{"adoption": {"forks": 742, "observed_at": "2026-08-28T04:08:35.898882+00:00", "stars": 4118}, "canonical_url": "https://ross.abutalabs.com/products/aws-sdk-pandas", "card": {"archived": false, "artifact_type": "library", "description": "pandas on AWS - Easy integration with Athena, Glue, Redshift, Timestream, Neptune, OpenSearch, QuickSight, Chime, CloudWatchLogs, DynamoDB, EMR, SecretManager, PostgreSQL, MySQL, SQLServer and S3 (Parquet, CSV, JSON and EXCEL).", "domain": ["data-science", "cloud-computing", "databases", "big-data"], "enriched": true, "function": ["etl", "database", "data-science", "serialization"], "health_score": 100, "homepage": "https://aws-sdk-pandas.readthedocs.io", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["aws/aws-sdk-pandas"], "name": "aws/aws-sdk-pandas", "platform": ["python", "cloud", "serverless"], "pushed_at": "2026-08-26T14:16:39+00:00", "repo": "aws/aws-sdk-pandas", "stars": 4118, "tags": ["pandas", "aws", "athena", "redshift", "glue", "s3", "parquet", "data-lake", "awswrangler", "apache-arrow", "data-engineering"], "topics": ["python", "aws", "pandas", "apache-arrow", "apache-parquet", "data-engineering", "etl", "data-science", "redshift", "athena", "lambda", "aws-lambda", "aws-glue", "emr", "amazon-athena", "glue-catalog", "mysql", "amazon-sagemaker-notebook", "modin", "ray"], "urls": [], "use_cases": ["read and write parquet datasets on S3 from pandas", "query Amazon Athena and get results as a pandas DataFrame", "load pandas DataFrames into Redshift", "build a data lake on S3 with Glue catalog integration", "run ETL jobs in AWS Lambda with pandas", "export data to DynamoDB or Timestream from pandas", "read CSV, JSON, and Excel files from S3 into pandas"], "what_it_is": "AWS SDK for pandas (awswrangler) is a Python library that extends pandas with high-level APIs for reading and writing data across AWS services like S3, Athena, Glue, Redshift, Timestream, DynamoDB, and OpenSearch. It simplifies building data lakes and ETL pipelines by bridging pandas DataFrames with AWS analytics and storage services.", "when_to_avoid": ["you work outside AWS or with non-AWS data stores", "you need a general-purpose ORM or database driver rather than analytics integration", "your project does not use pandas or Arrow-based workflows"], "when_to_choose": ["you work with pandas and need seamless AWS data lake integration", "you want to move data between S3, Athena, Redshift, and other AWS analytics services", "you build ETL pipelines in Python on AWS", "you need Glue Catalog-backed datasets with partitioning"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/aws-sdk-pandas", "repo": "aws/aws-sdk-pandas", "role": "main", "score": 94}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.898882+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:23:08.120459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f248295b1f9fc167c39f7aff4dc4e7bb183b90a35686159955d16df636a668dd", "fetched_at": "2026-08-28T04:08:35.898882+00:00", "kind": "readme", "missing": false, "url": "https://github.com/aws/aws-sdk-pandas"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 84}, "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": 2746, "days_push": 7, "days_rel": 30, "gap_med": 43.0, "n_releases_24m": 13}, "score": 94, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}