复制链接

克隆策略

In [4]:

# 本代码由可视化策略环境自动生成 2022年5月25日 24:19
# 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 m22_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()
    # 缺失值处理
    # if len(df)!=0:
    #     df.dropna(inplace=True)
        
    # 选股条件
    if len(df)!=0:
        df_filter1 = df[df['cond1']>0]
    else:
        df_filter1 = df
    
    # 指标排序
    if len(df_filter1)!=0:
        df_filter2 = df_filter1.groupby('date').apply(lambda x:x.sort_values(by=['cond2'],ascending=True))
    else:
        df_filter2 = df_filter1
    
    #输出条件过滤股票池
    data_1 = DataSource.write_df(df_filter2)

    
    # 进场条件
    if len(df)!=0:
        df_buy = df[df['cond3']>0]
    else:
        df_buy = df
    # 输出满足进场条件的股票池
    data_2 = DataSource.write_df(df_buy)

    
    # 出场条件
    if len(df)!=0:
        df_sell = df[df['cond4']>0]
    else:
        df_sell = df
    # 输出满足出场条件的股票池
    data_3 = DataSource.write_df(df_sell)    
    
    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 m22_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):
    df1 = input_1.read_df()
    df2 = input_2.read_df()
    df3 = input_3.read_df()

    if len(df1.index.names) == 2:
        df1.index.names = [None, None]
    else:
        df1.index.names = [None]
    
    df = {'df1':df1,'df2':df2,'df3':df3}
    ds = DataSource.write_pickle(df)
    return Outputs(data_1=ds)

# 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

# 回测引擎：初始化函数，只执行一次
def m12_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.0001, 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 = 1
    # 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
    context.options['hold_days'] = 1

# 回测引擎：每日数据处理函数，每天执行一次
def m12_handle_data_bigquant_run(context, data):
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
   
    #---------------------------START:止赢止损模块(含建仓期)--------------------
    # 新建当日止赢止损股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
    stopwin_stock=[]
    stoploss_stock = []   
    today = data.current_dt.strftime('%Y-%m-%d')
    positions_stop={e.symbol:p.cost_basis 
    for e,p in context.portfolio.positions.items()}
    if len(positions_stop)>0:
        for instrument in positions_stop.keys():
            # 获取股票买入成本价stock_cost和现价stock_market_price
            stock_cost=positions_stop[instrument]  
            stock_market_price=data.current(context.symbol(instrument),'price')  
            # 赚3元且为可交易状态就止盈
            if stock_market_price-stock_cost > 1.2 and data.can_trade(context.symbol(instrument)) and not context.has_unfinished_sell_order(instrument):
                context.order_target_percent(context.symbol(instrument),0)      
                stopwin_stock.append(instrument)
            # 亏10%并且为可交易状态就止损
            if stock_market_price/stock_cost-1 <= -0.05 and data.can_trade(context.symbol(instrument)) and not context.has_unfinished_sell_order(instrument):   
                context.order_target_percent(context.symbol(instrument),0)     
                stoploss_stock.append(instrument)
        if len(stopwin_stock)>0:
            print(today,'止盈股票列表',stopwin_stock)
        if len(stoploss_stock)>0:
            print(today,'止损股票列表',stoploss_stock)
    #--------------------------END: 止赢止损模块-----------------------------
    
    # 1. 资金分配
    # 平均持仓时间是hold_days，每日都将买入股票，每日预期使用 1/hold_days 的资金
    # 实际操作中，会存在一定的买入误差，所以在前hold_days天，等量使用资金；之后，尽量使用剩余资金（这里设置最多用等量的1.5倍）
    is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
    cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
    cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.perf_tracker.position_tracker.positions.items()}

    # 2. 生成卖出订单：hold_days天之后才开始卖出；对持仓的股票，按机器学习算法预测的排序末位淘汰
    if not is_staging and cash_for_sell > 0:
        equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        # print('rank order for sell %s' % instruments)
        for instrument in instruments:
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[instrument]
            if cash_for_sell <= 0:
                break

    # 3. 生成买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
    buy_cash_weights = context.stock_weights
    buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
    max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
    for i, instrument in enumerate(buy_instruments):
        cash = cash_for_buy * buy_cash_weights[i]
        if cash > max_cash_per_instrument - positions.get(instrument, 0):
            # 确保股票持仓量不会超过每次股票最大的占用资金量
            cash = max_cash_per_instrument - positions.get(instrument, 0)
        if cash > 0:
            context.order_value(context.symbol(instrument), cash)

