These are my go-to libraries for Python data crunching.
This is a full BI pipeline built over a 68,117-record cardiovascular health dataset, plus a parallel machine learning track on the same data. Raw patient data is loaded through SSIS into SQL Server, ...
MPEA dataset The complete database file. Contains all compositions, properties, and reference info. Compositions A csv of all the unique compositions in the database. Grouped by composition A styled ...