# csurfer/rake-nltk

Python implementation of the Rapid Automatic Keyword Extraction algorithm using NLTK.

Repository: https://github.com/csurfer/rake-nltk
Canonical: https://ross.abutalabs.com/products/rake-nltk
Homepage: https://csurfer.github.io/rake-nltk
Language: Python
License: MIT
License Family: permissive
Topics: nltk, algorithm, python, text-mining, keyword-extraction
Last push: 2022-12-09T05:43:43+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": 3514, "days_push": 1363, "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 1083, forks 151 (observed 2026-08-28T04:03:31.167366+00:00)

## What it is
rake-nltk is a Python library implementing the Rapid Automatic Keyword Extraction (RAKE) algorithm on top of NLTK. It determines key phrases in a body of text by analyzing word frequency and co-occurrence, with configurable tokenizers, language stopwords, and ranking metrics.

## Use cases
- extract keywords from text in python
- get key phrases from a document
- rake keyword extraction python implementation
- automatically tag articles with keyphrases
- find top ranked keywords with scores
- keyword extraction without training a machine learning model
- pull key phrases from sentences for search indexing

## When to choose
- you need a simple, domain-independent keyword extractor that works out of the box with no training data
- you want a lightweight pip-installable library rather than heavy ML or transformer dependencies
- you need configurable tokenization, language-based stopwords, or a custom ranking metric
- you are working with individual documents or short texts where statistical co-occurrence scoring is sufficient

## When to avoid
- you need semantically aware or state-of-the-art keyphrase extraction (consider embedding- or transformer-based tools like KeyBERT)
- you need to process very large corpora or streams at scale rather than individual documents
- you require languages or tokenization rules not covered by NLTK's stopwords and tokenizers
- you need actively developed software with frequent updates

## Facets
- artifact type: library
- maturity: stable
- function: nlp
- domain: -
- platform: python, cross-platform
- tags: keyword-extraction, text-mining, rake, keyphrases, nltk, stopwords, natural-language-processing

## Member repositories
- csurfer/rake-nltk (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.167366+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 2026-08-30T06:51:03.438094+00:00, confidence not recorded.
  - readme: https://github.com/csurfer/rake-nltk (fetched 2026-08-28T04:03:31.167366+00:00, sha a524fc9ccab4)
  - homepage: https://csurfer.github.io/rake-nltk (fetched 2026-08-29T12:53:25.704718+00:00, sha 9d24dc53ccef)
  - registry_pypi: https://pypi.org/pypi/rake-nltk/json (fetched 2026-08-29T12:53:25.713743+00:00, sha ba063457171d)
- Data as of 2026-08-30T08:39:29.467469+00:00.