final

+import win32com.client
+import pythoncom
+import pandas as pd
+import time
+
+class XASessionEventHandler:
+    login_state = 0
+
+    def OnLogin(self, code, msg):
+        if code == "0000":
+            print("로그인 성공")
+            XASessionEventHandler.login_state = 1
+        else:
+            print("로그인 실패")
+
+class XAQueryEventHandler:
+    query_state = 0
+
+    def OnReceiveData(self, code):
+        XAQueryEventHandler.query_state = 1
+
+# ===================================================================================================================
+instXASession = win32com.client.DispatchWithEvents("XA_Session.XASession", XASessionEventHandler)
+
+with open('account.txt') as f:
+    id, passwd, cert_passwd = f.read().split()
+
+instXASession.ConnectServer("hts.ebestsec.co.kr", 20001)
+instXASession.Login(id, passwd, cert_passwd, 0, 0)
+
+while XASessionEventHandler.login_state == 0:
+   pythoncom.PumpWaitingMessages()
+
+datecut = ["20210526", "20190517", "20170426","20150421","20130409","20110407","20090413","20070404","20050404","20030326","20010316","19900305","19880616","19860926","19850316"]
+res=pd.DataFrame()
+for i in range(0, 14):
+    # ----------------------------------------------------------------------------
+    # T8413
+    # ----------------------------------------------------------------------------
+    instXAQueryT8413 = win32com.client.DispatchWithEvents("XA_DataSet.XAQuery", XAQueryEventHandler)
+    instXAQueryT8413.ResFileName = "C:\\eBEST\\xingAPI\\Res\\t8413.res"
+
+    instXAQueryT8413.SetFieldData("t8413InBlock", "shcode", 0, "207940")
+    instXAQueryT8413.SetFieldData("t8413InBlock", "gubun", 0, "2")
+    instXAQueryT8413.SetFieldData("t8413InBlock", "sdate", 0, datecut[i+1])
+    instXAQueryT8413.SetFieldData("t8413InBlock", "edate", 0, datecut[i])
+    instXAQueryT8413.SetFieldData("t8413InBlock", "comp_yn", 0, "N")
+
+    instXAQueryT8413.Request(0)
+
+    while XAQueryEventHandler.query_state == 0:
+        pythoncom.PumpWaitingMessages()
+
+    count = instXAQueryT8413.GetBlockCount("t8413OutBlock1")
+
+    stockdata=[]
+    datelist=[]
+    for j in range(count):
+        date = instXAQueryT8413.GetFieldData("t8413OutBlock1", "date", j)
+        open = instXAQueryT8413.GetFieldData("t8413OutBlock1", "open", j)
+        high = instXAQueryT8413.GetFieldData("t8413OutBlock1", "high", j)
+        low = instXAQueryT8413.GetFieldData("t8413OutBlock1", "low", j)
+        close = instXAQueryT8413.GetFieldData("t8413OutBlock1", "close", j)
+        vol = instXAQueryT8413.GetFieldData("t8413OutBlock1", "jdiff_vol", j)
+        datelist.append(date)
+        stockdata.append([date, open, high, low, close, vol])
+
+    df = pd.DataFrame(stockdata, columns=['날짜','시가','고가','저가','종가','거래량'], index=datelist)
+    print(df)
+
+    res=res.append(df)
+    XAQueryEventHandler.query_state = 0
+    time.sleep(3)
+
+
+    # instXAQueryT8413 = win32com.client.DispatchWithEvents("XA_DataSet.XAQuery", XAQueryEventHandler)
+    # instXAQueryT8413.ResFileName = "C:\\eBEST\\xingAPI\\Res\\t8413.res"
+
+    # instXAQueryT8413.SetFieldData("t8413InBlock", "shcode", 0, "005930")
+    # instXAQueryT8413.SetFieldData("t8413InBlock", "gubun", 0, "2")
+    # instXAQueryT8413.SetFieldData("t8413InBlock", "sdate", 0, "20190520")
+    # instXAQueryT8413.SetFieldData("t8413InBlock", "edate", 0, "20210526")
+    # instXAQueryT8413.SetFieldData("t8413InBlock", "comp_yn", 0, "N")
+
+    # instXAQueryT8413.Request(0)
+
+    # while XAQueryEventHandler.query_state == 0:
+    #     pythoncom.PumpWaitingMessages()
+
+    # count = instXAQueryT8413.GetBlockCount("t8413OutBlock1")
+
+    # stockdata.clear()
+    # for i in range(count):
+    #     date = instXAQueryT8413.GetFieldData("t8413OutBlock1", "date", i)
