在本节中，我们将更新上一节中开发的编码器-解码器LSTM，使用8个时间序列变量中的每一个来预测下一个标准周的每日总功耗。我们将通过将每个一维时间序列作为单独的输入序列提供给模型来实现这一点。LSTM将依次创建每个输入序列的内部表示，这些输入序列将由解码器一起解释。使用多元输入有助于解决这样的问题，即输出序列是来自多个不同特征的先前时间步长的某个函数，而不只是(或包括)预测的特征。目前还不清楚在电力消耗问题上是否存在这种情况，但我们可以探索它。首先，我们必须更新培训数据的准备工作，使其包含所有八个特性，而不仅仅是每天消耗的总能量。

它需要一行更改:

X.append(data[in_start:in_end, :])

完成此更改的to_supervised()函数如下所示。

# convert history into inputs and outputs
def to_supervised(train, n_input, n_out=7):
	# flatten data
	data = train.reshape((train.shape[0]*train.shape[1], train.shape[2]))
	X, y = list(), list()
	in_start = 0
	# step over the entire history one time step at a time
	for _ in range(len(data)):
		# define the end of the input sequence
		in_end = in_start + n_input
		out_end = in_end + n_out
		# ensure we have enough data for this instance
		if out_end < len(data):
			X.append(data[in_start:in_end, :])
			y.append(data[in_end:out_end, 0])
		# move along one time step
		in_start += 1
	return array(X), array(y)

 

我们还必须更新使用fit模型进行预测的函数，以使用前面时间步骤中的所有8个特性。还有一个小变化:

# retrieve last observations for input data
input_x = data[-n_input:, :]
# reshape into [1, n_input, n]
input_x = input_x.reshape((1, input_x.shape[0], input_x.shape[1]))

修改后的complete forecast()函数如下:

# make a forecast
def forecast(model, history, n_input):
	# flatten data
	data = array(history)
	data = data.reshape((data.shape[0]*data.shape[1], data.shape[2]))
	# retrieve last observations for input data
	input_x = data[-n_input:, :]
	# reshape into [1, n_input, n]
	input_x = input_x.reshape((1, input_x.shape[0], input_x.shape[1]))
	# forecast the next week
	yhat = model.predict(input_x, verbose=0)
	# we only want the vector forecast
	yhat = yhat[0]
	return yhat

直接使用相同的模型体系结构和配置，尽管我们将把训练周期的数量从20个增加到50个，因为输入数据量增加了8倍。

完整的示例如下所示。

# multivariate multi-step encoder-decoder lstm
from math import sqrt
from numpy import split
from numpy import array
from pandas import read_csv
from sklearn.metrics import mean_squared_error
from matplotlib import pyplot
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import LSTM
from keras.layers import RepeatVector
from keras.layers import TimeDistributed

# split a univariate dataset into train/test sets
def split_dataset(data):
	# split into standard weeks
	train, test = data[1:-328], data[-328:-6]
	# restructure into windows of weekly data
	train = array(split(train, len(train)/7))
	test = array(split(test, len(test)/7))
	return train, test

# evaluate one or more weekly forecasts against expected values
def evaluate_forecasts(actual, predicted):
	scores = list()
	# calculate an RMSE score for each day
	for i in range(actual.shape[1]):
		# calculate mse
		mse = mean_squared_error(actual[:, i], predicted[:, i])
		# calculate rmse
		rmse = sqrt(mse)
		# store
		scores.append(rmse)
	# calculate overall RMSE
	s = 0
	for row in range(actual.shape[0]):
		for col in range(actual.shape[1]):
			s += (actual[row, col] - predicted[row, col])**2
	score = sqrt(s / (actual.shape[0] * actual.shape[1]))
	return score, scores

# summarize scores
def summarize_scores(name, score, scores):
	s_scores = ', '.join(['%.1f' % s for s in scores])
	print('%s: [%.3f] %s' % (name, score, s_scores))

# convert history into inputs and outputs
def to_supervised(train, n_input, n_out=7):
	# flatten data
	data = train.reshape((train.shape[0]*train.shape[1], train.shape[2]))
	X, y = list(), list()
	in_start = 0
	# step over the entire history one time step at a time
	for _ in range(len(data)):
		# define the end of the input sequence
		in_end = in_start + n_input
		out_end = in_end + n_out
		# ensure we have enough data for this instance
		if out_end < len(data):
			X.append(data[in_start:in_end, :])
			y.append(data[in_end:out_end, 0])
		# move along one time step
		in_start += 1
	return array(X), array(y)

# train the model
def build_model(train, n_input):
	# prepare data
	train_x, train_y = to_supervised(train, n_input)
	# define parameters
	verbose, epochs, batch_size = 0, 50, 16
	n_timesteps, n_features, n_outputs = train_x.shape[1], train_x.shape[2], train_y.shape[1]
	# reshape output into [samples, timesteps, features]
	train_y = train_y.reshape((train_y.shape[0], train_y.shape[1], 1))
	# define model
	model = Sequential()
	model.add(LSTM(200, activation='relu', input_shape=(n_timesteps, n_features)))
	model.add(RepeatVector(n_outputs))
	model.add(LSTM(200, activation='relu', return_sequences=True))
	model.add(TimeDistributed(Dense(100, activation='relu')))
	model.add(TimeDistributed(Dense(1)))
	model.compile(loss='mse', optimizer='adam')
	# fit network
	model.fit(train_x, train_y, epochs=epochs, batch_size=batch_size, verbose=verbose)
	return model

# make a forecast
def forecast(model, history, n_input):
	# flatten data
	data = array(history)
	data = data.reshape((data.shape[0]*data.shape[1], data.shape[2]))
	# retrieve last observations for input data
	input_x = data[-n_input:, :]
	# reshape into [1, n_input, n]
	input_x = input_x.reshape((1, input_x.shape[0], input_x.shape[1]))
	# forecast the next week
	yhat = model.predict(input_x, verbose=0)
	# we only want the vector forecast
	yhat = yhat[0]
	return yhat

# evaluate a single model
def evaluate_model(train, test, n_input):
	# fit model
	model = build_model(train, n_input)
	# history is a list of weekly data
	history = [x for x in train]
	# walk-forward validation over each week
	predictions = list()
	for i in range(len(test)):
		# predict the week
		yhat_sequence = forecast(model, history, n_input)
		# store the predictions
		predictions.append(yhat_sequence)
		# get real observation and add to history for predicting the next week
		history.append(test[i, :])
	# evaluate predictions days for each week
	predictions = array(predictions)
	score, scores = evaluate_forecasts(test[:, :, 0], predictions)
	return score, scores

# load the new file
dataset = read_csv('household_power_consumption_days.csv', header=0, infer_datetime_format=True, parse_dates=['datetime'], index_col=['datetime'])
# split into train and test
train, test = split_dataset(dataset.values)
# evaluate model and get scores
n_input = 14
score, scores = evaluate_model(train, test, n_input)
# summarize scores
summarize_scores('lstm', score, scores)
# plot scores
days = ['sun', 'mon', 'tue', 'wed', 'thr', 'fri', 'sat']
pyplot.plot(days, scores, marker='o', label='lstm')
pyplot.show()