复制链接

克隆策略

In [7]:

# 本代码由可视化策略环境自动生成 2023年3月2日 20:41
# 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。


# 回测引擎：初始化函数，只执行一次
def m4_initialize_bigquant_run(context):
    # 加载预测数据
    context.ranker_prediction = context.options['data'].read_df()

    # 系统已经设置了默认的交易手续费和滑点，要修改手续费可使用如下函数
    context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
    # 预测数据，通过options传入进来，使用 read_df 函数，加载到内存 (DataFrame)
    # 设置买入的股票数量，这里买入预测股票列表排名靠前的5只
    stock_count = 5
    # 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 =0.1
    context.options['hold_days'] = 5
    
    # 这一段感觉是在为盘前准备函数写的，当order.amount>0时，认为是买入，<0卖出。
    from zipline.finance.slippage import SlippageModel
    class FixedPriceSlippage(SlippageModel):
        def process_order(self, data, order, bar_volume=0, trigger_check_price=0):
            if order.limit is None:
                price_field = self._price_field_buy if order.amount > 0 else self._price_field_sell
                price = data.current(order.asset, price_field)
            else:
                price = data.current(order.asset, self._price_field_buy)
            # 返回希望成交的价格和数量
            return (price, order.amount)
    # 设置price_field,默认是开盘买入，收盘卖出
    context.fix_slippage = FixedPriceSlippage(price_field_buy='open', price_field_sell='close')
    context.set_slippage(us_equities=context.fix_slippage)
# 回测引擎：每日数据处理函数，每天执行一次
def m4_handle_data_bigquant_run(context, data):
    # 获取当前持仓
    positions = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.portfolio.positions.items()}
    
    today = data.current_dt.strftime('%Y-%m-%d')
    # 按日期过滤得到今日的预测数据
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == today]
    
    
    # 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)
   
    
    # 2. 根据需要加入移动止赢止损模块、固定天数卖出模块、ST或退市股卖出模块
    stock_sold = [] # 记录卖出的股票，防止多次卖出出现空单
    
#     #------------------------START:止赢止损模块(含建仓期)---------------
#     current_stopwin_stock=[]
#     current_stoploss_stock = []   
#     positions_cost={e.symbol:p.cost_basis for e,p in context.portfolio.positions.items()}
#     if len(positions)>0:
#         for instrument in positions.keys():
#             stock_cost=positions_cost[instrument]  
#             stock_market_price=data.current(context.symbol(instrument),'price')  
#             volume_since_buy = data.history(context.symbol(instrument), 'volume', 6, '1d')
#             # 赚60%且为可交易状态就止盈
#             if stock_market_price/stock_cost-1>=0.5 and data.can_trade(context.symbol(instrument)):
#                 context.order_target_percent(context.symbol(instrument),0)
#                 cash_for_sell -= positions[instrument]
#                 current_stopwin_stock.append(instrument)
#             # 亏5%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)):   
#                 context.order_target_percent(context.symbol(instrument),0)
#                 cash_for_sell -= positions[instrument]
#                 current_stoploss_stock.append(instrument)
#             # 放天量  止损：
# #             if  (volume_since_buy[0]>1.5*volume_since_buy[1]) |(volume_since_buy[0]>1.5*(volume_since_buy[1]+volume_since_buy[2]+volume_since_buy[3]+volume_since_buy[4]+volume_since_buy[5])/5):
# #                 context.order_target_percent(context.symbol(instrument),0)
# #                 cash_for_sell -= positions[instrument]
# #                 current_stoploss_stock.append(instrument)
#         if len(current_stopwin_stock)>0:
# #             print(today,'止盈股票列表',current_stopwin_stock)
#             stock_sold += current_stopwin_stock
#         if len(current_stoploss_stock)>0:
# #             print(today,'止损股票列表',current_stoploss_stock)
#             stock_sold += current_stoploss_stock
#     #--------------------------END: 止赢止损模块--------------------------
    
