{"adoption": {"forks": 224, "observed_at": "2026-08-28T04:03:28.316183+00:00", "stars": 1071}, "canonical_url": "https://ross.abutalabs.com/products/spark-sklearn", "card": {"archived": true, "artifact_type": "library", "description": "(Deprecated) Scikit-learn integration package for Apache Spark", "domain": ["machine-learning", "big-data", "data-science"], "enriched": true, "function": ["machine-learning", "concurrency"], "health_score": 10, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["databricks/spark-sklearn"], "name": "databricks/spark-sklearn", "platform": ["python", "cross-platform"], "pushed_at": "2019-12-03T18:37:45+00:00", "repo": "databricks/spark-sklearn", "stars": 1071, "tags": ["apache-spark", "scikit-learn", "grid-search", "hyperparameter-tuning", "deprecated"], "topics": ["apache-spark", "scikit-learn", "grid-search", "parameter-tuning", "machine-learning"], "urls": [], "use_cases": ["distribute scikit-learn GridSearchCV across a Spark cluster", "train and evaluate multiple scikit-learn models in parallel", "convert Spark DataFrames to numpy arrays or sparse matrices", "run hyperparameter tuning on small datasets using Spark", "distribute scipy sparse matrices as a Spark dataset"], "what_it_is": "A deprecated Python library from Databricks that integrates scikit-learn with Apache Spark, primarily to distribute grid-search cross-validation and model training tasks across a Spark cluster. It also converts Spark DataFrames into numpy arrays or sparse matrices.", "when_to_avoid": ["starting a new project - use joblib-spark (joblibspark) instead as officially recommended", "you need to distribute individual learning algorithms rather than simple tasks like grid search", "your datasets do not fit in memory - use Spark MLlib instead", "you use scikit-learn >= 0.20 or recent Spark versions, which are incompatible"], "when_to_choose": ["you are maintaining legacy code already built on spark-sklearn", "you need a quick way to parallelize scikit-learn grid search on an existing Spark cluster with older library versions"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/spark-sklearn", "repo": "databricks/spark-sklearn", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:28.316183+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:53:48.729250+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "cd0e16f9c9cee6f4112763e5cb650ae673fb8d84815879995beecaba32a94d0f", "fetched_at": "2026-08-28T04:03:28.316183+00:00", "kind": "readme", "missing": false, "url": "https://github.com/databricks/spark-sklearn"}, {"content_hash": "c6db87ec8ddccdb6968db66b449a9e6b42036227fb8f407d53e9d14e498c2013", "fetched_at": "2026-08-29T12:56:12.707336+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/spark-sklearn/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4018, "days_push": 2465, "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}}