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 top10_model(train_model='rnn'):
"""상위10개를 가지고 투자하는 모델"""
corp = Corp()
corps = corp.get_eval_corps()
params = GlobalParams(train_model=train_model)
params.invest_type = 'top10'
params.result_file_name = "top10_result"
invests = LearningNMockTop10(params)
invests.train_n_invests_top10(corps)
def train_all_corps(type='ALL_CORPS', start_no=1):
"""하나의 세션으로 모든 회사를 학습시킨다. """
corp = Corp(type)
corps = corp.get_corps()
params = GlobalParams(type)
params.result_file_name = "training_" + type.lower() + "_result"
invests = LearningNMockInvestment(params)
#invests.train_n_invests(corps, start_no)
invests.train_n_invests_for_all(corps)
def train_codes(corp_codes, train_model='rnn'):
"""하나의 세션으로 학습시키는 기본 모델 """
corp = Corp(type)
corps = corp.get_corps_for_codes(corp_codes)
params = GlobalParams(train_model=train_model)
invests = LearningNMockInvestment(params)
invests.train_n_invests(corps)
def train_one(corp_name='카카오', train_model='rnn'):
"""하나의 세션으로 학습시키는 기본 모델 """
corp = Corp(type)
corps = corp.get_corp(corp_name)
params = GlobalParams(train_model=train_model)
invests = LearningNMockInvestment(params)
invests.train_n_invests(corps)
def train(type: str = 'EACH',
start_no: int = 1,
train_model: str = 'rnn',
invest_only: bool = False) -> None:
"""하나의 세션으로 학습시키는 기본 모델 """
corps = get_corps(type)
params = GlobalParams(type, train_model=train_model)
invests = LearningNMockInvestment(params)
invests.train_n_invests(corps, start_no, invest_only)
def test_parameters(self):
expected_parameters = ('base_dir',)
parameters = GlobalParams.get_param_names()
all_parameters_present = all(
map(lambda param: param in parameters, expected_parameters)
)
equal_length = len(expected_parameters) == len(parameters)
assert equal_length and all_parameters_present
def main(corp_names: list = None,
train_model: str = 'rnn',
invest_only: bool = False) -> None:
if corp_names is None:
corp_names = ["에이치엘비", "동일철강", "키다리스튜디오"]
params = GlobalParams('FORCAST', train_model=train_model)
invests = LearningNMockInvestment(params)
invests.train_n_invests_for_name(corp_names, invest_only)
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_n_invest_twins(self, corp_code, corp_name, no) -> list:
"""겨별 세션과 통합세션에서 예측한 값의 평균을 예측값으로 한다."""
stocks = Stocks(self.params)
trains_data = TrainsData(self.params)
learning = Learning(self.params)
params_all = GlobalParams('ALL_CORPS')
learning_all = Learning(params_all)
invest = MockInvestment(self.params)
stock_data = stocks.get_stock_data(corp_code)
data_params, scaler_close, dataX_last = trains_data.get_train_test(
stock_data)
tp = learning.learn(corp_code, corp_name, data_params)
tp_all = learning_all.learn(corp_code, corp_name, data_params)
ip = invest.invest_n_all(corp_code, dataX_last, data_params,
params_all, scaler_close)
tp.test_rmse = np.mean([tp.test_rmse, tp_all.test_rmse])
tp.train_count = tp.train_count + tp_all.train_count
return self.get_train_invest_result(no, corp_code, corp_name,
stock_data, tp, ip)
def output(self):
path = entry_id_2_output_path(self.entry_id, GlobalParams().base_dir)
return luigi.LocalTarget(path)
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 get_corps(type='EACH'):
params = GlobalParams(type)
corp = Corp(params)
return corp.get_eval_corps_auto()
def date_2_output_path (date: datetime.datetime) -> str:
return path.join(GlobalParams().base_dir,
'diaries',
f"boe_diary_processed_{date.strftime('%d_%m_%Y')}.json")
self.params,
'remove_stock_days') and self.params.remove_stock_days > 0:
stock_data = stock_data[:-self.params.remove_stock_days]
return stock_data
def update_stocks_data(self):
files = glob.glob(self.DIR_STOCKS + "/*.txt")
for file_path in files:
file_name = os.path.basename(file_path)
stock_data = pd.read_csv(file_path)
stock_data = stock_data.dropna()
stock_data = stock_data[:-1]
date_last = stock_data.tail(1)['date'].to_string(index=False)
date_next = DateUtils.to_date(date_last) + datetime.timedelta(
days=1)
date_next = date_next.strftime("%Y.%m.%d")
comp_code = file_name.replace(".txt", "")
new_data = self.get_stock_web_data(comp_code, date_next)
if len(new_data) > 0:
stock_data = stock_data.append(new_data, ignore_index=True)
stock_data = stock_data.dropna()
stock_data.to_csv(file_path, index=False)
if __name__ == '__main__':
params = GlobalParams()
stocks = Stocks(params)
#stocks.update_stocks_data()
df = stocks.get_stock_daum_data('005930')
#df = stocks.get_stock_data('005930')
print(len(df))
def forcasts(corps_n_date: list) -> None:
params = GlobalParams('FORCAST')
invests = LearningNMockInvestment(params)
invests.forcasts(corps_n_date)