ARIMA模型，引數含義參考：https://www.cnblogs.com/bradleon/p/6827109.html

from statsmodels.tsa.arima_model import ARIMA
plt.figure(figsize = (15,8))
model = ARIMA(Train_log, order = (2,1,0))  #here q value is zero since it is just AR Model

SARIMAX Model，多元季節性時間序列模型，用於預測與異常診斷，參考部落格：https://blog.csdn.net/weixin_41512727/article/details/82999831

import statsmodels.api as sm
y_hat_avg = valid.copy()
fit1 = sm.tsa.statespace.SARIMAX(Train.Count, order = (2,1,4), seasonal_order =(0,1,1,7)).fit()
y_hat_avg['SARIMA'] = fit1.predict(start="2014-6-25", end="2014-9-25", dynamic=True)

LSTM Model

import numpy as np
from numpy import newaxis
 
from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential

my_model = Sequential()

my_model.add(LSTM(
    input_shape=(None, 1),
    units=50,
    return_sequences=True))


my_model.add(LSTM(100, return_sequences=False))
my_model.add(Dropout(
 
0.5))

my_model.add(Dense(1))
my_model.add(Activation('linear'))

my_model.compile(loss='mse', optimizer='rmsprop')

# Fill in the parameters to fit your model
my_model.fit(
    X_train,
    y_train,
    batch_size=1024,   # Fill this in
    epochs=1,       # Fill this in
    validation_split=0.05)