版本 v1.0
### 价值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 22:15
# 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 m9_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 m9_handle_data_bigquant_run(context, data):
#周期控制
if context.trading_day_index % 30 != 0:#以30天(交易日)换一次仓为例
return
# 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.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
try:
buy_stock = context.daily_stock_buy[today] # 当日符合买入条件的股票
except:
buy_stock=[] # 如果没有符合条件的股票,就设置为空
try:
sell_stock = context.daily_stock_sell[today] # 当日符合卖出条件的股票
except:
sell_stock=[] # 如果没有符合条件的股票,就设置为空
# 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:
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
# 因为是早盘买尾盘卖,所以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用来买股票
# cash_for_buy += stock_hold_now[instrument]
# 如果有买入信号/有持仓
if len(stock_to_buy)+len(stock_to_adjust)>0:
weight = 1/(len(stock_to_buy)+len(stock_to_adjust)) # 每只股票的比重为等资金比例持有
for instrument in stock_to_buy+stock_to_adjust:
sid = context.symbol(instrument) # 将标的转化为equity格式
if data.can_trade(sid):
context.order_target_value(sid, weight*cash_for_buy) # 买入
# 回测引擎:准备数据,只执行一次
def m9_prepare_bigquant_run(context):
# 加载预测数据
history_data = context.options['data'].read_df()
#获取每日买入股票列表
context.daily_stock_buy = history_data.groupby('date').apply(lambda x:x.instrument[:30])
m1 = 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((pb_lf_0<1.5) & (pe_ttm_0<15) & (amount_0>0) & (pb_lf_0>0) & (pe_ttm_0>0), 1, 0)"""
)
m2 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2017-05-01'),
end_date=T.live_run_param('trading_date', '2017-10-11'),
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m7 = M.general_feature_extractor.v7(
instruments=m2.data,
features=m1.data,
start_date='',
end_date='',
before_start_days=60
)
m8 = M.derived_feature_extractor.v3(
input_data=m7.data,
features=m1.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m4 = M.filter.v3(
input_data=m8.data,
expr='buy_condition>0',
output_left_data=False
)
m5 = M.dropnan.v2(
input_data=m4.data
)
m3 = M.sort.v4(
input_ds=m5.data,
sort_by='pe_ttm_0,pb_lf_0',
group_by='date',
keep_columns='--',
ascending=True
)
m9 = M.trade.v4(
instruments=m2.data,
options_data=m3.sorted_data,
start_date='',
end_date='',
initialize=m9_initialize_bigquant_run,
handle_data=m9_handle_data_bigquant_run,
prepare=m9_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='后复权',
product_type='股票',
plot_charts=True,
backtest_only=False,
benchmark='000300.HIX'
)
[2021-02-21 16:45:44.093244] INFO: moduleinvoker: input_features.v1 开始运行..
[2021-02-21 16:45:44.138607] INFO: moduleinvoker: input_features.v1 运行完成[0.045384s].
[2021-02-21 16:45:44.142683] INFO: moduleinvoker: instruments.v2 开始运行..
[2021-02-21 16:45:44.230656] INFO: moduleinvoker: instruments.v2 运行完成[0.087957s].
[2021-02-21 16:45:44.246850] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2021-02-21 16:45:45.949395] INFO: 基础特征抽取: 年份 2017, 特征行数=452934
[2021-02-21 16:45:46.194268] INFO: 基础特征抽取: 总行数: 452934
[2021-02-21 16:45:46.241172] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[1.994325s].
[2021-02-21 16:45:46.245583] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2021-02-21 16:45:48.222918] INFO: derived_feature_extractor: 提取完成 buy_condition=where((pb_lf_0<1.5) & (pe_ttm_0<15) & (amount_0>0) & (pb_lf_0>0) & (pe_ttm_0>0), 1, 0), 0.005s
[2021-02-21 16:45:50.236307] INFO: derived_feature_extractor: /y_2017, 452934
[2021-02-21 16:45:50.710608] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[4.465003s].
[2021-02-21 16:45:50.717693] INFO: moduleinvoker: filter.v3 开始运行..
[2021-02-21 16:45:50.722614] INFO: filter: 使用表达式 buy_condition>0 过滤
[2021-02-21 16:45:51.003449] INFO: filter: 过滤 /y_2017, 7622/0/452934
[2021-02-21 16:45:51.048091] INFO: moduleinvoker: filter.v3 运行完成[0.33039s].
[2021-02-21 16:45:51.053416] INFO: moduleinvoker: dropnan.v2 开始运行..
[2021-02-21 16:45:51.132730] INFO: dropnan: /y_2017, 7622/7622
[2021-02-21 16:45:51.180906] INFO: dropnan: 行数: 7622/7622
[2021-02-21 16:45:51.187633] INFO: moduleinvoker: dropnan.v2 运行完成[0.134241s].
[2021-02-21 16:45:51.195123] INFO: moduleinvoker: sort.v4 开始运行..
[2021-02-21 16:45:51.740633] INFO: moduleinvoker: sort.v4 运行完成[0.545488s].
[2021-02-21 16:45:54.010832] INFO: moduleinvoker: backtest.v8 开始运行..
[2021-02-21 16:45:54.015831] INFO: backtest: biglearning backtest:V8.5.0
[2021-02-21 16:45:54.123155] INFO: backtest: product_type:stock by specified
[2021-02-21 16:45:54.245608] INFO: moduleinvoker: cached.v2 开始运行..
[2021-02-21 16:46:05.446115] INFO: backtest: 读取股票行情完成:1191194
[2021-02-21 16:46:08.702640] INFO: moduleinvoker: cached.v2 运行完成[14.457025s].
[2021-02-21 16:46:10.399368] INFO: algo: TradingAlgorithm V1.8.0
[2021-02-21 16:46:10.747614] INFO: algo: trading transform...
[2021-02-21 16:46:12.322472] INFO: Performance: Simulated 110 trading days out of 110.
[2021-02-21 16:46:12.323956] INFO: Performance: first open: 2017-05-02 09:30:00+00:00
[2021-02-21 16:46:12.324981] INFO: Performance: last close: 2017-10-11 15:00:00+00:00
[2021-02-21 16:46:16.342099] INFO: moduleinvoker: backtest.v8 运行完成[22.331264s].
[2021-02-21 16:46:16.343732] INFO: moduleinvoker: trade.v4 运行完成[24.596452s].