基于keras多层LSTM实现（二）

数据：链接：https://pan.baidu.com/s/1BdAY5r5AgFVkKOtDDaJipg 
提取码：2tzp

题目： 国际航空公司的客流量的预测

# LSTM for international airline passengers problem with time step regression framing
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
from keras.layers.core import Dense, Activation, Dropout

# convert an array of values into a dataset matrix
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]
		dataX.append(a)
		dataY.append(dataset[i + look_back, 0])
	return numpy.array(dataX), numpy.array(dataY)

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

# 1.加载数据
dataframe = read_csv('airline-passengers.csv', usecols=[1], engine='python')
dataset = dataframe.values
dataset = dataset.astype('float32')

# 2.数据的标准化处理
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

# 3.数据的切分
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size, :], dataset[train_size:len(dataset), :]
# reshape into X=t and Y=t+1
look_back = 3
print("train:",train)

trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# reshape input to be [samples, time steps, features]
trainX = numpy.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = numpy.reshape(testX, (testX.shape[0], testX.shape[1], 1))

# 4.模型的训练   （只是建立了一个2层的LSTM模型）
# model = Sequential()
# model.add(LSTM(4, input_shape=(look_back, 1)))
# model.add(Dense(1))
# model.compile(loss='mean_squared_error', optimizer='adam')
# model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)

layers=[1, 50, 100, 1]
model = Sequential()
model.add(LSTM(input_dim=layers[0], output_dim=layers[1], return_sequences=True))
model.add(Dropout(0.2))  # 被遗忘的比例

model.add(LSTM(layers[2], return_sequences=False))
model.add(Dropout(0.2))  # 被遗忘的比例

model.add(Dense(output_dim=layers[3]))
model.add(Activation('tanh'))  # 激活因子
model.compile(loss="mse", optimizer="rmsprop")
# model.fit(trainX, trainY, batch_size=512,  validation_split=0.05)
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)


# 5. 预测执行
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
print("testPredict1:", testPredict)

# 6. 预测结果的反标准化
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
print("testPredict2:", testPredict)

# 7. 计算模型的评估器
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))

# 8.预测结果和实际结果的对比图
# 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()