def get_k_data_in_range(self, start_date, end_date):
ndays = delta_days(start_date, end_date)
date_dmy_format = time.strftime("%m/%d/%Y",
time.strptime(start_date, "%Y-%m-%d"))
data_times = pd.date_range(date_dmy_format, periods=ndays, freq='D')
date_only_array = np.vectorize(lambda s: s.strftime('%Y-%m-%d'))(
data_times.to_pydatetime())
data_dict = OrderedDict()
for _date in date_only_array:
if CCalendar.is_trading_day(_date, redis=self.redis):
table_name = self.get_table_name(_date)
if table_name not in data_dict: data_dict[table_name] = list()
data_dict[table_name].append(str(_date))
all_df = pd.DataFrame()
for key in data_dict:
table_list = sorted(data_dict[key], reverse=False)
if len(table_list) == 1:
df = self.get_data(table_list[0])
if df is not None: all_df = all_df.append(df)
else:
start_date = table_list[0]
end_date = table_list[len(table_list) - 1]
df = self.get_data_between(start_date, end_date)
if df is not None: all_df = all_df.append(df)
return all_df
def init_all_stock_tick(self):
start_date = '2015-01-01'
_today = datetime.now().strftime('%Y-%m-%d')
num_days = delta_days(start_date, _today)
start_date_dmy_format = time.strftime(
"%m/%d/%Y", time.strptime(start_date, "%Y-%m-%d"))
data_times = pd.date_range(start_date_dmy_format,
periods=num_days,
freq='D')
date_only_array = np.vectorize(lambda s: s.strftime('%Y-%m-%d'))(
data_times.to_pydatetime())
date_only_array = date_only_array[::-1]
obj_pool = Pool(4)
df = self.stock_info_client.get()
for _, code_id in df.code.iteritems():
_obj = self.stock_objs[
code_id] if code_id in self.stock_objs else CStock(
self.dbinfo, code_id)
for _date in date_only_array:
if self.cal_client.is_trading_day(_date):
try:
if obj_pool.full(): obj_pool.join()
obj_pool.spawn(_obj.set_ticket, _date)
except Exception as e:
logger.info(e)
obj_pool.join()
obj_pool.kill()
def get_stock_pool(start_date, end_date):
'''
更新股票池。该方法在收盘后调用。
1. 全市场(不包含ST)股票作为基础股票池
2. 剔除自制股票黑名单中的股票
3. 剔除成交额小于1个亿的股票
4. 剔除总市值中位数在100亿以下的股票
5. 取25日跌幅前10%的股票作为最终的股票池
'''
#获取所有股票数据
num = delta_days(start_date, end_date)
all_df = get_stock_data(start_date, end_date, num)
#黑名单股票
black_list = get_blacklist()
#所有单股票
all_code_list = get_all_codelist()
all_code_list = list(set(all_code_list).difference(set(black_list)))
all_df = all_df.loc[all_df.code.isin(all_code_list)]
#获取开盘天数大于30%的股票的数量
codes = list()
amounts = list()
outstandings = list()
pchanges = list()
for code, df in all_df.groupby('code'):
df = df.sort_values(by=['date'], ascending=True)
df = df.reset_index(drop=True)
if len(df) > int(num * 0.5):
codes.append(code)
amounts.append(np.median(df.amount))
close = np.median(df.close)
open_ = df['open'][0]
close_ = df['close'][len(df) - 1]
pchange = (close_ - open_) / open_
pchanges.append(pchange)
totals = np.median(df.totals)
outstandings.append(close * totals)
all_df = all_df.loc[all_df.code.isin(codes)]
#info = {'code': codes, 'amount': amounts, 'outstanding': outstandings, 'pchange': pchanges}
#stock_df = pd.DataFrame(info)
#stock_df = stock_df.reset_index(drop = True)
##总市值大于100亿的股票的列表
#stock_df = stock_df.sort_values(by=['outstanding'], ascending = False)
#biglist = stock_df.loc[stock_df.outstanding > 1e10].code.tolist()
#all_df = all_df.loc[all_df.code.isin(biglist)]
##获取成交额大于1个亿的股票
#stock_df = stock_df.sort_values(by=['amount'], ascending = False)
#code_list = stock_df.loc[stock_df.amount > 1e8].code.tolist()
#all_df = all_df.loc[all_df.code.isin(code_list)]
#取25日跌幅前10%的股票
#stock_df = stock_df.sort_values(by=['pchange'], ascending = True)
#code_list = stock_df.head(int(len(stock_df) * 0.5)).code.tolist()
#all_df = all_df.loc[all_df.code.isin(code_list)]
return all_df
def test_delta_days(self):
_from = "2019-06-07"
_to = "2019-06-07"
self.assertEqual(common.delta_days(_from, _to), 0)