Sachithx/EntroPE

This includes the codebase for EntroPE (Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting) paper.

40
/ 100
Emerging

This project helps operations engineers, data scientists, and analysts predict future values in time-series data like energy consumption or weather patterns. Instead of breaking data into arbitrary chunks, it intelligently segments your raw time series into meaningful pieces based on how much the data changes. This allows for more accurate forecasts of critical metrics, improving planning and resource allocation.

Use this if you need to improve the accuracy of your time series forecasts, especially for complex or rapidly changing data, and want to incorporate the natural structure of your time series.

Not ideal if your time series data is very simple, changes predictably, or if you require an extremely lightweight solution where maximum predictive power is not the primary goal.

time-series-forecasting energy-prediction weather-forecasting operations-analytics predictive-maintenance
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

41

Forks

3

Language

Python

License

Apache-2.0

Last pushed

Feb 01, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Sachithx/EntroPE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.