复制链接

克隆策略

In [46]:

m3.data_1.read()

Out[46]:

	date	bm_1	bm_2	bm_3
0	2022-02-07	NaN	NaN	4638.575195
1	2022-02-08	-0.005463	NaN	4626.436523
2	2022-02-09	0.009392	0.003878	4608.148926
3	2022-02-10	-0.002622	0.006746	4657.210938
4	2022-02-11	-0.008291	-0.010891	4617.874023
...	...	...	...	...
100	2022-07-05	-0.001444	0.005109	4505.457031
101	2022-07-06	-0.014605	-0.016028	4475.481445
102	2022-07-07	0.004409	-0.010260	4425.281250
103	2022-07-08	-0.003307	0.001088	4468.062500
104	2022-07-11	-0.016746	-0.019997	4406.147461

105 rows × 4 columns

In [4]:

# 本代码由可视化策略环境自动生成 2022年7月15日 11:16
# 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 m1_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 = 3
    # 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, ..]
    # 每只股票的权重平均分配
    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 = 0.33
    context.hold_days = 10

# 回测引擎：每日数据处理函数，每天执行一次
def m1_handle_data_bigquant_run(context, data):
    ranker_prediction = context.ranker_prediction[
        context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
 #------------------------------------------止赢模块START--------------------------------------------
    date = data.current_dt.strftime('%Y-%m-%d')
    positions = {e.symbol: p.cost_basis  for e, p in context.portfolio.positions.items()}
    # 新建当日止赢股票列表是为了handle_data 策略逻辑部分不再对该股票进行判断
    current_stopwin_stock = [] 
    if len(positions) > 0:
        for i in positions.keys():
            stock_cost = positions[i] 
            stock_market_price = data.current(context.symbol(i), 'price') 
            # 赚30%就止赢
            if (stock_market_price - stock_cost ) / stock_cost>= 0.7:   
                context.order_target_percent(context.symbol(i),0)     
                current_stopwin_stock.append(i)
                print('日期：',date,'股票：',i,'出现止盈状况')
    #-------------------------------------------止赢模块END---------------------------------------------

       
         #------------------------------------------止损模块START--------------------------------------------
    date = data.current_dt.strftime('%Y-%m-%d')  
    equities = {e.symbol: p for e, p in context.portfolio.positions.items() if p.amount>0}
    # 新建当日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
    current_stoploss_stock = [] 
    if len(equities) > 0:
        for i in equities.keys():
            stock_market_price = data.current(context.symbol(i), 'price')  # 最新市场价格
            last_sale_date = equities[i].last_sale_date   # 上次交易日期
            delta_days = data.current_dt - last_sale_date  
            hold_days = delta_days.days # 持仓天数
            # 建仓以来的最高价
            highest_price_since_buy = data.history(context.symbol(i), 'high', hold_days, '1d').max()
            # 确定止损位置
            stoploss_line = highest_price_since_buy - highest_price_since_buy * 0.2
            record('止损位置', stoploss_line)
            # 如果价格下穿止损位置
            if stock_market_price < stoploss_line:
                context.order_target_percent(context.symbol(i), 0)     
                current_stoploss_stock.append(i)
                print('日期：', date , '股票：', i, '出现止损状况')
    #-------------------------------------------止损模块END--------------------------------------------------
     #-------------------------- 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 --------------------- 
     # 获取今日的日期
    today = data.current_dt.strftime('%Y-%m-%d')  
    # 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 = {e.symbol: p.amount * p.last_sale_price
                 for e, p in context.portfolio.positions.items()}

    # 记录用于买入股票的可用现金,因为是早盘卖股票，需要记录卖出的股票市值并在买入下单前更新可用现金；
    # 如果是早盘买尾盘卖，则卖出时不需更新可用现金，因为尾盘卖出股票所得现金无法使用
    cash_for_buy = context.portfolio.cash    
    
    try:
        buy_stock = list(ranker_prediction[ranker_prediction.buy_condition>0].instrument) # 当日符合买入条件的股票
    except:
        buy_stock=[]
    try:
        sell_stock = list(context.daily_sell_stock[ranker_prediction.sell_condition>0].instrument)  # 当日符合卖出条件的股票
    except:
        sell_stock = []
    
