具有单变量输入的CNN-LSTM编解码器模型
卷积神经网络(CNN)可以作为编解码器结构中的编码器。CNN不直接支持序列输入;相反，一维CNN能够读取序列输入并自动学习显著特征。然后可以按照正常情况由LSTM解码器解释这些。我们将使用CNN和LSTM的混合模型称为cn -LSTM模型，在本例中，我们将在一个编解码器体系结构中同时使用它们。CNN希望输入的数据具有与LSTM模型相同的3D结构，尽管多个特性被读取为不同的通道，最终具有相同的效果。我们将简化这个示例，并将重点放在具有单变量输入的cn - lstm上，但是它也可以很容易地更新为使用多元输入，这只是一个练习。与之前一样，我们将使用由14天的日总功耗组成的输入序列。我们将为编码器定义一个简单但有效的CNN架构，它由两个卷积层和一个最大池化层组成，然后将结果扁平化。第一个卷积层读取输入序列并将结果投影到特征图上。第二层对第一层创建的特征图执行相同的操作，试图放大任何显著的特征。我们将在每个卷积层使用64个feature map，读取内核大小为3个时间步长的输入序列。最大池层通过保留最大信号值的1/4来简化特征映射。在池化层之后提取的特征映射被压扁成一个长向量，然后可以用作解码过程的输入。
model.add(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())解码器与前面几节定义的解码器相同。唯一的其他变化是将训练时间设置为20个。带有这些更改的build_model()函数如下所示。
# 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, 20, 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(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
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现在我们准备使用CNN编码器来尝试编码器-解码器架构。下面提供了完整的代码清单。
# univariate multi-step encoder-decoder cnn-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
from keras.layers.convolutional import Conv1D
from keras.layers.convolutional import MaxPooling1D
# 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_input = data[in_start:in_end, 0]
x_input = x_input.reshape((len(x_input), 1))
X.append(x_input)
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, 20, 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(Conv1D(filters=64, kernel_size=3, activation='relu', input_shape=(n_timesteps,n_features)))
model.add(Conv1D(filters=64, kernel_size=3, activation='relu'))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
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:, 0]
# reshape into [1, n_input, 1]
input_x = input_x.reshape((1, len(input_x), 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()