多层 LSTM 对航空乘客预测

前言

1.LSTM 航空乘客预测单步预测的两种情况。 简单运用LSTM 模型进行预测分析。
2.加入注意力机制的LSTM 对航空乘客预测采用了目前市面上比较流行的注意力机制，将两者进行结合预测。

本文采用的多层LSTM网络对其进行预测。

我喜欢直接代码+ 结果展示
先代码可以跑通，才值得深入研究每个部分之间的关系；进而改造成自己可用的数据。

1 数据集

链接: https://pan.baidu.com/s/1jv7A2JvIhA6oqvtYnYh9vQ
提取码: m5j5

2 模型

2.1 单步预测 1—》1

• 代码

# 单变量，1---》1 

import numpy
import matplotlib.pyplot as plt
from pandas import read_csv
import math
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
#matplotlib inline

# load the dataset
dataframe = read_csv('airline-passengers.csv', usecols=[1], engine='python')
# print(dataframe)
print("数据集的长度：",len(dataframe))
dataset = dataframe.values
# 将整型变为float
dataset = dataset.astype('float32')

plt.plot(dataset)
plt.show()


# X是给定时间(t)的乘客人数，Y是下一次(t + 1)的乘客人数。
# 将值数组转换为数据集矩阵,look_back是步长。
def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back), 0]
        # X按照顺序取值
        dataX.append(a)
        # Y向后移动一位取值
        dataY.append(dataset[i + look_back, 0])
    return numpy.array(dataX), numpy.array(dataY)

# fix random seed for reproducibility
numpy.random.seed(7)


# 数据缩放
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)


# 将数据拆分成训练和测试，2/3作为训练数据
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
print("原始训练集的长度：",train_size)
print("原始测试集的长度：",test_size)



# 构建监督学习型数据
look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back) 
print("转为监督学习，训练集数据长度：", len(trainX))
# print(trainX,trainY)
print("转为监督学习，测试集数据长度：",len(testX))
# print(testX, testY )
# 数据重构为3D [samples, time steps, features]
trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))
print('构造得到模型的输入数据(训练数据已有标签trainY): ',trainX.shape,testX.shape)

# create and fit the LSTM network
model = Sequential()
model.add(LSTM(4, input_shape=(1, look_back), return_sequences=True))
model.add(LSTM(4))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)

# 打印模型
model.summary()

# 开始预测
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

# 逆缩放预测值
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])

# 计算误差
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))


# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict

# shift test predictions for plotting
testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict

# plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()

• 结果展示

Train Score: 22.70 RMSE
Test Score: 49.15 RMSE

2.2 单步预测 3—》1

• 代码

# 单变量，3---》1 

import numpy
import matplotlib.pyplot as plt
from pandas import read_csv
import math
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
#matplotlib inline

# load the dataset
dataframe = read_csv('airline-passengers.csv', usecols=[1], engine='python')
# print(dataframe)
print("数据集的长度：",len(dataframe))
dataset = dataframe.values
# 将整型变为float
dataset = dataset.astype('float32')

plt.plot(dataset)
plt.show()


# X是给定时间(t)的乘客人数，Y是下一次(t + 1)的乘客人数。
# 将值数组转换为数据集矩阵,look_back是步长。
def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back), 0]
        # X按照顺序取值
        dataX.append(a)
        # Y向后移动一位取值
        dataY.append(dataset[i + look_back, 0])
    return numpy.array(dataX), numpy.array(dataY)

# fix random seed for reproducibility
numpy.random.seed(7)


# 数据缩放
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)


# 将数据拆分成训练和测试，2/3作为训练数据
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
print("原始训练集的长度：",train_size)
print("原始测试集的长度：",test_size)



# 构建监督学习型数据
look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back) 
print("转为监督学习，训练集数据长度：", len(trainX))
# print(trainX,trainY)
print("转为监督学习，测试集数据长度：",len(testX))
# print(testX, testY )
# 数据重构为3D [samples, time steps, features]
# trainX = numpy.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
# testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

trainX = numpy.reshape(trainX, (trainX.shape[0],  trainX.shape[1],1))
testX = numpy.reshape(testX, (testX.shape[0], testX.shape[1], 1))

print('构造得到模型的输入数据(训练数据已有标签trainY): ',trainX.shape,testX.shape)

# create and fit the LSTM network
model = Sequential()
# model.add(LSTM(4, input_shape=(1, look_back)))
 # 与上面的重构格式对应，要改都改，才能跑通代码
model.add(LSTM(4, input_shape=(look_back,1), return_sequences=True))
model.add(LSTM(4))

model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)

# 打印模型
model.summary()

# 开始预测
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

# 逆缩放预测值
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])

# 计算误差
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))


# shift train predictions for plotting
trainPredictPlot = numpy.empty_like(dataset)
trainPredictPlot[:, :] = numpy.nan
trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict

# shift test predictions for plotting
testPredictPlot = numpy.empty_like(dataset)
testPredictPlot[:, :] = numpy.nan
testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict

# plot baseline and predictions
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.show()

• 结果展示

Train Score: 31.57 RMSE
Test Score: 83.86 RMSE

3 总结

• 多层LSTM，就是多加几层LSTM网络，LSTM这里return_sequences=True 修改一下，后面就可以加LSTM层了
• 多层网络的结果也不一定有单层的好，具体原因就要涉及到很多复杂计算，这里不讨论