版本v1.0
在开发策略时,经常使用个股的固定点位/百分比止盈止损功能。
本策略以买入后最高价下跌10%止损为例,介绍移动止损功能的实现步骤:
1、新建AI可视化模板策略
2、在回测/模拟模块m19的属性栏中进入“主函数”代码框,在函数体最前面插入移动止损的相关代码,详见策略
初始化变量stoploss_stock用来记录移动止损卖出的股票,
针对持仓的股票计算买入以来的最高价,并计算最新价相比最高价的回撤百分比,如果下跌超过10%就止损卖出,同时将股票添加到stoploss_stock变量:
3、在回测/模拟模块m19的属性栏中进入“主函数”代码框,在函数体中找到“# 2. 生成卖出订单”位置,
在上方初始化 sell_stock 列表用来记录轮仓卖出的股票;
在下方轮仓卖出代码 context.order_target(context.symbol(instrument), 0) 前加入判断语句:
#如果已经移动止损卖出过则不再轮仓卖出,以防止出现空头持仓 if instrument in stoploss_stock:
continue
4、在回测/模拟模块m19的属性栏中进入“主函数”代码框,在函数体中找到“# 3. 生成买入订单”位置,将原有的buy_instruments一行代码改为如下:
# 获取所有排序结果股票列表
buy_list = list(ranker_prediction.instrument)
# 不再买入已经移动止损和轮仓卖出的股票,以防止出现空头持仓
buy_instruments = [i for i in buy_list if i not in sell_stock + stoploss_stock][:len(buy_cash_weights)]
# 本代码由可视化策略环境自动生成 2023年4月23日 22:31
# 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 m19_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 = 5
# 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)])
# 设置每只股票占用的最大资金比例
context.max_cash_per_instrument = 0.2
context.options['hold_days'] = 5
# 回测引擎:每日数据处理函数,每天执行一次
def m19_handle_data_bigquant_run(context, data):
today = data.current_dt.strftime('%Y-%m-%d')
#------------------------------------------止损模块START--------------------------------------------
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
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 * 0.1
#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)
stoploss_stock.append(i)
if len(stoploss_stock)>0:
print('日期:', today, '股票:', stoploss_stock, '出现跟踪止损状况')
#-------------------------------------------止损模块END---------------------------------------------
# 按日期过滤得到今日的预测数据
ranker_prediction = context.ranker_prediction[
context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
# 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)
cash_avg = context.portfolio.portfolio_value / context.options['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()}
sell_stock = []
# 2. 生成卖出订单: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_staging and cash_for_sell > 0:
equities = {e.symbol: e for e, p in context.perf_tracker.position_tracker.positions.items()}
instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
for instrument in instruments:
# 如果已经移动止损卖出过则不再轮仓卖出,以防止出现空头持仓
if instrument in stoploss_stock:
continue
context.order_target(context.symbol(instrument), 0)
cash_for_sell -= positions[instrument]
# 记录轮仓卖出的股票
sell_stock.append(instrument)
if cash_for_sell <= 0:
break
# 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票
buy_cash_weights = context.stock_weights
buy_list = list(ranker_prediction.instrument)
# 不再买入已经轮仓卖出和移动止损的股票,以防止出现空头持仓
buy_instruments = [i for i in buy_list if i not in sell_stock + stoploss_stock][: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 m19_prepare_bigquant_run(context):
pass
m1 = M.instruments.v2(
start_date='2010-01-02',
end_date='2010-05-01',
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m2 = M.advanced_auto_labeler.v2(
instruments=m1.data,
label_expr="""# #号开始的表示注释
# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
# 1. 可用数据字段见 https://bigquant.com/docs/data_history_data.html
# 添加benchmark_前缀,可使用对应的benchmark数据
# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/big_expr.html>`_
# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
shift(close, -5) / shift(open, -1)
# 极值处理:用1%和99%分位的值做clip
clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
# 将分数映射到分类,这里使用20个分类
all_wbins(label, 20)
# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
where(shift(high, -1) == shift(low, -1), NaN, label)
""",
start_date='',
end_date='',
benchmark='000300.SHA',
drop_na_label=True,
cast_label_int=True
)
m3 = 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
return_5
return_10
return_20
avg_amount_0/avg_amount_5
avg_amount_5/avg_amount_20
rank_avg_amount_0/rank_avg_amount_5
rank_avg_amount_5/rank_avg_amount_10
rank_return_0
rank_return_5
rank_return_10
rank_return_0/rank_return_5
rank_return_5/rank_return_10
pe_ttm_0
"""
)
m15 = M.general_feature_extractor.v7(
instruments=m1.data,
features=m3.data,
start_date='',
end_date='',
before_start_days=0
)
m16 = M.derived_feature_extractor.v3(
input_data=m15.data,
features=m3.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m7 = M.join.v3(
data1=m2.data,
data2=m16.data,
on='date,instrument',
how='inner',
sort=False
)
m5 = M.dropnan.v2(
input_data=m7.data
)
m4 = M.stock_ranker_train.v6(
training_ds=m5.data,
features=m3.data,
learning_algorithm='排序',
number_of_leaves=30,
minimum_docs_per_leaf=1000,
number_of_trees=20,
learning_rate=0.1,
max_bins=1023,
feature_fraction=1,
data_row_fraction=1,
plot_charts=True,
ndcg_discount_base=1,
m_lazy_run=False
)
m9 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2015-01-01'),
end_date=T.live_run_param('trading_date', '2015-05-01'),
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m17 = M.general_feature_extractor.v7(
instruments=m9.data,
features=m3.data,
start_date='',
end_date='',
before_start_days=60
)
m18 = M.derived_feature_extractor.v3(
input_data=m17.data,
features=m3.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m10 = M.dropnan.v2(
input_data=m18.data
)
m8 = M.stock_ranker_predict.v5(
model=m4.model,
data=m10.data,
m_lazy_run=False
)
m19 = M.trade.v4(
instruments=m9.data,
options_data=m8.predictions,
start_date='',
end_date='',
initialize=m19_initialize_bigquant_run,
handle_data=m19_handle_data_bigquant_run,
prepare=m19_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'
)
m6 = M.strategy_ret_risk_analysis.v2(
input_1=m19.raw_perf,
analysis_flag='absolute',
benchmark_index='000300.HIX',
terms='long'
)
[2023-04-23 22:29:47.505684] INFO: moduleinvoker: instruments.v2 开始运行..
