Training Data: Assessing a structure agnostic machine learning framework with experimental screening of magnetic materials

Dataset in CSV format supporting this article in Physical Review Materials: https://doi.org/10.1103/kjrr-ypd9 The set consists of 3826 rows, each corresponding to a crystalline inorganic material. Each row contains the material's composition, identifier in the Magnetic Materials Database (https://doi.org/10.1103/PhysRevMaterials.4.114408), DFT-computed saturation polarization value, and fold identifier used during leave-one-cluster-out cross validation in the present work.