This tutorial is designed to easily learn TensorFlow for time series prediction. Each tutorial subject includes both code and notebook with descriptions.
- Classification for MNIST using RNN (notebook)
- 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
Python (3.4.4)
TensorFlow (r0.9)
numpy (1.11.1)
pandas (0.16.2)
cuda (to run examples on GPU)
- Energy Price Forecast 2016: http://complatt.smartwatt.net
- Or use the uploaded csv file for price history for 2015.
tf:split_squeeze
is deprecated and will be removed after 2016-08-01. Usetf.unpack
instead.tf:dnn
is deprecated and will be removed after 2016-08-01. Usetf.contrib.layers.stack
instead.
Now I am working on modifying previous source code for tensorflow ver. 0.10.0rc0.
- 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