skforecast

Skforecast is a Python library for time series forecasting using statistical and machine learning models. It works with any estimator compatible with the scikit-learn API, including popular options like LightGBM, XGBoost, CatBoost, Keras, and many others.

skforecast has been downloaded 3,355,602 times in total on PyPI, including 129,968 in the last 30 days. The latest version is 0.22.0, released Apr 23, 2026.

Version0.22.0
Downloads
3.36M
License
AuthorJoaquin Amat Rodrigo
UpdatedApr 23, 2026

Downloads

Weekly, last 90d.
Includes CI traffic.

VersionsTotal0.*
Range
View
Granularity
Group by
CI traffic
Stack: OffCI: Included2 / 37 series
Selected total725.45k
3.4MAll-time
130.0kLast 30 days
3.5kLast 24 h
0.03/sPer second

Version distribution

Share of downloads by released version. Computed over the last quarter.

  • 01

    0.14.0

    132.4k downloads
    36.5%
  • 02

    0.12.1

    45.1k downloads
    12.4%
  • 03

    0.22.0

    21.5k downloads
    5.9%
  • 04

    0.23.0

    21.1k downloads
    5.8%
  • 05

    0.18.0

    17.9k downloads
    4.9%
  • 06

    0.19.1

    13.2k downloads
    3.6%
  • 07

    0.6.0

    13.1k downloads
    3.6%
  • 08

    0.16.0

    11.6k downloads
    3.2%
  • 09

    Other

    86.9k downloads
    24.0%

Guess the next day

Thirteen recent days of skforecast downloads. Drag the green handle on the right to guess where day fourteen lands.

TRUTH3.5k3.1kFRISATSUNMONTUEWEDTHUFRISATSUNMONTUEWED
    skforecast · 3.4M downloads on PyPI