def __init__(self): stock_code = '005930' start_date = '2010-03-01' end_date = '2015-03-04' chart_data = data_manager.load_chart_data( os.path.join(settings.BASE_DIR, 'data/chart_data/{}.csv'.format(stock_code))) prep_data = data_manager.preprocess(chart_data) training_data = data_manager.build_training_data(prep_data) # 기간 필터링 training_data = training_data[(training_data['date'] >= self.start_date) & (training_data['date'] <= self.end_date)] training_data = training_data.dropna() # 차트 데이터 분리 features_chart_data = ['date', 'open', 'high', 'low', 'close', 'volume'] chart_data = training_data[features_chart_data] chart_data['data']= pd.to_datetime(chart_data.date).astype(np.int64)/1000000 data = torch.from_numpy(chart_data.values) self.data = torch.stack([data[:,0],data[:,4],data[:,5]],dim=1).float() self.data = self.data - self.data.mean(dim=0) self.data = self.data/self.data.std(0) self.count_max= self.data.size(0)
def _pre_process(self): chart_data = data_manager.load_chart_data('test.csv') print("chart_data:", chart_data.head()) prep_data = data_manager.preprocess(chart_data) print("prep_data:", prep_data) training_data = data_manager.build_training_data(prep_data) print("training_data:", training_data)
def reset(self): stock_code = np.random.choice([ '005930', '000270', '000660', '005380', '005490', '009240', '009540' ]) self.prev_action = 0 self.count = 0 self.balance = self.init_money self.num_stocks = 0 self.sum_action = 0 chart_data = data_manager.load_chart_data( os.path.join('./', 'data/chart_data/{}.csv'.format(stock_code))) prep_data = data_manager.preprocess(chart_data) training_data = data_manager.build_training_data(prep_data) # 기간 필터링 start = random.randint(self.view_seq, (len(training_data) - self.count_max - 200)) training_data = training_data[start - self.view_seq:start + self.count_max + 200] # training_data = training_data[(training_data['date'] >= self.start_date) & # (training_data['date'] <= self.end_date)] training_data = training_data.dropna() # 차트 데이터 분리 features_chart_data = [ 'date', 'open', 'high', 'low', 'close', 'volume' ] self.chart_data = training_data[features_chart_data] self.chart_data['date'] = pd.to_datetime(self.chart_data.date).astype( np.int64) / 1e12 # 학습 데이터 분리 features_training_data = [ 'open_lastclose_ratio', 'high_close_ratio', 'low_close_ratio', 'close_lastclose_ratio', 'volume_lastvolume_ratio', 'close_ma5_ratio', 'volume_ma5_ratio', 'close_ma10_ratio', 'volume_ma10_ratio', 'close_ma20_ratio', 'volume_ma20_ratio', 'close_ma60_ratio', 'volume_ma60_ratio', 'close_ma120_ratio', 'volume_ma120_ratio' ] training_data = training_data[features_training_data] self.data = torch.from_numpy(training_data.values).float() state = self.data[self.count:self.count + self.view_seq].view(1, -1) state = torch.cat( [state, torch.Tensor([self.sum_action]).view(1, -1)], dim=1) return state pass
def __init__(self, stock_list, start, end): self.stock_list = stock_list self.start_date = start self.end_date = end data_base = [] for stock_code in self.stock_list: # 주식 데이터 준비 chart_data = data_manager.load_chart_data( os.path.join(settings.BASE_DIR, 'data/chart_data/{}.csv'.format(stock_code))) prep_data = data_manager.preprocess(chart_data) training_data = data_manager.build_training_data(prep_data) # 기간 필터링 training_data = training_data[ (training_data['date'] >= self.start_date) & (training_data['date'] <= self.end_date)] training_data = training_data.dropna() # 차트 데이터 분리 features_chart_data = [ 'date', 'open', 'high', 'low', 'close', 'volume' ] chart_data = training_data[features_chart_data] chart_data['date'] = pd.to_datetime(chart_data.date).values.astype( np.int64) #차트 index축을 date 로변경 # chart_data.set_index('date', inplace=True) chart_data = torch.from_numpy(chart_data.values) data_base.append(chart_data) data_base = torch.cat(data_base, dim=1).float() scaled_data = (data_base - data_base.mean(dim=0)) self.scaled_data = scaled_data / scaled_data.std() self.max_count = self.scaled_data.size(0)
