{"adoption": {"forks": 608, "observed_at": "2026-08-28T04:04:10.016282+00:00", "stars": 1260}, "canonical_url": "https://ross.abutalabs.com/products/dataset-examples", "card": {"archived": true, "artifact_type": "learning-resource", "description": "Samples for users of the Yelp Academic Dataset", "domain": ["data-science", "big-data", "analytics", "tutorials"], "enriched": true, "function": ["data-science", "etl", "nlp", "machine-learning", "csv"], "health_score": 10, "homepage": "http://www.yelp.com/academic_dataset", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["YelpArchive/dataset-examples"], "name": "YelpArchive/dataset-examples", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2023-05-28T04:06:33+00:00", "repo": "YelpArchive/dataset-examples", "stars": 1260, "tags": ["yelp-dataset", "mrjob", "sample-code", "mapreduce", "academic-dataset", "-to-csv", "markov-chain", "aws-emr", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["convert the yelp academic dataset from  to csv", "learn how to process the yelp open dataset with python", "predict business categories from review text", "generate fake yelp-style reviews with a markov chain", "run mapreduce jobs on the yelp dataset with mrjob", "analyze word sentiment per review category", "get started with the yelp dataset challenge"], "what_it_is": "A collection of Python example scripts from Yelp demonstrating how to work with the Yelp Academic/Open Dataset, including a JSON-to-CSV converter, a category predictor, a Markov-chain review generator, and a word positivity scorer. The examples are built on Yelp's mrjob library and can run locally or on AWS EMR/Hadoop.", "when_to_avoid": ["you need a production data pipeline or maintained library rather than sample code", "you need Python 3-only tooling, since the examples target Python 2.6+ era mrjob", "you are not working with the Yelp dataset specifically"], "when_to_choose": ["you are a student or researcher starting with the Yelp Academic Dataset", "you want simple, runnable Python examples for JSON dataset conversion and basic NLP", "you want to learn mrjob and run jobs locally or on AWS EMR"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dataset-examples", "repo": "YelpArchive/dataset-examples", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:10.016282+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:04:22.608725+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7c7f3023c5f2991a1185930b5771df3b3960b65fd1d88393c886d071f2ec6027", "fetched_at": "2026-08-28T04:04:10.016282+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YelpArchive/dataset-examples"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5458, "days_push": 1193, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}