Python LSTM 长短期预测：代码示例与流程详解

以下是使用 Python 进行 LSTM 长短时预测的基本流程和代码：

导入所需的库和模块

import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, LSTM
from sklearn.preprocessing import MinMaxScaler

加载数据集并进行预处理

# 加载数据集
data = pd.read_csv('data.csv', usecols=[1])

# 将数据集转换为numpy数组
dataset = data.values
dataset = dataset.astype('float32')

# 归一化数据
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

准备训练数据和测试数据

# 将数据集划分为训练数据和测试数据
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-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 = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

# 将数据集重塑为LSTM的输入格式 [样本数，时间步，特征数]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

构建LSTM模型

model = Sequential()
model.add(LSTM(4, input_shape=(1, look_back)))
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)

使用模型进行预测

# 使用训练好的模型进行预测
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

# 将预测结果进行反归一化
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])

计算模型的准确率

# 计算训练集和测试集的均方根误差
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))

完整代码如下：

import numpy as np
import pandas as pd
from keras.models import Sequential
from keras.layers import Dense, LSTM
from sklearn.preprocessing import MinMaxScaler

# 加载数据集
data = pd.read_csv('data.csv', usecols=[1])

# 将数据集转换为numpy数组
dataset = data.values
dataset = dataset.astype('float32')

# 归一化数据
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)

# 将数据集划分为训练数据和测试数据
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-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 = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)

# 将数据集重塑为LSTM的输入格式 [样本数，时间步，特征数]
trainX = np.reshape(trainX, (trainX.shape[0], 1, trainX.shape[1]))
testX = np.reshape(testX, (testX.shape[0], 1, testX.shape[1]))

# 构建LSTM模型
model = Sequential()
model.add(LSTM(4, input_shape=(1, look_back)))
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)

# 使用训练好的模型进行预测
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

# 将预测结果进行反归一化
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform([testY])

# 计算训练集和测试集的均方根误差
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))