In [1]:

# 本代码由可视化策略环境自动生成 2025年1月26日 11:56
# 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。
 
# 显式导入 BigQuant 相关 SDK 模块
from bigdatasource.api import DataSource
from bigdata.api.datareader import D
from biglearning.api import M
from biglearning.api import tools as T
from biglearning.module2.common.data import Outputs
 
import pandas as pd
import numpy as np
import math
import warnings
import datetime
 
from zipline.finance.commission import PerOrder
from zipline.api import get_open_orders
from zipline.api import symbol
 
from bigtrader.sdk import *
from bigtrader.utils.my_collections import NumPyDeque
from bigtrader.constant import OrderType
from bigtrader.constant import Direction

# <aistudiograph>

# @param(id="m20", name="initialize")
# 回测引擎：初始化函数，只执行一次
def m20_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 = 2
    # 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)])
    
    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)
    # 设置每只股票占用的最大资金比例
    context.max_cash_per_instrument = 0.02
    context.options['hold_days'] = 100
    context.options['hold_days1'] = 10
    context.options['hold_days2'] = 50

 
# @param(id="m20", name="handle_data")
# 回测引擎：每日数据处理函数，每天执行一次
def m20_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）
    is_staging1 = context.trading_day_index < context.options['hold_days2']
    cash_avg = context.portfolio.portfolio_value / context.options['hold_days1']
    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')  
            
            # 赚9%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)):
                context.order_target_percent(context.symbol(instrument),0)
                cash_for_sell -= positions[instrument]
                current_stopwin_stock.append(instrument)

        if len(current_stopwin_stock)>0:
           
            stock_sold += current_stopwin_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(100) 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:        
            
            stock_sold += current_stopdays_stock
    #-------------------------  END:持有固定天数卖出-----------------------

    
    # 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_staging1 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
        import random

    def select_stocks(ranker_prediction):
    
    # 选择前50名股票
        top_50_stocks = ranker_prediction.sort_values('position', ascending=False).head(20)
    # 随机选择2只股票
        selected_stocks = top_50_stocks.sample(n=2)
        return selected_stocks
        selected_stocks = select_stocks(ranker_prediction)

    # 计算所有禁止买入的股票池
    banned_list = stock_sold
    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:
            context.order_value(context.symbol(instrument), cash)
    


# @param(id="m20", name="prepare")
# 回测引擎：准备数据，只执行一次
def m20_prepare_bigquant_run(context):
    pass

# @param(id="m20", name="before_trading_start")
def m20_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，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

# @module(position="678,782", comment='预测数据，用于回测和模拟', comment_collapsed=False)
m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2024-10-07'),
    end_date=T.live_run_param('trading_date', '2025-12-19'),
    market='CN_STOCK_A',
    instrument_list='',
    max_count=0
)

# @module(position="797,-212", comment='', comment_collapsed=True)
m25 = M.input_features.v1(
    features="""shift(beta_csi500_90_0/group_sum(industry_sw_level2_0, beta_csi500_90_0-0.5),-5)
shift(correlation(log(volume_0),abs(return_0-1),5),-5)
shift(mean(mf_net_amount_xl_0,15),-5)
shift(sum(mf_net_amount_xl_0,12)/market_cap_float_0,-5)
shift(ta_willr_14_0,-5)"""
)

# @module(position="822,-49", comment='', comment_collapsed=True)
m3 = M.input_features.v1(
    features_ds=m25.data,
    features="""shift(beta_csi500_90_0/group_sum(industry_sw_level2_0, beta_csi500_90_0-0.5),-5)
shift(correlation(log(volume_0),abs(return_0-1),5),-5)
shift(mean(mf_net_amount_xl_0,15),-5)
shift(sum(mf_net_amount_xl_0,12)/market_cap_float_0,-5)
shift(ta_willr_14_0,-5)
shift(rank(((close_0-open_0)/open_0),6),-5)

"""
)

# @module(position="908,174", comment='这里放置要过滤的条件', comment_collapsed=True)
m4 = M.input_features.v1(
    features_ds=m3.data,
    features="""
    
     fangb=ta_ema(((2*close_0+high_0+low_0)/4-ts_min(low_0, 34))/(ts_max(high_0, 34)-ts_min(low_0, 34))*100, 8)
b1=ta_ema(fangb, 5)
    c1=fangb-b1  
    d1= ta_ema((sum(close_0-where(high_0<= close_1, high_0, close_1),7)/(sum(where(high_0<= close_1, high_0, close_1)-where(low_0<=close_1, low_0, close_1), 7))*14*28+sum(close_0-where(high_0<= close_1, high_0, close_1),14)/(sum(where(high_0<= close_1, high_0, close_1)-where(low_0<=close_1, low_0, close_1), 14))*7*28+sum(close_0-where(high_0<= close_1, high_0, close_1),28)/(sum(where(high_0<= close_1, high_0, close_1)-where(low_0<=close_1, low_0, close_1), 28))*7*14)*100/(7*14+7*28+14*28), 6)