#     #--------------------------START：持有固定天数卖出(不含建仓期)-----------
#     current_stopdays_stock = []
#     positions_lastdate = {e.symbol:p.last_sale_date for e,p in context.portfolio.positions.items()}
#     # 不是建仓期（在前hold_days属于建仓期）
#     if not is_staging:
#         for instrument in positions.keys():
#             #如果上面的止盈止损已经卖出过了，就不要重复卖出以防止产生空单
#             if instrument in stock_sold:
#                 continue
#             # 今天和上次交易的时间相隔hold_days就全部卖出 datetime.timedelta(context.options['hold_days'])也可以换成自己需要的天数，比如datetime.timedelta(5)
#             if data.current_dt - positions_lastdate[instrument]>=datetime.timedelta(22) and data.can_trade(context.symbol(instrument)):
#                 context.order_target_percent(context.symbol(instrument), 0)
#                 current_stopdays_stock.append(instrument)
#                 cash_for_sell -= positions[instrument]
#         if len(current_stopdays_stock)>0:        
# #             print(today,'固定天数卖出列表',current_stopdays_stock)
#             stock_sold += current_stopdays_stock
#     #-------------------------  END:持有固定天数卖出-----------------------
    
#     #-------------------------- START: ST和退市股卖出 ---------------------  
#     st_stock_list = []
#     for instrument in positions.keys():
#         try:
#             instrument_name = ranker_prediction[ranker_prediction.instrument==instrument].name.values[0]
#             # 如果股票状态变为了st或者退市 则卖出
#             if 'ST' in instrument_name or '退' in instrument_name:
#                 if instrument in stock_sold:
#                     continue
#                 if data.can_trade(context.symbol(instrument)):
#                     context.order_target(context.symbol(instrument), 0)
#                     st_stock_list.append(instrument)
#                     cash_for_sell -= positions[instrument]
#         except:
#             continue
#     if st_stock_list!=[]:
# #         print(today,'持仓出现st股/退市股',st_stock_list,'进行卖出处理')    
#         stock_sold += st_stock_list

#     #-------------------------- END: ST和退市股卖出 --------------------- 
    
    
    # 3. 生成轮仓卖出订单：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:
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in positions)])))
        for instrument in instruments:
            # 如果资金够了就不卖出了
            if cash_for_sell <= 0:
                break
            #防止多个止损条件同时满足，出现多次卖出产生空单
            if instrument in stock_sold:
                continue
            context.order_target(context.symbol(instrument), 0)
            cash_for_sell -= positions[instrument]
            stock_sold.append(instrument)

    # 4. 生成轮仓买入订单：按机器学习算法预测的排序，买入前面的stock_count只股票
    # 计算今日跌停的股票
    #dt_list = list(ranker_prediction[ranker_prediction.price_limit_status_0==1].instrument)
    # 计算今日ST/退市的股票
    st_list = list(ranker_prediction[ranker_prediction.name.str.contains('ST')|ranker_prediction.name.str.contains('退')].instrument)
    # 计算所有禁止买入的股票池
    banned_list = stock_sold+st_list
    buy_cash_weights = context.stock_weights
    buy_instruments=[k for k in list(ranker_prediction.instrument) if k not in banned_list][: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:
            current_price = data.current(context.symbol(instrument), 'price')
            amount = math.floor(cash / current_price - cash / current_price % 100)
            context.order(context.symbol(instrument), amount)
    


def m4_before_trading_start_bigquant_run(context, data):
    # 获取涨跌停状态数据
    df_price_limit_status = context.ranker_prediction.set_index('date')
    today=data.current_dt.strftime('%Y-%m-%d')
    # 得到当前未完成订单
    for orders in get_open_orders().values():
        # 循环，撤销订单
        for _order in orders:
            ins=str(_order.sid.symbol)
            try:
                #判断一下如果当日涨停（3），则取消卖单
                if  df_price_limit_status[df_price_limit_status.instrument==ins].price_limit_status_0.ix[today]>2 and _order.amount<0:
                    cancel_order(_order)
                    print(today,'尾盘涨停取消卖单',ins) 
            except:
                continue
# 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 m26_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    pred_label = input_1.read_pickle()
    df = input_2.read_df()
    df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})
    df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])
    df_value = pd.merge(left=df,right=input_3.read(),on=['date','instrument'],how='inner')
    return Outputs(data_1=DataSource.write_df(df), data_2=DataSource.write_df(df_value), 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 m26_post_run_bigquant_run(outputs):
    return outputs


m1 = M.instruments.v2(
    start_date='2016-01-01',
    end_date='2019-12-31',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m2 = M.advanced_auto_labeler.v2(
    instruments=m1.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -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, 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)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=True
)

m3 = M.input_features.v1(
    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
high_0
high_1
high_2
high_3
high_4
low_0
low_1
low_2
low_3
low_4
# 5日平均换手率
avg_turn_5   
# 5日平均振幅
(high_0-low_0+high_1-low_1+high_2-low_2+high_3-low_3+high_4-low_4)/5 
# 市盈率LYR
pe_lyr_0
# 5日净主动买入额
mf_net_amount_5 
# 10日净主动买入额
mf_net_amount_10 
# 20日净主动买入额
mf_net_amount_20

