# chartbeat-labs/textacy

NLP, before and after spaCy

Repository: https://github.com/chartbeat-labs/textacy
Canonical: https://ross.abutalabs.com/products/textacy
Homepage: https://textacy.readthedocs.io
Language: Python
License: NOASSERTION
License Family: other
Topics: natural-language-processing, nlp, python, spacy
Last push: 2023-09-22T23:38:28+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": 3864, "days_push": 1076, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2239, forks 247 (observed 2026-08-28T04:06:29.628399+00:00)

## What it is
textacy is a Python NLP library built on spaCy that handles tasks before and after spaCy's core pipeline, such as text cleaning, information extraction, and topic modeling. It also provides prepared text datasets and readability/lexical diversity statistics.

## Use cases
- extract keyterms and n-grams from documents
- train and visualize topic models on a corpus
- clean and normalize raw text before spaCy processing
- compute Flesch-Kincaid readability scores
- extract entities, acronyms, and SVO triples from text
- load prepared NLP datasets like Congressional speeches
- compare strings with similarity metrics

## When to choose
- you already use spaCy and need higher-level text analysis utilities
- you need keyterm extraction, topic modeling, or readability statistics in Python
- you want convenient access to prepared text datasets with metadata

## When to avoid
- you need core tokenization, tagging, or parsing - use spaCy directly
- you need a framework-agnostic NLP toolkit independent of spaCy
- you need actively developed features - releases have slowed since 2023

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, parser, machine-learning, data-science
- domain: text-editors, data-science
- platform: python
- tags: spacy, topic-modeling, text-processing, keyterm-extraction, readability-statistics, linguistics, natural-language-processing

## Member repositories
- chartbeat-labs/textacy (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.628399+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 2026-08-30T02:44:09.021217+00:00, confidence not recorded.
  - readme: https://github.com/chartbeat-labs/textacy (fetched 2026-08-28T04:06:29.628399+00:00, sha 774288efaf7c)
  - registry_pypi: https://pypi.org/pypi/textacy/json (fetched 2026-08-29T10:25:12.548660+00:00, sha 19b0f38a90f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.