    # 需要卖出的股票:已有持仓中符合卖出条件的股票
    stock_to_sell = [ i for i in stock_hold_now if i in sell_stock ]
    # 需要买入的股票:没有持仓且符合买入条件的股票
    stock_to_buy = [ i for i in buy_stock if i not in stock_hold_now ]  
    # 需要调仓的股票：已有持仓且不符合卖出条件的股票
    stock_to_adjust=[ i for i in stock_hold_now if i not in sell_stock ]
    
    # 如果有卖出信号
    if len(stock_to_sell)>0:
        for instrument in stock_to_sell:
            if instrument in current_stopwin_stock:
                continue
            sid = context.symbol(instrument) # 将标的转化为equity格式
            cur_position = context.portfolio.positions[sid].amount # 持仓
            if cur_position > 0 and data.can_trade(sid):
                context.order_target_percent(sid, 0) # 全部卖出 
                # 因为设置的是早盘卖出早盘买入，需要根据卖出的股票更新可用现金；如果设置尾盘卖出早盘买入，则不需更新可用现金(可以删除下面的语句)
                cash_for_buy += stock_hold_now[instrument]
    
    # 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.hold_days # 是否在建仓期间（前 hold_days 天）
    cash_avg = context.portfolio.portfolio_value / context.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()}

    
    

    # 3. 生成买入订单：按StockRanker预测的排序，买入前面的stock_count只股票
    ranker_prediction = ranker_prediction[ranker_prediction.buy_condition>=1]
    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 m1_prepare_bigquant_run(context):
    # 加载预测数据
    df = context.options['data'].read_df()

    # 函数：求满足开仓条件的股票列表
    def open_pos_con(df):
        return list(df[df['buy_condition']>0].instrument)

    # 函数：求满足平仓条件的股票列表
    def close_pos_con(df):
        return list(df[df['sell_condition']>0].instrument)

    # 每日买入股票的数据框
    context.daily_stock_buy= df.groupby('date').apply(open_pos_con)
    # 每日卖出股票的数据框
    context.daily_stock_sell= df.groupby('date').apply(close_pos_con)

m11 = M.instruments.v2(
    start_date='2022-06-01',
    end_date='2022-07-11',
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0,
    m_cached=False
)

m4 = M.input_features.v1(
    features="""# return_0
bm_1=close/shift(close,1)-1
# return_1
bm_2=close/shift(close,2)-1

bm_3=open""",
    m_cached=False
)

m3 = M.index_feature_extract.v3(
    input_1=m11.data,
    input_2=m4.data,
    before_days=120,
    index='000300.HIX',
    m_cached=False
)

m5 = M.select_columns.v3(
    input_ds=m3.data_1,
    columns_ds=m3.data_2,
    columns='date,bm_1,bm_2,bm_3',
    reverse_select=False,
    m_cached=False
)

m7 = 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""",
    m_cached=False
)

m9 = M.use_datasource.v1(
    instruments=m11.data,
    features=m7.data,
    datasource_id='instruments_CN_STOCK_A',
    start_date='',
    end_date='',
    m_cached=False
)

m10 = M.join.v3(
    data1=m9.data,
    data2=m5.data,
    on='date',
    how='left',
    sort=True,
    m_cached=False
)

m8 = M.input_features.v1(
    features="""amout_zf=amount_0/amount_1
zhangf=(close_0-open_0)/close_1
zhangf_max=max((close_0-open_0)/open_0,(close_0-close_1)/close_1)

priceHighb10=close_0/ts_max(close_0,10)
priceLow10=close_0/ts_min(close_0,10)

priceHighb30=close_0/ts_max(close_0,30)
priceLow30=close_0/ts_min(close_0,30)

hpb10=ts_max(close_0,10)/ts_min(close_0,10)

zt=where(price_limit_status_0==3,1,0)
zt_num=group_sum(date,zt)
zt_shouyi=where(shift(zt,1),1,0)
mean_ztshouyi=group_sum(date,zt_shouyi)/shift(zt_num,1)

# my1=where((zs_return_0>1)&(zs_return_1<1)&(zs_open<1.0025)&(shift(priceLow10,1)==1)&(return_1>0.96)&(abs(open_0/close_1-1.03)<0.01)&(zhangf>0)&(amount_zf<2)&(priceLow30<1.08,1,0)
# my2=where((shift(zt_num,2)<=90)&(shift(mean_ztshouyi,1)>1)&(zs_return_0<1.005)&(shift(hpb10,3)<1.1)&(ts_max(return_3,120)>1.2)&(shift(zt,2)==1)&(ts_max(high_0,2)/close_0>1.05)&(rpiceLow10<1.2)&(abs(close_0/close_2-1)<0.02)&(zhangf>0),1,0)