"""
)

m23 = M.input_features.v1(
    features_ds=m3.data,
    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
#周线金叉，择时思路
# 当天股价在收盘时的涨跌停状态（1跌停，2未涨跌停，3涨停）
close_0
high_1
open_0
low_0
st_status_0
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m23.data,
    start_date='',
    end_date='',
    before_start_days=300
)

m16 = M.derived_feature_extractor.v3(
    input_data=m15.data,
    features=m23.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={}
)

m7 = M.join.v3(
    data1=m2.data,
    data2=m16.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m12 = M.dropnan.v1(
    input_data=m7.data
)

m24 = M.features_short.v1(
    input_1=m23.data
)

m17 = M.stock_ranker_train.v6(
    training_ds=m12.data,
    features=m24.data_1,
    test_ds=m12.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    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
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2020-01-01'),
    end_date=T.live_run_param('trading_date', '2021-12-31'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m18 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m23.data,
    start_date='',
    end_date='',
    before_start_days=300
)

m19 = M.derived_feature_extractor.v3(
    input_data=m18.data,
    features=m23.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m13 = M.dropnan.v1(
    input_data=m19.data
)

m8 = M.stock_ranker_predict.v5(
    model=m17.model,
    data=m13.data,
    m_lazy_run=False
)

m22 = M.sort.v4(
    input_ds=m8.predictions,
    sort_by='score',
    group_by='date',
    keep_columns='--',
    ascending=False
)

m4 = M.trade.v4(
    instruments=m9.data,
    options_data=m22.sorted_data,
    start_date='',
    end_date='',
    initialize=m4_initialize_bigquant_run,
    handle_data=m4_handle_data_bigquant_run,
    before_trading_start=m4_before_trading_start_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000001,
    auto_cancel_non_tradable_orders=True,
    data_frequency='daily',
    price_type='后复权',
    product_type='股票',
    plot_charts=True,
    backtest_only=False,
    benchmark=''
)

m27 = M.advanced_auto_labeler.v2(
    instruments=m9.data,
    label_expr="""# #号开始的表示注释
# 0. 每行一个，顺序执行，从第二个开始，可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
#   添加benchmark_前缀，可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_

# 计算收益：5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)-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))

# 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)
""",
    start_date='',
    end_date='',
    benchmark='000300.SHA',
    drop_na_label=True,
    cast_label_int=False
)

m26 = M.cached.v3(
    input_1=m22.sorted_data,
    input_2=m19.data,
    input_3=m27.data,
    run=m26_run_bigquant_run,
    post_run=m26_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m21 = M.metrics_regression.v1(
    predictions=m26.data_2,
    explained_variance_score=True,
    mean_absolute_error=True,
    mean_squared_error=True,
    mean_squared_log_error=False,
    median_absolute_error=True,
    r2_score=True
)

m5 = M.input_features.v1(
    features="""
# #号开始的表示注释，注释需单独一行
# 多个特征，每行一个，可以包含基础特征和衍生特征，特征须为本平台特征
name"""
)

m6 = M.use_datasource.v1(
    instruments=m9.data,
    features=m5.data,
    datasource_id='instruments_CN_STOCK_A',
    start_date='',
    end_date=''
)

m11 = M.input_features.v1(
    features="""
# #号开始的表示注释，注释需单独一行
# 多个特征，每行一个，可以包含基础特征和衍生特征，特征须为本平台特征
#bm_0 = where(close/shift(close,5)-1<-0.05,1,0)
# 如果macd中的dif下穿macd中的dea，则bm_0等于1，否则等于0
bm_0=where(ta_macd_dif(close,2,4,4)-ta_macd_dea(close,2,4,4)<0,1,0)"""
)

m14 = M.index_feature_extract.v3(
    input_1=m9.data,
    input_2=m11.data,
    before_days=100,
    index='000300.HIX'
)

m20 = M.select_columns.v3(
    input_ds=m14.data_1,
    columns='date,bm_0',
    reverse_select=False
)

m10 = M.join.v3(
    data1=m6.data,
    data2=m20.data,
    on='date',
    how='left',
    sort=True
)

m25 = M.join.v3(
    data1=m8.predictions,
    data2=m10.data,
    on='date,instrument',
    how='left',
    sort=False
)

[2023-03-02 20:40:01.913320] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-03-02 20:40:01.924174] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:01.928642] INFO: moduleinvoker: instruments.v2 运行完成[0.015315s].

