A time serie can be described with an LSTM Autoencoder. Usually, LSTM's are required to have fixed timesteps in order for the decoder part of the autoencoder to know beforehand how many timesteps should produce. However, this version of LSTM Autoencoder allows to describe timeseries based on random samples with unfixed timesteps.
In this LSTM autoencoder version, the decoder part is capable of producing, from an encoded version, as many timesteps as desired, serving the purposes of also predicting future steps.
It is required keras, tensorflow under the hood, pandas for the example and pyfolder for save/load of the trained model.
They can be installed with pip:
pip3 install -r requirements.txtTensorflow is not included in the requirements.txt, so it must be manually installed:
pip3 install tensorflowThere is an example in a example.py