Space-time prediction with sparse and irregular space-time multi-timeserie.
Project description
steams
Space-time prediction with sparse and irregular space-time multi-timeseries.
Models presented in this packages are using an adaptive distance attention mechanism. The weight of the attention are based either on the Ordinary Kriging equation system or the Nadaraya-Watson Kernel.
Install from PyPi
pip install steams
install from source
cd /tmp
git clone https://git.nilu.no/aqdl/steams_pkg.git
cd steams_pkg
pip3 install -e .
Package 'steams' has been tested on python 3.8 and 3.9
Running 'steams' with CUDA (v11.3), requires a manual installation of pytorch:
pip3 install torch==1.11.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
steams-0.18.tar.gz
(15.1 kB
view hashes)
Built Distribution
steams-0.18-py3-none-any.whl
(16.8 kB
view hashes)