如果我们想看看通过股指期货对冲后的策略收益率，我们有如下两种方式：
通过基准指数设置成股指期货指数，通过相对收益率来进行衡量
直接在拥有多仓的时候，直接建股指期货的空头头寸
# 本代码由可视化策略环境自动生成 2019年3月5日 17:31
# 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：每日数据处理函数，每天执行一次
def m20_handle_data_bigquant_run(context, data):
# 获取当日指标数据
print('index', context.trading_day_index)
today = data.current_dt.strftime('%Y-%m-%d') # 当前交易日期
context.extension['index'] += 1
instrument = context.future_symbol(context.instruments[0]) # 交易标的
if context.extension['index'] == 1 :
context.order(instrument, -1)
print(today, '卖空全部')
# 回测引擎：准备数据，只执行一次
def m20_prepare_bigquant_run(context):
pass
# 回测引擎：初始化函数，只执行一次
def m20_initialize_bigquant_run(context):
# 设置是否是结算模式
context.set_need_settle(False)
# 设置最大杠杆
context.set_max_leverage(1, 'fill_amap')
if 'index' not in context.extension:
context.extension['index'] = 0
# 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 m20_before_trading_start_bigquant_run(context, data):
pass
# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m10_run_bigquant_run(input_1, input_2, input_3):
# 示例代码如下。在这里编写您的代码
bm = DataSource('bar1d_CN_FUTURE').read(instruments=['IC8888.CFE'],start_date='2016-01-01',end_date='2017-01-02')
bm.index = range(len(bm))
data_1 = DataSource.write_df(bm)
return Outputs(data_1=data_1)
# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m10_post_run_bigquant_run(Outputs):
return Outputs
# 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):
# 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()}
# 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]))])))
# print('rank order for sell %s' % instruments)
for instrument in instruments:
context.order_target(context.symbol(instrument), 0)
cash_for_sell -= positions[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_instruments = list(ranker_prediction.instrument[: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
# 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
# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m21_run_bigquant_run(input_1, input_2, input_3):
# 示例代码如下。在这里编写您的代码
perf1 = input_1.read_df()['algorithm_period_return']+1 # 净值
perf2 = input_2.read_df()['algorithm_period_return']+1 # 净值
net_pv = perf1-perf2+1 # 对冲后净值
net_pv.name = 'net value after hedge'
net_pv_ds = DataSource.write_df(net_pv)
return Outputs(data_1=net_pv_ds)
# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m21_post_run_bigquant_run(outputs):
net_pv = outputs.data_1.read_df()
T.plot(net_pv, title='对冲后策略净值')
return outputs
m1 = M.instruments.v2(
start_date='2010-01-01',
end_date='2015-01-01',
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
)
m13 = M.dropnan.v1(
input_data=m7.data
)
m5 = M.chinaa_stock_filter.v1(
input_data=m13.data,
index_constituent_cond=['中证500'],
board_cond=['全部'],
industry_cond=['全部'],
st_cond=['全部'],
output_left_data=False
)
m6 = M.stock_ranker_train.v5(
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,
m_lazy_run=False
)
m9 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2016-01-01'),
end_date=T.live_run_param('trading_date', '2017-01-02'),
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=0
)
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
)
m14 = M.dropnan.v1(
input_data=m18.data
)
m22 = M.chinaa_stock_filter.v1(
input_data=m14.data,
index_constituent_cond=['中证500'],
board_cond=['全部'],
industry_cond=['全部'],
st_cond=['全部'],
output_left_data=False
)
m8 = M.stock_ranker_predict.v5(
model=m6.model,
data=m22.data,
m_lazy_run=False
)
m4 = M.instruments.v2(
start_date='2016-01-01',
end_date='2017-01-02',
market='CN_FUTURE',
instrument_list='IC8888.CFE',
max_count=0
)
m20 = M.trade.v4(
instruments=m4.data,
start_date='',
end_date='',
handle_data=m20_handle_data_bigquant_run,
prepare=m20_prepare_bigquant_run,
initialize=m20_initialize_bigquant_run,
before_trading_start=m20_before_trading_start_bigquant_run,
volume_limit=0,
order_price_field_buy='open',
order_price_field_sell='open',
capital_base=2100001,
auto_cancel_non_tradable_orders=True,
data_frequency='daily',
price_type='真实价格',
product_type='期货',
plot_charts=True,
backtest_only=False,
benchmark='000300.SHA'
)
m10 = M.cached.v3(
run=m10_run_bigquant_run,
post_run=m10_post_run_bigquant_run,
input_ports='',
params='{}',
output_ports='',
m_cached=False
)
m19 = M.trade.v4(
instruments=m9.data,
options_data=m8.predictions,
benchmark_ds=m10.data_1,
start_date='',
end_date='',
handle_data=m19_handle_data_bigquant_run,
prepare=m19_prepare_bigquant_run,
initialize=m19_initialize_bigquant_run,
volume_limit=0.0251,
order_price_field_buy='open',
order_price_field_sell='close',
capital_base=2000000,
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.SHA'
)
m21 = M.cached.v3(
input_1=m19.raw_perf,
input_2=m20.raw_perf,
run=m21_run_bigquant_run,
post_run=m21_post_run_bigquant_run,
input_ports='',
params='{}',
output_ports='',
m_cached=False
)
[2019-03-05 17:28:10.773826] INFO: bigquant: instruments.v2 开始运行..
