简体繁体中英

Handling Missing Data in RNN / LSTM (Time-Series)

原文 2017-04-28 12:37:40 4 1 python/ machine-learning/ neural-network/ keras/ lstm

As the title suggests, I have a time-series data set and there is a lot of missing data. What is the best way to handle this for a LSTM model?

To give further detail, I have about five data sources to create the dataset and some of them do not allow me to get historical data so I'm missing quite a bit for the features in that source. I can fill some in using the most recently observed sample, but for the most part that isn't possible.

Some suggestions I have seen are:

Hidden Markov Modeling
Expectation Maximization
Using a neural net to predict the missing values

But for all I feel like I will be losing a lot of data integrity. How is this usually handled / what is the best way to adjust for this in LSTM models?

I'm using Python / Keras / TensorFlow.

1 answers

Maybe masking at the top layer of your model could help.

For each timestep in the input tensor (dimension #1 in the tensor), if all values in the input tensor at that timestep are equal to mask_value, then the timestep will be masked (skipped) in all downstream layers (as long as they support masking).

How to input multiple time-series data(wave) for RNN

How to correctly shape time-series data for RNN?

LSTM with multiple time-series

Are there some pre-trained LSTM, RNN or ANN models for time-series prediction?

Proper way to feed time-series data to stateful LSTM?

Time-Series prediction of seasonal data using keras' LSTM

Extremely poor prediction: LSTM time-series

Initializing LSTM for time-series classification on TensorFlow

Keras LSTM Autoencoder time-series reconstruction

Pandas - fill missing times in Time-Series data

暂无

The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.

Related Question How to input multiple time-series data(wave) for RNN How to correctly shape time-series data for RNN? LSTM with multiple time-series Are there some pre-trained LSTM, RNN or ANN models for time-series prediction? Proper way to feed time-series data to stateful LSTM? Time-Series prediction of seasonal data using keras' LSTM Extremely poor prediction: LSTM time-series Initializing LSTM for time-series classification on TensorFlow Keras LSTM Autoencoder time-series reconstruction Pandas - fill missing times in Time-Series data

Related Tags

Handling Missing Data in RNN / LSTM (Time-Series)

Question

1 answers

solution1 3 2017-06-22 14:53:40

solution1
3 2017-06-22 14:53:40