如何按流通盘大小选标的

新手专区
标签: #<Tag:0x00007f20bb36e858>

(luckychan) #1

#3.1 通过内置变量自动标注
class conf:
start_date = '2010-01-10’
end_date=‘2018-04-05’
split_date = ‘2015-07-10’
instruments = D.instruments(start_date, end_date)
label_expr = [’(sell_price-buy_price)/atr*10’, ‘where(label > {0}, {0}, where(label < -{0}, -{0}, label)) + {0}’.format(20)]
hold_days = 5
features = []

m2 = M.fast_auto_labeler.v7(
instruments=conf.instruments, start_date=conf.start_date, end_date=conf.end_date,
label_expr=conf.label_expr, hold_days=conf.hold_days,
benchmark=‘000300.SHA’, sell_at=‘close’, buy_at=‘open’)

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
"""

)

m4 = M.general_feature_extractor.v6(
instruments=conf.instruments,
features=m3.data,
start_date=conf.start_date,
end_date=conf.end_date,
before_start_days=0
)

m5 = M.derived_feature_extractor.v2(
input_data=m4.data,
features=m3.data,
date_col=‘date’,
instrument_col=‘instrument’
)

m7 = M.join.v3(
data1=m2.data,
data2=m5.data,
on=‘date,instrument’,
how=‘inner’,
sort=False
)

m13 = M.dropnan.v1(
input_data=m7.data
)

m6 = M.stock_ranker_train.v5(
training_ds=m13.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’, ‘2015-07-10’),
end_date=T.live_run_param(‘trading_date’, ‘2018-04-05’),
market=‘CN_STOCK_A’,
instrument_list=’’,
max_count=0
)

m10 = M.general_feature_extractor.v6(
instruments=m9.data,
features=m3.data,
start_date=’’,
end_date=’’,
before_start_days=0
)

m11 = M.derived_feature_extractor.v2(
input_data=m10.data,
features=m3.data,
date_col=‘date’,
instrument_col=‘instrument’
)

m14 = M.dropnan.v1(
input_data=m11.data
)

m8 = M.stock_ranker_predict.v5(
model=m6.model,
data=m14.data,
m_lazy_run=False
)

def add_column(df, series, name):
df[name] = series
return df

回测引擎:每日数据处理函数,每天执行一次

def m12_handle_data_bigquant_run(context, data):
date = data.current_dt.strftime(’%Y-%m-%d’)
# 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 m12_prepare_bigquant_run(context):
# 引进prepare数据准备函数是为了保持回测和模拟能够通用
# 获取股票代码
instruments = D.instruments()
start_date = context.start_date
# 确定结束时间
end_date = context.end_date

# 获取股票历史数据,返回DataFrame数据格式
market_cap_float_data = D.history_data(instruments,start_date,end_date,
          fields=['market_cap_float','close','amount','adjust_factor'])
# 获取股票流通股数数据,返回DataFrame数据格式
market_cap_float_data = market_cap_float_data.groupby('instrument').apply(lambda x:add_column(x,x.market_cap_float/x.close*x.adjust_factor,'market_cap_float_gu'))
# 获取按流通股排序少于1亿流通股的股票
daily_buy_stock = market_cap_float_data.groupby('date').apply(lambda df:df[(df['amount'] > 0)&((df['market_cap_float_gu'] <100000000))].sort_values('market_cap_float_gu'))

instruments = daily_buy_stock

回测引擎:初始化函数,只执行一次

def m12_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 = 2
# 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 = 0.3
context.options['hold_days'] = 5

m12 = M.trade.v3(
instruments=m9.data,
options_data=m8.predictions,
start_date=’’,
end_date=’’,
handle_data=m12_handle_data_bigquant_run,
prepare=m12_prepare_bigquant_run,
initialize=m12_initialize_bigquant_run,
volume_limit=0.025,
order_price_field_buy=‘open’,
order_price_field_sell=‘close’,
capital_base=100000,
benchmark=‘000300.SHA’,
auto_cancel_non_tradable_orders=True,
data_frequency=‘daily’,
price_type=‘前复权’,
plot_charts=True,
backtest_only=False,
amount_integer=False
)

#---------------------------------
如上:在m12_prepare_bigquant_run里写一段代码是按流通股数选出1亿以下的个数来做交易,但最后的结果是大于1亿的也有,请问这段代码放在prepare里是否合适。如果不合适,应放在那里才好。

另外:如果想使用两融标的股进行交易,这代码又应怎样写。请大神指教。谢谢!


(达达) #2

https://community.bigquant.com/t/【宽客学院】如何选出符合一定条件的股票/2564
建议使用可视化界面编程,在证券代码选择模块中进行过滤


(luckychan) #3

可以讲详细些吗,申万里好象没有两融标的的代码。