层顺序的输入与层不兼容:LSTM中的形状错误

2024-04-20 08:55:19 发布

您现在位置:Python中文网/ 问答频道 /正文

我是神经网络的新手,我想用它们与其他机器学习方法进行比较。我有一个大约两年的多元时间序列数据。我想使用LSTM根据其他变量预测未来几天的“y”。我的数据的最后一天是2020-07-31

df.tail()

              y   holidays  day_of_month    day_of_week month   quarter
   Date                     
 2020-07-27 32500      0      27                 0        7        3
 2020-07-28 33280      0      28                 1        7        3
 2020-07-29 31110      0      29                 2        7        3
 2020-07-30 37720      0      30                 3        7        3
 2020-07-31 32240      0      31                 4        7        3

为了训练LSTM模型,我还将数据分为训练数据和测试数据

from sklearn.model_selection import train_test_split
split_date = '2020-07-27' #to predict the next 4 days
df_train = df.loc[df.index <= split_date].copy()
df_test = df.loc[df.index > split_date].copy()
X1=df_train[['day_of_month','day_of_week','month','quarter','holidays']]
y1=df_train['y']
X2=df_test[['day_of_month','day_of_week','month','quarter','holidays']]
y2=df_test['y']

X_train, y_train =X1, y1
X_test, y_test = X2,y2

因为我正在使用LSTM,所以需要进行一些缩放:

scaler = MinMaxScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

现在,我们来看看最难的部分:模型

num_units=50
activation_function = 'sigmoid'
optimizer = 'adam'
loss_function = 'mean_squared_error'
batch_size = 10
num_epochs = 100

 # Initialize the RNN
regressor = Sequential()

 # Adding the input layer and the LSTM layer
regressor.add(LSTM(units = num_units, return_sequences=True ,activation = activation_function, 
input_shape=(X_train.shape[1], 1)))

 # Adding the output layer
regressor.add(Dense(units = 1))

 # Compiling the RNN
regressor.compile(optimizer = optimizer, loss = loss_function)

# Using the training set to train the model
regressor.fit(X_train_scaled, y_train, batch_size = batch_size, epochs = num_epochs)

但是,我收到以下错误:

ValueError: Input 0 of layer sequential_11 is incompatible with the layer: expected ndim=3, found 
ndim=2. Full shape received: [None, 5]

我不明白我们如何选择输入的参数或形状。我看过一些视频,阅读了一些Github页面,每个人似乎都以不同的方式运行LSTM,这使得它更难实现。前面的错误可能来自形状,但除此之外,其他所有错误都正确吗?我怎样才能解决这个问题?谢谢

编辑:This类似的问题不能解决我的问题。。我已经从那里尝试了解决方案

x_train = X_train_scaled.reshape(-1, 1, 5)
x_test  = X_test_scaled.reshape(-1, 1, 5)

(我的X_测试和y_测试只有一列)。而且这个解决方案似乎也不起作用。我现在得到这个错误:

ValueError: Input 0 is incompatible with layer sequential_22: expected shape= 
(None, None, 1), found shape=[None, 1, 5]

Tags: ofthe数据testlayerdftrainnum
2条回答

这是一个使用LSTM解决的多元回归问题。在开始编写代码之前,让我们先看看它的含义

问题陈述:

  • k天内,您每天有5功能holidays, day_of_month, day_of_week,month,quarter
  • 对于任何一天n,假设最后的'm'天的特征,您希望预测第y天的n

正在创建窗口数据集:

  • 我们首先需要决定我们想要输入模型的天数。这称为序列长度(在本例中,让我们将其固定为3)
  • 我们必须分割序列长度的天数来创建训练和测试数据集。这是通过使用滑动窗口完成的,其中窗口大小为序列长度
  • 如您所见,最后的p记录没有可用的预测,其中p是序列长度
  • 我们将使用timeseries_dataset_from_array方法创建窗口数据集
  • 有关更多高级资料,请参见官方tfdocs

