克隆策略

In [2]:

# 本代码由可视化策略环境自动生成 2021年12月3日 13:46
# 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。


def cal_bm_return(df):
    bm_df = DataSource('bar1d_index_CN_STOCK_A').read(instruments=['000001.HIX'])
    bm_df["bm_ret"] = bm_df["close"]/bm_df["close"].shift(10)-1
    merge_df = pd.merge(df, bm_df[['date','bm_ret']], on='date', how='left')
    return merge_df['bm_ret']


m16_user_functions_bigquant_run = {
    'cal_bm_return': cal_bm_return,
}

# 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))
    # 设置每只股票占用的最大资金比例
    context.order_pct = 0.05

    #大盘数据获取
    bm_df = DataSource('bar1d_index_CN_STOCK_A').read(instruments=['000001.HIX'])
    bm_df["bm_ret"] = bm_df["close"]/bm_df["close"].shift(10)-1
    bm_df["bm_ret"] = bm_df["bm_ret"].shift(1) #取昨日的收益情况
    context.bm_df = bm_df[['date','bm_ret']]
    
    #个股风控计算
    start_date = context.ranker_prediction.date.iloc[0]
    start_date = pd.to_datetime(start_date)-timedelta(days=30)
    end_date = context.ranker_prediction.date.iloc[-1]
    stocks = context.ranker_prediction.instrument.to_list()
    data = DataSource("bar1d_CN_STOCK_A").read(instruments=stocks,start_date=start_date.strftime("%Y-%m-%d"),end_date=end_date)
    #计算个股风控，小于20日均线
    def cal_risk(df):
        df = df.sort_values("date")
        df["ma"] = df.close.rolling(20).mean()
        df["risk"] = np.where(df.close.shift(1)<df.ma.shift(1),1,0)
        return df
    context.stock_risk_data = data.groupby("instrument").apply(cal_risk).reset_index(drop=True)




# 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):
    # 每10天执行一次
#     if context.trading_day_index % 2 != 0:
#         return
    
    if(context.bm_risk==1):
        print("触发大盘风控，每日处理函数直接返回！")
        return
    today = data.current_dt.strftime('%Y-%m-%d')  

    #====卖出股票
    stock_hold_now = [e.symbol for e, _ in context.perf_tracker.position_tracker.positions.items()]
    print(today,"=======卖出的股票:",stock_hold_now)
    for instr in stock_hold_now:
        context.order_target(context.symbol(instr), 0) #卖出
    
    #买入股票
    ranker_prediction = context.ranker_prediction[context.ranker_prediction.date == today]
    #取排名靠前的前5只
    today_to_buy = list(ranker_prediction.instrument[:5])
    print(today,"=======买入的股票 {}".format(today_to_buy))
    
    # 获取账户资金
    total_portfolio = context.portfolio.portfolio_value
        
    for instr in today_to_buy:
        #最新价格
        price = data.current(context.symbol(instr), 'close')
        #计算买入此股票的数量，不要超过总资金的某个比例
        order_num = int(total_portfolio*context.order_pct/price/100)*100
        context.order_target(context.symbol(instr), order_num) # 买入
        print("{} 买入{}  最新价={} 下单量={}".format(today,instr,str(price),order_num))

# 回测引擎：准备数据，只执行一次
def m4_prepare_bigquant_run(context):
    pass

from zipline.finance.order import Order

#插入定单
def insert_order(context,date,instr,amount):
    order = Order(
        dt = pd.to_datetime(date+" 09:30:00"),
        asset=context.symbol(instr),
        amount=-amount,
        stop=None,
        limit=None,
        price_field='open')

    try:
        context.blotter.open_orders[order.asset].append(order)
    except Exception:
        context.blotter.open_orders[order.asset] = [order]

    context.blotter.orders[order.id] = order
    context.blotter.new_orders.append(order) 
    
#个股风控判断
def stock_risk(context, data):
    today=data.current_dt.strftime('%Y-%m-%d')
    #====卖出股票
    stock_hold_now = {e.symbol:p.amount for e, p in context.perf_tracker.position_tracker.positions.items()}
    stocks = stock_hold_now.keys()

    for instr,amount in stock_hold_now.items():
        nowdata = context.stock_risk_data[(context.stock_risk_data.instrument==instr)&(context.stock_risk_data.date==today)]
        #触发个股风控，早盘卖出
        if nowdata.risk.iloc[0] == 1 and amount>0:
            print(today,'个股风控卖出：',instr) 
            insert_order(context,today,instr,amount)
            
