def recommend_corps(recommend_month: str, train_model: str = 'rnn') -> None:
"""하나의 세션으로 학습시키는 기본 모델 """
month = DateUtils.to_date(recommend_month, '%Y.%m')
params = GlobalParams(train_model=train_model)
#params.remove_session_file = True
before_month_start = DateUtils.to_month_str(month,
-params.mock_period_months)
before_month_end = DateUtils.to_month_str(month, -1)
params.invest_start_date = before_month_start + '.01'
params.invest_end_date = DateUtils.to_date_str(month -
datetime.timedelta(days=1))
params.result_file_name = "MOCK_" + before_month_start + "-" + before_month_end
corp = Corp(params)
corps = corp.get_eval_corps_auto(params.invest_end_date)
invests = LearningNMockInvestment(params)
invests.train_n_invests(corps)
before_result = pd.read_csv(invests.get_result_file_path())
if params.rmse_max_recommend is not None:
before_result = before_result.query("rmse<" +
str(params.rmse_max_recommend))
before_result = before_result.sort_values(by='invest_result',
ascending=False)
before_result.index = range(len(before_result.index))
save_file_name = "recommend_months_" + recommend_month + ".xlsx"
save_file_path = os.path.join('result', train_model, save_file_name)
DataUtils.save_csv(before_result, save_file_path)
print(before_result)
def train_n_invests_for_name(self,
corp_names: list,
invest_only: bool = False) -> None:
"""회사이름으로 검색하여 학습시킴 """
corp = Corp()
comp_rmses = []
no = 1
date = None
for corp_name in corp_names:
corp_code = corp.get_corp_code(corp_name)
try:
result, invest_daily = self.train_n_invest(
corp_code, corp_name, no, invest_only)
date = result[1]
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
file=sys.stdout)
no += 1
continue
#result = self.let_train_invest(corp_code, corp_name, no)
comp_rmses.append(result)
no += 1
df_comp_rmses = pd.DataFrame(comp_rmses, columns=self.result_columns)
DataUtils.save_csv(df_comp_rmses, self.get_result_file_path(date))
def train_n_invests(self,
corps,
start_no=1,
invest_only: bool = False) -> pd.DataFrame:
"""입력한 회사들에 대해서 학습시키고 모의투자를 실행한다."""
comp_rmses = []
no = 1
invest_daily_data = []
date: str = None
for index, corp_data in corps.iterrows():
if no < start_no:
no += 1
continue
corp_code = corp_data['종목코드']
corp_name = corp_data['회사명']
try:
result, invest_daily = self.train_n_invest(
corp_code, corp_name, no, invest_only)
date = result[7]
if invest_daily is not None:
invest_daily_data.append(invest_daily)
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
file=sys.stdout)
no += 1
continue
comp_rmses.append(result)
if no % 10 == 0 and self.params.debug == True:
df_comp_rmses = pd.DataFrame(comp_rmses,
columns=self.result_columns)
DataUtils.save_csv(df_comp_rmses,
self.get_result_file_path(date))
no += 1
df_comp_rmses = pd.DataFrame(comp_rmses, columns=self.result_columns)
DataUtils.save_csv(df_comp_rmses, self.get_result_file_path(date))
#DataUtils.save_csv(df_comp_rmses, self.get_result_file_path(date))
if len(invest_daily_data) > 1:
try:
visualizer = InvestVisualizer(self.params)
return visualizer.draw_invest_daily(invest_daily_data, corps)
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
file=sys.stdout)
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 forcasts(self, corps_n_date: list) -> None:
""" 각 종목의 날짜로 예측을 수행한다. """
comp_rmses = []
no = 1
date = None
for corp_n_date in corps_n_date:
corp_code = corp_n_date[0].replace("A", "")
corp_name = corp_n_date[1]
forcast_date = corp_n_date[2]
params = GlobalParams('FORCAST')
params.forcast_date = forcast_date
invests = LearningNMockInvestment(params)
result, invest_daily = invests.train_n_invest(
corp_code, corp_name, no, False)
comp_rmses.append(result)
date = result[1]
no += 1
df_comp_rmses = pd.DataFrame(comp_rmses, columns=self.result_columns)
DataUtils.save_csv(df_comp_rmses, self.get_result_file_path(date))
def train_months(start: str = '2018.01',
end: str = '2018.09',
invest_money: float = 100000000,
train_model: str = 'rnn') -> None:
"""하나의 세션으로 학습시키는 기본 모델 """
start_month = DateUtils.to_date(start, '%Y.%m')
end_month = DateUtils.to_date(end, '%Y.%m')
between = DateUtils.between_months(start_month, end_month)
invest_months_result = []
result_columns = ["month", "invest_money", "result_money"]
MOCK_MONEY = 10000000
chart_data = []
params = None
index_money = None
for i in range(between + 1):
params = GlobalParams(train_model=train_model)
#params.remove_session_file = True
before_month_start = DateUtils.to_month_str(
start_month, i - params.mock_period_months)
before_month_end = DateUtils.to_month_str(start_month, i - 1)
params.invest_start_date = before_month_start + '.01'
params.invest_end_date = before_month_end + '.31'
params.result_file_name = "MOCK_" + before_month_start + "-" + before_month_end
