lstm 预测模型案列

以下是一个LSTM预测模型的案例：

# 导入必要的库
import numpy as np
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from sklearn.preprocessing import MinMaxScaler

# 创建数据集
data = [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]

# 将数据集转换为适合LSTM的数据格式
def create_dataset(dataset, look_back=1):
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back):
        a = dataset[i:(i+look_back)]
        dataX.append(a)
        dataY.append(dataset[i + look_back])
    return np.array(dataX), np.array(dataY)

# 创建随机种子
np.random.seed(7)

# 将数据集归一化
scaler = MinMaxScaler(feature_range=(0, 1))
data = scaler.fit_transform(np.array(data).reshape(-1, 1))

# 拆分数据集为训练集和测试集
train_size = int(len(data) * 0.67)
test_size = len(data) - train_size
train, test = data[0:train_size,:], data[train_size:len(data),:]

# 创建dataset，让数据产生相关性
look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

# 将输入转换成为【样本数，时间步长，特征数】的格式
trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = np.reshape(testX, (testX.shape[0], testX.shape[1], 1))

# 创建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)

# 在训练集上的预测表现
trainPredict = model.predict(trainX)
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))

# 在测试集上的预测表现
testPredict = model.predict(testX)
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))