[2019-03-05 17:28:11.075392] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.079781] INFO: bigquant: instruments.v2 运行完成[0.309143s].
[2019-03-05 17:28:11.157944] INFO: bigquant: advanced_auto_labeler.v2 开始运行..
[2019-03-05 17:28:11.167305] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.171344] INFO: bigquant: advanced_auto_labeler.v2 运行完成[0.013375s].
[2019-03-05 17:28:11.180103] INFO: bigquant: input_features.v1 开始运行..
[2019-03-05 17:28:11.186409] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.188298] INFO: bigquant: input_features.v1 运行完成[0.008187s].
[2019-03-05 17:28:11.438358] INFO: bigquant: general_feature_extractor.v7 开始运行..
[2019-03-05 17:28:11.457214] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.459084] INFO: bigquant: general_feature_extractor.v7 运行完成[0.020724s].
[2019-03-05 17:28:11.501664] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-03-05 17:28:11.515150] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.517166] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.015502s].
[2019-03-05 17:28:11.552633] INFO: bigquant: join.v3 开始运行..
[2019-03-05 17:28:11.564916] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.566857] INFO: bigquant: join.v3 运行完成[0.014227s].
[2019-03-05 17:28:11.579306] INFO: bigquant: dropnan.v1 开始运行..
[2019-03-05 17:28:11.585770] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.587234] INFO: bigquant: dropnan.v1 运行完成[0.007928s].
[2019-03-05 17:28:11.663362] INFO: bigquant: chinaa_stock_filter.v1 开始运行..
[2019-03-05 17:28:11.674374] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.676038] INFO: bigquant: chinaa_stock_filter.v1 运行完成[0.01266s].
[2019-03-05 17:28:11.770600] INFO: bigquant: stock_ranker_train.v5 开始运行..
[2019-03-05 17:28:11.783359] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.785908] INFO: bigquant: stock_ranker_train.v5 运行完成[0.015308s].
[2019-03-05 17:28:11.792063] INFO: bigquant: instruments.v2 开始运行..
[2019-03-05 17:28:11.809608] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.811852] INFO: bigquant: instruments.v2 运行完成[0.019781s].
[2019-03-05 17:28:11.829331] INFO: bigquant: general_feature_extractor.v7 开始运行..
[2019-03-05 17:28:11.838331] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.839989] INFO: bigquant: general_feature_extractor.v7 运行完成[0.010658s].
[2019-03-05 17:28:11.852825] INFO: bigquant: derived_feature_extractor.v3 开始运行..
[2019-03-05 17:28:11.871291] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.873049] INFO: bigquant: derived_feature_extractor.v3 运行完成[0.020202s].
[2019-03-05 17:28:11.881392] INFO: bigquant: dropnan.v1 开始运行..
[2019-03-05 17:28:11.890169] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.892285] INFO: bigquant: dropnan.v1 运行完成[0.010885s].
[2019-03-05 17:28:11.904108] INFO: bigquant: chinaa_stock_filter.v1 开始运行..
[2019-03-05 17:28:11.913283] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.915365] INFO: bigquant: chinaa_stock_filter.v1 运行完成[0.01126s].
[2019-03-05 17:28:11.960796] INFO: bigquant: stock_ranker_predict.v5 开始运行..
[2019-03-05 17:28:11.980191] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.982782] INFO: bigquant: stock_ranker_predict.v5 运行完成[0.021988s].
[2019-03-05 17:28:11.985827] INFO: bigquant: instruments.v2 开始运行..
[2019-03-05 17:28:11.992346] INFO: bigquant: 命中缓存
[2019-03-05 17:28:11.994106] INFO: bigquant: instruments.v2 运行完成[0.008265s].
[2019-03-05 17:28:13.102724] INFO: bigquant: backtest.v8 开始运行..
[2019-03-05 17:28:13.112616] INFO: bigquant: 命中缓存
[2019-03-05 17:28:28.824605] INFO: bigquant: backtest.v8 运行完成[15.721864s].
[2019-03-05 17:28:28.874446] INFO: bigquant: cached.v3 开始运行..
[2019-03-05 17:29:26.255824] INFO: bigquant: cached.v3 运行完成[57.381372s].
[2019-03-05 17:29:27.354310] INFO: bigquant: backtest.v8 开始运行..
[2019-03-05 17:29:27.359728] INFO: bigquant: biglearning backtest:V8.1.11
[2019-03-05 17:29:27.438283] INFO: bigquant: product_type:stock by specified
[2019-03-05 17:30:59.363228] INFO: bigquant: 读取股票行情完成:1368603
[2019-03-05 17:31:13.882612] INFO: algo: TradingAlgorithm V1.4.7
[2019-03-05 17:31:23.731448] INFO: algo: trading transform...
[2019-03-05 17:31:29.207071] INFO: Performance: Simulated 244 trading days out of 244.
[2019-03-05 17:31:29.225504] INFO: Performance: first open: 2016-01-04 09:30:00+00:00
[2019-03-05 17:31:29.227891] INFO: Performance: last close: 2016-12-30 15:00:00+00:00
[2019-03-05 17:31:31.804546] INFO: bigquant: backtest.v8 运行完成[124.450228s].
[2019-03-05 17:31:31.824657] INFO: bigquant: cached.v3 开始运行..
[2019-03-05 17:31:32.057468] INFO: bigquant: cached.v3 运行完成[0.23281s].