Are you able to provide a dataset you had in mind or is this a generic question?

@NevMthw this is because average_precision_score is expecting binary labels for classification. If you have 100 classes then you need to one-hot encode them to give something like this: y_pred =np.array([[1,0,0],[1,0,0],[1,0,0],[0,1,0],[0,0,1]]) y_truth = np.array([[1,0,0],[0,1,0],[1,0,0],[0,1,0],[0,0,1]]) average_precision_score(y_pred, y_truth)

You are definitely correct about UMAP / tsne, I did my own exploration in TSNE and discovered an outlier cluster of melanoma. See the images in the main cluster of raw.githubusercontent.com/adbandy/data_files/main/… compared to the rogue cluster of raw.githubusercontent.com/adbandy/data_files/main/… for instance if you were curious