# 回测引擎：准备数据，只执行一次
def m12_prepare_bigquant_run(context):
    pass


m1 = M.instruments.v2(
    start_date='2013-01-01',
    end_date='2019-12-31',
    market='CN_STOCK_A',
    instrument_list=''
)

m3 = M.input_features.v1(
    features="""
in_csi300_0
in_csi500_0
in_sse50_0
industry_sw_level1_0
st_status_0

# 选股条件
cond1=(market_cap_float_0>1000000000)&(market_cap_float_0<40000000000)&\
(close_0/adjust_factor_0>mean(close_0/adjust_factor_0, 5))&\
(volume_0>mean(volume_0, 5))&\
(amount_0>100000000)&\
(turn_0>0.08)&\
(list_days_0>60)&\
(mf_net_amount_main_0>60000000)

# 排序选股
cond2=rank(turn_0 * -1)*1.00

# 进场条件
cond3=1
              
# 卖出条件
cond4=1
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=300
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m10 = M.input_features.v1(
    features="""concept
"""
)

m5 = M.use_datasource.v1(
    instruments=m1.data,
    features=m10.data,
    datasource_id='industry_CN_STOCK_A',
    start_date='',
    end_date=''
)

m7 = M.join.v3(
    data1=m5.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m6 = M.input_features.v1(
    features='suspended'
)

m19 = M.use_datasource.v1(
    instruments=m1.data,
    features=m6.data,
    datasource_id='stock_status_CN_STOCK_A',
    start_date='',
    end_date=''
)

m20 = M.join.v3(
    data1=m7.data,
    data2=m19.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m2 = M.stockpool_select.v6(
    input_1=m20.data,
    self_instruments=[],
    input_concepts=[],
    input_industrys=[360000,710000,220000,460000,370000,330000,340000,720000,240000,630000,280000,420000,510000,640000,610000,620000,650000,230000,410000,350000,490000,110000,210000,480000,730000,450000,270000,430000],
    input_indexs=['中小板'],
    input_st='过滤',
    input_suspend='过滤'
)

m22 = M.cached.v3(
    input_1=m2.data,
    run=m22_run_bigquant_run,
    post_run=m22_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m17 = M.cached.v3(
    input_1=m22.data_1,
    input_2=m22.data_2,
    input_3=m22.data_3,
    run=m17_run_bigquant_run,
    post_run=m17_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m9 = M.stock_ranker_train.v6(
    training_ds=m17.data_1,
    features=m3.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=280,
    number_of_trees=21,
    learning_rate=0.1,
    max_bins=1023,
    feature_fraction=1,
    data_row_fraction=1,
    plot_charts=True,
    ndcg_discount_base=1,
    m_lazy_run=False
)

m13 = M.instruments.v2(
    start_date='2022-01-01',
    end_date='2022-05-21',
    market='CN_STOCK_A',
    instrument_list=''
)

m14 = M.general_feature_extractor.v7(
    instruments=m13.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=0
)

m18 = M.derived_feature_extractor.v3(
    input_data=m14.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m21 = M.dropnan.v2(
    input_data=m18.data
)

m11 = M.stock_ranker_predict.v5(
    model=m9.model,
    data=m21.data,
    m_lazy_run=False
)

m12 = M.trade.v4(
    instruments=m13.data,
    options_data=m11.predictions,
    start_date='',
    end_date='',
    initialize=m12_initialize_bigquant_run,
    handle_data=m12_handle_data_bigquant_run,
    prepare=m12_prepare_bigquant_run,
    volume_limit=0,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=20000,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='真实价格',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark='000300.HIX'
)

[2022-05-25 00:04:32.916104] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-05-25 00:04:32.923387] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:32.924898] INFO: moduleinvoker: instruments.v2 运行完成[0.008802s].

[2022-05-25 00:04:32.928759] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-25 00:04:32.935086] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:32.938966] INFO: moduleinvoker: input_features.v1 运行完成[0.010206s].

[2022-05-25 00:04:32.951542] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-05-25 00:04:32.961819] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:32.963471] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01194s].

[2022-05-25 00:04:32.972121] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-05-25 00:04:32.986897] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:32.988539] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.016421s].

[2022-05-25 00:04:32.994126] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-25 00:04:33.003071] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:33.004921] INFO: moduleinvoker: input_features.v1 运行完成[0.010798s].

[2022-05-25 00:04:33.010381] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-25 00:04:33.017929] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:33.019794] INFO: moduleinvoker: use_datasource.v1 运行完成[0.00942s].

[2022-05-25 00:04:33.028422] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-25 00:04:33.041549] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:33.043506] INFO: moduleinvoker: join.v3 运行完成[0.015082s].