#{STICKLINE(防线B-B1>0,防线B,B1,8,1),COLOR00FF00;}
#妙趣横生:-一进一出,COLORRED;
#{STICKLINE(防线B-B1<0,防线B,B1,8,1),COLORRED;}
#卖出:(REF(一进一出,1)>0 AND 一进一出<=0) OR (一进一出<1 AND 一进一出>=0 AND C<O),COLORRED;

#DRAWICON(卖出,36,1);
#STICKLINE(卖出,0,28,1,0),COLORRED;
#DRAWTEXT(卖出,30,'卖'),COLORMAGENTA;
#买入:卖出=0 AND REF(一进一出,1)<0 AND 一进一出>0,COLORRED; 
# mairu= c1=0    shift(c1,1)<0  c1>0  

#{STICKLINE(防线B-B1>0,防线B,B1,8,1),COLOR00FF00;}
#妙趣横生:-一进一出,COLORRED;
#{STICKLINE(防线B-B1<0,防线B,B1,8,1),COLORRED;}
#卖出:(REF(一进一出,1)>0 AND 一进一出<=0) OR (一进一出<1 AND 一进一出>=0 AND C<O),COLORRED;
maichu1= where((shift(c1, 1)>0) & (((c1 >0))|(c1==0)),1,0)
maichu2=where((c1<1)&(((c1 >0))|(c1==0))&(close_1-close_0<0), 1, 0)
_total_count=sum(maichu1+maichu1, 1)

#DRAWICON(卖出,36,1);
#STICKLINE(卖出,0,28,1,0),COLORRED;
#DRAWTEXT(卖出,30,'卖'),COLORMAGENTA;
#买入:卖出=0 AND REF(一进一出,1)<0 AND 一进一出>0,COLORRED; 
# mairu= c1=0    shift(c1,1)<0  c1>0  
con = where((c1.shift(1) < 0) ,1,0)
con3=where(((c1 >0))|(c1==0), 1, 0)               
total_count=con+con3
con2= where((_total_count<1), 1,0)
total_count2= sum(con2,1)



# 个股最近1日收益率 return_1 close_0/shift(close_0,1)
# 大单净流入占比最近5日平均 mean(mf_net_pct_l_0,5)   收盘价的5日简单移动平均值 ta_sma_5_0 &(low_0<mean(close_0, 20)
#收盘价的5日指数移动平均值 因子分析: ta_ema_5_0 过去5个交易日的平均换手率 avg_turn_5 close_0>mean(close_0, 15))&(close_0>mean(close_0, 10))&(close_0>mean(close_0, 5))&
# 小单净流入占比最近5日平均 mean(mf_net_pct_s_0,5) 主力净流入占比最近5日平均值 mean(mf_net_pct_main_0,5) buy_cond_1==1&buy_cond_2==1&buy_cond_3==1&a3>0
 #收盘突破所有短期均线，收盘表现强势
buy_cond_1 = where((close_0<mean(close_0, 15))&(close_0<mean(close_0, 10))&(close_0<mean(close_0, 5))&(close_0<mean(close_0, -5)),1,0)
#底部冲短线均线下方开始反弹
buy_cond_2 = where((low_0<mean(close_0, 5))&(low_0<mean(close_0, 10)), 1, 0)
#确保当天为阳
buy_cond_3 = where((close_0>open_0), 1, 0)
#资金流因子，近几天大单相对流通市值
a3 = sum(mf_net_amount_xl_0,10)/market_cap_float_0"""
)

# @module(position="1466,135", comment='', comment_collapsed=True)
m17 = M.general_feature_extractor.v7(
    instruments=m9.data,
    features=m4.data,
    start_date='',
    end_date='',
    before_start_days=120
)

# @module(position="1570,277", comment='', comment_collapsed=True)
m18 = M.derived_feature_extractor.v3(
    input_data=m17.data,
    features=m4.data,
    date_col='date',
    instrument_col='instrument',
    drop_na=False,
    remove_extra_columns=False
)

# @module(position="1464,377", comment='', comment_collapsed=True)
m29 = M.chinaa_stock_filter.v1(
    index_constituent_cond=['全部'],
    board_cond=['上证主板', '深证主板'],
    industry_cond=['全部'],
    st_cond=['正常'],
    delist_cond=['非退市'],
    output_left_data=False
)

# @module(position="1715,423", comment='', comment_collapsed=True)
m1 = M.filtet_st_stock_tomo.v3(
    input_1=m29.data
)

