{"library":"koheesio","type":"library","category":null,"description":"Koheesio is a unified, composable, and scalable steps-based framework for data processing and ETL tasks built on top of Apache Spark. It simplifies the creation and orchestration of data pipelines by providing a structured way to define and execute steps. The current version is 0.10.6, and it maintains an active release cadence with frequent updates and bug fixes.","language":"python","status":"active","version":"0.10.6","tags":["data-processing","spark","etl","pipeline","dataframe","snowflake","databricks","pydantic"],"last_verified":"Fri May 22","install":[{"cmd":"pip install koheesio","imports":["from koheesio.spark import KoheesioSparkSession","from koheesio.steps import Step","from koheesio.pipelines import Pipeline","from koheesio.steps.readers import CsvReader"]},{"cmd":"pip install 'koheesio[snowflake]' # for Snowflake features","imports":[]},{"cmd":"pip install 'koheesio[all]' # for all optional dependencies","imports":[]}],"homepage":null,"github":"https://github.com/Nike-Inc/koheesio#readme","docs":"https://github.com/Nike-Inc/koheesio#readme","changelog":null,"pypi":"https://pypi.org/project/koheesio/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":67,"avg_install_s":4.9,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/koheesio/compatibility"}}