Directory overview:

- data: contains raw dataset files
    - data/datasets.txt contains dataset details and citations
    - gen_cluster.py contains code for generating synthetic cluster dataset (not used)

- mc_sim: contains codes for running monte carlo simulations and plotting results

- plots: contains plots of experimental results (including those in the paper)

- sim: codes for running proposed algorithms and baselines
    - sim/dkwt.py: DKWT code
    - sim/pbr.py: DE/DEBC code
    - sim/env.py: environment class for running simulation
    - sim/gen_data.py: preprocess dataset, generate query vectors for trials
    - sim/baseline.py: code for running DKWT algorithm trials
    - sim/pbr_sim.py: code for running DE/DEBC algorithm trials (set mode='noinf' for DE, mode='pbr' for DEBC)
    - sim/*.log files: incomplete log files from running experiments
    - sim/g2*/ folders: contain results for various settings and various algorithms for g2 datasets
    - sim/separated* folders: contain results for various settings and various algorithms for DIM datasets
    - sim/random* folders: contain results for various settings and various algorithms for synthetic datasets

- tables: latex code for experimental result tables in paper

- data.ipynb: jupyter notebook for producing plots pertaining to dataset analysis
- multi_plot.ipynb: jupyter notebook for producing plots pertaining to experimental results
- results.ipynb: jupyter notebook for generating latex tables containing experimental results