# @module(position="1249,559", comment='', comment_collapsed=True)
m14 = M.dropnan.v1(
    input_data=m1.data_1
)

# @module(position="652,646", comment='', comment_collapsed=True)
m6 = M.xgboost.v1(
    features=m3.data,
    predict_ds=m14.data,
    num_boost_round=150,
    objective='排序(map)',
    booster='gbtree',
    max_depth=6,
    key_cols='date,instrument',
    group_col='date',
    nthread=1,
    n_gpus=-1,
    other_train_parameters={}
)

# @module(position="1028,930", comment='', comment_collapsed=True)
m21 = M.sort.v4(
    input_ds=m6.predictions,
    sort_by='prediction',
    group_by='date',
    keep_columns='--',
    ascending=False
)

# @module(position="878,1221", comment='', comment_collapsed=True)
m20 = M.trade.v4(
    instruments=m9.data,
    options_data=m21.sorted_data,
    start_date='',
    end_date='',
    initialize=m20_initialize_bigquant_run,
    handle_data=m20_handle_data_bigquant_run,
    prepare=m20_prepare_bigquant_run,
    before_trading_start=m20_before_trading_start_bigquant_run,
    volume_limit=0,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=100000000,
    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.SHA'
)
# </aistudiograph>

/home/aiuser/.ipython/profile_default/startup/000-aistudio.py:234: DeprecationWarning: This module is deprecated. Please use `from bigdatasource.api import D`.
  return original_import(name, globals, locals, fromlist, level)
/home/aiuser/.ipython/profile_default/startup/000-aistudio.py:234: DeprecationWarning: Using or importing the ABCs from 'collections' instead of from 'collections.abc' is deprecated since Python 3.3, and in 3.10 it will stop working
  return original_import(name, globals, locals, fromlist, level)
/home/aiuser/.ipython/profile_default/startup/000-aistudio.py:234: MovedIn20Warning: Deprecated API features detected! These feature(s) are not compatible with SQLAlchemy 2.0. To prevent incompatible upgrades prior to updating applications, ensure requirements files are pinned to "sqlalchemy<2.0". Set environment variable SQLALCHEMY_WARN_20=1 to show all deprecation warnings.  Set environment variable SQLALCHEMY_SILENCE_UBER_WARNING=1 to silence this message. (Background on SQLAlchemy 2.0 at: https://sqlalche.me/e/b8d9)
  return original_import(name, globals, locals, fromlist, level)
[2025-01-23 15:13:03.190363] INFO: moduleinvoker:1631030319.py:114: instruments.v2 开始运行..
[2025-01-23 15:13:03.205348] INFO: moduleinvoker:1631030319.py:114: 命中缓存
[2025-01-23 15:13:03.210221] INFO: moduleinvoker:1631030319.py:114: instruments.v2 运行完成[0.019838s].
[2025-01-23 15:13:03.231302] INFO: moduleinvoker:1631030319.py:123: use_datasource.v1 开始运行..
[2025-01-23 15:13:03.241262] INFO: moduleinvoker:1631030319.py:123: 命中缓存
[2025-01-23 15:13:03.245108] INFO: moduleinvoker:1631030319.py:123: use_datasource.v1 运行完成[0.013831s].
[2025-01-23 15:13:03.268166] INFO: moduleinvoker:1631030319.py:131: general_feature_extractor.v7 开始运行..
[2025-01-23 15:13:03.276869] ERROR: moduleinvoker:1631030319.py:131: module name: general_feature_extractor, module version: v7, trackeback: TypeError: __init__() takes at least 3 positional arguments (2 given)

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[1], line 131
    123 m31 = M.use_datasource.v1(
    124     instruments=m5.data,
    125     datasource_id='bar1d_CN_STOCK_A',
    126     start_date='',
    127     end_date=''
    128 )
    130 # @module(position="18,-125", comment='', comment_collapsed=True)
--> 131 m15 = M.general_feature_extractor.v7(
    132     instruments=m5.data,
    133     start_date='',
    134     end_date='',
    135     before_start_days=120
    136 )
    138 # @module(position="7,-18", comment='', comment_collapsed=True)
    139 m16 = M.derived_feature_extractor.v3(
    140     input_data=m15.data,
    141     date_col='date',
   (...)
    144     remove_extra_columns=False
    145 )

File module2/common/modulemanagerv2.py:88, in biglearning.module2.common.modulemanagerv2.BigQuantModuleVersion.__call__()

File module2/common/moduleinvoker.py:370, in biglearning.module2.common.moduleinvoker.module_invoke()

File module2/common/moduleinvoker.py:292, in biglearning.module2.common.moduleinvoker._invoke_with_cache()

File module2/common/moduleinvoker.py:253, in biglearning.module2.common.moduleinvoker._invoke_with_cache()

File module2/common/moduleinvoker.py:210, in biglearning.module2.common.moduleinvoker._module_run()

File module2/modules/general_feature_extractor/v7/__init__.py:26, in biglearning.module2.modules.general_feature_extractor.v7.__init__.BigQuantModule.__init__()

TypeError: __init__() takes at least 3 positional arguments (2 given)