# GestaltCogTeam/BasicTS

A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.

Repository: https://github.com/GestaltCogTeam/BasicTS
Canonical: https://ross.abutalabs.com/products/basicts
Homepage: https://ieeexplore.ieee.org/document/10726722/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: time-series, traffic-forecasting, benchmarking, long-time-series-forecasting
Last push: 2025-12-23T09:30:15+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 58, release rhythm 62, longevity 100
- inputs: {"age_days": 1655, "days_push": 253, "days_rel": 257, "gap_med": 6, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1814, forks 216 (observed 2026-08-28T04:05:39.836440+00:00)

## What it is
BasicTS is a Python benchmark library and toolkit for fair and scalable time series analysis, built on PyTorch. It supports forecasting, classification, and imputation tasks with statistical, machine learning, and deep learning baselines.

## Use cases
- benchmark time series forecasting models fairly
- train traffic flow forecasting models
- run long-term time series forecasting experiments
- compare deep learning baselines for time series
- impute missing values in time series data
- build custom time series models with modular components

## When to choose
- you need reproducible, fair comparisons across time series forecasting models
- you want a PyTorch toolkit with plug-and-play components for forecasting, classification, or imputation
- you work on spatial-temporal or long-term forecasting research

## When to avoid
- you need production time series forecasting as a service rather than a research toolkit
- you work outside Python/PyTorch ecosystems
- you need non-time-series ML tasks

## Facets
- artifact type: library
- maturity: active
- function: benchmarking, machine-learning, deep-learning, data-science
- domain: time-series, machine-learning, data-science
- platform: python
- tags: time-series-forecasting, traffic-forecasting, pytorch, benchmark, spatial-temporal-forecasting, long-term-forecasting, imputation, classification, gpu

## Member repositories
- GestaltCogTeam/BasicTS (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:39.836440+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:20:39.784491+00:00, confidence not recorded.
  - readme: https://github.com/GestaltCogTeam/BasicTS (fetched 2026-08-28T04:05:39.836440+00:00, sha 2d13b386c0e1)
  - homepage: https://ieeexplore.ieee.org/document/10726722/ (fetched 2026-08-29T10:59:50.410676+00:00, sha 44136fa355b3)
  - registry_pypi: https://pypi.org/pypi/basicts/json (fetched 2026-08-29T10:59:50.414478+00:00, sha 40610743eecd)
- Data as of 2026-08-30T08:39:29.467469+00:00.