log_dir = os.path.join(settings.BASE_DIR, 'logs/%s' % stock_code) timestr = settings.get_time_str() file_handler = logging.FileHandler(filename=os.path.join( log_dir, "%s_%s.log" % (stock_code, timestr)), encoding='utf-8') stream_handler = logging.StreamHandler() file_handler.setLevel(logging.DEBUG) stream_handler.setLevel(logging.INFO) logging.basicConfig(format="%(message)s", handlers=[file_handler, stream_handler], level=logging.DEBUG) # 주식 데이터 준비 chart_data = data_manager.load_chart_data( os.path.join(settings.BASE_DIR, 'data/chart_data/{}.csv'.format(stock_code))) prep_data = data_manager.preprocess(chart_data) training_data = data_manager.build_training_data(prep_data) # 기간 필터링 training_data = training_data[(training_data['date'] >= '2018-01-01') & (training_data['date'] <= '2018-01-31')] training_data = training_data.dropna() # 차트 데이터 분리 features_chart_data = ['date', 'open', 'high', 'low', 'close', 'volume'] chart_data = training_data[features_chart_data] # 학습 데이터 분리 features_training_data = [ 'open_lastclose_ratio', 'high_close_ratio', 'low_close_ratio', 'close_lastclose_ratio', 'volume_lastvolume_ratio', 'close_ma5_ratio', 'volume_ma5_ratio',
# os.makedirs('logs/%s' % stock_code) #file_handler = logging.FileHandler(filename=os.path.join( # log_dir, "%s_%s.log" % (stock_code, timestr)), encoding='utf-8') #stream_handler = logging.StreamHandler() #file_handler.setLevel(logging.DEBUG) #stream_handler.setLevel(logging.INFO) #logging.basicConfig(format="%(message)s", # handlers=[file_handler, stream_handler], level=logging.DEBUG) # 주식 데이터 준비 chart_data = data_manager.load_chart_data( os.path.join(settings.BASE_DIR, 'data/chart_data/{}.csv'.format(stock_code))) #prep_data = data_manager.preprocess(chart_data) #training_data = data_manager.build_training_data(prep_data) training_data = data_manager.build_training_data(chart_data) # 기간 필터링 training_data = training_data[(training_data['date'] >= '2013-12-27') & (training_data['date'] <= '2019-01-03')] training_data = training_data.dropna() # 차트 데이터 분리 features_chart_data = ['date', 'open', 'high', 'low', 'close', 'volume'] chart_data = training_data[features_chart_data] # 학습 데이터 분리 features_training_data = [ 'high_low_ratio', 'open_close_ratio', 'high_open_ratio',
def learnFunc(self): if self.code is None or self.df is None: return self.change_value.emit(ZERO) # 데이터 전처리 code = self.code chart_data = self.df prep_data = data_manager.preprocess(chart_data) training_data = data_manager.build_training_data(prep_data) training_data = training_data.dropna() # 차트데이터 분리 feature_chart_data = ['date', 'open', 'high', 'low', 'close', 'volume'] chart_data = training_data[feature_chart_data] # emit self.change_value.emit(TWENTY_FIVE) # 학습데이터 분리 feature_chart_data = [ 'open_lastclose_ratio', 'high_close_ratio', 'low_close_ratio', 'close_lastclose_ratio', 'volume_lastvolume_ratio', 'close_ma5_ratio', 'volume_ma5_ratio', 'close_ma10_ratio', 'volume_ma10_ratio', 'close_ma20_ratio', 'volume_ma20_ratio', 'close_ma60_ratio', 'volume_ma60_ratio', 'close_ma120_ratio', 'volume_ma120_ratio', ] training_data = training_data[feature_chart_data] # 정책 신경망을 파일로 저장 self.createFolder('model') mdir = os.path.join(settings.BASE_DIR, 'model') self.createFolder(os.path.join(mdir, code)) model_dir = os.path.join(mdir, code) model_path = os.path.join(model_dir, 'model%s.h5' % code) # model_path 경로가 없으면 학습모델을 해당 dir에 만들어서 학습 # model_path가 있으면 해당 모델 선택 후 예측 print(model_path) # emit self.change_value.emit(FIFTY) if not os.path.isfile(model_path): start_time = time.time() policy_learner = PolicyLearner(stock_code=code, chart_data=chart_data, training_data=training_data, fig=self.fig, canvas=self.canvas, min_trading_unit=1, max_trading_unit=2, delayed_reward_threshold=0.2, lr=0.001) policy_learner.fit(balance=10000000, num_epoches=200, discount_factor=0, start_epsilon=0.5) end_time = time.time() policy_learner.policy_network.save_model(model_path) print("LearningTime: {} sec".format(end_time - start_time)) else: start_time = time.time() policy_learner = PolicyLearner(stock_code=code, chart_data=chart_data, training_data=training_data, fig=self.fig, canvas=self.canvas, min_trading_unit=1, max_trading_unit=2) end_time = time.time() print("LearningTime: {} sec".format(end_time - start_time)) policy_learner.trade(balance=1000000, model_path=os.path.join( model_dir, 'model%s.h5' % (code))) # emit self.change_value.emit(A_HUNDRED)