+    #     open = instXAQueryT8413.GetFieldData("t8413OutBlock1", "open", i)
+    #     high = instXAQueryT8413.GetFieldData("t8413OutBlock1", "high", i)
+    #     low = instXAQueryT8413.GetFieldData("t8413OutBlock1", "low", i)
+    #     close = instXAQueryT8413.GetFieldData("t8413OutBlock1", "close", i)
+    #     vol = instXAQueryT8413.GetFieldData("t8413OutBlock1", "jdiff_vol", i)
+    #     stockdata.append([date, open, high, low, close, vol])
+
+    # df2 = df.append(pd.DataFrame(stockdata, columns=['날짜','시가','고가','저가','종가','거래량']))
+
+    # print(df2)
+
+
+res.drop_duplicates()
+print(res)
+res.to_csv('C:/Users/myung/OneDrive/바탕 화면/삼성바이오로직스.csv', sep=',', na_rep='NaN',index=False)
\ No newline at end of file

+from google.colab import drive
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.preprocessing import MinMaxScaler
+import numpy as np
+from keras.models import Sequential
+from keras.layers import Dense
+from keras.callbacks import EarlyStopping, ModelCheckpoint
+from keras.layers import LSTM
+
+drive.mount('/content/drive')
+df_price = pd.read_csv('/content/drive/My Drive/Colab Notebooks/삼성바이오로직스.csv', encoding='cp949')
+pd.to_datetime(df_price['날짜'], format='%Y%m%d')
+
+df_price['날짜'] = pd.to_datetime(df_price['날짜'], format='%Y%m%d')
+df_price['연도'] =df_price['날짜'].dt.year
+df_price['월'] =df_price['날짜'].dt.month
+df_price['일'] =df_price['날짜'].dt.day
+
+df = df_price.loc[df_price['연도']>=1990]
+scaler = MinMaxScaler()
+scale_cols = ['시가', '고가', '저가', '종가', '거래량']
+
+df_scaled = scaler.fit_transform(df[scale_cols])
+df_scaled = pd.DataFrame(df_scaled)
+df_scaled.columns = scale_cols
+
+
+TEST_SIZE = 200
+window_size=20
+
+def make_dataset(data, label, window_size=20):
+    feature_list = []
+    label_list = []
+    for i in range(len(data) - window_size):
+        feature_list.append(np.array(data.iloc[i:i+window_size]))
+        label_list.append(np.array(label.iloc[i+window_size]))
+    return np.array(feature_list), np.array(label_list)
+
+def main():
+  train = df_scaled[:-TEST_SIZE]
+  test = df_scaled[-TEST_SIZE:]
+  feature_cols = ['시가', '고가', '저가', '거래량']
+  label_cols = ['종가']
+
+  train_feature = train[feature_cols]
+  train_label = train[label_cols]
+
+  # train dataset
+  train_feature, train_label = make_dataset(train_feature, train_label, 20)
+
+  # train, validation set 생성
+  from sklearn.model_selection import train_test_split
+  x_train, x_valid, y_train, y_valid = train_test_split(train_feature, train_label, test_size=0.2)
+
+  x_train.shape, x_valid.shape
+
+  test_feature = test[feature_cols]
+  test_label = test[label_cols]
+
+  # test dataset (실제 예측 해볼 데이터)
+  test_feature, test_label = make_dataset(test_feature, test_label, 20)
+  
+  test_feature.shape, test_label.shape
+
+
+  model = Sequential()
+  model.add(LSTM(16, 
+                input_shape=(train_feature.shape[1], train_feature.shape[2]), 
+                activation='relu', 
+                return_sequences=False)
+            )
+  model.add(Dense(1))
+  
+  model.compile(loss='mean_squared_error', optimizer='adam')
+  early_stop = EarlyStopping(monitor='val_loss', patience=10)
+  filename = '/content/drive/My Drive/Colab Notebooks/tmp_samba.h5'
+  checkpoint = ModelCheckpoint(filename, monitor='val_loss', verbose=1, save_best_only=True, mode='auto')
+
+  # history = model.fit(x_train, y_train, 
+  #                     epochs=200, 
+  #                     batch_size=16,
+  #                     validation_data=(x_valid, y_valid), 
+  #                     callbacks=[early_stop, checkpoint])
+  
+  # weight 로딩
+  model.load_weights(filename)
+
+  model.summary()
+  # 예측
+  pred = model.predict(test_feature)
+  plt.figure(figsize=(12, 9))
+  plt.plot(test_label, label='actual')
+  plt.plot(pred, label='prediction')
+  plt.legend()
+  plt.show()
+
+if __name__ == "__main__":
+  main()