https://github.com/tgjeon/tensorflow-tutorials-for-time-series
TensorFlow Tutorial for Time Series Prediction
https://github.com/tgjeon/tensorflow-tutorials-for-time-series
rnn series-prediction tensorflow-tutorials
Last synced: about 1 year ago
JSON representation
TensorFlow Tutorial for Time Series Prediction
- Host: GitHub
- URL: https://github.com/tgjeon/tensorflow-tutorials-for-time-series
- Owner: tgjeon
- License: mit
- Created: 2016-05-30T01:15:55.000Z (about 10 years ago)
- Default Branch: master
- Last Pushed: 2017-08-01T07:55:55.000Z (almost 9 years ago)
- Last Synced: 2025-04-03T16:13:18.072Z (about 1 year ago)
- Topics: rnn, series-prediction, tensorflow-tutorials
- Language: Jupyter Notebook
- Homepage:
- Size: 2.26 MB
- Stars: 1,104
- Watchers: 89
- Forks: 417
- Open Issues: 11
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# TensorFlow Tutorial for Time Series Prediction
This tutorial is designed to easily learn TensorFlow for time series prediction.
Each tutorial subject includes both code and notebook with descriptions.
## Tutorial Index
#### MNIST classification using Recurrent Neural Networks (RNN)
- Classification for MNIST using RNN ([notebook](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/blob/master/mnist-rnn.ipynb))
#### Time series prediction using Recurrent Neural Networks (RNN)
- Prediction for sine wave function using Gaussian process ([code](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/blob/master/gp-for-sine-wave.py) / [notebook](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/blob/master/gp-for-sine-wave.ipynb))
- Prediction for sine wave function using RNN ([code](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/blob/master/lstm-for-sine-wave.py) / [notebook](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/blob/master/lstm-for-sine-wave.ipynb))
- Prediction for electricity price ([code](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/blob/master/lstm-for-epf.py) / notebook)
These codes are adapted from the source: https://github.com/mouradmourafiq/tensorflow-lstm-regression
## Slide materials
- [Slides on slideshare (TensorFlow-KR Meetup)](http://www.slideshare.net/TaegyunJeon1/electricity-price-forecasting-with-recurrent-neural-networks)
- [Slides on github (KSC 2016 Tutorial)](https://github.com/tgjeon/TensorFlow-Tutorials-for-Time-Series/raw/master/KSC2016%20-%20Recurrent%20Neural%20Networks.pptx)
#### Dependencies
```
Python (3.4.4)
TensorFlow (r0.9)
numpy (1.11.1)
pandas (0.16.2)
cuda (to run examples on GPU)
```
#### Dataset
- Energy Price Forecast 2016: http://complatt.smartwatt.net
- Or use the uploaded csv file for price history for 2015.
#### Current issues
- ```tf:split_squeeze``` is deprecated and will be removed after 2016-08-01. Use ```tf.unpack``` instead.
- ```tf:dnn``` is deprecated and will be removed after 2016-08-01. Use ```tf.contrib.layers.stack``` instead.
Now I am working on modifying previous source code for tensorflow ver. 0.10.0rc0.
#### Notice
- I have received many request for revising the code for the current tensorflow version.
- I will provide summarized presentation file for the theory of time series prediction.
- And How to apply the tensorflow implementation for kaggle competitions.
- Target implementation will be tensorflow v1.2