{"adoption": {"forks": 563, "observed_at": "2026-08-28T04:06:11.671972+00:00", "stars": 2081}, "canonical_url": "https://ross.abutalabs.com/products/nyc-taxi-data", "card": {"archived": false, "artifact_type": "dataset", "description": "Import public NYC taxi and for-hire vehicle (Uber, Lyft) trip data into a PostgreSQL or ClickHouse database", "domain": ["big-data", "analytics"], "enriched": true, "function": ["etl", "database", "data-science", "analytics"], "health_score": 42, "homepage": null, "language": "R", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["toddwschneider/nyc-taxi-data"], "name": "toddwschneider/nyc-taxi-data", "platform": ["cli"], "pushed_at": "2025-08-18T17:13:46+00:00", "repo": "toddwschneider/nyc-taxi-data", "stars": 2081, "tags": ["nyc-taxi", "parquet", "uber", "lyft", "trip-data", "r-scripts", "shell-scripts", "open-data", "data-engineering", "transportation", "postgresql", "clickhouse", "macos", "linux"], "topics": ["clickhouse", "nyc", "nyc-taxi-dataset", "postgresql"], "urls": [], "use_cases": ["import nyc taxi trip data into postgres", "load uber and lyft trip records into clickhouse", "analyze billions of taxi trips", "build a taxi dataset for sql practice", "convert tlc parquet files for database import", "reproduce nyc taxi data analysis"], "what_it_is": "A collection of R and shell scripts to download, process, and import 3+ billion NYC taxi and for-hire vehicle (Uber, Lyft) trip records into PostgreSQL or ClickHouse. It handles the TLC's Parquet data format and includes schema setup for analysis.", "when_to_avoid": ["you need real-time taxi data feeds", "you want a prebuilt hosted dataset rather than running your own import pipeline", "you rely on the old TLC CSV files, which are no longer supported"], "when_to_choose": ["you want the full NYC TLC taxi/FHV trip history in your own PostgreSQL or ClickHouse database", "you need a large real-world dataset for SQL or analytics experimentation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/nyc-taxi-data", "repo": "toddwschneider/nyc-taxi-data", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:11.671972+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:56:01.464323+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "170d83c6bc59dc91025011715e3bbc2c927472fdeb4f9baead8f11076103b859", "fetched_at": "2026-08-28T04:06:11.671972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/toddwschneider/nyc-taxi-data"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 37, "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": 3943, "days_push": 380, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}