# maciejkula/glove-python

Toy Python implementation of http://www-nlp.stanford.edu/projects/glove/

Repository: https://github.com/maciejkula/glove-python
Canonical: https://ross.abutalabs.com/products/glove-python
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2022-02-19T11:37:43+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4341, "days_push": 1656, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1253, forks 316 (observed 2026-08-28T04:04:08.512322+00:00)

## What it is
A toy Python/Cython implementation of the GloVe algorithm for training dense word vector embeddings by factorizing the log of the word co-occurrence matrix. It provides a Corpus class and a Glove class with a sklearn-esque API, plus basic paragraph vector support.

## Use cases
- train word embeddings from a text corpus in python
- compute most similar words to a given word
- build a co-occurrence matrix from tokenized text
- get paragraph embeddings for multi-word text
- alternative to word2vec for word vectors

## When to choose
- you want a pure-Python, hackable GloVe implementation with a simple sklearn-like API
- you need to train word embeddings on a small to medium corpus
- you want paragraph vectors similar to tf-idf weighted averaging

## When to avoid
- you need production-grade, well-tested GloVe training at scale
- you need modern transformer-based embeddings
- you are on macOS with Clang and cannot install gcc/OpenMP

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp
- domain: machine-learning
- platform: python, windows
- tags: word-embeddings, glove, cython, word-vectors, co-occurrence-matrix, natural-language-processing, linux, macos

## Member repositories
- maciejkula/glove-python (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:08.512322+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 2026-08-30T05:07:29.154949+00:00, confidence not recorded.
  - readme: https://github.com/maciejkula/glove-python (fetched 2026-08-28T04:04:08.512322+00:00, sha 6365827f4045)
  - registry_pypi: https://pypi.org/pypi/glove-python/json (fetched 2026-08-29T12:18:14.990076+00:00, sha 3223e1b04908)
- Data as of 2026-08-30T08:39:29.467469+00:00.