encoding='utf-8') stream_handler = logging.StreamHandler() file_handler.setLevel(logging.DEBUG) stream_handler.setLevel(logging.INFO) logging.basicConfig(format="%(message)s", handlers=[file_handler, stream_handler], level=logging.DEBUG) # 강화학습에 필요한 주식 데이터 준비 # 1) csv 파일에서 데이터 불러오기 # chart_data = data_manager.load_chart_data_fromCSV(os.path.join(settings.BASE_DIR, 'data/chart_data/{}.csv'.format(stock_code))) # 2) database에서 데이터 불러오기 chart_data = data_manager.load_chart_data_fromDB(stock_code) prep_data = data_manager.preprocess( chart_data) # 불러온 차트데이터 전처리하여 학습 데이터를 만들 준비 training_data = data_manager.build_training_data( prep_data) # 학습 데이터에 포함될 열들을 추가 # 이 training_data는 차트 데이터의 열들, 전처리에서 추가된 열들, 학습 데이터의 열들이 모두 포함된 데이터이다. # 기간 필터링 training_data = training_data[(training_data['date'] >= '2017-01-01') & (training_data['date'] <= '2017-12-31')] training_data = training_data.dropna() # 데이터를 강화학습에 필요한 차트 데이터와 학습 데이터로 분리하기 --> 여러 feature를 가진 training_data는 필요한 부분들(DOHLCV의 차트 데이터와 15개의 feature를 가진 학습 데이터)로 떼어낸다. # 차트 데이터 분리 features_chart_data = ['date', 'open', 'high', 'low', 'close', 'volume'] chart_data = training_data[features_chart_data] # 학습 데이터 분리 features_training_data = [ 'open_lastclose_ratio', 'high_close_ratio', 'low_close_ratio',
def __init__(self): stock_code='BTCUSDT' global timestr #global 함수로 불러와 바로 사용 model_ver=timestr self.dataclose = self.datas[0].close log_dir = os.path.join(settings.BASE_DIR, 'logs/%s' % stock_code) timestr = settings.get_time_str() if not os.path.exists('logs/%s' % stock_code): os.makedirs('logs/%s' % stock_code) file_handler = logging.FileHandler(filename=os.path.join( log_dir, "%s_%s.log" % (stock_code, timestr)), encoding='utf-8') stream_handler = logging.StreamHandler() file_handler.setLevel(logging.DEBUG) stream_handler.setLevel(logging.INFO) logging.basicConfig(format="%(message)s", handlers=[file_handler, stream_handler], level=logging.DEBUG) chart_data = data_manager.load_chart_data( os.path.join(settings.BASE_DIR, '{}'.format(stock_code))) prep_data = data_manager.preprocess(chart_data) training_data = data_manager.build_training_data(prep_data) training_data = training_data.loc['2018-07-01 01:00:00':] features_chart_data = ['o_t', 'open', 'high', 'low', 'close', 'volume'] chart_data = training_data[features_chart_data] features_training_data = [ 'high_close_ratio', 'low_close_ratio', 'close_lastclose_ratio', 'volume_lastvolume_ratio', 'close_ma5_ratio', 'volume_ma5_ratio', 'close_ma10_ratio', 'volume_ma10_ratio', 'close_ma20_ratio', 'volume_ma20_ratio', 'close_ma60_ratio', 'volume_ma60_ratio', 'close_ma120_ratio', 'volume_ma120_ratio', 'ema12','ema26','dn','mavg','up','pctB','macd','signal','cci' ] training_data = training_data[features_training_data] #print (training_data[:3]) training_data = training_data.dropna(axis=1) chart_data=chart_data.dropna(axis=1) #chart_data = chart_data.loc[:1530352800000] #training_data = training_data.loc[:1530352800000] delayed_reward_threshold=.001 lr=0.1 self.TRADING_TAX =0 self.TRADING_CHARGE=0 self.stock_code = stock_code self.chart_data = chart_data self.environment = Environment(chart_data) self.agent = Agent(self.environment, delayed_reward_threshold=delayed_reward_threshold) self.training_data = training_data self.sample = None self.pvdata=[] self.training_data_idx = -1 self.num_features = self.training_data.shape[1] #+ self.agent.STATE_DIM self.policy_network = PolicyNetwork( input_dim=self.num_features, output_dim=self.agent.NUM_ACTIONS, lr=lr) model_path=os.path.join(settings.BASE_DIR, 'models/{}/model_{}.h5'.format(stock_code,model_ver)) self.policy_network.load_model(model_path=model_path) self.agent.set_balance(self.broker.getcash()) self.epsilon=0 self.num_stocks=0 df=pd.read_csv('out.csv') self.stopit=df.loc[7692]['c_p'] #2903 4135 7692