# chakki-works/seqeval

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

Repository: https://github.com/chakki-works/seqeval
Canonical: https://ross.abutalabs.com/products/seqeval
Language: Python
License: MIT
License Family: permissive
Topics: sequence-labeling, natural-language-processing, deep-learning, machine-learning, python, sequence-labeling-evaluation, conlleval, named-entity-recognition
Last push: 2024-08-28T11:35:51+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3122, "days_push": 735, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1184, forks 130 (observed 2026-08-28T04:03:54.630755+00:00)

## What it is
seqeval is a Python library for evaluating sequence labeling tasks such as named-entity recognition, part-of-speech tagging, and semantic role labeling. It computes accuracy, precision, recall, and F1 scores with support for IOB1/IOB2/IOE1/IOE2/IOBES/BILOU schemes and a conlleval-compatible default mode.

## Use cases
- evaluate NER model predictions with F1 score
- compute precision and recall for sequence labeling output
- generate a classification report for chunking tasks
- validate BIO-tagged predictions against conlleval behavior
- evaluate POS tagging or semantic role labeling performance
- score IOBES or BILOU scheme predictions in strict mode

## When to choose
- you need standard NER/sequence-labeling metrics in Python
- you want results compatible with the Perl conlleval script
- you need strict scheme-aware evaluation for IOBES or BILOU tags

## When to avoid
- you need general classification metrics without sequence structure
- you are not working with sequence labeling or chunking tasks

## Facets
- artifact type: library
- maturity: stable
- function: testing, nlp, machine-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: sequence-labeling, named-entity-recognition, ner-evaluation, conlleval, pos-tagging, iobes, f1-score, natural-language-processing

## Member repositories
- chakki-works/seqeval (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.630755+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 2026-08-30T06:24:14.286966+00:00, confidence not recorded.
  - readme: https://github.com/chakki-works/seqeval (fetched 2026-08-28T04:03:54.630755+00:00, sha ecdfc8448b03)
  - registry_pypi: https://pypi.org/pypi/seqeval/json (fetched 2026-08-29T12:31:27.460048+00:00, sha b7555fe739ee)
- Data as of 2026-08-30T08:39:29.467469+00:00.