Name		Name	Last commit message	Last commit date
parent directory ..
CSV_files		CSV_files
NPZ_files		NPZ_files
CreateNPZfromCSV.ipynb		CreateNPZfromCSV.ipynb
DermaMNIST-Corrected.ipynb		DermaMNIST-Corrected.ipynb
DermaMNIST-Corrected_HAM10000-duplicates-removed.ipynb		DermaMNIST-Corrected_HAM10000-duplicates-removed.ipynb
DermaMNIST-Extended.ipynb		DermaMNIST-Extended.ipynb
DermaMNIST_plots.ipynb		DermaMNIST_plots.ipynb
HAM10000_metadata.csv		HAM10000_metadata.csv
PartitionStats.ipynb		PartitionStats.ipynb
README.md		README.md
dermamnist_split_info.csv		dermamnist_split_info.csv

README.md

DermaMNIST_Analysis

Directory containing the code for all our analysis of the DermaMNIST dataset, including the preparation of DermaMNIST-C and DermaMNIST-E datasets.

CSV_files/: Directory containing metadata files (.csv).
NPZ_files/: Directory containing datasets files as NumPy arrays (.npz) for 28 × 28 spatial resolution. The .npz files for 224 × 224 resolution are too large for GitHub (> 1 GB).
DermaMNIST-Corrected.ipynb: Notebook containing code to generate the DermaMNIST-C dataset.
DermaMNIST-Extended.ipynb: Notebook containing code to generate the DermaMNIST-E dataset.
DermaMNIST_plots.ipynb: Notebook containing code to reproduce the plots in our paper.
PartitionStats.ipynb: Notebook containing code to plot dataset statistics for DermaMNIST and DermaMNIST-C datasets.
dermamnist_split_info.csv: CSV file containing image_id to split (dataset partition) mapping for DermaMNIST.
HAM10000_metadata.csv: CSV file containing HAM10000 metadata, which includes the lesion_id to image_id mapping.