Would you kindly provide us advice on how to minimize the noise in the data points that HDBSCAN collects? If we wish to preserve every piece of data, how can we manage it? For instance, clustering a large number of keywords using HDBSCAN, while it has also detected a bunch of keywords as noise.
I appreciate you sharing!
Would you kindly provide us advice on how to minimize the noise in the data points that HDBSCAN collects? If we wish to preserve every piece of data, how can we manage it? For instance, clustering a large number of keywords using HDBSCAN, while it has also detected a bunch of keywords as noise.
Even though I've not make use of DBSCAN before, all because I've been using KMeans lately. With this articles, there's much to what I can learn.