params.invest_money = MOCK_MONEY
corp = Corp(params)
corps = corp.get_eval_corps_auto(params.invest_end_date)
invests = LearningNMockInvestment(params)
invests.train_n_invests(corps)
before_result = pd.read_csv(invests.get_result_file_path())
now_month = DateUtils.to_month_str(start_month, i)
if params.rmse_max_recommend is not None:
before_result = before_result.query("rmse<" +
str(params.rmse_max_recommend))
before_result = corp.exclude_corps(before_result, now_month)
before_result = before_result.sort_values(by='invest_result',
ascending=False)
before_result.index = range(len(before_result.index))
corp10_codes = before_result.loc[:9, 'code']
corp10_codes.index = range(len(corp10_codes.index))
corp10 = corp.get_corps_for_codes(corp10_codes)
corp10_len = len(corp10_codes.index)
params = GlobalParams(train_model=train_model)
#params.remove_session_file = False
params.invest_start_date = now_month + '.01'
params.invest_end_date = now_month + '.31'
params.result_file_name = "INVEST_" + now_month
params.invest_money = invest_money / corp10_len
if index_money is not None:
params.index_money = index_money / corp10_len
invests = LearningNMockInvestment(params)
invest_chart_data = invests.train_n_invests(corp10, invest_only=False)
chart_data.append(invest_chart_data)
now_result = pd.read_csv(invests.get_result_file_path())
invest_money = now_result['invest_result'].sum()
index_money = now_result['all_invest_result'].sum()
invest_months_result.append(
[now_month, params.invest_money * corp10_len, invest_money])
print(now_month, params.invest_money * corp10_len, invest_money)
df_imr = pd.DataFrame(invest_months_result, columns=result_columns)
save_file_name = "recommend_months_" + start + "-" + end + ".xlsx"
if "_" in train_model:
save_file_path = os.path.join('result', train_model,
params.ensemble_type, save_file_name)
else:
save_file_path = os.path.join('result', train_model, save_file_name)
DataUtils.save_csv(df_imr, save_file_path)
if len(chart_data) > 1 and params is not None:
visualizer = InvestVisualizer(params)
visualizer.draw_invest_months(chart_data, start, end)
print()
def save_csv(self, df_rmses, dir, corp_name):
"""Seaborn 차트로 그래프를 그린다."""
file_path = self.get_file_path(dir, corp_name, "csv")
DataUtils.save_csv(df_rmses, file_path)
def save_csv(self, df_rmses, dir, corp_name, start=None, end=None)->None:
"""차트 테이터를 저장한다."""
file_path = self.get_file_path(dir, corp_name, "csv", start, end)
DataUtils.save_csv(df_rmses, file_path)
def save_corps_csv(self, file_path):
""" 주식회사 정보를 가져와서 csv로 저장한다. """
corps = self.get_corps_master()
corps = corps[['종목코드', '회사명', '상장일']]
DataUtils.save_csv(corps, file_path)
def train_n_invests_for_all(self, corps):
"""입력한 회사들에 대해서 학습시키고 모의투자를 실행한다."""
stocks = Stocks(self.params)
trains_data = TrainsData(self.params)
learning = Learning(self.params)
invest = MockInvestment(self.params)
list = []
for index, corp_data in corps.iterrows():
corp_code = corp_data['종목코드']
corp_name = corp_data['회사명']
try:
stock_data = stocks.get_stock_data(corp_code)
data_params, scaler_close, dataX_last = trains_data.get_train_test(
stock_data)
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
file=sys.stdout)
continue
list.append({
'corp_code': corp_code,
'corp_name': corp_name,
'scaler_close': scaler_close,
'dataX_last': dataX_last,
'data_params': data_params,
'stock_data': stock_data
})
all_data_params = self.gather_data_params(list)
tp = learning.learn("ALL_CORPS", "ALL_CORPS", all_data_params)
invest_daily_data = []
comp_rmses = []
index = 1
for item in list:
corp_code = item['corp_code']
corp_name = item['corp_data']
dataX_last = item['dataX_last']
data_params = item['data_params']
scaler_close = item['scaler_close']
stock_data = item['stock_data']
ip = invest.invest(corp_code, corp_name, tp)
visualizer = LearningVisualizer(self.params)
visualizer.draw_predictions(corp_name, scaler_close, data_params,
tp.test_predict, ip.predict_list)
result, invest_daily = self.get_train_invest_result(
index, corp_code, corp_name, tp.test_rmse, ip.last_money,
ip.index_money, tp.train_count, stock_data, data_params,
scaler_close, ip.last_predict)
if invest_daily != None:
invest_daily_data.append(invest_daily)
comp_rmses.append(result)
index += 1
df_comp_rmses = pd.DataFrame(comp_rmses, columns=self.result_columns)
DataUtils.save_csv(df_comp_rmses, self.get_result_file_path())
if len(invest_daily_data) > 1:
try:
visualizer = InvestVisualizer(self.params)
return visualizer.draw_invest_daily(invest_daily_data, corps)
except Exception:
exc_type, exc_value, exc_traceback = sys.exc_info()
traceback.print_exception(exc_type,
exc_value,
exc_traceback,
file=sys.stdout)
