复制链接
克隆策略
多条件选股策略¶
版本 v1.0
目录¶
### 多条件选股策略的交易规则
### 策略构建步骤
### 策略的实现
正文¶
一、多条件选股策略的交易规则¶
- 买入条件：满足 1）今日开盘价大于昨日收盘价；2）5日收盘价均线大于10日收盘价均线，按PE升序排名取前十名,次日以开盘价买入；
- 买入后，如果5日收盘价均线小于10日收盘价均线，则次日以开盘价卖出。
二、策略构建步骤¶
1、确定股票池和回测时间¶
- 通过证券代码列表输入要回测的单只/多只股票，以及回测的起止日期
2、确定买卖条件信号¶
- 在输入特征列表中通过表达式引擎定义 buy_condition=where((open_0>close_1)&(mean(close_0,5)>mean(close_0,10)),1,0)，实现买入信号。
- 在输入特征列表中通过表达式引擎定义 sell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)，实现卖出信号。
- 通过基础特征和衍生特征抽取模块实现买卖条件指标 buy_condition 和 sell_condition 数据的抽取。
- 通过缺失数据处理模块删去有缺失值的数据。
3、确定买卖原则¶
- 已有持仓中满足卖出条件的股票为卖出股票列表，需执行卖出操作并更新可用现金。
- 满足买入条件且没有持仓的股票为买入股票列表，需根据可用现金执行等资金买入操作,此例采用整百股数下单。
4、模拟回测¶
- 通过 trade 模块中的初始化函数定义交易手续费和滑点；
- 通过 trade 模块中的准备函数定义 context.daily_stock_buy 和 context.daily_stock_sell 变量来获取并存放每日符合买卖条件的股票列表；
- 通过 trade 模块中的主函数(handle函数)查看每日的买卖交易信号，按照买卖原则执行相应的买入/卖出操作。
三、策略的实现¶
可视化策略实现如下：
{"description":"实验创建于2018/6/27","graph":{"edges":[{"to_node_id":"-353:instruments","from_node_id":"-51:data"},{"to_node_id":"-370:instruments","from_node_id":"-51:data"},{"to_node_id":"-353:features","from_node_id":"-59:data"},{"to_node_id":"-360:features","from_node_id":"-59:data"},{"to_node_id":"-360:input_data","from_node_id":"-353:data"},{"to_node_id":"-390:input_ds","from_node_id":"-360:data"},{"to_node_id":"-370:options_data","from_node_id":"-390:sorted_data"}],"nodes":[{"node_id":"-51","module_id":"BigQuantSpace.instruments.instruments-v2","parameters":[{"name":"start_date","value":"2021-01-01","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"2022-01-31","type":"Literal","bound_global_parameter":"交易日期"},{"name":"market","value":"CN_STOCK_A","type":"Literal","bound_global_parameter":null},{"name":"instrument_list","value":"","type":"Literal","bound_global_parameter":null},{"name":"max_count","value":0,"type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"rolling_conf","node_id":"-51"}],"output_ports":[{"name":"data","node_id":"-51"}],"cacheable":true,"seq_num":1,"comment":"","comment_collapsed":true},{"node_id":"-59","module_id":"BigQuantSpace.input_features.input_features-v1","parameters":[{"name":"features","value":"\n# #号开始的表示注释\n# 多个特征，每行一个，可以包含基础特征和衍生特征\nbuy_condition=where((open_0>close_1)&(mean(close_0,5)>mean(close_0,10)),1,0)\nsell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)\npe_ttm_0\n","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"features_ds","node_id":"-59"}],"output_ports":[{"name":"data","node_id":"-59"}],"cacheable":true,"seq_num":2,"comment":"","comment_collapsed":true},{"node_id":"-353","module_id":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"before_start_days","value":"60","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-353"},{"name":"features","node_id":"-353"}],"output_ports":[{"name":"data","node_id":"-353"}],"cacheable":false,"seq_num":5,"comment":"","comment_collapsed":true},{"node_id":"-360","module_id":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","parameters":[{"name":"date_col","value":"date","type":"Literal","bound_global_parameter":null},{"name":"instrument_col","value":"instrument","type":"Literal","bound_global_parameter":null},{"name":"drop_na","value":"False","type":"Literal","bound_global_parameter":null},{"name":"remove_extra_columns","value":"False","type":"Literal","bound_global_parameter":null},{"name":"user_functions","value":"{}","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_data","node_id":"-360"},{"name":"features","node_id":"-360"}],"output_ports":[{"name":"data","node_id":"-360"}],"cacheable":true,"seq_num":7,"comment":"","comment_collapsed":true},{"node_id":"-370","module_id":"BigQuantSpace.trade.trade-v4","parameters":[{"name":"start_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"end_date","value":"","type":"Literal","bound_global_parameter":null},{"name":"initialize","value":"# 回测引擎：初始化函数，只执行一次\ndef bigquant_run(context):\n\n # 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\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n\n","type":"Literal","bound_global_parameter":null},{"name":"handle_data","value":"# 