The repository here has some sample code and files used for the generation of an in silico library of DSI catalysts and validation of the catalysts selection by committee The folders here comprise the code needed for clustering and CSC both the LOO study for identification of prediction paramaters and the code needed to perform the predictions. The large descriptor file needed for any models generated in CSC-files is available at https://drive.google.com/file/d/1LjVSEZ-E3CdhxNwQ9J_nXNjD5cl1yTWU/view?usp=sharing as it is far to large to upload on github itself.