# 加入注意力机制的LSTM 对航空乘客预测

2021/8/21 19:06:22 浏览：

## 2 模型

``````pip install attention
``````

### 2.1 单步预测

``````# 单变量，1---》1

import numpy
import matplotlib.pyplot as plt
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

# 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
from attention import  Attention
model = Sequential()
Attention(name='attention_weight')
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()
``````

``````Train Score: 22.98 RMSE
Test Score: 48.30 RMSE
``````

``````# 预测未来的数据

#测试数据的最后一个数据没有预测,这里补上
finalX = numpy.reshape(test[-1], (1, 1, testX.shape[1]))

#预测得到标准化数据
featruePredict = model.predict(finalX)

#将标准化数据转换为人数
featruePredict = scaler.inverse_transform(featruePredict)

#原始数据是1949-1960年的数据,下一个月是1961年1月份
print('模型预测1961年1月份的国际航班人数是: ',featruePredict)
``````

``````模型预测1961年1月份的国际航班人数是:  [[419.07907]]
``````

### 2.2 多步预测

``````# 单变量，3---》1

import numpy
import matplotlib.pyplot as plt
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

# 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()

Attention(name='attention_weight')

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()
``````

``````Train Score: 28.57 RMSE
Test Score: 66.73 RMSE
``````

``````# 预测未来的数据

#测试数据的最后一个数据没有预测,这里补上
finalX = numpy.reshape(test[-3:], (1, testX.shape[1], 1))
print(finalX)

#预测得到标准化数据
featruePredict = model.predict(finalX)

#将标准化数据转换为人数
featruePredict = scaler.inverse_transform(featruePredict)

#原始数据是1949-1960年的数据,下一个月是1961年1月份
print('模型预测1961年1月份的国际航班人数是: ',featruePredict)
``````

``````模型预测1961年1月份的国际航班人数是:  [[394.95465]]
``````

## 3 总结

• 注意力机制的作用
• 代码中 LSTM后面连接注意力机制的代码
• 不是说加了注意力机制的LSTM网络一定会好于LSTM，具体要看数据、参数和实验环境等条件