多变量和多步 LSTM
Multivariate and multistep LSTM
给出 this example（部分：训练多个滞后时间步示例），为了根据前 2 年的数据预测接下来 6 小时的污染，我应该设置 n_hours= 17520，以及我要预测的未来步数（设置 n_out=6）？
否则，我在某处读到我也应该将 Dense 层单元修改为未来预测的步数（这里是 6），但是，它总是 returns 一个错误。会有什么问题？
谢谢
修改后的代码：
from math import sqrt
from numpy import concatenate
from matplotlib import pyplot
from pandas import read_csv
from pandas import DataFrame
from pandas import concat
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
n_vars = 1 if type(data) is list else data.shape[1]
df = DataFrame(data)
cols, names = list(), list()
# input sequence (t-n, ... t-1)
for i in range(n_in, 0, -1):
cols.append(df.shift(i))
names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
# forecast sequence (t, t+1, ... t+n)
for i in range(0, n_out):
cols.append(df.shift(-i))
if i == 0:
names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
else:
names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
# put it all together
agg = concat(cols, axis=1)
agg.columns = names
# drop rows with NaN values
if dropnan:
agg.dropna(inplace=True)
return agg
# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# specify the number of lag hours
n_hours = 17520
n_features = 8
# frame as supervised learning
reframed = series_to_supervised(scaled, n_hours, 6) # predict the next 6 hours
print(reframed.shape)
# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24 *2
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
n_obs = n_hours * n_features
train_X, train_y = train[:, :n_obs], train[:, -n_features]
test_X, test_y = test[:, :n_obs], test[:, -n_features]
print(train_X.shape, len(train_X), train_y.shape)
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], n_hours, n_features))
test_X = test_X.reshape((test_X.shape[0], n_hours, n_features))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()
# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], n_hours*n_features))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)
编辑：
我已将 Dense layer units 的值更改为 6，将 train_y.shape[1] 以及 test_y.shape[1] 的值更改为 6，如下所示：
# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# specify the number of lag hours
n_hours =48
n_out=6
n_features = 8
# frame as supervised learning
reframed = series_to_supervised(scaled, n_hours, n_out)
print(reframed.shape)
# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24 * 2
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
n_obs = n_hours * n_features
train_X, train_y = train[:, :n_obs], train[:, :6]#I put 6 instead of -n_features
print(train_X.shape, len(train_X), train_y.shape)
test_X, test_y = test[:, :n_obs], test[:,:6] # I put 6 instead of -n_features
print(test_X.shape, len(test_X), test_y.shape)
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], n_hours, n_features))
train_y = train_y
test_X = test_X.reshape((test_X.shape[0], n_hours, n_features))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
train_y.shape
# design network
model = Sequential()
model.add(LSTM(5, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(6))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=5, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()
# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], n_hours*n_features))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)
我遇到的错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-57-8e17d1d76420> in <module>
9 # invert scaling for forecast
10 inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
---> 11 inv_yhat = scaler.inverse_transform(inv_yhat)
12 inv_yhat = inv_yhat[:,0]
13 # invert scaling for actual
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\preprocessing\data.py in inverse_transform(self, X)
404 force_all_finite="allow-nan")
405
--> 406 X -= self.min_
407 X /= self.scale_
408 return X
ValueError: operands could not be broadcast together with shapes (26227,13) (8,) (26227,13)
如错误输出所示，当您尝试反转最小-最大比例运算时会出现问题。问题是您已经为所有列安装了缩放器，现在您只需要反转数据集第一列的缩放。为了解决这个问题，本教程的作者将预测列与其余属性连接起来，但您不能这样做，因为您要为每一行预测多个值。一个可能的解决方案是：
改变这个
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
有了这个
# invert scaling for forecast
pred_scaler = MinMaxScaler(feature_range=(0, 1)).fit(dataset.values[:,0].reshape(-1, 1))
inv_yhat = pred_scaler.inverse_transform(yhat)
# invert scaling for actual
inv_y = pred_scaler.inverse_transform(test_y)
给出 this example（部分：训练多个滞后时间步示例），为了根据前 2 年的数据预测接下来 6 小时的污染，我应该设置 n_hours= 17520，以及我要预测的未来步数（设置 n_out=6）？
否则，我在某处读到我也应该将 Dense 层单元修改为未来预测的步数（这里是 6），但是，它总是 returns 一个错误。会有什么问题？
谢谢
修改后的代码：
from math import sqrt
from numpy import concatenate
from matplotlib import pyplot
from pandas import read_csv
from pandas import DataFrame
from pandas import concat
from sklearn.preprocessing import MinMaxScaler
from sklearn.preprocessing import LabelEncoder
from sklearn.metrics import mean_squared_error
from keras.models import Sequential
from keras.layers import Dense
from keras.layers import LSTM
# convert series to supervised learning
def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):
n_vars = 1 if type(data) is list else data.shape[1]
