Training data file: Top10-all-win2-train.csv (136 records related to years 1988-2005). Testing data file: Top10-all-win2-test.csv (49 records related to years 2006-2010). The data includes only top 1
Supplementary data for the metaseq manuscript. This dataset is intended to be downloaded and unpacked automatically, along with the rest of the supplemental data files, using the download-metase
This python script was used to split one file with 1000 simulated datasets into 1000 files with one dataset each. This script was used after simulating data in ms and seqgen and before summary statist