Data Preparation for Variable Length Input Sequences

是 否 +2 论坛币

k人 参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

本帖隐藏的内容

Deep learning libraries assume a vectorized representation of your data.
In the case of variable length sequence prediction problems, this requires that your data be transformed such that each sequence has the same length.
This vectorization allows code to efficiently perform the matrix operations in batch for your chosen deep learning algorithms.
In this tutorial, you will discover techniques that you can use to prepare your variable length sequence data for sequence prediction problems in Python with Keras.
After completing this tutorial, you will know:

• How to pad variable length sequences with dummy values.
• How to pad variable length sequences to a new longer desired length.
• How to truncate variable length sequences to a shorter desired length.
  

Let’s get started.


Data Preparation for Variable-Length Input Sequences for Sequence Prediction
Photo by Adam Bautz, some rights reserved.

OverviewThis section is divided into 3 parts; they are:

• Contrived Sequence Problem
• Sequence Padding
• Sequence Truncation
  

EnvironmentThis tutorial assumes you have a Python SciPy environment installed. You can use either Python 2 or 3 with this example.
This tutorial assumes you have Keras (v2.0.4+) installed with either the TensorFlow (v1.1.0+) or Theano (v0.9+) backend.
This tutorial also assumes you have scikit-learn, Pandas, NumPy, and Matplotlib installed.
If you need help setting up your Python environment, see this post:

• How to Setup a Python Environment for Machine Learning and Deep Learning with Anaconda
  

Contrived Sequence ProblemWe can contrive a simple sequence problem for the purposes of this tutorial.
The problem is defined as sequences of integers. There are three sequences with a length between 4 and 1 timesteps, as follows:

1. 1, 2, 3, 4
   
2. 1, 2, 3
   
3. 1

复制代码

These can be defined as a list of lists in Python as follows (with spacing for readability):

1. sequences = [
   
2. [1, 2, 3, 4],
   
3. [1, 2, 3],
   
4. [1]
   
5. ]

复制代码

We will use these sequences as the basis for exploring sequence padding in this tutorial.
Sequence PaddingThe pad_sequences() function in the Keras deep learning library can be used to pad variable length sequences.
The default padding value is 0.0, which is suitable for most applications, although this can be changed by specifying the preferred value via the “value” argument. For example:
pad_sequences(..., value=99)The padding to be applied to the beginning or the end of the sequence, called pre- or post-sequence padding, can be specified by the “padding” argument, as follows.
Pre-Sequence PaddingPre-sequence padding is the default (padding=’pre’)
The example below demonstrates pre-padding 3-input sequences with 0 values.

1. from keras.preprocessing.sequence import pad_sequences
   
2. # define sequences
   
3. sequences = [
   
4.         [1, 2, 3, 4],
   
5.            [1, 2, 3],
   
6.                      [1]
   
7.         ]
   
8. # pad sequence
   
9. padded = pad_sequences(sequences)
   
10. print(padded)

复制代码

Running the example prints the 3 sequences pre-pended with zero values.

1. [[1 2 3 4]
   
2. [0 1 2 3]
   
3. [0 0 0 1]

复制代码

Post-Sequence PaddingPadding can also be applied to the end of the sequences, which may be more appropriate for some problem domains.
Post-sequence padding can be specified by setting the “padding” argument to “post”.

1. from keras.preprocessing.sequence import pad_sequences
   
2. # define sequences
   
3. sequences = [
   
4.         [1, 2, 3, 4],
   
5.            [1, 2, 3],
   
6.                      [1]
   
7.         ]
   
8. # pad sequence
   
9. padded = pad_sequences(sequences, padding='post')
   
10. print(padded)

复制代码

Running the example prints the same sequences with zero-values appended.

1. [[1 2 3 4]
   
2. [1 2 3 0]
   
3. [1 0 0 0]]

复制代码

Pad Sequences To LengthThe pad_sequences() function can also be used to pad sequences to a preferred length that may be longer than any observed sequences.
This can be done by specifying the “maxlen” argument to the desired length. Padding will then be performed on all sequences to achieve the desired length, as follows.

1. from keras.preprocessing.sequence import pad_sequences
   
2. # define sequences
   
3. sequences = [
   
4.         [1, 2, 3, 4],
   
5.            [1, 2, 3],
   
6.                      [1]
   
7.         ]
   
8. # pad sequence
   
9. padded = pad_sequences(sequences, maxlen=5)
   
10. print(padded)

复制代码

Running the example pads each sequence to the desired length of 5 timesteps, even though the maximum length of an observed sequence is only 4 timesteps.

1. [[0 1 2 3 4]
   
2. [0 0 1 2 3]
   
3. [0 0 0 0 1]]

复制代码

Sequence TruncationThe length of sequences can also be trimmed to a desired length.
The desired length for sequences can be specified as a number of timesteps with the “maxlen” argument.
There are two ways that sequences can be truncated: by removing timesteps from the beginning or the end of sequences.
Pre-Sequence TruncationThe default truncation method is to remove timesteps from the beginning of sequences. This is called pre-sequence truncation.
The example below truncates sequences to a desired length of 2.

1. from keras.preprocessing.sequence import pad_sequences
   
2. # define sequences
   
3. sequences = [
   
4.         [1, 2, 3, 4],
   
5.            [1, 2, 3],
   
6.                      [1]
   
7.         ]
   
8. # truncate sequence
   
9. truncated= pad_sequences(sequences, maxlen=2)
   
10. print(truncated)

复制代码

Running the example removes the first two timesteps from the first sequence, the first timestep from the second sequence, and pads the final sequence.

1. [[3 4]
   
2. [2 3]
   
3. [0 1]]

复制代码

Post-Sequence TruncationSequences can also be trimmed by removing timesteps from the end of the sequences.
This approach may be more desirable for some problem domains.
Post-sequence truncation can be configured by changing the “truncating” argument from the default ‘pre’ to ‘post’, as follows:

1. from keras.preprocessing.sequence import pad_sequences
   
2. # define sequences
   
3. sequences = [
   
4.         [1, 2, 3, 4],
   
5.            [1, 2, 3],
   
6.                      [1]
   
7.         ]
   
8. # truncate sequence
   
9. truncated= pad_sequences(sequences, maxlen=2, truncating='post')
   
10. print(truncated)

复制代码

Running the example removes the last two timesteps from the first sequence, the last timestep from the second sequence, and again pads the final sequence.

1. [[1 2]
   
2. [1 2]
   
3. [0 1]]

复制代码

SummaryIn this tutorial, you discovered how to prepare variable length sequence data for use with sequence prediction problems in Python.

扫码加我 拉你入群

请注明：姓名-公司-职位

以便审核进群资格，未注明则拒绝

分享0 收藏0 回帖

关键词：Preparation Sequences Variable sequence ration prediction techniques learning discover problems

00000000000

谢谢楼主分享！

谢谢分享

谢谢分享

谢谢分享