Dataset for Repeated double cross validation applied to the PCA-LDA classification of SERS spectra: a case study with serum samples from hepatocellular carcinoma patients

This dataset contains all the spectra used in the paper  "Repeated double cross validation applied to the PCA-LDA classification of SERS spectra: a case study with serum samples from hepatocellular carcinoma patients", plus the R code to import the TXT (ASCII) files into a dataset, preprocess data, set-up and cross validate the PCA-LDA model and generate the figures shown in the paper.

Data are available in 2 different formats: 

- 1 compressed archive ("dataset.zip") containing all the 144 TXT files (1 file = 1 spectrum) 

- 1 single CSV file (“dataset.csv”) with all the 144 spectra in the form of a table. The data are structured as follow, with each row being 1 spectrum, preceded by metadata: "acquisition_date", "substrate_batch", "class", "sample_code".

The code for R is available as a single file "Rcode.R".