To extract, run the following code on your terminal: tar -xvzf Data.tar.gz This is the directory structure that is inside the Data Folder. Home/└── Data/ ├── Var_recomb_Neutral_01/ ├── Var_recomb_Neutral1/ ├── CEU_200haplotypes/ │ ├── Neutral/ │ │ └── Test_files/ │ └── Sweep/ │ └── Test_files/ └── Variable_Mutation_CEU_200haplotypes/ ├── Neutral/ └── Sweep/ Var_recomb_Neutral_01 and Var_recomb_Neutral_1 contains test replicates with variable recombination rate (test replicates simulated with recombination rates drawn from an exponential distribution with mean of 10^-10 or 10^-9 and truncated at three times the mean, respectively. [Used in Figure 4] CEU_200haplotypes/ contains the Neutral and Sweep training (10,000 per class) and test files (1000 per class). Test files are located in the Test_files folder. [Used in Figure 2,6, and 7] Variable_Mutation_CEU_200haplotypes/ contains the Neutral and Sweep test files (1000 per class) under variable mutation rate [Used in Figure 5]