You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
25 lines
1.1 KiB
25 lines
1.1 KiB
1 year ago
|
# LSTM Neural Network for Time Series Prediction
|
||
|
|
|
||
|
|
LSTM built using the Keras Python package to predict time series steps and sequences. Includes sine wave and stock market data.
|
||
|
|
|
||
|
|
[Full article write-up for this code](https://www.altumintelligence.com/articles/a/Time-Series-Prediction-Using-LSTM-Deep-Neural-Networks)
|
||
|
|
|
||
|
|
[Video on the workings and usage of LSTMs and run-through of this code](https://www.youtube.com/watch?v=2np77NOdnwk)
|
||
|
|
|
||
|
|
## Requirements
|
||
|
|
|
||
|
|
Install requirements.txt file to make sure correct versions of libraries are being used.
|
||
|
|
|
||
|
|
* Python 3.5.x
|
||
|
|
* TensorFlow 1.10.0
|
||
|
|
* Numpy 1.15.0
|
||
|
|
* Keras 2.2.2
|
||
|
|
* Matplotlib 2.2.2
|
||
|
|
|
||
|
|
Output for sine wave sequential prediction:
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
Output for stock market multi-dimensional multi-sequential predictions:
|
||
|
|
|
||
|
|
|