预测 single/multiple 时间步 lstm 的多行
Predict for multiple rows for single/multiple timesteps lstm
我有 250 天的数据，训练样本的 72 个特征和目标变量的一列。并希望为具有 72 个特征的 21351 行中的每一行预测接下来的 30 天。我将如何重塑我的输入和输出数据。看来我有点困惑，图书馆给我关于形状不兼容的错误。
我重塑为：
trainX.reshape(1, len(trainX), trainX.shape[1])
trainY.reshape(1, len(trainX))
但给我错误：
ValueError: Input arrays should have the same number of samples as
target arrays. Found 1 input samples and 250 target samples.
同样的错误：
trainX.reshape(1, len(trainX), trainX.shape[1])
trainY.reshape(len(trainX), )
和同样的错误：
trainX.reshape(1, len(trainX), trainX.shape[1])
trainY.reshape(len(trainX), 1)
目前，trainX 重塑为：
trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
array([[[ 4.49027601e+00, -3.71848297e-01, -3.71848297e-01, ...,
1.06175239e+17, 1.24734085e+06, 5.16668131e+00]],
[[ 2.05921386e+00, -3.71848297e-01, -3.71848297e-01, ...,
8.44426594e+17, 1.39098642e+06, 4.01803817e+00]],
[[ 9.25515792e+00, -3.71848297e-01, -3.71848297e-01, ...,
4.08800518e+17, 1.24441013e+06, 3.69129399e+00]],
...,
[[ 3.80037999e+00, -3.71848297e-01, -3.71848297e-01, ...,
1.35414902e+18, 1.23823291e+06, 3.54601899e+00]],
[[ 3.73994822e+00, -3.71848297e-01, 8.40698741e+00, ...,
3.93863169e+17, 1.25693299e+06, 3.29993440e+00]],
[[ 3.56843035e+00, -3.71848297e-01, 1.53710656e+00, ...,
3.28306336e+17, 1.22667253e+06, 3.36569960e+00]]])
trainY 重塑为：
trainY.reshape(trainY.shape[0], )
array([[-0.7238661 ],
[-0.43128777],
[-0.31542821],
[-0.35185375],
...,
[-0.28319519],
[-0.28740503],
[-0.24209411],
[-0.3202021 ]])
并将 testX 重塑为：
testX.reshape(1, testX.shape[0], testX.shape[1])
array([[[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, 2.73982042e+06, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, 2.73982042e+06, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
2.00988794e+18, 1.05992636e+06, 2.49920150e+01],
...,
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, -3.71848297e-01, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, -3.71848297e-01, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, -3.71848297e-01, -3.71848297e-01]]])
错误是：
ValueError: Error when checking : expected lstm_25_input to have shape
(None, 1, 72) but got array with shape (1, 2895067, 72)
编辑 1：
这是我的模型代码：
trainX = trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
trainY = trainY.reshape(trainY.shape[0], )
testX = testX.reshape(1, testX.shape[0], testX.shape[1])
model = Sequential()
model.add(LSTM(100, return_sequences=True, input_shape = trainX.shape[0], trainX.shape[2])))
model.add(LSTM(100))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam')
model.fit(trainX, trainY, epochs=500, shuffle=False, verbose=1)
model.save('model_lstm.h5')
model = load_model('model_lstm.h5')
prediction = model.predict(testX, verbose=0)
ValueError Traceback (most recent call
last) in ()
43 model.compile(loss='mse', optimizer='adam')
44
---> 45 model.fit(exog, endog, epochs=50, shuffle=False, verbose=1)
46
47 start_date = endog_end + timedelta(days = 1)
D:\AnacondaIDE\lib\site-packages\keras\models.py in fit(self, x, y,
batch_size, epochs, verbose, callbacks, validation_split,
validation_data, shuffle, class_weight, sample_weight, initial_epoch,
**kwargs)
865 class_weight=class_weight,
866 sample_weight=sample_weight,
--> 867 initial_epoch=initial_epoch)
868
869 def evaluate(self, x, y, batch_size=32, verbose=1,
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in fit(self,
x, y, batch_size, epochs, verbose, callbacks, validation_split,
validation_data, shuffle, class_weight, sample_weight, initial_epoch,
steps_per_epoch, validation_steps, **kwargs) 1520
class_weight=class_weight, 1521 check_batch_axis=False,
-> 1522 batch_size=batch_size) 1523 # Prepare validation data. 1524 do_validation = False
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in
_standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size) 1376
self._feed_input_shapes, 1377
check_batch_axis=False,
-> 1378 exception_prefix='input') 1379 y = _standardize_input_data(y, self._feed_output_names,
1380 output_shapes,
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in
_standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
142 ' to have shape ' + str(shapes[i]) +
143 ' but got array with shape ' +
--> 144 str(array.shape))
145 return arrays
146
ValueError: Error when checking input: expected lstm_31_input to have
