On the nature of mixed-type features in materials datasets

<p>We provide four crystalline materials datasets that contain both numerical and categorical features of materials.</p> <ol> <li>The Lattice dataset [1,2] contains 1,439 binary AB body-centered cubic crystals, as described by 12 numerical and 9 categorical variables. The lattice constant is considered as the physical property of interest.</li> <li>The TC dataset [2,3] contains 101 binary alloys of transition and rare earth metals, as described by 15 numerical and 17 categorical features. The Curie temperature (TC) is considered as the property of interest.</li> <li>The Octet binary materials dataset [4] contains 82 materials, as described by 11 numerical and 2 categorical features. The difference in LDA energy between RS and ZB (∆E = E(RS) &minus; E(ZB)) in eV&nbsp;is considered as the physical property of interest.</li> <li>The Fm3m dataset [5] contains 239 binary compounds collected from the Materials Project, as described by 12 numerical and 17 categorical variables. The formation of energy is considered as the physical property of interest.</li> </ol> <p>References:</p> <p>[1] K. Takahashi, L. Takahashi, J. D. Baran, and Y. Tanaka, &quot;Descriptors for predicting the lattice constant of body centered cubic crystal&quot;, The Journal of chemical physics 146, 204104 (2017).<br> [2] D.-N. Nguyen, T.-L. Pham, V.-C. Nguyen, T.-D. Ho, T. Tran, K. Takahashi, and H.-C. Dam, &quot;Committee machine that votes for similarity between materials&quot;, IUCrJ 5, 830-840 (2018).<br> [3] Y. Xu, M. Yamazaki, and P. Villars, &quot;Inorganic materials database for exploring the nature of material&quot;, Japanese Journal of Applied Physics 50, 11RH02 (2011).<br> [4] L. M. Ghiringhelli, J. Vybiral, S. V. Levchenko, C. Draxl, and M. Scheer, &quot;Big data of materials science: critical role of the descriptor&quot;, Physical review letters 114, 105503 (2015).<br> [5] A. Jain, S. P. Ong, G. Hautier, W. Chen, W. D. Richards, S. Dacek, S. Cholia, D. Gunter, D. Skinner, G. Ceder, et al., &quot;Commentary: The materials project: A materials genome approach to accelerating materials innovation&quot;, Apl Materials 1, 011002 (2013).</p>