{"adoption": {"forks": 236, "observed_at": "2026-08-28T04:07:29.130952+00:00", "stars": 2907}, "canonical_url": "https://ross.abutalabs.com/products/texthero", "card": {"archived": false, "artifact_type": "library", "description": "Text preprocessing, representation and visualization from zero to hero.", "domain": ["data-science", "machine-learning"], "enriched": true, "function": ["nlp", "data-science", "data-visualization", "machine-learning", "parser"], "health_score": 20, "homepage": "https://texthero.org", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["jbesomi/texthero"], "name": "jbesomi/texthero", "platform": ["python"], "pushed_at": "2023-08-29T08:45:13+00:00", "repo": "jbesomi/texthero", "stars": 2907, "tags": ["text-preprocessing", "pandas", "tf-idf", "word-embeddings", "text-clustering", "topic-modeling", "named-entity-recognition", "scikit-learn", "natural-language-processing", "text-mining"], "topics": ["text-preprocessing", "text-representation", "text-visualization", "nlp", "word-embeddings", "machine-learning", "text-mining", "nlp-pipeline", "text-clustering", "texthero"], "urls": [], "use_cases": ["clean and preprocess text data in pandas", "compute tf-idf vectors for a text corpus", "cluster documents with k-means", "visualize text vector spaces with pca and tsne", "extract named entities from text", "find top words and keywords in a dataset", "remove stopwords, punctuation, and html tags from text"], "what_it_is": "Texthero is a Python toolkit for text preprocessing, representation, and visualization, designed to work on top of Pandas Series and DataFrames. It provides pipelines for cleaning text, mapping it into vector spaces (TF-IDF, term frequency), clustering, dimensionality reduction, and visualizing text datasets in a few lines of code.", "when_to_avoid": ["you need state-of-the-art NLP models or transformer-based pipelines", "you need actively developed features or timely bug fixes", "you need production-grade, highly customizable NLP pipelines"], "when_to_choose": ["you work with text datasets in Pandas and want quick cleaning and vectorization", "you need fast exploratory insights into text-only data", "you want a simple scikit-learn-like API for text preprocessing and clustering"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/texthero", "repo": "jbesomi/texthero", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:29.130952+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:34:23.846675+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8bbf98304d9d870df3122d6b5f420b8a16fb004cd6d9e7001ae163d204a4bd7", "fetched_at": "2026-08-28T04:07:29.130952+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jbesomi/texthero"}, {"content_hash": "558e07bfe983a11788e147f59e0c948ab49d5d330cb213865a9d452c02324019", "fetched_at": "2026-08-29T09:49:41.784577+00:00", "kind": "homepage", "missing": false, "url": "https://texthero.org"}, {"content_hash": "4344e832fdf754848b5ceeb82c34ccb7dc56f1adeb23b67e5752898c330122ba", "fetched_at": "2026-08-29T09:49:41.794195+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/getting-started"}, {"content_hash": "80b724589586eb9fe11b15e16ae37506a2e43918d78613027dac1555ec898bb4", "fetched_at": "2026-08-29T09:49:41.796506+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-preprocessing"}, {"content_hash": "4b71b429f618735d3b6d28ab326241d8d0ce4d00085a425359bd8365a7ca3505", "fetched_at": "2026-08-29T09:49:41.798282+00:00", "kind": "site_page", "missing": false, "url": "https://texthero.org/docs/api-representation"}, {"content_hash": "c92c0e50d869ff23db1fac900060507c8134a3667650c88ad2163ef8dbb455d2", "fetched_at": "2026-08-29T09:49:41.799833+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/texthero/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2340, "days_push": 1100, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}