LSTM模型

因此,我们希望达到的效果如下:

enter image description here

对于每个LSTM单元展开,我们传入当天的5个特征,并在m时间内展开,其中m是序列长度。我们正在预测最后一天的天气

代码:

import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers, models
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split

# Model
regressor =  models.Sequential()
regressor.add(layers.LSTM(5, return_sequences=True))
regressor.add(layers.Dense(1))
regressor.compile(optimizer='sgd', loss='mse')

# Dummy data
n = 10000
df = pd.DataFrame(
    {
      'y': np.arange(n),
      'holidays': np.random.randn(n),
      'day_of_month': np.random.randn(n),
      'day_of_week': np.random.randn(n),
      'month': np.random.randn(n),
      'quarter': np.random.randn(n),     
    }
)

# Train test split
train_df, test_df = train_test_split(df)
print (train_df.shape, test_df.shape)\

# Create y to be predicted 
# given last n days predict todays y

# train data
sequence_length = 3
y_pred = train_df['y'][sequence_length-1:].values
train_df = train_df[:-2]
train_df['y_pred'] = y_pred

# Validataion data
y_pred = test_df['y'][sequence_length-1:].values
test_df = test_df[:-2]
test_df['y_pred'] = y_pred

# Create window datagenerators

# Train data generator
train_X = train_df[['holidays','day_of_month','day_of_week','month','month']]
train_y = train_df['y_pred']
train_dataset = tf.keras.preprocessing.timeseries_dataset_from_array(
    train_X, train_y, sequence_length=sequence_length, shuffle=True, batch_size=4)

# Validation data generator
test_X = test_df[['holidays','day_of_month','day_of_week','month','month']]
test_y = test_df['y_pred']
test_dataset = tf.keras.preprocessing.timeseries_dataset_from_array(
    test_X, test_y, sequence_length=sequence_length, shuffle=True, batch_size=4)

# Finally fit the model
regressor.fit(train_dataset, validation_data=test_dataset, epochs=3)

输出:

(7500, 6) (2500, 6)
Epoch 1/3
1874/1874 [==============================] - 8s 3ms/step - loss: 9974697.3664 - val_loss: 8242597.5000
Epoch 2/3
1874/1874 [==============================] - 6s 3ms/step - loss: 8367530.7117 - val_loss: 8256667.0000
Epoch 3/3
1874/1874 [==============================] - 6s 3ms/step - loss: 8379048.3237 - val_loss: 8233981.5000
<tensorflow.python.keras.callbacks.History at 0x7f3e94bdd198>

输入:

问题是,您的模型需要一个形状为(batch, sequence, features)的3D输入,但您的X_train实际上是一个数据帧切片,因此2D数组:

X1=df_train[['day_of_month','day_of_week','month','quarter','holidays']]
X_train, y_train =X1, y1

我假设您的列应该是您的特性,所以您通常会对df进行“堆栈切片”,以便X_train看起来像这样:

以下是形状(15,5)的虚拟2D数据集:

data = np.zeros((15,5))

array([[0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.],
       [0., 0., 0., 0., 0.]])

您可以对其进行重塑以添加批次维度,例如(15,1,5)

data = data[:,np.newaxis,:] 

array([[[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]],

       [[0., 0., 0., 0., 0.]]])

数据相同,但呈现方式不同。现在在这个例子中,batch = 15sequence = 1,我不知道在你的例子中序列的长度是多少,但它可以是任何东西

型号:

现在在您的模型中,kerasinput_shapeexpect(batch, sequence, features),当您传递此消息时:

input_shape=(X_train.shape[1], 1)

这就是您的模型所看到的:(None, Sequence = X_train.shape[1] , num_features = 1)None用于批处理维度。我不认为这就是你想要做的,一旦你改变了形状,你也应该修正input_shape以匹配新的数组

相关问题 更多 >