[2023-03-02 20:40:01.946200] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-03-02 20:40:01.961734] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:01.964929] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.018742s].

[2023-03-02 20:40:01.979134] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-03-02 20:40:01.988694] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:01.991902] INFO: moduleinvoker: input_features.v1 运行完成[0.012738s].

[2023-03-02 20:40:02.011436] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-03-02 20:40:02.020329] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.023570] INFO: moduleinvoker: input_features.v1 运行完成[0.012153s].

[2023-03-02 20:40:02.055998] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-03-02 20:40:02.068559] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.071094] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.015115s].

[2023-03-02 20:40:02.082251] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-03-02 20:40:02.091746] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.097936] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.015636s].

[2023-03-02 20:40:02.109394] INFO: moduleinvoker: join.v3 开始运行..

[2023-03-02 20:40:02.120673] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.123009] INFO: moduleinvoker: join.v3 运行完成[0.013611s].

[2023-03-02 20:40:02.146188] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-03-02 20:40:02.159646] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.166500] INFO: moduleinvoker: dropnan.v1 运行完成[0.020312s].

[2023-03-02 20:40:02.187262] INFO: moduleinvoker: features_short.v1 开始运行..

[2023-03-02 20:40:02.198853] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.202027] INFO: moduleinvoker: features_short.v1 运行完成[0.014775s].

[2023-03-02 20:40:02.213819] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..

[2023-03-02 20:40:02.228583] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.511188] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.297345s].

[2023-03-02 20:40:02.521983] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-03-02 20:40:02.530270] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.533263] INFO: moduleinvoker: instruments.v2 运行完成[0.011353s].

[2023-03-02 20:40:02.560342] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-03-02 20:40:02.569381] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.572486] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.012154s].

[2023-03-02 20:40:02.591798] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-03-02 20:40:02.606878] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.610423] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.018752s].

[2023-03-02 20:40:02.627392] INFO: moduleinvoker: dropnan.v1 开始运行..

[2023-03-02 20:40:02.637723] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.641526] INFO: moduleinvoker: dropnan.v1 运行完成[0.014239s].

[2023-03-02 20:40:02.656315] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2023-03-02 20:40:02.676369] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:02.680217] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.023881s].

[2023-03-02 20:40:02.696237] INFO: moduleinvoker: sort.v4 开始运行..

[2023-03-02 20:40:11.904659] INFO: moduleinvoker: sort.v4 运行完成[9.208426s].

[2023-03-02 20:40:11.913809] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-03-02 20:40:11.921351] INFO: moduleinvoker: 命中缓存

[2023-03-02 20:40:11.923404] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009605s].

[2023-03-02 20:40:11.934970] INFO: moduleinvoker: cached.v3 开始运行..

[2023-03-02 20:40:12.033326] ERROR: moduleinvoker: module name: cached, module version: v3, trackeback: _pickle.UnpicklingError: invalid load key, 'H'.

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-6bd753c6b60e47cbb1096f764551a59d"}/bigcharts-data-end

---------------------------------------------------------------------------
UnpicklingError                           Traceback (most recent call last)
<ipython-input-7-9f2363dc1826> in <module>
    214 )
    215 
--> 216 m26 = M.cached.v3(
    217     input_1=m22.sorted_data,
    218     input_2=m19.data,

<ipython-input-7-9f2363dc1826> in m26_run_bigquant_run(input_1, input_2, input_3)
      6 def m26_run_bigquant_run(input_1, input_2, input_3):
      7     # 示例代码如下。在这里编写您的代码
----> 8     pred_label = input_1.read_pickle()
      9     df = input_2.read_df()
     10     df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})

UnpicklingError: invalid load key, 'H'.