#主函数
def m4_before_trading_start_bigquant_run(context, data):
    today=data.current_dt.strftime('%Y-%m-%d')
    now_bm = context.bm_df[context.bm_df.date==today]
    #个股风控
    stock_risk(context,data)
    context.bm_risk = 0
    #大盘风控判断
    if(now_bm.bm_ret.iloc[0]<-0.01):
        context.bm_risk = 1
        # 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)
                if data.can_trade(_order.sid) and _order.amount>0:
                    #大盘风控取消买单
                    cancel_order(_order)
                    print(today,'大盘风控取消买单',ins) 
                if data.can_trade(_order.sid) and _order.amount<0:#卖单由后续统一处理，先取消
                    #大盘风控取消卖单
                    cancel_order(_order)
                    print(today,'大盘风控取消卖单',ins) 
                    
        #====卖出股票
        stock_hold_now = {e.symbol:p.amount for e, p in context.perf_tracker.position_tracker.positions.items()}
        print(today,"=======风控卖出所有的股票:",stock_hold_now)
        for instr,amount in stock_hold_now.items():
            #插入定单
            insert_order(context,today,instr,amount)
                   

m1 = M.instruments.v2(
    start_date='2020-10-01',
    end_date='2020-12-31',
    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
# ts_rank(turn_0, 5)
avg_turn_15/turn_0
mf_net_amount_xl_0
alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2
#macd的红柱量能线要大于绿色量能线收盘价最低回踩25日内均线不破，可以防止趋势走坏要求macd的黄线慢线要大于0.2
"""
)

m15 = M.general_feature_extractor.v7(
    instruments=m1.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=60
)

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,
    user_functions=m16_user_functions_bigquant_run
)

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

m13 = M.dropnan.v1(
    input_data=m7.data
)

m5 = M.chinaa_stock_filter.v1(
    input_data=m13.data,
    index_constituent_cond=['全部'],
    board_cond=['全部'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m6 = M.stock_ranker_train.v5(
    training_ds=m5.data,
    features=m3.data,
    learning_algorithm='排序',
    number_of_leaves=30,
    minimum_docs_per_leaf=1000,
    number_of_trees=20,
    learning_rate=0.5,
    max_bins=1023,
    feature_fraction=1,
    m_lazy_run=False
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2021-01-21'),
    end_date=T.live_run_param('trading_date', '2021-02-01'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m3.data,
    start_date='',
    end_date='',
    before_start_days=60
)

m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m3.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

m14 = M.dropnan.v1(
    input_data=m18.data
)

m10 = M.chinaa_stock_filter.v1(
    input_data=m14.data,
    index_constituent_cond=['全部'],
    board_cond=['全部'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

m8 = M.stock_ranker_predict.v5(
    model=m6.model,
    data=m10.data,
    m_lazy_run=False
)

m4 = M.trade.v4(
    instruments=m9.data,
    options_data=m8.predictions,
    start_date='',
    end_date='',
    initialize=m4_initialize_bigquant_run,
    handle_data=m4_handle_data_bigquant_run,
    prepare=m4_prepare_bigquant_run,
    before_trading_start=m4_before_trading_start_bigquant_run,
    volume_limit=0,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000,
    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=''
)

[2021-12-03 13:36:40.033769] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-12-03 13:36:40.042118] INFO: moduleinvoker: 命中缓存

[2021-12-03 13:36:40.044518] INFO: moduleinvoker: instruments.v2 运行完成[0.010778s].

[2021-12-03 13:36:40.054445] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2021-12-03 13:36:40.062214] INFO: moduleinvoker: 命中缓存

[2021-12-03 13:36:40.063658] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[0.009223s].

[2021-12-03 13:36:40.068781] INFO: moduleinvoker: input_features.v1 开始运行..

[2021-12-03 13:36:40.079905] INFO: moduleinvoker: 命中缓存

[2021-12-03 13:36:40.081173] INFO: moduleinvoker: input_features.v1 运行完成[0.012393s].

[2021-12-03 13:36:40.100205] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-12-03 13:36:40.155880] WARNING: bigdatasource: cannot find filed [close_0avg_turn_0] table in field_table_map!

[2021-12-03 13:36:40.157367] WARNING: bigdatasource: cannot find filed [close_1avg_turn_1] table in field_table_map!

