(rank(板块流通收益率)>=0.95)
&(rank(sum(板块流通收益率,5))>=0.9)
&(mean(板块流通收益率,3)>=mean(板块流通收益率,5))
&(mean(板块流通收益率,5)>=mean(板块流通收益率,10))
#我们可以看一下 m12中的数据长啥样
m12.data.read()
#我们可以看一下 m21中的标注数据长啥样
m21.data.read()
# 本代码由可视化策略环境自动生成 2022年9月9日 14:05
# 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。
# 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 m34_run_bigquant_run(input_1, input_2, input_3, SW_type):
basic_data = input_1.read()
start_date = str(basic_data.date.min())
end_date = str(basic_data.date.max())
SW_data = DataSource('basic_info_IndustrySw').read()
SW_data['code'] = SW_data.code.astype('int')
SW_data_2014_2 = SW_data[(SW_data.version==2014)&(SW_data.industry_sw_level==2)][['code','name']].rename(columns={'code':'industry_sw_level2_0','name':'name_SW2'})
SW_data_2021_2 = SW_data[(SW_data.version==2021)&(SW_data.industry_sw_level==2)][['code','name']].rename(columns={'code':'industry_sw_level2_0','name':'name_SW2'})
basic_data['daily_return_0'] = basic_data['daily_return_0']-1
if end_date < '2021-12-13':
basic_data = basic_data.merge(SW_data_2014_2,how='left',on='industry_sw_level2_0')
else:
basic_data_2014 = basic_data[basic_data.date < '2021-12-13']
basic_data_2014 = basic_data_2014.merge(SW_data_2014_2,how='left',on='industry_sw_level2_0')
basic_data_2021 = basic_data[basic_data.date >= '2021-12-13']
basic_data_2021 = basic_data_2021.merge(SW_data_2021_2,how='left',on='industry_sw_level2_0')
basic_data = pd.concat([basic_data_2014,basic_data_2021])
block_data = basic_data.groupby(['name_SW2','date']).agg({'daily_return_0':'sum','market_cap_float_0':'sum'}).reset_index()
block_data.columns = ['name_SW2','date','daily_return_0_block_sum','market_cap_float_0_block_sum']
rst = pd.merge(basic_data[['date','name_SW2','instrument','daily_return_0','market_cap_float_0']],block_data,on=['date','name_SW2'],how='left').dropna()
rst['板块流通收益率'] = rst['daily_return_0']*rst['market_cap_float_0']/rst['market_cap_float_0_block_sum']
data_1 = DataSource.write_df(rst)
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 m34_post_run_bigquant_run(outputs):
return outputs
# 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 m19_run_bigquant_run(input_1, input_2, input_3, SW_type):
basic_data = input_1.read()
start_date = str(basic_data.date.min())
end_date = str(basic_data.date.max())
SW_data = DataSource('basic_info_IndustrySw').read()
SW_data['code'] = SW_data.code.astype('int')
SW_data_2014_2 = SW_data[(SW_data.version==2014)&(SW_data.industry_sw_level==2)][['code','name']].rename(columns={'code':'industry_sw_level2_0','name':'name_SW2'})
SW_data_2021_2 = SW_data[(SW_data.version==2021)&(SW_data.industry_sw_level==2)][['code','name']].rename(columns={'code':'industry_sw_level2_0','name':'name_SW2'})
basic_data['daily_return_0'] = basic_data['daily_return_0']-1
if end_date < '2021-12-13':
basic_data = basic_data.merge(SW_data_2014_2,how='left',on='industry_sw_level2_0')
else:
basic_data_2014 = basic_data[basic_data.date < '2021-12-13']
basic_data_2014 = basic_data_2014.merge(SW_data_2014_2,how='left',on='industry_sw_level2_0')
basic_data_2021 = basic_data[basic_data.date >= '2021-12-13']
basic_data_2021 = basic_data_2021.merge(SW_data_2021_2,how='left',on='industry_sw_level2_0')
basic_data = pd.concat([basic_data_2014,basic_data_2021])
block_data = basic_data.groupby(['name_SW2','date']).agg({'daily_return_0':'sum','market_cap_float_0':'sum'}).reset_index()
block_data.columns = ['name_SW2','date','daily_return_0_block_sum','market_cap_float_0_block_sum']
rst = pd.merge(basic_data[['date','name_SW2','instrument','daily_return_0','market_cap_float_0']],block_data,on=['date','name_SW2'],how='left').dropna()
rst['板块流通收益率'] = rst['daily_return_0']*rst['market_cap_float_0']/rst['market_cap_float_0_block_sum']
data_1 = DataSource.write_df(rst)
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 m19_post_run_bigquant_run(outputs):
return outputs
# 回测引擎:初始化函数,只执行一次
def m10_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 = 1
context.options['hold_days'] = 0
# 回测引擎:每日数据处理函数,每天执行一次
def m10_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.portfolio.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.portfolio.positions.items()}
instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
lambda x: x in equities)])))
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 m10_prepare_bigquant_run(context):
pass
# 回测引擎:初始化函数,只执行一次
def m32_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 = 1
context.options['hold_days'] = 0
# 回测引擎:每日数据处理函数,每天执行一次
def m32_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.portfolio.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.portfolio.positions.items()}
instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
lambda x: x in equities)])))
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 m32_prepare_bigquant_run(context):
pass
m1 = M.instruments.v2(
start_date='2018-06-01',
end_date='2022-01-01',
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m20 = M.use_datasource.v1(
instruments=m1.data,
datasource_id='bar1d_CN_STOCK_A',
start_date='',
end_date=''
)
m9 = M.instruments.v2(
start_date=T.live_run_param('trading_date', '2022-01-01'),
end_date=T.live_run_param('trading_date', '2022-06-22'),
market='CN_STOCK_A',
instrument_list='',
max_count=0
)
m5 = M.use_datasource.v1(
instruments=m9.data,
datasource_id='bar1d_CN_STOCK_A',
start_date='',
end_date=''
)
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
correlation(log(volume_0),return_0,10)
"""
)
m15 = M.general_feature_extractor.v7(
instruments=m1.data,
features=m2.data,
start_date='',
end_date='',
before_start_days=90
)
m16 = M.derived_feature_extractor.v3(
input_data=m15.data,
features=m2.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m17 = M.general_feature_extractor.v7(
instruments=m9.data,
features=m2.data,
start_date='',
end_date='',
before_start_days=90
)
m18 = M.derived_feature_extractor.v3(
input_data=m17.data,
features=m2.data,
date_col='date',
instrument_col='instrument',
drop_na=False,
remove_extra_columns=False
)
m26 = M.filter_stockcode.v2(
input_1=m18.data,
start='688'
)
m27 = M.filtet_st_stock.v7(
input_1=m26.data_1
)
m28 = M.filter_delist_stocks.v3(
input_1=m27.data_1
)
m31 = M.input_features.v1(
features="""industry_sw_level2_0
market_cap_float_0
daily_return_0
"""
)
m33 = M.general_feature_extractor.v7(
instruments=m1.data,
features=m31.data,
start_date='',
end_date='',
before_start_days=90
)
m34 = M.cached.v3(
input_1=m33.data,
run=m34_run_bigquant_run,
post_run=m34_post_run_bigquant_run,
input_ports='',
params="""{
'SW_type':'name_SW2'
}""",
output_ports='data_1,data_2'
)
m12 = M.join.v3(
data1=m34.data_1,
data2=m20.data,
on='date,instrument',
how='inner',
sort=False
)
m25 = M.filter.v3(
input_data=m12.data,
expr='rank(板块流通收益率)>0.95',
output_left_data=False
)
m21 = M.auto_labeler_on_datasource.v1(
input_data=m25.data,
label_expr="""
# 计算收益:3日最高价(作为卖出价格) 除以明日开盘价(作为买入价格) / 未来3日 的板块流通收益率
-1*(shift(high, -3)/shift(open, -1))/shift(板块流通收益率, -3) -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)""",
drop_na_label=True,
cast_label_int=True,
date_col='date',
instrument_col='instrument',
user_functions={}
)
m7 = M.join.v3(
data1=m21.data,
data2=m16.data,
on='date,instrument',
how='inner',
sort=False
)
m29 = M.filtet_st_stock.v7(
input_1=m7.data
)
m13 = M.dropnan.v1(
input_data=m29.data_1
)
m6 = M.stock_ranker_train.v6(
training_ds=m13.data,
features=m2.data,
test_ds=m13.data,
learning_algorithm='排序',
number_of_leaves=30,
minimum_docs_per_leaf=1000,
number_of_trees=50,
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
)
m4 = M.input_features.v1(
features="""industry_sw_level2_0
market_cap_float_0
daily_return_0
"""
)
m11 = M.general_feature_extractor.v7(
instruments=m9.data,
features=m4.data,
start_date='',
end_date='',
before_start_days=90
)
m19 = M.cached.v3(
input_1=m11.data,
run=m19_run_bigquant_run,
post_run=m19_post_run_bigquant_run,
input_ports='',
params="""{
'SW_type':'name_SW2'
}""",
output_ports='data_1,data_2'
)
m22 = M.join.v3(
data1=m19.data_1,
data2=m5.data,
on='date,instrument',
how='inner',
sort=False
)
m24 = M.join.v3(
data1=m28.data,
data2=m22.data,
on='date,instrument',
how='inner',
sort=False
)
m30 = M.filter.v3(
input_data=m24.data,
expr='rank(板块流通收益率)>0.95',
output_left_data=False
)
m14 = M.dropnan.v1(
input_data=m30.data
)
m8 = M.stock_ranker_predict.v5(
model=m6.model,
data=m14.data,
m_lazy_run=False
)
m23 = M.sort.v5(
input_ds=m8.predictions,
sort_by='score',
group_by='date',
keep_columns='--',
ascending=False
)
m10 = M.trade.v4(
instruments=m9.data,
options_data=m23.sorted_data,
start_date='',
end_date='',
initialize=m10_initialize_bigquant_run,
handle_data=m10_handle_data_bigquant_run,
prepare=m10_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='真实价格',
product_type='股票',
plot_charts=True,
backtest_only=False,
benchmark='000300.SHA'
)
m3 = M.sort.v5(
input_ds=m8.predictions,
sort_by='score',
group_by='date',
keep_columns='--',
ascending=True
)
m32 = M.trade.v4(
instruments=m9.data,
options_data=m3.sorted_data,
start_date='',
end_date='',
initialize=m32_initialize_bigquant_run,
handle_data=m32_handle_data_bigquant_run,
prepare=m32_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='真实价格',
product_type='股票',
plot_charts=True,
backtest_only=False,
benchmark='000300.SHA'
)