# 用 LSTM 做时间序列预测的一个小例子

```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```

dataframe = read_csv('international-airline-passengers.csv', usecols=[1], engine='python', skipfooter=3) dataset = dataframe.values# 将整型变为floatdataset = dataset.astype('float32') plt.plot(dataset) plt.show()

look_back 就是预测下一步所需要的 time steps：

timesteps 就是 LSTM 认为每个输入数据与前多少个陆续输入的数据有联系。例如具有这样用段序列数据 “…ABCDBCEDF…”，当 timesteps 为 3 时，在模型预测中如果输入数据为“D”，那么之前接收的数据如果为“B”和“C”则此时的预测输出为 B 的概率更大，之前接收的数据如果为“C”和“E”，则此时的预测输出为 F 的概率更大。

# X is the number of passengers at a given time (t) and Y is the number of passengers at the next time (t + 1). # 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)

# normalize the datasetscaler = MinMaxScaler(feature_range=(0, 1)) dataset = scaler.fit_transform(dataset)# split into train and test setstrain_size = int(len(dataset) * 0.67) test_size = len(dataset) - train_size train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]

X=t and Y=t+1 时的数据，并且此时的维度为 [samples, features]

# use this function to prepare the train and test datasets for modeling look_back = 1 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], 1, trainX.shape[1])) testX = numpy.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

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

Epoch 100/100 1s - loss: 0.0020

# make predictionstrainPredict = model.predict(trainX) testPredict = model.predict(testX)

`# invert predictionstrainPredict = scaler.inverse_transform(trainPredict) trainY = scaler.inverse_transform([trainY]) testPredict = scaler.inverse_transform(testPredict) testY = scaler.inverse_transform([testY])`

```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))
Train Score: 22.92 RMSE
Test Score: 47.53 RMSE```

# shift train predictions for plottingtrainPredictPlot = numpy.empty_like(dataset) trainPredictPlot[:, :] = numpy.nan trainPredictPlot[look_back:len(trainPredict)+look_back, :] = trainPredict# shift test predictions for plottingtestPredictPlot = numpy.empty_like(dataset) testPredictPlot[:, :] = numpy.nan testPredictPlot[len(trainPredict)+(look_back*2)+1:len(dataset)-1, :] = testPredict# plot baseline and predictionsplt.plot(scaler.inverse_transform(dataset)) plt.plot(trainPredictPlot) plt.plot(testPredictPlot) plt.show()

http://machinelearningmastery.com/time-series-prediction-lstm-recurrent-neural-networks-python-keras/

424 篇文章81 人订阅

0 条评论

## 相关文章

4469

3576

3784

2874

3033

4493

1825

942

1.1K4

### 论文阅读: Faster R-CNN

RP原本主要用SS (Selective Search) 来生成，只能在CPU上跑。一张图片生成~2,000个proposal，效率0.5fps，实在太慢。 ...

1383