Ctrl K

Lilio

A Python package for generating calendars to resample timeseries into training and target data for machine learning. Named after the inventor of the Gregorian Calendar.

3
mentions
5
contributors

Cite this software

DOI:

10.5281/zenodo.7620212

Description

Lilio helps you to organize timeseries data in such a way that it can easily be used in a machine learning workflow. It is geared towards predictions of events with (annual) return periods. Lilio distinguishes between target and precursor periods (features) and stacks the timeseries such that targets from different years are treated as independent records (samples).

Concretely, Lilio helps you to:

  • Define target and precursor periods
  • Resample and reshape input data
  • Split data into train-test sets
  • Avoid information leakage between train/test sets
Logo of Lilio
Keywords
AI
Preprocessing
S2S
Programming languages
License
</>Source code

Participating organisations

Netherlands eScience Center
Vrije Universiteit Amsterdam

Reference papers

Mentions

Contributors

Contact person

Bart Schilperoort
Yang Liu
Yang Liu
SV
Sem Vijverberg
JvI
Jannes van Ingen
Vrije Universiteit Amsterdam

Related projects

AI4S2S

A high-level python package integrating expert knowledge and artificial intelligence to boost (sub) seasonal forecasting

Updated 10 months ago
Finished

Related software

s2spy

S2

A high-level python package integrating expert knowledge and artificial intelligence to boost sub-seasonal to seasonal (S2S) forecasting.

Updated 26 months ago
3 6