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 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 get_train_test(self, data, scaler_close=None):
"""train, test 데이터로 만든다."""
data = data.copy()
data = data[(data[['close', 'open', 'high', 'low', 'volume']] !=
0).all(1)]
data.index = pd.RangeIndex(len(data.index))
#data = self.add_mean_line(data)
if self.params.invest_end_date is not None:
data = data.query("date<='{}'".format(self.params.invest_end_date))
if self.params.invest_start_date is not None:
invest_data = data.query("date>='{}'".format(
self.params.invest_start_date))
invest_count = len(invest_data.index) - 1
self.params.invest_count = invest_count
invest_start_date_str = self.params.invest_start_date
else:
invest_count = 0
self.params.invest_count = 0
invest_start_date_str = data.tail(1)['date'].to_string(index=False)
invest_start_date = DateUtils.to_date(invest_start_date_str)
if hasattr(self.params, 'stock_training_period_years'):
period = self.params.stock_training_period_years
stock_start_date = DateUtils.add_years(invest_start_date, -period)
stock_start_date = stock_start_date.strftime("%Y.%m.%d")
data = data.query("date>='{}'".format(stock_start_date))
test_count = None
if hasattr(self.params, 'stock_test_period_years'
) and self.params.stock_test_period_years is not None:
period = self.params.stock_test_period_years
test_start_date = DateUtils.add_years(invest_start_date, -period)
test_start_date = DateUtils.to_date_str(test_start_date)
test_data = data.query("date>='{}'".format(test_start_date))
test_count = len(test_data.index) - invest_count
scaled_data, scaler_close = self.get_scaled_data(data, scaler_close)
dataX, dataY, dataX_last, y_date = self.get_dataXY(scaled_data)
data_params = self.split_train_test(dataX, dataY, invest_count,
test_count, y_date)
return data_params, scaler_close, dataX_last