def trains(self, corps:pd.DataFrame=None)->(pd.DataFrame, pd.DataFrame):
if corps is None:
corp = Corp(self._global_params)
corps = corp.get_eval_corps_auto()
no = 1
invest_date = self._global_params.invest_start_date + "~" + self._global_params.invest_end_date
results = []
info_data = []
for index, corp_data in corps.iterrows():
corp_code = corp_data['종목코드']
corp_name = corp_data['회사명']
invest_value, index_value, infos = self.train(corp_code=corp_code, corp_name=corp_name)
result = [no, corp_code, corp_name, invest_value, index_value, invest_date]
results.append(result)
info_data.append(infos)
print(result)
# if no % 10 == 0:
# df_results = pd.DataFrame(results, columns=self.RESULT_COLUMNS)
# DataUtils.save_excel(df_results, self._get_result_file_path())
no += 1
df_results = pd.DataFrame(results, columns=self.RESULT_COLUMNS)
DataUtils.save_excel(df_results, self._get_result_file_path())
chart_data = None
try:
visualizer = InvestVisualizer(self._global_params)
chart_data = visualizer.draw_invest_4reinforcement(info_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)
return df_results, chart_data
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_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 top10_model():
corp = Corp()
corps = corp.get_eval_corps()
params = TrainParams()
params.invest_type = 'top10'
params.result_file_name = "top10_result"
invests = LearningNMockTop10(params)
invests.let_train_invests_top10(corps)
def train_all_corps(type='ALL_CORPS', start_no=1):
"""하나의 세션으로 모든 회사를 학습시킨다. """
corp = Corp()
corps = corp.get_corps()
params = TrainParams(type)
params.result_file_name = "training_" + type.lower() + "_result"
invests = LearningNMockInvestment(params)
invests.let_train_invests(corps, start_no)
def twins(start_no=1):
corp = Corp()
corps = corp.get_eval_corps()
params = TrainParams("EACH")
params.result_file_name = 'twins_result'
invests = LearningNMockInvestment(params)
invests.let_train_invests_twins(corps, start_no)
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_months(self, start:str='2018.01', end:str='2018.11', invest_money:float=100000000)->None:
train_model = self._global_params.train_model
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 = []
for i in range(between + 1):
# params.remove_session_file = True
before_month_start = DateUtils.to_month_str(start_month, i - self._global_params.mock_period_months)
before_month_end = DateUtils.to_month_str(start_month, i - 1)
self._global_params.invest_start_date = before_month_start + '.01'
self._global_params.invest_end_date = before_month_end + '.31'
self._global_params.result_file_name = "MOCK_" + before_month_start + "-" + before_month_end
self._global_params.invest_money = MOCK_MONEY
corp = Corp(self._global_params)
corps = corp.get_eval_corps_auto(self._global_params.invest_end_date)
self._env.set_params(params=self._global_params)
before_result, _ = self.trains(corps)
now_month = DateUtils.to_month_str(start_month, i)
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.index)
self._global_params.invest_start_date = now_month + '.01'
self._global_params.invest_end_date = now_month + '.31'
self._global_params.result_file_name = "INVEST_" + now_month
self._global_params.invest_money = invest_money / corp10_len
self._env.set_params(params=self._global_params)
now_result, invest_chart_data = self.trains(corp10)
chart_data.append(invest_chart_data)
invest_money = now_result['invest_result'].sum()
result = [now_month, self._global_params.invest_money * corp10_len, invest_money]
invest_months_result.append(result)
print(result)
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', 'reinforcement', train_model, self._global_params.ensemble_type, save_file_name)
else:
save_file_path = os.path.join('result', 'reinforcement', train_model, save_file_name)
DataUtils.save_excel(df_imr, save_file_path)
if len(chart_data) > 1:
visualizer = InvestVisualizer(self._global_params)
visualizer.draw_invest_months(chart_data, start, end)
print()
def get_kospi_kosdaq(self, market):
invest_start_date = self.params.invest_start_date
invest_end_date = self.params.invest_end_date
corp = Corp(self.params)
if market == 'KOSPI':
data = corp.get_kospi()
elif market == 'KOSDAQ':
data = corp.get_kosdaq()
else:
data = pd.DataFrame()
return data.query("date>='{}' & date<='{}'".format(invest_start_date, invest_end_date))
def let_train_invests_for_name(self, corp_names):
"""회사이름으로 검색하여 학습시킴 """
corp = Corp()
comp_rmses = []
no = 1
for corp_name in corp_names:
corp_code = corp.get_corp_code(corp_name)
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_excel(df_comp_rmses, self.get_result_file_path())
def get_corps(type='EACH'):
params = GlobalParams(type)
corp = Corp(params)
return corp.get_eval_corps_auto()
def train_codes(self, corp_codes, train_model='rnn'):
"""하나의 세션으로 학습시키는 기본 모델 """
corp = Corp()
corps = corp.get_corps_for_codes(corp_codes)
self.trains(corps)
verbose_eval=10)
print('Plotting metrics recorded during training...')
ax = lgb.plot_metric(evals_result, metric='l1')
plt.show()
print('Plotting feature importances...')
ax = lgb.plot_importance(gbm, max_num_features=10)
plt.show()
print('Plotting 84th tree...') # one tree use categorical feature to split
ax = lgb.plot_tree(gbm, tree_index=83, figsize=(20, 8), show_info=['split_gain'])
plt.show()
print('Plotting 84th tree with graphviz...')
graph = lgb.create_tree_digraph(gbm, tree_index=83, name='Tree84')
graph.render(view=True)
if __name__ == '__main__':
corp_name = "카카오"
corp = Corp()
corp_code = corp.get_corp_code(corp_name)
learning = LearningPlainModels('light_gbm')
learning.train(corp_code, corp_name, 1)
# from sklearn.datasets import load_iris
#
# iris = load_iris()
# X = iris.data[:, [2, 3]]
# y = iris.target
# print(X, y)
def draw_invest_seaborn(self, pridects_data:pd.DataFrame, dir:str, title:str, start:str=None, end:str=None)->None:
file_path = self.get_file_path(dir, title, 'png', start, end)
pridects_data = pridects_data.copy()
pridects_data['date'] = pd.to_datetime(pridects_data['date'], format='%Y.%m.%d')
pridects_data.set_index('date', inplace=True)
plt = self.main.get_plt()
fig, ax = plt.subplots(figsize=self.main.FIG_SIZE)
sns.lineplot(data=pridects_data).set_title(title)
ax.xaxis.set_major_locator(mdates.AutoDateLocator())
ax.xaxis.set_major_formatter(mdates.DateFormatter('%Y.%m.%d'))
ax.set(xlabel='Date', ylabel='Margin(%)')
#fig.autofmt_xdate()
plt.grid(color='k', linestyle='dotted', linewidth=1, alpha=0.4)
fig.savefig(file_path)
plt.close()
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)
if __name__ == '__main__':
params = GlobalParams()
corp = Corp(params)
kospi = corp.get_kospi()
kospi = kospi.query("date>='{}' & date<='{}'".format(params.invest_start_date, params.invest_end_date))
print(kospi[0:1]['close'].values[0])
def get_corps():
corp = Corp()
return corp.get_eval_corps()
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(self):
corp = Corp()
return corp.get_corps3()