mounalab / Multivariate-time-series-forecasting-keras

This project provides implementations with Keras/Tensorflow of some deep learning algorithms for Multivariate Time Series Forecasting: Transformers, Recurrent neural networks (LSTM and GRU), Convolutional neural networks, Multi-layer perceptron

Multivariate Time series forecasting with Keras

This project provides implementations of some deep learning algorithms for Multivariate Time Series Forecasting

• Transformers
• Recurrent neural networks (LSTM and GRU)
• Convolutional neural networks
• Multi-head multi-layer perceptron

Prequisites

Prequisites are defined in requirements.txt file

Running Example

A running example is implemented in _main_.py
Used Dataset is not included in this project
A Jupyter notebook for RNN model is also available.

Dataset

The used open dataset 'Household Power Consumption' available at https://archive.ics.uci.edu/ml/datasets/individual+household+electric+power+consumption
Prep-processing steps to get the used cleaned version are available in the tutorial https://machinelearningmastery.com/multi-step-time-series-forecasting-with-machine-learning-models-for-household-electricity-consumption/