shape (None, 250, 72) but got array with shape (21351, 1, 72)
编辑 2：
尝试@Paddy 的更新解决方案后，我在调用 predict() 时遇到此错误：
ValueError Traceback (most recent call
last) in ()
1 model = load_model('model_lstm.h5')
2
----> 3 prediction = model.predict(exog_test, verbose=0)
4 # for x in range(0, len(exog_test)):
D:\AnacondaIDE\lib\site-packages\keras\models.py in predict(self, x,
batch_size, verbose)
911 if not self.built:
912 self.build()
--> 913 return self.model.predict(x, batch_size=batch_size, verbose=verbose)
914
915 def predict_on_batch(self, x):
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in
predict(self, x, batch_size, verbose, steps) 1693 x =
_standardize_input_data(x, self._feed_input_names, 1694 self._feed_input_shapes,
-> 1695 check_batch_axis=False) 1696 if self.stateful: 1697 if x[0].shape[0] >
batch_size and x[0].shape[0] % batch_size != 0:
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in
_standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix)
130 ' to have ' + str(len(shapes[i])) +
131 ' dimensions, but got array with shape ' +
--> 132 str(array.shape))
133 for j, (dim, ref_dim) in enumerate(zip(array.shape, shapes[i])):
134 if not j and not check_batch_axis:
ValueError: Error when checking : expected lstm_64_input to have 3
dimensions, but got array with shape (2895067, 72)
试试这个重塑：
trainX.reshape(len(trainX),1, trainX.shape[1])
trainY.reshape(len(trainX), 1)
但是，一般来说，您有两种方法，即重塑输入数据或更改模型参数。
请查看错误消息，它在这里说明了一切！
好的，这是您的代码更新：
trainX = trainX.reshape(trainX.shape[0], trainX.shape[1],1)
trainY = trainY.reshape(trainY.shape[0],)
testX = testX.reshape(testX.shape[0], testX.shape[1], 1)
model = Sequential()
model.add(LSTM(100, return_sequences= True, input_shape=(trainX.shape[1],1) ))
model.add(LSTM(100, return_sequences= False))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam')
model.fit(trainX, trainY, epochs=500, shuffle=False, verbose=1)
model.save('model_lstm.h5')
model = load_model('model_lstm.h5')
prediction = model.predict(testX, verbose=0)
你有：
trainX = trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
trainY = trainY.reshape(trainY.shape[0], )
testX = testX.reshape(1, testX.shape[0], testX.shape[1])
你想要：
trainX = trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
trainY = trainY.reshape(trainY.shape[0], )
testX = testX.reshape(testX.shape[0],1, testX.shape[1])
您在 testX 中混淆了样本和时间步长维度
我有 250 天的数据，训练样本的 72 个特征和目标变量的一列。并希望为具有 72 个特征的 21351 行中的每一行预测接下来的 30 天。我将如何重塑我的输入和输出数据。看来我有点困惑，图书馆给我关于形状不兼容的错误。
我重塑为：
trainX.reshape(1, len(trainX), trainX.shape[1])
trainY.reshape(1, len(trainX))
但给我错误：
ValueError: Input arrays should have the same number of samples as target arrays. Found 1 input samples and 250 target samples.
同样的错误：
trainX.reshape(1, len(trainX), trainX.shape[1])
trainY.reshape(len(trainX), )
和同样的错误：
trainX.reshape(1, len(trainX), trainX.shape[1])
trainY.reshape(len(trainX), 1)
目前，trainX 重塑为：
trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
array([[[ 4.49027601e+00, -3.71848297e-01, -3.71848297e-01, ...,
1.06175239e+17, 1.24734085e+06, 5.16668131e+00]],
[[ 2.05921386e+00, -3.71848297e-01, -3.71848297e-01, ...,
8.44426594e+17, 1.39098642e+06, 4.01803817e+00]],
[[ 9.25515792e+00, -3.71848297e-01, -3.71848297e-01, ...,
4.08800518e+17, 1.24441013e+06, 3.69129399e+00]],
...,
[[ 3.80037999e+00, -3.71848297e-01, -3.71848297e-01, ...,
1.35414902e+18, 1.23823291e+06, 3.54601899e+00]],
[[ 3.73994822e+00, -3.71848297e-01, 8.40698741e+00, ...,
3.93863169e+17, 1.25693299e+06, 3.29993440e+00]],
[[ 3.56843035e+00, -3.71848297e-01, 1.53710656e+00, ...,
3.28306336e+17, 1.22667253e+06, 3.36569960e+00]]])
trainY 重塑为：
trainY.reshape(trainY.shape[0], )
array([[-0.7238661 ],
[-0.43128777],
[-0.31542821],
[-0.35185375],
...,
[-0.28319519],
[-0.28740503],
[-0.24209411],
[-0.3202021 ]])
并将 testX 重塑为：
testX.reshape(1, testX.shape[0], testX.shape[1])
array([[[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, 2.73982042e+06, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, 2.73982042e+06, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
2.00988794e+18, 1.05992636e+06, 2.49920150e+01],
...,
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, -3.71848297e-01, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, -3.71848297e-01, -3.71848297e-01],
[ -3.71848297e-01, -3.71848297e-01, -3.71848297e-01, ...,
-3.71848297e-01, -3.71848297e-01, -3.71848297e-01]]])
错误是：
