20  zhangfu  \
0             NaN           NaN             NaN     NaN         NaN      NaN   
1       -0.599572  6.093608e+08       -1.032285     NaN         NaN      NaN   

   std_zhangfu  std_ln_pre_open  
0          NaN              NaN  
1          NaN        -2.711947  

[2 rows x 33 columns]
tp_index :
RangeIndex(start=0, stop=225, step=1)
   index  instrument       date    open    high     low   close     volume  \
0      0  161017.ZOF 2020-06-01  2.2009  2.2567  2.2009  2.2554  3000479.0   
1      1  161017.ZOF 2020-06-02  2.2567  2.2728  2.2468  2.2554  1403088.0   

        amount  adjust_factor  ...  std_pre_open  pre_volume  std_pre_volume  \
0  5441987.193        1.23855  ...           NaN         NaN             NaN   
1  2554776.191        1.23855  ...     -3.278864   3000479.0        3.532128   

    pre_amount  std_pre_amount  mom_20  std_mom_20  zhangfu  std_zhangfu  \
0          NaN             NaN     NaN         NaN      NaN          NaN   
1  5441987.193        2.742584     NaN         NaN      NaN          NaN   

   std_ln_pre_open  
0              NaN  
1        -3.421213  

[2 rows x 33 columns]
tp_index :
RangeIndex(start=0, stop=225, step=1)
   index  instrument       date    open   high     low   close       volume  \
0      0  510330.HOF 2020-06-01  4.5108  4.615  4.5108  4.6080  205954831.0   
1      1  510330.HOF 2020-06-02  4.6080  4.630  4.5965  4.6196  107216737.0   

        amount  adjust_factor  ...  std_pre_open   pre_volume  std_pre_volume  \
0  813650964.0       1.157789  ...           NaN          NaN             NaN   
1  426967604.0       1.157794  ...      -2.52979  205954831.0        0.981722   

    pre_amount  std_pre_amount  mom_20  std_mom_20  zhangfu  std_zhangfu  \
0          NaN             NaN     NaN         NaN      NaN          NaN   
1  813650964.0        0.439037     NaN         NaN      NaN          NaN   

   std_ln_pre_open  
0              NaN  
1        -2.731327  

[2 rows x 33 columns]
pre_start_date,pre_end_date 2021-06-01 2022-06-01
tp_index :
RangeIndex(start=0, stop=243, step=1)
   index  instrument       date   open   high    low  close       volume  \
0      0  159949.ZOF 2021-06-01  1.435  1.442  1.411  1.439  643360309.0   
1      1  159949.ZOF 2021-06-02  1.441  1.445  1.403  1.408  744331379.0   

         amount  adjust_factor  ...  std_pre_open   pre_volume  \
0  9.204310e+08            1.0  ...           NaN          NaN   
1  1.056368e+09            1.0  ...      0.467544  643360309.0   

   std_pre_volume    pre_amount  std_pre_amount  mom_20  std_mom_20  zhangfu  \
0             NaN           NaN             NaN     NaN         NaN      NaN   
1       -0.216134  9.204310e+08       -0.053506     NaN         NaN      NaN   

   std_zhangfu  std_ln_pre_open  
0          NaN              NaN  
1          NaN         0.492441  

[2 rows x 33 columns]
tp_index :
RangeIndex(start=0, stop=243, step=1)
   index  instrument       date    open    high     low   close    volume  \
0      0  161017.ZOF 2021-06-01  2.9106  2.9354  2.8859  2.9218  465328.0   
1      1  161017.ZOF 2021-06-02  2.9218  2.9230  2.8945  2.9044  510014.0   

        amount  adjust_factor  ...  std_pre_open  pre_volume  std_pre_volume  \
0  1093198.557       1.238576  ...           NaN         NaN             NaN   
1  1198952.227       1.238550  ...     -0.638813    465328.0       -0.509458   

    pre_amount  std_pre_amount  mom_20  std_mom_20  zhangfu  std_zhangfu  \
0          NaN             NaN     NaN         NaN      NaN          NaN   
1  1093198.557       -0.536977     NaN         NaN      NaN          NaN   

   std_ln_pre_open  
0              NaN  
1        -0.604723  

[2 rows x 33 columns]
tp_index :
RangeIndex(start=0, stop=243, step=1)
   index  instrument       date    open    high     low   close       volume  \
0      0  510330.HOF 2021-06-01  6.2829  6.3006  6.2099  6.2935  149795700.0   
1      1  510330.HOF 2021-06-02  6.3006  6.3100  6.2123  6.2452  119155700.0   

        amount  adjust_factor  ...  std_pre_open   pre_volume  std_pre_volume  \
0  796794080.0       1.177676  ...           NaN          NaN             NaN   
1  633040575.0       1.177673  ...      1.434463  149795700.0        0.779143   

    pre_amount  std_pre_amount  mom_20  std_mom_20  zhangfu  std_zhangfu  \
0          NaN             NaN     NaN         NaN      NaN          NaN   
1  796794080.0        1.228691     NaN         NaN      NaN          NaN   

   std_ln_pre_open  
0              NaN  
1          1.34209  

[2 rows x 33 columns]

!!!!!!!!!含有大量脏数据 turn 669
turn 669
!!!!!!!!!含有大量脏数据 mom_20 63
!!!!!!!!!含有大量脏数据 std_mom_20 63
!!!!!!!!!含有大量脏数据 zhangfu 42
!!!!!!!!!含有大量脏数据 std_zhangfu 42
!!!!!!!!!含有大量脏数据 m:turn 669
m:turn 669
!!!!!!!!!含有大量脏数据 m:mom_20 63
!!!!!!!!!含有大量脏数据 m:std_mom_20 63
!!!!!!!!!含有大量脏数据 m:zhangfu 42
!!!!!!!!!含有大量脏数据 m:std_zhangfu 42
!!!!!!!!!含有大量脏数据 turn 437
turn 437
!!!!!!!!!含有大量脏数据 mom_20 63
!!!!!!!!!含有大量脏数据 std_mom_20 63
!!!!!!!!!含有大量脏数据 zhangfu 42
!!!!!!!!!含有大量脏数据 std_zhangfu 42

['pre_close', 'pre_low', 'pre_volume', 'pre_amount', 'high', 'open', 'close', 'amount', 'volume']
pre_close
pre_low
pre_volume
pre_amount
high
open
close
amount
volume

---------------------------------------------------------------------------
ModuleNotFoundError                       Traceback (most recent call last)
<ipython-input-18-584cae58ced1> in <module>
    307 )
    308 
--> 309 m13 = M.fearutre_auto.v2(
    310     input_1=m17.data_1,
    311     df_unique_id='date',

ModuleNotFoundError: No module named 'featuretools'