# my=max(my1,my2)
# buy_condition=where(my>0,1,0)
# sell_condition=where(my>1,1,0)"""
)

m12 = M.general_feature_extractor.v7(
    instruments=m11.data,
    features=m8.data,
    start_date='',
    end_date='',
    before_start_days=20,
    m_cached=False
)

m14 = M.derived_feature_extractor.v3(
    input_data=m12.data,
    features=m8.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False,
    user_functions={},
    m_cached=False
)

m13 = M.chinaa_stock_filter.v1(
    input_data=m14.data,
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板', '创业板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False,
    m_cached=False
)

m6 = M.join.v3(
    data1=m13.data,
    data2=m10.data,
    on='date,instrument',
    how='left',
    sort=False,
    m_cached=False
)

m17 = M.sort.v5(
    input_ds=m6.data,
    sort_by='lr',
    group_by='date',
    keep_columns='--',
    ascending=False,
    m_cached=False
)

m1 = M.trade.v4(
    instruments=m11.data,
    options_data=m17.sorted_data,
    start_date='',
    end_date='',
    initialize=m1_initialize_bigquant_run,
    handle_data=m1_handle_data_bigquant_run,
    prepare=m1_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=1000000,
    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'
)

[2022-07-15 11:15:19.233345] INFO: moduleinvoker: instruments.v2 开始运行..

[2022-07-15 11:15:19.389710] INFO: moduleinvoker: instruments.v2 运行完成[0.156343s].

[2022-07-15 11:15:19.398275] INFO: moduleinvoker: input_features.v1 开始运行..

[2022-07-15 11:15:19.446755] INFO: moduleinvoker: input_features.v1 运行完成[0.048463s].

[2022-07-15 11:15:19.485157] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2022-07-15 11:15:22.137085] INFO: 基础特征抽取: 年份 2022, 特征行数=201169

[2022-07-15 11:15:22.826514] INFO: 基础特征抽取: 总行数: 201169

[2022-07-15 11:15:22.833089] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[3.347954s].

[2022-07-15 11:15:22.869666] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2022-07-15 11:15:23.430748] INFO: derived_feature_extractor: 提取完成 amout_zf=amount_0/amount_1, 0.007s

[2022-07-15 11:15:23.438215] INFO: derived_feature_extractor: 提取完成 zhangf=(close_0-open_0)/close_1, 0.005s

[2022-07-15 11:15:23.452388] INFO: derived_feature_extractor: 提取完成 zhangf_max=max((close_0-open_0)/open_0,(close_0-close_1)/close_1), 0.012s

[2022-07-15 11:15:25.450780] INFO: derived_feature_extractor: 提取完成 priceHighb10=close_0/ts_max(close_0,10), 1.996s

[2022-07-15 11:15:25.947926] INFO: derived_feature_extractor: 提取完成 priceLow10=close_0/ts_min(close_0,10), 0.495s

[2022-07-15 11:15:26.447629] INFO: derived_feature_extractor: 提取完成 priceHighb30=close_0/ts_max(close_0,30), 0.498s

[2022-07-15 11:15:26.962384] INFO: derived_feature_extractor: 提取完成 priceLow30=close_0/ts_min(close_0,30), 0.513s

[2022-07-15 11:15:27.872375] INFO: derived_feature_extractor: 提取完成 hpb10=ts_max(close_0,10)/ts_min(close_0,10), 0.908s

[2022-07-15 11:15:27.876717] INFO: derived_feature_extractor: 提取完成 zt=where(price_limit_status_0==3,1,0), 0.002s

[2022-07-15 11:15:27.938407] INFO: derived_feature_extractor: 提取完成 zt_num=group_sum(date,zt), 0.059s

[2022-07-15 11:15:27.972604] INFO: derived_feature_extractor: 提取失败 zt_shouyi=where(shift(zt,1),1,0): couldn't find matching opcode for 'where_ddii'

[2022-07-15 11:15:27.974552] INFO: derived_feature_extractor: 提取失败 mean_ztshouyi=group_sum(date,zt_shouyi)/shift(zt_num,1): Unknown zt_shouyi

[2022-07-15 11:15:36.530549] INFO: derived_feature_extractor: all data, 201169

[2022-07-15 11:15:37.193398] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[14.323713s].