以下是使用LSTM实现单变量时间序列预测的代码示例:
```python
import pandas as pd
import numpy as np
from keras.models import Sequential
from keras.layers import LSTM, Dense
# 加载数据
data = pd.read_csv('data.csv', usecols=[1])
dataset = data.values
dataset = dataset.astype('float32')
# 数据归一化
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
# 将数据集分为训练集和测试集
train_size = int(len(dataset) * 0.67)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
# 将时间序列数据转换为监督学习问题
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 np.array(dataX), np.array(dataY)
look_back = 3
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# 将输入重构成 [样本数, 时间步, 特征] 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')
# 训练模型
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
# 在训练集和测试集上进行预测
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# 将预测的数据转换为同一单位
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])
# 计算 RMSE 误差
from sklearn.metrics import mean_squared_error
trainScore = np.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = np.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))
```
在这个示例中,我们首先加载了数据并将其归一化。然后,我们将数据集分为训练集和测试集,并将时间序列数据转换为监督学习问题。接下来,我们通过重构输入来创建LSTM模型,并在训练集上训练模型。最后,我们在训练集和测试集上进行预测,并计算RMSE误差。