{"adoption": {"forks": 286, "observed_at": "2026-08-28T04:06:38.895563+00:00", "stars": 2341}, "canonical_url": "https://ross.abutalabs.com/products/scattertext", "card": {"archived": false, "artifact_type": "library", "description": "Beautiful visualizations of how language differs among document types.", "domain": ["data-visualization", "data-science"], "enriched": true, "function": ["nlp", "data-visualization", "data-science"], "health_score": 74, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["JasonKessler/scattertext"], "name": "JasonKessler/scattertext", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-04T21:25:24+00:00", "repo": "JasonKessler/scattertext", "stars": 2341, "tags": ["text-analysis", "scatter-plot", "d3", "exploratory-data-analysis", "stylometry", "topic-modeling", "word-embeddings", "corpus-comparison", "natural-language-processing"], "topics": ["nlp", "d3", "word-embeddings", "machine-learning", "natural-language-processing", "visualization", "word2vec", "text-visualization", "text-mining", "japanese-language", "computational-social-science", "sentiment", "eda", "exploratory-data-analysis", "text-as-data", "scatter-plot", "topic-modeling", "stylometry", "stylometric", "semiotic-squares"], "urls": [], "use_cases": ["visualize how language differs between two document categories", "find distinguishing terms in a text corpus", "compare word usage between political parties in speeches", "exploratory data analysis of text data", "stylometric analysis of authorship", "create interactive term scatter plots for a report"], "what_it_is": "A Python library for finding and visualizing distinguishing terms across document categories as interactive HTML scatter plots. It integrates with NLP pipelines to compare corpora and render browser-based term visualizations with selective labeling.", "when_to_avoid": ["you need general-purpose charting beyond text term comparison", "you need a production NLP pipeline rather than analysis/visualization", "you're not working in Python"], "when_to_choose": ["you need to compare term usage across document categories in Python", "you want publication-quality interactive text visualizations", "you're doing computational social science or text-as-data research"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scattertext", "repo": "JasonKessler/scattertext", "role": "main", "score": 63}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:38.895563+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:37:21.940475+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "652d2be4f840dc32bc7b209574f9801f2d3e28a431afc8351ee81140ed4e4537", "fetched_at": "2026-08-28T04:06:38.895563+00:00", "kind": "readme", "missing": false, "url": "https://github.com/JasonKessler/scattertext"}, {"content_hash": "5643a6fbf9a741634eabe279a0c41f38dd18d6d2a1f06ac7909c003b7ec1fd5c", "fetched_at": "2026-08-29T10:17:51.563812+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/scattertext/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 90, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3696, "days_push": 60, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 63, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}