[2022-05-25 00:04:33.047743] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-05-25 00:04:33.059197] INFO: moduleinvoker: 命中缓存

[2022-05-25 00:04:33.061479] INFO: moduleinvoker: input_features.v1 运行完成[0.013728s].

[2022-05-25 00:04:33.067002] INFO: moduleinvoker: use_datasource.v1 开始运行..

[2022-05-25 00:04:34.537965] INFO: moduleinvoker: use_datasource.v1 运行完成[1.470957s].

[2022-05-25 00:04:34.547146] INFO: moduleinvoker: join.v3 开始运行..

[2022-05-25 00:04:43.146068] INFO: join: /y_2012, 行数=0/0, 耗时=1.121147s

[2022-05-25 00:04:46.731842] INFO: join: /y_2013, 行数=564168/564168, 耗时=3.584043s

[2022-05-25 00:04:50.463881] INFO: join: /y_2014, 行数=569948/569948, 耗时=3.718822s

[2022-05-25 00:04:54.376072] INFO: join: /y_2015, 行数=569698/569698, 耗时=3.901537s

[2022-05-25 00:04:58.615365] INFO: join: /y_2016, 行数=641546/641546, 耗时=4.23082s

[2022-05-25 00:05:04.064985] INFO: join: /y_2017, 行数=743233/743233, 耗时=5.41686s

[2022-05-25 00:05:09.909016] INFO: join: /y_2018, 行数=816987/816987, 耗时=5.832998s

[2022-05-25 00:05:15.596323] INFO: join: /y_2019, 行数=884867/884867, 耗时=5.669565s

[2022-05-25 00:05:15.772192] INFO: join: 最终行数: 4790447

[2022-05-25 00:05:15.808333] INFO: moduleinvoker: join.v3 运行完成[41.261187s].

[2022-05-25 00:05:15.831925] INFO: moduleinvoker: stockpool_select.v6 开始运行..

[2022-05-25 00:15:27.001073] INFO: moduleinvoker: stockpool_select.v6 运行完成[611.169323s].

[2022-05-25 00:15:27.020441] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-25 00:15:36.084115] INFO: moduleinvoker: cached.v3 运行完成[9.063661s].

[2022-05-25 00:15:36.101754] INFO: moduleinvoker: cached.v3 开始运行..

[2022-05-25 00:15:40.425327] INFO: moduleinvoker: cached.v3 运行完成[4.323595s].

[2022-05-25 00:15:40.444813] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2022-05-25 00:15:40.519931] ERROR: moduleinvoker: module name: cached, module version: v2, trackeback: tables.exceptions.HDF5ExtError: HDF5 error back trace

  File "H5F.c", line 509, in H5Fopen
    unable to open file
  File "H5Fint.c", line 1400, in H5F__open
    unable to open file
  File "H5Fint.c", line 1700, in H5F_open
    unable to read superblock
  File "H5Fsuper.c", line 411, in H5F__super_read
    file signature not found

End of HDF5 error back trace

Unable to open/create file '/var/app/data/bigquant/datasource/user/v3/d/d9/dd9a2886e8e040a9912046292f949380T'

[2022-05-25 00:15:40.539532] ERROR: moduleinvoker: module name: stock_ranker_train, module version: v6, trackeback: tables.exceptions.HDF5ExtError: HDF5 error back trace

  File "H5F.c", line 509, in H5Fopen
    unable to open file
  File "H5Fint.c", line 1400, in H5F__open
    unable to open file
  File "H5Fint.c", line 1700, in H5F_open
    unable to read superblock
  File "H5Fsuper.c", line 411, in H5F__super_read
    file signature not found

End of HDF5 error back trace

Unable to open/create file '/var/app/data/bigquant/datasource/user/v3/d/d9/dd9a2886e8e040a9912046292f949380T'

---------------------------------------------------------------------------
HDF5ExtError                              Traceback (most recent call last)
<ipython-input-4-7a92dc4f7c7f> in <module>
    279 )
    280 
--> 281 m9 = M.stock_ranker_train.v6(
    282     training_ds=m17.data_1,
    283     features=m3.data,

HDF5ExtError: HDF5 error back trace

  File "H5F.c", line 509, in H5Fopen
    unable to open file
  File "H5Fint.c", line 1400, in H5F__open
    unable to open file
  File "H5Fint.c", line 1700, in H5F_open
    unable to read superblock
  File "H5Fsuper.c", line 411, in H5F__super_read
    file signature not found

End of HDF5 error back trace

Unable to open/create file '/var/app/data/bigquant/datasource/user/v3/d/d9/dd9a2886e8e040a9912046292f949380T'