def compute(self, begin_date=None, end_date=None):
"""
计算指定时间段内所有股票的该因子的值，并保存到数据库中
:param begin_date: 开始时间
:param end_date: 结束时间
"""
dm = DataModule()
# 如果没有指定日期范围，则默认为计算当前交易日的数据
if begin_date is None:
begin_date = datetime.now().strftime('%Y-%m-%d')
if end_date is None:
end_date = datetime.now().strftime('%Y-%m-%d')
dates = get_trading_dates(begin_date, end_date)
for date in dates:
# 查询出股票在某一交易日的总股本
df_basics = dm.get_stock_basic_at(date)
if df_basics.index.size == 0:
continue
# 将索引改为code
df_basics.set_index(['code'], 1, inplace=True)
# 查询出股票在某一个交易日的收盘价
df_dailies = dm.get_one_day_k_data(autype=None, date=date)
if df_dailies.index.size == 0:
continue
# 将索引设为code
df_dailies.set_index(['code'], 1, inplace=True)
update_requests = []
for code in df_dailies.index:
try:
# 股价
close = df_dailies.loc[code]['close']
# 总股本
total_shares = df_basics.loc[code]['totals']
# 总市值 = 股价 * 总股本
total_capital = round(close * total_shares, 2)
print('%s, %s, mkt_cap: %15.2f' %
(code, date, total_capital),
flush=True)
update_requests.append(
UpdateOne(
{'code': code, 'date': date},
{'$set': {'code': code, 'date': date, self.name: total_capital}}, upsert=True))
except:
print('计算规模因子时发生异常，股票代码：%s，日期：%s'
% (code, date),
flush=True)
if len(update_requests) > 0:
save_result = self.collection.bulk_write(update_requests, ordered=False)
print('股票代码: %s, 因子: %s, 插入：%4d, 更新: %4d' %
(code, self.name, save_result.upserted_count, save_result.modified_count), flush=True)
def analyze(self):
# 初始化对数据管理子系统接口的调用
dm = DataModule()
# 初始化对因子管理子系统接口的调用
fm = FactorModule()
# 获取分析周期内的
all_dates = get_trading_dates(self.begin_date, self.end_date)
# 首档和末档，股票代码和后复权价格的Dictionary
top_dailies = dict()
bottom_dailies = dict()
# 暂存上一个调整
last_adjust_date = None
# 设置沪深300的首日值
hs300_k = dm.get_k_data('000300',
index=True,
begin_date=all_dates[0],
end_date=all_dates[0])
self.hs300_first_value = hs300_k.loc[0]['close']
# 计算每日收益
for index in range(0, len(all_dates), self.interval):
adjust_date = all_dates[index]
# 获取因子值，按照指定的顺序排序
df_factor = fm.get_single_date_factors(self.factor, adjust_date)
if df_factor.index.size == 0:
continue
df_factor.sort_values(self.factor,
ascending=self.ascending,
inplace=True)
# 将股票代码设为index
df_factor.set_index(['code'], inplace=True)
# 获取当日所有股票的行情
df_dailies = dm.get_one_day_k_data(autype='hfq', date=adjust_date)
# 将code设为index
df_dailies.set_index(['code'], inplace=True)
# 计算收益
self.compute_profit(last_adjust_date, df_dailies, top_dailies,
bottom_dailies, adjust_date)
# 删除停牌股票
df_dailies = df_dailies[df_dailies['is_trading']]
# 计算每当包含的股票数
total_size = df_dailies.index.size
single_position_count = int(total_size / self.position)
# 调整首档组合
self.adjust_top_position(top_dailies, df_factor, df_dailies,
single_position_count)
# 调整末档组合
self.adjust_bottom_position(bottom_dailies, df_factor, df_dailies,
single_position_count)
# 保存上一个调整日
last_adjust_date = adjust_date
# 生成零投资组合的组合收益
self.profit_df[
'portfolio'] = self.profit_df['top'] - self.profit_df['bottom']
self.draw()
