NIST Dataset of CAS ID's and associated functional group presence and interpolated IR spectra in % absorbance

This dataset consists of two large CSV files.molecular_descriptors.csv is structured such that each row corresponds to a new molecule. The molecule's associated CAS ID indexes the file. Each column represents a functional group. The presence of a functional group in a molecule is denoted by a 1, and a functional absence in a molecule's functional group is denoted by a 0.CAS-IRS.csv is structured so that each row corresponds to a new molecule (Indexed by the associated CAS ID). There are 6200 columns, each representing a different wavenumber in the IR spectrum from 3700cm^-1 to 600cm^-1. Each cell has a value from 0 to 1, corresponding to the percent absorbance at the corresponding wavenumber.