# cemoody/lda2vec

Repository: https://github.com/cemoody/lda2vec
Canonical: https://ross.abutalabs.com/products/lda2vec
Language: Python
License: MIT
License Family: permissive
Last push: 2021-11-16T03:32:50+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3905, "days_push": 1751, "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 3169, forks 622 (observed 2026-08-28T04:07:47.339548+00:00)

## What it is
A Python library implementing lda2vec, a hybrid topic model that combines word2vec word embeddings with LDA-style interpretable document topics. It supports supervised topics and topics over metadata like clients, times, and regions.

## Use cases
- discover interpretable topics in a document corpus
- combine word embeddings with topic modeling
- model topics over documents, time, and metadata
- explore research topic models beyond LDA and word2vec
- analyze twenty newsgroups style text datasets

## When to choose
- you need interpretable document topics plus word-relationship structure
- you want a research starting point for custom topic models
- both plain LDA and word2vec are inadequate for your task

## When to avoid
- production systems - the author explicitly warns it is research software
- Windows environments
- you need well-maintained, heavily documented tooling
- modern GPU/PyTorch stacks - the codebase is dated

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, data-science
- domain: machine-learning, data-science
- platform: python
- tags: topic-modeling, word-embeddings, lda, word2vec, research-software, unsupervised-learning, natural-language-processing, linux, macos

## Member repositories
- cemoody/lda2vec (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:47.339548+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 2026-08-29T18:45:30.428938+00:00, confidence not recorded.
  - readme: https://github.com/cemoody/lda2vec (fetched 2026-08-28T04:07:47.339548+00:00, sha 97602b7efb95)
- Data as of 2026-08-30T08:39:29.467469+00:00.