{"adoption": {"forks": 151, "observed_at": "2026-08-28T04:03:31.167366+00:00", "stars": 1083}, "canonical_url": "https://ross.abutalabs.com/products/rake-nltk", "card": {"archived": false, "artifact_type": "library", "description": "Python implementation of the Rapid Automatic Keyword Extraction algorithm using NLTK.", "domain": [], "enriched": true, "function": ["nlp"], "health_score": 20, "homepage": "https://csurfer.github.io/rake-nltk", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["csurfer/rake-nltk"], "name": "csurfer/rake-nltk", "platform": ["python", "cross-platform"], "pushed_at": "2022-12-09T05:43:43+00:00", "repo": "csurfer/rake-nltk", "stars": 1083, "tags": ["keyword-extraction", "text-mining", "rake", "keyphrases", "nltk", "stopwords", "natural-language-processing"], "topics": ["nltk", "algorithm", "python", "text-mining", "keyword-extraction"], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rake-nltk", "repo": "csurfer/rake-nltk", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.167366+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:51:03.438094+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a524fc9ccab465e1e135bb2fc62f099bd1930db7d3fbeb5a419529aed9a2cc35", "fetched_at": "2026-08-28T04:03:31.167366+00:00", "kind": "readme", "missing": false, "url": "https://github.com/csurfer/rake-nltk"}, {"content_hash": "9d24dc53ccef0477ea801982372f75fd479688fa8a6819e14697ebe814fe6a07", "fetched_at": "2026-08-29T12:53:25.704718+00:00", "kind": "homepage", "missing": false, "url": "https://csurfer.github.io/rake-nltk"}, {"content_hash": "ba063457171d12d6c6e1fd655bffbbb73ee27e7cac21219ce3d5613eb4beea00", "fetched_at": "2026-08-29T12:53:25.713743+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/rake-nltk/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3514, "days_push": 1363, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}