回测引擎：每日数据处理函数，每天执行一次\ndef bigquant_run(context, data):\n # 回测引擎：每日数据处理函数，每天执行一次\n today = data.current_dt.strftime('%Y-%m-%d') # 日期\n # 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和对应的最新市值\n stock_hold_now = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.perf_tracker.position_tracker.positions.items()}\n\n # 记录用于买入股票的可用现金\n cash_for_buy = context.portfolio.cash\n \n # 获取当日符合买入/卖出条件的股票列表\n try:\n buy_stock = context.daily_buy_stock[today] # 当日符合买入条件的股票\n except:\n buy_stock=[]\n try:\n sell_stock = context.daily_sell_stock[today] # 当日符合卖出条件的股票\n except:\n sell_stock = []\n\n # 需要卖出的股票:已有持仓中符合卖出条件的股票\n stock_to_sell = [i for i in stock_hold_now if i in sell_stock]\n # 需要买入的股票:没有持仓且符合买入条件的股票\n stock_to_buy = [i for i in buy_stock if i not in stock_hold_now]\n # 卖出\n for instrument in stock_to_sell:\n # 如果该股票停牌，则没法成交。因此需要用can_trade方法检查下该股票的状态\n # 如果返回真值，则可以正常下单，否则会出错\n # 因为stock是字符串格式，我们用symbol方法将其转化成平台可以接受的形式：Equity格式\n if data.can_trade(context.symbol(instrument)):\n # order_target_percent是平台的一个下单接口，表明下单使得该股票的权重为0，即卖出全部股票，可参考回测文档\n context.order_target_percent(context.symbol(instrument), 0)\n # 开盘卖出后所得资金可用来买入股票，更新当日可用现金\n cash_for_buy += stock_hold_now[instrument]\n \n # 如果当天没有买入的股票，就返回\n if len(stock_to_buy) == 0:\n return\n \n # 买入\n for instrument in stock_to_buy:\n # 利用当日可用现金使用等资金比例下单买入\n cash = cash_for_buy / len(stock_to_buy)\n if data.can_trade(context.symbol(instrument)):\n current_price = data.current(context.symbol(instrument), 'price')\n amount = math.floor(cash / current_price / 100) * 100\n context.order(context.symbol(instrument), amount)","type":"Literal","bound_global_parameter":null},{"name":"prepare","value":"# 回测引擎：准备数据，只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n df = context.options['data'].read_df()\n # 函数：求满足开仓条件的股票列表\n def open_pos_con(df):\n return list(df[df['buy_condition']>0].instrument)[:10]\n\n # 函数：求满足平仓条件的股票列表\n def close_pos_con(df):\n return list(df[df['sell_condition']>0].instrument)\n \n # 每日买入股票的数据框\n context.daily_buy_stock= df.groupby('date').apply(open_pos_con)\n # 每日卖出股票的数据框\n context.daily_sell_stock= df.groupby('date').apply(close_pos_con) \n \n \n","type":"Literal","bound_global_parameter":null},{"name":"before_trading_start","value":"# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。\ndef bigquant_run(context, data):\n pass\n","type":"Literal","bound_global_parameter":null},{"name":"volume_limit","value":0.025,"type":"Literal","bound_global_parameter":null},{"name":"order_price_field_buy","value":"open","type":"Literal","bound_global_parameter":null},{"name":"order_price_field_sell","value":"open","type":"Literal","bound_global_parameter":null},{"name":"capital_base","value":1000000,"type":"Literal","bound_global_parameter":null},{"name":"auto_cancel_non_tradable_orders","value":"True","type":"Literal","bound_global_parameter":null},{"name":"data_frequency","value":"daily","type":"Literal","bound_global_parameter":null},{"name":"price_type","value":"后复权","type":"Literal","bound_global_parameter":null},{"name":"product_type","value":"股票","type":"Literal","bound_global_parameter":null},{"name":"plot_charts","value":"True","type":"Literal","bound_global_parameter":null},{"name":"backtest_only","value":"False","type":"Literal","bound_global_parameter":null},{"name":"benchmark","value":"000300.HIX","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"instruments","node_id":"-370"},{"name":"options_data","node_id":"-370"},{"name":"history_ds","node_id":"-370"},{"name":"benchmark_ds","node_id":"-370"},{"name":"trading_calendar","node_id":"-370"}],"output_ports":[{"name":"raw_perf","node_id":"-370"}],"cacheable":false,"seq_num":8,"comment":"","comment_collapsed":true},{"node_id":"-390","module_id":"BigQuantSpace.sort.sort-v4","parameters":[{"name":"sort_by","value":"pe_ttm_0","type":"Literal","bound_global_parameter":null},{"name":"group_by","value":"date","type":"Literal","bound_global_parameter":null},{"name":"keep_columns","value":"--","type":"Literal","bound_global_parameter":null},{"name":"ascending","value":"True","type":"Literal","bound_global_parameter":null}],"input_ports":[{"name":"input_ds","node_id":"-390"},{"name":"sort_by_ds","node_id":"-390"}],"output_ports":[{"name":"sorted_data","node_id":"-390"}],"cacheable":true,"seq_num":9,"comment":"","comment_collapsed":true}],"node_layout":"<node_postions><node_position