/TensorFlow-Tutorials-for-Time-Series

TensorFlow Tutorial for Time Series Prediction

Primary LanguageJupyter NotebookMIT LicenseMIT

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)

Time series prediction using Recurrent Neural Networks (RNN)

  • Prediction for sine wave function using Gaussian process (code / notebook)
  • Prediction for sine wave function using RNN (code / notebook)
  • Prediction for electricity price (code / notebook)

These codes are adapted from the source: https://github.com/mouradmourafiq/tensorflow-lstm-regression

Slide materials

Dependencies

Python (3.4.4)
TensorFlow (r0.9)
numpy (1.11.1)
pandas (0.16.2)
cuda (to run examples on GPU)

Dataset

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