版本 v1.0
### 多条件选股策略的交易规则
### 策略构建步骤
### 策略的实现
可视化策略实现如下:
# 本代码由可视化策略环境自动生成 2021年12月6日 22:14
# 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='2017-05-01',
end_date=T.live_run_param('trading_date', '2017-07-01'),
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'
)
[2021-02-21 16:44:14.022520] INFO: moduleinvoker: instruments.v2 开始运行..
[2021-02-21 16:44:15.804196] INFO: moduleinvoker: instruments.v2 运行完成[1.781668s].
[2021-02-21 16:44:15.808886] INFO: moduleinvoker: input_features.v1 开始运行..
[2021-02-21 16:44:15.814202] INFO: moduleinvoker: 命中缓存
[2021-02-21 16:44:15.815489] INFO: moduleinvoker: input_features.v1 运行完成[0.006609s].
[2021-02-21 16:44:15.828118] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2021-02-21 16:44:16.798238] INFO: 基础特征抽取: 年份 2017, 特征行数=242716
[2021-02-21 16:44:16.912481] INFO: 基础特征抽取: 总行数: 242716
[2021-02-21 16:44:16.930858] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[1.102743s].
[2021-02-21 16:44:16.935209] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2021-02-21 16:44:18.850739] 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), 0.862s
[2021-02-21 16:44:19.722461] INFO: derived_feature_extractor: 提取完成 sell_condition=where(mean(close_0,5)[2021-02-21 16:44:20.926059] INFO: derived_feature_extractor: /y_2017, 242716[2021-02-21 16:44:21.172004] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[4.236754s].[2021-02-21 16:44:21.180137] INFO: moduleinvoker: sort.v4 开始运行..[2021-02-21 16:44:22.033802] INFO: moduleinvoker: sort.v4 运行完成[0.853685s].[2021-02-21 16:44:24.213530] INFO: moduleinvoker: backtest.v8 开始运行..[2021-02-21 16:44:24.218594] INFO: backtest: biglearning backtest:V8.5.0[2021-02-21 16:44:24.649195] INFO: backtest: product_type:stock by specified[2021-02-21 16:44:24.793696] INFO: moduleinvoker: cached.v2 开始运行..[2021-02-21 16:44:35.737832] INFO: backtest: 读取股票行情完成:944077[2021-02-21 16:44:38.611393] INFO: moduleinvoker: cached.v2 运行完成[13.817699s].[2021-02-21 16:44:39.958871] INFO: algo: TradingAlgorithm V1.8.0[2021-02-21 16:44:40.233126] INFO: algo: trading transform...[2021-02-21 16:44:42.344997] INFO: Performance: Simulated 42 trading days out of 42.[2021-02-21 16:44:42.346531] INFO: Performance: first open: 2017-05-02 09:30:00+00:00[2021-02-21 16:44:42.347637] INFO: Performance: last close: 2017-06-30 15:00:00+00:00[2021-02-21 16:44:45.600644] INFO: moduleinvoker: backtest.v8 运行完成[21.387105s].[2021-02-21 16:44:45.603259] INFO: moduleinvoker: trade.v4 运行完成[23.564731s].