ValueError: Error when checking : expected lstm_25_input to have shape (None, 1, 72) but got array with shape (1, 2895067, 72)
编辑 1：
这是我的模型代码：
trainX = trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
trainY = trainY.reshape(trainY.shape[0], )
testX = testX.reshape(1, testX.shape[0], testX.shape[1])
model = Sequential()
model.add(LSTM(100, return_sequences=True, input_shape = trainX.shape[0], trainX.shape[2])))
model.add(LSTM(100))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam')
model.fit(trainX, trainY, epochs=500, shuffle=False, verbose=1)
model.save('model_lstm.h5')
model = load_model('model_lstm.h5')
prediction = model.predict(testX, verbose=0)
ValueError Traceback (most recent call last) in () 43 model.compile(loss='mse', optimizer='adam') 44 ---> 45 model.fit(exog, endog, epochs=50, shuffle=False, verbose=1) 46 47 start_date = endog_end + timedelta(days = 1)
D:\AnacondaIDE\lib\site-packages\keras\models.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, **kwargs) 865 class_weight=class_weight, 866 sample_weight=sample_weight, --> 867 initial_epoch=initial_epoch) 868 869 def evaluate(self, x, y, batch_size=32, verbose=1,
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, **kwargs) 1520
class_weight=class_weight, 1521 check_batch_axis=False, -> 1522 batch_size=batch_size) 1523 # Prepare validation data. 1524 do_validation = FalseD:\AnacondaIDE\lib\site-packages\keras\engine\training.py in _standardize_user_data(self, x, y, sample_weight, class_weight, check_batch_axis, batch_size) 1376
self._feed_input_shapes, 1377
check_batch_axis=False, -> 1378 exception_prefix='input') 1379 y = _standardize_input_data(y, self._feed_output_names,
1380 output_shapes,D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 142 ' to have shape ' + str(shapes[i]) + 143 ' but got array with shape ' + --> 144 str(array.shape)) 145 return arrays 146
ValueError: Error when checking input: expected lstm_31_input to have shape (None, 250, 72) but got array with shape (21351, 1, 72)
编辑 2：
尝试@Paddy 的更新解决方案后，我在调用 predict() 时遇到此错误：
ValueError Traceback (most recent call last) in () 1 model = load_model('model_lstm.h5') 2 ----> 3 prediction = model.predict(exog_test, verbose=0) 4 # for x in range(0, len(exog_test)):
D:\AnacondaIDE\lib\site-packages\keras\models.py in predict(self, x, batch_size, verbose) 911 if not self.built: 912 self.build() --> 913 return self.model.predict(x, batch_size=batch_size, verbose=verbose) 914 915 def predict_on_batch(self, x):
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in predict(self, x, batch_size, verbose, steps) 1693 x = _standardize_input_data(x, self._feed_input_names, 1694 self._feed_input_shapes, -> 1695 check_batch_axis=False) 1696 if self.stateful: 1697 if x[0].shape[0] > batch_size and x[0].shape[0] % batch_size != 0:
D:\AnacondaIDE\lib\site-packages\keras\engine\training.py in _standardize_input_data(data, names, shapes, check_batch_axis, exception_prefix) 130 ' to have ' + str(len(shapes[i])) + 131 ' dimensions, but got array with shape ' + --> 132 str(array.shape)) 133 for j, (dim, ref_dim) in enumerate(zip(array.shape, shapes[i])): 134 if not j and not check_batch_axis:
ValueError: Error when checking : expected lstm_64_input to have 3 dimensions, but got array with shape (2895067, 72)
试试这个重塑：
trainX.reshape(len(trainX),1, trainX.shape[1])
trainY.reshape(len(trainX), 1)
但是，一般来说，您有两种方法，即重塑输入数据或更改模型参数。
请查看错误消息，它在这里说明了一切！
好的，这是您的代码更新：
trainX = trainX.reshape(trainX.shape[0], trainX.shape[1],1)
trainY = trainY.reshape(trainY.shape[0],)
testX = testX.reshape(testX.shape[0], testX.shape[1], 1)
model = Sequential()
model.add(LSTM(100, return_sequences= True, input_shape=(trainX.shape[1],1) ))
model.add(LSTM(100, return_sequences= False))
model.add(Dense(1, activation='linear'))
model.compile(loss='mse', optimizer='adam')
model.fit(trainX, trainY, epochs=500, shuffle=False, verbose=1)
model.save('model_lstm.h5')
model = load_model('model_lstm.h5')
prediction = model.predict(testX, verbose=0)
你有：
trainX = trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
trainY = trainY.reshape(trainY.shape[0], )
testX = testX.reshape(1, testX.shape[0], testX.shape[1])
你想要：
trainX = trainX.reshape(trainX.shape[0], 1, trainX.shape[1])
trainY = trainY.reshape(trainY.shape[0], )
testX = testX.reshape(testX.shape[0],1, testX.shape[1])
您在 testX 中混淆了样本和时间步长维度