def get_eval_corps_auto(self, date_maket_cap=None) -> pd.DataFrame:
"""100개의 주식 종목을 정해진 방법에 의해 가져온다"""
if hasattr(self.params, 'invest_start_date'
) == False or self.params.invest_start_date is None:
invest_start_date_str = DateUtils.today_str('%Y.%m.%d')
else:
invest_start_date_str = self.params.invest_start_date
invest_start_date = DateUtils.to_date(invest_start_date_str)
if hasattr(self.params, 'max_listing_period_years'
) == False or self.params.max_listing_period_years is None:
max_listing_period_years = 20
else:
max_listing_period_years = self.params.max_listing_period_years
max_listing_date = DateUtils.add_years(invest_start_date,
-max_listing_period_years)
max_listing_date = DateUtils.to_date_str(max_listing_date, '%Y-%m-%d')
corps = self.get_corps_all()
corps = corps.query("상장일<'{}'".format(max_listing_date))
corps.loc[:, '종목코드'] = corps['종목코드'].astype(str).str.zfill(6)
if date_maket_cap is None:
date_maket_cap = invest_start_date_str
#corps_cap = self.get_corps_maket_cap(date_maket_cap)
corps_cap = self.get_now_corps_maket_cap()
corps = corps.merge(corps_cap, on='종목코드')
corps = corps.sort_values(by=["시가총액"], ascending=False)
selected_corps_first = corps[:50]
selected_corps_last = corps[len(corps) - 60:-10]
return selected_corps_first.append(selected_corps_last,
ignore_index=True)
def get_corps_all(self):
today = DateUtils.today_str('%Y.%m.%d')
year = today[0:4]
file_path = os.path.join(self.DIR, 'files', 'corps', year,
'corps_' + today + '.txt')
if not os.path.isfile(file_path):
self.save_corps_csv(file_path)
return pd.read_csv(file_path)
def get_now_corps_maket_cap(self):
date = DateUtils.today_str('%Y%m%d') # 오늘 날짜
year = date[0:4]
file_path = os.path.join(self.DIR, "files", "corps_market_cap", year,
"market_cap_" + date + ".txt")
if not os.path.isfile(file_path):
master_data = self.get_now_coprs_master_price_from_krx()
market_cap = master_data[['종목코드', '자본금(원)']]
market_cap.rename(columns={'자본금(원)': '시가총액'}, inplace=True)
DataUtils.save_csv(market_cap, file_path)
else:
market_cap = pd.read_csv(file_path)
market_cap.loc[:, '종목코드'] = market_cap['종목코드'].astype(str).str.zfill(6)
return market_cap
def get_corps_maket_cap(self, date=None):
if date == None:
date = DateUtils.today_str() # 오늘 날짜
else:
date = date.replace(".", "").replace("-", "")
for i in range(30):
try:
year = date[0:4]
file_path = os.path.join(self.DIR, "files", "corps_market_cap",
year, "market_cap_" + date + ".txt")
if not os.path.isfile(file_path):
master_data = self.get_coprs_master_price_from_krx(date)
market_cap = master_data[['종목코드', '시가총액']]
DataUtils.save_csv(market_cap, file_path)
else:
market_cap = pd.read_csv(file_path)
break
except:
print(date, "에 시가총액 데이터를 가져오는데 에러 발생하여 이전 데이터 사용")
date = DateUtils.add_days(date, -i, '%Y%m%d')
return market_cap
def get_coprs_master_price_from_krx(self, date=None):
if date is None:
date = DateUtils.today_str('%Y%m%d')
else:
date = date.replace(".", "").replace("-", "")
df = None
for i in range(30):
date = DateUtils.add_days(date, -i, '%Y%m%d')
# STEP 01: Generate OTP
gen_otp_url = 'https://marketdata.krx.co.kr/contents/COM/GenerateOTP.jspx'
gen_otp_data = {
'name': 'fileDown',
'filetype': 'csv',
'url': 'MKD/04/0404/04040200/mkd04060200_01',
'market_gubun': 'ALL', # 시장구분: ALL=전체
'indx_ind_cd': '',
'sect_tp_cd': '',
'schdate': date,
'pagePath': '/contents/MKD/04/0404/04040200/MKD04040200.jsp',
}
r = requests.post(gen_otp_url,
gen_otp_data,
headers=self.KTX_HEADER)
code = r.content # 리턴받은 값을 아래 요청의 입력으로 사용.
#STEP 02: download
down_url = 'http://file.krx.co.kr/download.jspx'
down_data = {'code': code}
r = requests.post(down_url, down_data, headers=self.KTX_HEADER)
df = pd.read_csv(BytesIO(r.content), header=0, thousands=',')
if len(df) > 0:
break
return df