常用的LSTM时间序列预测（单变量时间序列预测 | 多变量时间序列预测 | 他们的预测未来数据方法）

本文探讨了使用LSTM进行时间序列预测的方法，包括单变量预测的单步和多步策略，以及多变量预测的单步和多步策略，详细阐述了如何利用历史数据预测未来的趋势。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

单变量时间序列预测

数据类型：单列


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

dataset = df.values
# 将整型变为float
dataset = dataset.astype('float32')

from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
train_size = int(len(dataset) * 0.65)
trainlist = dataset[:train_size]
testlist = dataset[train_size:]

def create_dataset(dataset, look_back):
#这里的look_back与timestep相同
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back)]
        dataX.append(a)
        dataY.append(dataset[i + look_back])
    return numpy.array(dataX),numpy.array(dataY)
#训练数据太少 look_back并不能过大
look_back = 1
trainX,trainY  = create_dataset(trainlist,look_back)
testX,testY = create_dataset(testlist,look_back)
trainX = numpy.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = numpy.reshape(testX, (testX.shape[0], testX.shape[1] ,1 ))
# create and fit the LSTM network
model = Sequential()
model.add(LSTM(4, input_shape=(None,1)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)
# model.save(os.path.join("DATA","Test" + ".h5"))
# make predictions

#模型验证
#model = load_model(os.path.join("DATA","Test" + ".h5"))
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)

#反归一化
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform(trainY)
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform(testY)
plt.plot(trainY)
plt.plot(trainPredict[1:])
plt.show()s
plt.plot(testY)
plt.plot(testPredict[1:])
plt.show()

预测未来数据方法

.单维单步（使用前n（2，代码演示为3）步预测后一步）

#对全部数据进行训练 
import numpy
import matplotlib.pyplot as plt
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
from keras.models import Sequential, load_model

dataset = df.values
# 将整型变为float
dataset = dataset.astype('float32')
from sklearn.preprocessing import MinMaxScaler
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
def create_dataset(dataset, look_back):
#这里的look_back与timestep相同
    dataX, dataY = [], []
    for i in range(len(dataset)-look_back-1):
        a = dataset[i:(i+look_back)]
        dataX.append(a)
        dataY.append(dataset[i + look_back])
    return numpy.array(dataX),numpy.array(dataY)
#训练数据太少 look_back并不能过大
look_back = 1
trainX,trainY  = create_dataset(dataset,look_back)
trainX = numpy.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
# create and fit the LSTM network
model = Sequential()
model.add(LSTM(2, input_shape=(None,1)))
model.add(Dense(1))
model.compile(loss='mse', optimizer='adam')
model.fit(trainX, trainY, epochs=100, batch_size=1, verbose=2)


######################滚动预测########
predict_xlist = []#添加预测x列表
predict_y = []#添加预测y列表
timesteps=1
length=12
predict_xlist.extend(dataset[dataset.shape[0]-timesteps:dataset.shape[0],0].tolist())#已