LSTM预测python和matlab代码

以下是使用LSTM进行时间序列预测的Python代码：

import numpy as np
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense, LSTM

# 生成时间序列数据
def generate_data():
    x = np.linspace(0, 10, 1000)
    y = np.sin(x) + np.random.uniform(-0.5, 0.5, 1000)
    return x, y

# 构建LSTM模型
def build_model():
    model = Sequential()
    model.add(LSTM(50, input_shape=(1, 1)))
    model.add(Dense(1))
    model.compile(loss='mse', optimizer='adam')
    return model

# 训练模型
def train_model(model, x, y):
    x = x.reshape(len(x), 1, 1)
    model.fit(x, y, epochs=50, batch_size=32)

# 预测模型
def predict(model, x):
    x = x.reshape(len(x), 1, 1)
    y_pred = model.predict(x)
    return y_pred.flatten()

# 绘制结果
def plot_result(x, y_true, y_pred):
    plt.plot(x, y_true, label='True')
    plt.plot(x, y_pred, label='Predicted')
    plt.legend()
    plt.show()

# 主函数
if __name__ == '__main__':
    x, y_true = generate_data()
    model = build_model()
    train_model(model, x, y_true)
    y_pred = predict(model, x)
    plot_result(x, y_true, y_pred)

以下是使用LSTM进行时间序列预测的MATLAB代码：

% 生成时间序列数据
t = linspace(0, 10, 1000);
y = sin(t) + 0.1 * randn(size(t));

% 构建LSTM模型
layers = [ ...
    sequenceInputLayer(1)
    lstmLayer(50)
    fullyConnectedLayer(1)
    regressionLayer];
options = trainingOptions(...
    'adam', ...
    'MaxEpochs', 50, ...
    'MiniBatchSize', 32, ...
    'Plots', 'training-progress');
net = trainNetwork(t', y', layers, options);

% 预测模型
y_pred = predict(net, t');

% 绘制结果
plot(t, y, t, y_pred)
legend('True', 'Predicted')