{"adoption": {"forks": 370, "observed_at": "2026-08-28T04:07:58.421310+00:00", "stars": 3372}, "canonical_url": "https://ross.abutalabs.com/products/koalas", "card": {"archived": false, "artifact_type": "library", "description": "Koalas: pandas API on Apache Spark", "domain": ["big-data", "data-science"], "enriched": true, "function": ["data-science", "etl", "streaming"], "health_score": 20, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["databricks/koalas"], "name": "databricks/koalas", "platform": ["python", "cross-platform"], "pushed_at": "2024-03-20T15:33:34+00:00", "repo": "databricks/koalas", "stars": 3372, "tags": ["pandas", "apache-spark", "dataframe", "distributed-computing", "deprecated", "pyspark", "data-engineering"], "topics": ["spark", "pandas", "pydata", "dataframe", "mlflow", "big-data", "data-science"], "urls": [], "use_cases": ["run pandas code on large distributed datasets with spark", "scale existing pandas dataframes to big data", "use one codebase for pandas and spark", "migrate pandas workflows to spark without rewriting", "do data science on big data with familiar api"], "what_it_is": "Koalas implements the pandas DataFrame API on top of Apache Spark, letting data scientists use familiar pandas code on distributed big data. It is now deprecated and merged into PySpark as of Apache Spark 3.2.", "when_to_avoid": ["you use Apache Spark 3.2 or above - use PySpark's built-in pandas API instead", "you are starting a new project - the project is deprecated and in maintenance mode", "your datasets fit comfortably in memory on a single machine - plain pandas is simpler"], "when_to_choose": ["you are on Spark 3.1 or below and want the pandas API on Spark", "you need a single codebase that works with both pandas and Spark", "your team knows pandas but not the Spark DataFrame API"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/koalas", "repo": "databricks/koalas", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.421310+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:39:56.667068+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6eeccf23ddc53d05c87e4c1b011b230ba8e35d272047e79391a91188eaba606b", "fetched_at": "2026-08-28T04:07:58.421310+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/koalas"}, {"content_hash": "b84fe66e0f39be681febb28d83da349a70db10d04085021712d9759a993e5a76", "fetched_at": "2026-08-29T09:33:40.630248+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/koalas/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "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": 2799, "days_push": 896, "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}}