{"adoption": {"forks": 374, "observed_at": "2026-08-28T04:03:45.519491+00:00", "stars": 1145}, "canonical_url": "https://ross.abutalabs.com/products/keyword_extraction", "card": {"archived": false, "artifact_type": "library", "description": "利用Python实现中文文本关键词抽取，分别采用TF-IDF、TextRank、Word2Vec词聚类三种方法。", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "parser", "machine-learning"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["AimeeLee77/keyword_extraction"], "name": "AimeeLee77/keyword_extraction", "platform": ["python"], "pushed_at": "2018-01-16T01:10:56+00:00", "repo": "AimeeLee77/keyword_extraction", "stars": 1145, "tags": ["keyword-extraction", "tf-idf", "textrank", "word2vec", "chinese-text", "jieba", "gensim", "text-summarization", "natural-language-processing", "chinese-language"], "topics": [], "urls": [], "use_cases": ["extract keywords from Chinese text", "compare TF-IDF and TextRank keyword extraction", "cluster words with Word2Vec to find document keywords", "learn Chinese NLP keyword extraction in Python", "extract keywords from patent abstracts", "build Chinese word embeddings with Gensim"], "what_it_is": "A Python project implementing Chinese text keyword extraction using three methods: TF-IDF, TextRank, and Word2Vec word clustering. It includes a detailed tutorial-style walkthrough with sample patent text data and Chinese stopword dictionaries.", "when_to_avoid": ["you need a production-ready maintained library with a license", "you need multilingual keyword extraction beyond Chinese", "you need Python 3 compatibility guarantees, since it was built on Python 2.7"], "when_to_choose": ["you need to extract keywords from Chinese-language documents", "you want a learning resource explaining TF-IDF, TextRank, and Word2Vec clustering side by side", "you are working with patent or technical Chinese corpora"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/keyword_extraction", "repo": "AimeeLee77/keyword_extraction", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:45.519491+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:34:14.035087+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fce692b210ef45607b2913a8488373a50514a261bb8a3da038b4f5e76c28f90d", "fetched_at": "2026-08-28T04:03:45.519491+00:00", "kind": "readme", "missing": false, "url": "https://github.com/AimeeLee77/keyword_extraction"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3206, "days_push": 3152, "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}}