Node='-51' Position='153.28524780273438,112.1507339477539,200,200'/><node_position Node='-59' Position='448,124,200,200'/><node_position Node='-353' Position='257,236,200,200'/><node_position Node='-360' Position='239,338,200,200'/><node_position Node='-370' Position='195,549,200,200'/><node_position Node='-390' Position='291,437,200,200'/></node_postions>"},"nodes_readonly":false,"studio_version":"v2"}
In [1]:
# 本代码由可视化策略环境自动生成 2023年1月11日 18:41
# 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 m8_initialize_bigquant_run(context):
# 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))
# 回测引擎：每日数据处理函数，每天执行一次
def m8_handle_data_bigquant_run(context, data):
# 回测引擎：每日数据处理函数，每天执行一次
today = data.current_dt.strftime('%Y-%m-%d') # 日期
# 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和对应的最新市值
stock_hold_now = {e.symbol: p.amount * p.last_sale_price
for e, p in context.perf_tracker.position_tracker.positions.items()}
# 记录用于买入股票的可用现金
cash_for_buy = context.portfolio.cash
# 获取当日符合买入/卖出条件的股票列表
try:
buy_stock = context.daily_buy_stock[today] # 当日符合买入条件的股票
except:
buy_stock=[]
try:
sell_stock = context.daily_sell_stock[today] # 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]
# 卖出
for instrument in stock_to_sell:
# 如果该股票停牌，则没法成交。因此需要用can_trade方法检查下该股票的状态
# 如果返回真值，则可以正常下单，否则会出错
# 因为stock是字符串格式，我们用symbol方法将其转化成平台可以接受的形式：Equity格式
if data.can_trade(context.symbol(instrument)):
# order_target_percent是平台的一个下单接口，表明下单使得该股票的权重为0，即卖出全部股票，可参考回测文档
context.order_target_percent(context.symbol(instrument), 0)
# 开盘卖出后所得资金可用来买入股票，更新当日可用现金
cash_for_buy += stock_hold_now[instrument]
# 如果当天没有买入的股票，就返回
if len(stock_to_buy) == 0:
return
# 买入
for instrument in stock_to_buy:
# 利用当日可用现金使用等资金比例下单买入
cash = cash_for_buy / len(stock_to_buy)
if data.can_trade(context.symbol(instrument)):
current_price = data.current(context.symbol(instrument), 'price')
amount = math.floor(cash / current_price / 100) * 100
context.order(context.symbol(instrument), amount)
# 回测引擎：准备数据，只执行一次
def m8_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)[:10]
# 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_buy_stock= df.groupby('date').apply(open_pos_con)
# 每日卖出股票的数据框
context.daily_sell_stock= df.groupby('date').apply(close_pos_con)
# 回测引擎：每个单位时间开始前调用一次，即每日开盘前调用一次。
def m8_before_trading_start_bigquant_run(context, data):
pass
m1 = M.instruments.v2(
start_date='2021-01-01',
end_date=T.live_run_param('trading_date', '2022-01-31'),
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m2 = 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
buy_condition=where((open_0>close_1)&(mean(close_0,5)>mean(close_0,10)),1,0)
sell_condition=where(mean(close_0,5)<mean(close_0,10),1,0)
pe_ttm_0
"""
)
m5 = M.general_feature_extractor.v7(
instruments=m1.data,
features=m2.data,
start_date='',
end_date='',
before_start_days=60,
m_cached=False
)
m7 = M.derived_feature_extractor.v3(
input_data=m5.data,
features=m2.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False,
user_functions={}
)
m9 = M.sort.v4(
input_ds=m7.data,
sort_by='pe_ttm_0',
group_by='date',
keep_columns='--',
ascending=True
)
m8 = M.trade.v4(
instruments=m1.data,
options_data=m9.sorted_data,
start_date='',
end_date='',
initialize=m8_initialize_bigquant_run,
handle_data=m8_handle_data_bigquant_run,
prepare=m8_prepare_bigquant_run,
before_trading_start=m8_before_trading_start_bigquant_run,
volume_limit=0.025,
order_price_field_buy='open',
order_price_field_sell='open',
capital_base=1000000,
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='000300.HIX'
)
日志 35 条，错误日志
0 条
[2023-01-11 18:38:27.980089] INFO: moduleinvoker: instruments.v2 开始运行..