[2023-04-23 22:29:47.522456] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:47.523926] INFO: moduleinvoker: instruments.v2 运行完成[0.018251s].
[2023-04-23 22:29:47.536540] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..
[2023-04-23 22:29:47.546032] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:48.850179] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[1.313619s].
[2023-04-23 22:29:48.888845] INFO: moduleinvoker: input_features.v1 开始运行..
[2023-04-23 22:29:48.905917] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:48.907562] INFO: moduleinvoker: input_features.v1 运行完成[0.018727s].
[2023-04-23 22:29:49.015162] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2023-04-23 22:29:49.026279] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.027607] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.01247s].
[2023-04-23 22:29:49.131863] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2023-04-23 22:29:49.144153] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.145551] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.013693s].
[2023-04-23 22:29:49.164756] INFO: moduleinvoker: join.v3 开始运行..
[2023-04-23 22:29:49.181092] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.182820] INFO: moduleinvoker: join.v3 运行完成[0.01806s].
[2023-04-23 22:29:49.211867] INFO: moduleinvoker: dropnan.v2 开始运行..
[2023-04-23 22:29:49.231249] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.232675] INFO: moduleinvoker: dropnan.v2 运行完成[0.020818s].
[2023-04-23 22:29:49.246800] INFO: moduleinvoker: stock_ranker_train.v6 开始运行..
[2023-04-23 22:29:49.267792] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.832824] INFO: moduleinvoker: stock_ranker_train.v6 运行完成[0.586024s].
[2023-04-23 22:29:49.838375] INFO: moduleinvoker: instruments.v2 开始运行..
[2023-04-23 22:29:49.845890] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.847354] INFO: moduleinvoker: instruments.v2 运行完成[0.008973s].
[2023-04-23 22:29:49.860961] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..
[2023-04-23 22:29:49.872640] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.874339] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[0.013389s].
[2023-04-23 22:29:49.882494] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..
[2023-04-23 22:29:49.890843] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.892334] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[0.009842s].
[2023-04-23 22:29:49.900757] INFO: moduleinvoker: dropnan.v2 开始运行..
[2023-04-23 22:29:49.906514] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:49.907878] INFO: moduleinvoker: dropnan.v2 运行完成[0.007122s].
[2023-04-23 22:29:49.923532] INFO: moduleinvoker: stock_ranker_predict.v5 开始运行..
[2023-04-23 22:29:50.652024] INFO: StockRanker预测: /y_2014 ..
[2023-04-23 22:29:51.746827] INFO: StockRanker预测: /y_2015 ..
[2023-04-23 22:29:52.495390] INFO: moduleinvoker: stock_ranker_predict.v5 运行完成[2.571845s].
[2023-04-23 22:29:55.818895] INFO: moduleinvoker: backtest.v8 开始运行..
[2023-04-23 22:29:55.825399] INFO: backtest: biglearning backtest:V8.6.3
[2023-04-23 22:29:55.826984] INFO: backtest: product_type:stock by specified
[2023-04-23 22:29:55.900271] INFO: moduleinvoker: cached.v2 开始运行..
[2023-04-23 22:29:55.910225] INFO: moduleinvoker: 命中缓存
[2023-04-23 22:29:55.911670] INFO: moduleinvoker: cached.v2 运行完成[0.011436s].
[2023-04-23 22:30:05.049116] INFO: backtest: algo history_data=DataSource(8da9253c15ac415b90df9b61d42f949eT)
[2023-04-23 22:30:05.050461] INFO: algo: TradingAlgorithm V1.8.9
[2023-04-23 22:30:07.248557] INFO: algo: trading transform...
[2023-04-23 22:30:12.379291] INFO: Performance: Simulated 78 trading days out of 78.
[2023-04-23 22:30:12.380735] INFO: Performance: first open: 2015-01-05 09:30:00+00:00
[2023-04-23 22:30:12.382470] INFO: Performance: last close: 2015-04-30 15:00:00+00:00
[2023-04-23 22:30:15.945570] INFO: moduleinvoker: backtest.v8 运行完成[20.126679s].
[2023-04-23 22:30:15.947129] INFO: moduleinvoker: trade.v4 运行完成[23.438959s].
[2023-04-23 22:30:15.965296] INFO: moduleinvoker: strategy_ret_risk_analysis.v2 开始运行..
[2023-04-23 22:30:17.338055] ERROR: moduleinvoker: module name: strategy_ret_risk_analysis, module version: v2, trackeback: AttributeError: 'NoneType' object has no attribute 'set_index'