[2021-12-03 13:36:42.441575] WARNING: bigdatasource: unknown fields: ['close_0avg_turn_0', 'close_1avg_turn_1']

[2021-12-03 13:36:42.823278] INFO: 基础特征抽取: 年份 2020, 特征行数=413515

[2021-12-03 13:36:42.899862] INFO: 基础特征抽取: 总行数: 413515

[2021-12-03 13:36:42.907206] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[2.807007s].

[2021-12-03 13:36:42.918560] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-03 13:36:43.668024] WARNING: derived_feature_extractor: 特征 alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2，找不到依赖的列：close_0avg_turn_0

[2021-12-03 13:36:43.669663] WARNING: derived_feature_extractor: 特征 alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2，找不到依赖的列：close_1avg_turn_1

[2021-12-03 13:36:43.702117] INFO: derived_feature_extractor: 提取完成 avg_turn_15/turn_0, 0.002s

[2021-12-03 13:36:43.704054] INFO: derived_feature_extractor: 提取失败 alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2: Unknown close_0avg_turn_0

[2021-12-03 13:36:44.413803] INFO: derived_feature_extractor: /y_2020, 413515

[2021-12-03 13:36:44.596723] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[1.678156s].

[2021-12-03 13:36:44.611184] INFO: moduleinvoker: join.v3 开始运行..

[2021-12-03 13:36:46.200442] INFO: join: /y_2020, 行数=222757/413515, 耗时=1.034107s

[2021-12-03 13:36:46.268723] INFO: join: 最终行数: 222757

[2021-12-03 13:36:46.281693] INFO: moduleinvoker: join.v3 运行完成[1.670435s].

[2021-12-03 13:36:46.294406] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-12-03 13:36:46.615969] INFO: dropnan: /y_2020, 221440/222757

[2021-12-03 13:36:46.669966] INFO: dropnan: 行数: 221440/222757

[2021-12-03 13:36:46.678609] INFO: moduleinvoker: dropnan.v1 运行完成[0.384198s].

[2021-12-03 13:36:46.690733] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2021-12-03 13:36:47.761173] INFO: A股股票过滤: 过滤 /y_2020, 210402/0/221440

[2021-12-03 13:36:47.764624] INFO: A股股票过滤: 过滤完成, 210402 + 0

[2021-12-03 13:36:47.797058] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[1.10631s].

[2021-12-03 13:36:47.807480] INFO: moduleinvoker: stock_ranker_train.v5 开始运行..

[2021-12-03 13:36:48.002048] INFO: StockRanker: 特征预处理 ..

[2021-12-03 13:36:48.105780] INFO: StockRanker: prepare data: training ..

[2021-12-03 13:36:48.169226] INFO: StockRanker: sort ..

[2021-12-03 13:36:50.325379] INFO: StockRanker训练: 021228b8 准备训练: 210402 行数

[2021-12-03 13:36:50.534617] INFO: StockRanker训练: 正在训练 ..

[2021-12-03 13:39:12.443270] INFO: moduleinvoker: stock_ranker_train.v5 运行完成[144.63579s].

[2021-12-03 13:39:12.448251] INFO: moduleinvoker: instruments.v2 开始运行..

[2021-12-03 13:39:12.459130] INFO: moduleinvoker: 命中缓存

[2021-12-03 13:39:12.460553] INFO: moduleinvoker: instruments.v2 运行完成[0.012299s].

[2021-12-03 13:39:12.480939] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2021-12-03 13:39:12.547712] WARNING: bigdatasource: cannot find filed [close_0avg_turn_0] table in field_table_map!

[2021-12-03 13:39:12.549259] WARNING: bigdatasource: cannot find filed [close_1avg_turn_1] table in field_table_map!

[2021-12-03 13:39:14.255428] WARNING: bigdatasource: unknown fields: ['close_0avg_turn_0', 'close_1avg_turn_1']

[2021-12-03 13:39:14.362852] INFO: 基础特征抽取: 年份 2020, 特征行数=118463

[2021-12-03 13:39:14.368419] WARNING: bigdatasource: cannot find filed [close_0avg_turn_0] table in field_table_map!

[2021-12-03 13:39:14.369561] WARNING: bigdatasource: cannot find filed [close_1avg_turn_1] table in field_table_map!

[2021-12-03 13:39:15.919427] WARNING: bigdatasource: unknown fields: ['close_0avg_turn_0', 'close_1avg_turn_1']

[2021-12-03 13:39:16.001514] INFO: 基础特征抽取: 年份 2021, 特征行数=86766

[2021-12-03 13:39:16.109295] INFO: 基础特征抽取: 总行数: 205229

[2021-12-03 13:39:16.117975] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[3.637027s].