[2023-01-11 18:38:28.003360] INFO: moduleinvoker: 命中缓存
[2023-01-11 18:38:28.006068] INFO: moduleinvoker: instruments.v2 运行完成[0.026133s].
[2023-01-11 18:38:28.013840] INFO: moduleinvoker: input_features.v1 开始运行..
[2023-01-11 18:38:28.023750] INFO: moduleinvoker: 命中缓存
[2023-01-11 18:38:28.027659] INFO: moduleinvoker: input_features.v1 运行完成[0.013836s].
[2023-01-11 18:38:28.059635] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2023-01-11 18:38:29.020801] INFO: 基础特征抽取: 年份 2020, 特征行数=179288
[2023-01-11 18:38:34.343095] INFO: 基础特征抽取: 年份 2021, 特征行数=1061527
[2023-01-11 18:38:35.341145] INFO: 基础特征抽取: 年份 2022, 特征行数=89016
[2023-01-11 18:38:35.455471] INFO: 基础特征抽取: 总行数: 1329831
[2023-01-11 18:38:35.459734] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[7.400106s].
[2023-01-11 18:38:35.484159] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2023-01-11 18:38:45.547781] INFO: derived_feature_extractor: 提取完成 buy_condition=where((open_0>close_1)&(mean(close_0,5)>mean(close_0,10)),1,0), 5.089s
[2023-01-11 18:38:48.040268] INFO: derived_feature_extractor: 提取完成 sell_condition=where(mean(close_0,5)[2023-01-11 18:38:48.606239] INFO: derived_feature_extractor: /y_2020, 179288[2023-01-11 18:38:50.473828] INFO: derived_feature_extractor: /y_2021, 1061527[2023-01-11 18:38:51.082403] INFO: derived_feature_extractor: /y_2022, 89016[2023-01-11 18:38:51.294967] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[15.810803s].[2023-01-11 18:38:51.309239] INFO: moduleinvoker: sort.v4 开始运行..[2023-01-11 18:38:56.594700] INFO: moduleinvoker: sort.v4 运行完成[5.28544s].[2023-01-11 18:39:01.551188] INFO: moduleinvoker: backtest.v8 开始运行..[2023-01-11 18:39:01.563098] INFO: backtest: biglearning backtest:V8.6.3[2023-01-11 18:39:05.937638] INFO: backtest: product_type:stock by specified[2023-01-11 18:39:06.105300] INFO: moduleinvoker: cached.v2 开始运行..[2023-01-11 18:39:06.122544] INFO: moduleinvoker: 命中缓存[2023-01-11 18:39:06.125353] INFO: moduleinvoker: cached.v2 运行完成[0.020069s].[2023-01-11 18:39:19.699057] INFO: backtest: algo history_data=DataSource(0f4ed08058ce43d4825b42312cfc0e80T)[2023-01-11 18:39:19.702022] INFO: algo: TradingAlgorithm V1.8.9[2023-01-11 18:39:21.231925] INFO: algo: trading transform...[2023-01-11 18:39:28.884595] INFO: Performance: Simulated 262 trading days out of 262.[2023-01-11 18:39:28.889366] INFO: Performance: first open: 2021-01-04 09:30:00+00:00[2023-01-11 18:39:28.891628] INFO: Performance: last close: 2022-01-28 15:00:00+00:00[2023-01-11 18:39:34.921317] INFO: moduleinvoker: backtest.v8 运行完成[33.370134s].[2023-01-11 18:39:34.924139] INFO: moduleinvoker: trade.v4 运行完成[38.310932s].
In [2]:
m8.read_raw_perf().to_csv("多条件选股.csv")