univariate.py

from sklearn.preprocessing import MinMaxScaler
data = df.sort_index(ascending=True, axis=0)
new_data = pd.DataFrame(index=range(0,len(df)),columns=['Date', 'Close'])
for i in range(0,len(data)):
    new_data['Date'][i] = data['Date'][i]
    new_data['Close'][i] = data['Close'][i]
new_data.index = new_data.Date
new_data.drop('Date', axis=1, inplace=True)
dataset = new_data.values
scaler = MinMaxScaler(feature_range=(0, 1))
scaled_data = scaler.fit_transform(dataset)
train= scaled_data[:int(df.shape[0]*0.8)]
valid = scaled_data[int(df.shape[0]*0.8):]

x_train,y_train,x_test,y_test = [],[],[],[]
for i in range(60,train.shape[0]):
    x_train.append(train[i-60:i,0])
    y_train.append(train[i,0])

for z in range(60,valid.shape[0]):
    x_test.append(valid[z-60:z,0])
    y_test.append(valid[z,0])

x_train, y_train,x_test,y_test = np.array(x_train), np.array(y_train),np.array(x_test),np.array(y_test)
x_train = np.reshape(x_train, (x_train.shape[0],x_train.shape[1],1))
x_test=np.reshape(x_test,(x_test.shape[0],x_test.shape[1],1))