df = DataFrame(data)
cols, names = list(), list()
# input sequence (t-n, ... t-1)
for i in range(n_in, 0, -1):
cols.append(df.shift(i))
names += [('var%d(t-%d)' % (j+1, i)) for j in range(n_vars)]
# forecast sequence (t, t+1, ... t+n)
for i in range(0, n_out):
cols.append(df.shift(-i))
if i == 0:
names += [('var%d(t)' % (j+1)) for j in range(n_vars)]
else:
names += [('var%d(t+%d)' % (j+1, i)) for j in range(n_vars)]
# put it all together
agg = concat(cols, axis=1)
agg.columns = names
# drop rows with NaN values
if dropnan:
agg.dropna(inplace=True)
return agg
# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# specify the number of lag hours
n_hours = 17520
n_features = 8
# frame as supervised learning
reframed = series_to_supervised(scaled, n_hours, 6) # predict the next 6 hours
print(reframed.shape)
# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24 *2
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
n_obs = n_hours * n_features
train_X, train_y = train[:, :n_obs], train[:, -n_features]
test_X, test_y = test[:, :n_obs], test[:, -n_features]
print(train_X.shape, len(train_X), train_y.shape)
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], n_hours, n_features))
test_X = test_X.reshape((test_X.shape[0], n_hours, n_features))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
# design network
model = Sequential()
model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(1))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()
# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], n_hours*n_features))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)
编辑：
我已将 Dense layer units 的值更改为 6，将 train_y.shape[1] 以及 test_y.shape[1] 的值更改为 6，如下所示：
# load dataset
dataset = read_csv('pollution.csv', header=0, index_col=0)
values = dataset.values
# integer encode direction
encoder = LabelEncoder()
values[:,4] = encoder.fit_transform(values[:,4])
# ensure all data is float
values = values.astype('float32')
# normalize features
scaler = MinMaxScaler(feature_range=(0, 1))
scaled = scaler.fit_transform(values)
# specify the number of lag hours
n_hours =48
n_out=6
n_features = 8
# frame as supervised learning
reframed = series_to_supervised(scaled, n_hours, n_out)
print(reframed.shape)
# split into train and test sets
values = reframed.values
n_train_hours = 365 * 24 * 2
train = values[:n_train_hours, :]
test = values[n_train_hours:, :]
# split into input and outputs
n_obs = n_hours * n_features
train_X, train_y = train[:, :n_obs], train[:, :6]#I put 6 instead of -n_features
print(train_X.shape, len(train_X), train_y.shape)
test_X, test_y = test[:, :n_obs], test[:,:6] # I put 6 instead of -n_features
print(test_X.shape, len(test_X), test_y.shape)
# reshape input to be 3D [samples, timesteps, features]
train_X = train_X.reshape((train_X.shape[0], n_hours, n_features))
train_y = train_y
test_X = test_X.reshape((test_X.shape[0], n_hours, n_features))
print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)
train_y.shape
# design network
model = Sequential()
model.add(LSTM(5, input_shape=(train_X.shape[1], train_X.shape[2])))
model.add(Dense(6))
model.compile(loss='mae', optimizer='adam')
# fit network
history = model.fit(train_X, train_y, epochs=5, batch_size=72, validation_data=(test_X, test_y), verbose=2, shuffle=False)
# plot history
pyplot.plot(history.history['loss'], label='train')
pyplot.plot(history.history['val_loss'], label='test')
pyplot.legend()
pyplot.show()
# make a prediction
yhat = model.predict(test_X)
test_X = test_X.reshape((test_X.shape[0], n_hours*n_features))
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
# calculate RMSE
rmse = sqrt(mean_squared_error(inv_y, inv_yhat))
print('Test RMSE: %.3f' % rmse)
我遇到的错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-57-8e17d1d76420> in <module>
9 # invert scaling for forecast
10 inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
---> 11 inv_yhat = scaler.inverse_transform(inv_yhat)
12 inv_yhat = inv_yhat[:,0]
13 # invert scaling for actual
~\AppData\Local\Continuum\anaconda3\lib\site-packages\sklearn\preprocessing\data.py in inverse_transform(self, X)
404 force_all_finite="allow-nan")
405
--> 406 X -= self.min_
407 X /= self.scale_
408 return X
ValueError: operands could not be broadcast together with shapes (26227,13) (8,) (26227,13)
如错误输出所示，当您尝试反转最小-最大比例运算时会出现问题。问题是您已经为所有列安装了缩放器，现在您只需要反转数据集第一列的缩放。为了解决这个问题，本教程的作者将预测列与其余属性连接起来，但您不能这样做，因为您要为每一行预测多个值。一个可能的解决方案是：
改变这个
# invert scaling for forecast
inv_yhat = concatenate((yhat, test_X[:, -7:]), axis=1)
inv_yhat = scaler.inverse_transform(inv_yhat)
inv_yhat = inv_yhat[:,0]
# invert scaling for actual
test_y = test_y.reshape((len(test_y), 1))
inv_y = concatenate((test_y, test_X[:, -7:]), axis=1)
inv_y = scaler.inverse_transform(inv_y)
inv_y = inv_y[:,0]
有了这个
# invert scaling for forecast
pred_scaler = MinMaxScaler(feature_range=(0, 1)).fit(dataset.values[:,0].reshape(-1, 1))
inv_yhat = pred_scaler.inverse_transform(yhat)
# invert scaling for actual
inv_y = pred_scaler.inverse_transform(test_y)