Python深度学习教程：LSTM时间序列预测小练习—国航乘客数量预测

Python深度学习教程：LSTM时间序列预测小练习—国航乘客数量预测

参考数据：

数据一共两列，左边是日期，右边是乘客数量

对数据做可视化：

import math
import numpy as np 
import pandas as pd 
import matplotlib.pyplot as plt 
from pandas import read_csv 
from keras.models import Sequential 
from keras.layers import Dense 
from keras.layers import LSTM 
from sklearn.preprocessing import MinMaxScaler 
from sklearn.metrics import mean_squared_error 

#load dataset 
dataframe = read_csv('./international-airline-passengers.csv',usecols =[1],header = None,engine = 'python',skipfooter = 3)
dataset = dataframe.values
#将整型变为float
dataset = dataset.astype('float32')
plt.plot(dataset)
plt.show() 

可视化结果：

下面开始进行建模：

完整代码：

import math
import numpy 
import pandas as pd 
import matplotlib.pyplot as plt 
from pandas import read_csv 
from keras.models import Sequential 
from keras.layers import Dense 
from keras.layers import LSTM 
from sklearn.preprocessing import MinMaxScaler 
from sklearn.metrics import mean_squared_error 

def create_dataset(dataset,look_back = 1