[2021-12-03 13:39:16.126959] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2021-12-03 13:39:16.381515] WARNING: derived_feature_extractor: 特征 alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2，找不到依赖的列：close_0avg_turn_0

[2021-12-03 13:39:16.383041] WARNING: derived_feature_extractor: 特征 alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2，找不到依赖的列：close_1avg_turn_1

[2021-12-03 13:39:16.561794] INFO: derived_feature_extractor: 提取完成 avg_turn_15/turn_0, 0.007s

[2021-12-03 13:39:16.563485] INFO: derived_feature_extractor: 提取失败 alpha4=close_0avg_turn_0+close_1avg_turn_1+close_2*avg_turn_2: Unknown close_0avg_turn_0

[2021-12-03 13:39:16.818802] INFO: derived_feature_extractor: /y_2020, 118463

[2021-12-03 13:39:17.027205] INFO: derived_feature_extractor: /y_2021, 86766

[2021-12-03 13:39:17.108331] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.981363s].

[2021-12-03 13:39:17.117594] INFO: moduleinvoker: dropnan.v1 开始运行..

[2021-12-03 13:39:17.280262] INFO: dropnan: /y_2020, 117748/118463

[2021-12-03 13:39:17.376848] INFO: dropnan: /y_2021, 86179/86766

[2021-12-03 13:39:17.435364] INFO: dropnan: 行数: 203927/205229

[2021-12-03 13:39:17.440246] INFO: moduleinvoker: dropnan.v1 运行完成[0.322644s].

[2021-12-03 13:39:17.449394] INFO: moduleinvoker: chinaa_stock_filter.v1 开始运行..

[2021-12-03 13:39:18.080265] INFO: A股股票过滤: 过滤 /y_2020, 111901/0/117748

[2021-12-03 13:39:18.493840] INFO: A股股票过滤: 过滤 /y_2021, 81983/0/86179

[2021-12-03 13:39:18.498059] INFO: A股股票过滤: 过滤完成, 193884 + 0

[2021-12-03 13:39:18.527120] INFO: moduleinvoker: chinaa_stock_filter.v1 运行完成[1.077713s].

[2021-12-03 13:39:18.543369] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..

[2021-12-03 13:39:18.738073] INFO: StockRanker预测: /y_2020 ..

[2021-12-03 13:39:18.919144] INFO: StockRanker预测: /y_2021 ..

[2021-12-03 13:39:19.339420] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[0.796039s].

[2021-12-03 13:39:21.091939] INFO: moduleinvoker: backtest.v8 开始运行..

[2021-12-03 13:39:21.098506] INFO: backtest: biglearning backtest:V8.6.0

[2021-12-03 13:39:21.100297] INFO: backtest: product_type:stock by specified

[2021-12-03 13:39:21.198904] INFO: moduleinvoker: cached.v2 开始运行..

[2021-12-03 13:39:21.209563] INFO: moduleinvoker: 命中缓存

[2021-12-03 13:39:21.212083] INFO: moduleinvoker: cached.v2 运行完成[0.013196s].

[2021-12-03 13:39:22.181466] INFO: algo: TradingAlgorithm V1.8.5

[2021-12-03 13:39:23.269094] ERROR: moduleinvoker: module name: backtest, module version: v8, trackeback: NameError: name 'timedelta' is not defined

[2021-12-03 13:39:23.275823] ERROR: moduleinvoker: module name: trade, module version: v4, trackeback: NameError: name 'timedelta' is not defined

设置测试数据集，查看训练迭代过程的NDCG

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-edb6c367354b4b808c773f5d9602c1d0"}/bigcharts-data-end

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-2-64c5991a982e> in <module>
    294 )
    295 
--> 296 m4 = M.trade.v4(
    297     instruments=m9.data,
    298     options_data=m8.predictions,

<ipython-input-2-64c5991a982e> in m4_initialize_bigquant_run(context)
     31     #个股风控计算
     32     start_date = context.ranker_prediction.date.iloc[0]
---> 33     start_date = pd.to_datetime(start_date)-timedelta(days=30)
     34     end_date = context.ranker_prediction.date.iloc[-1]
     35     stocks = context.ranker_prediction.instrument.to_list()

NameError: name 'timedelta' is not defined