¿Where can I find the references that describes the methods used in n_clusters
?
#984
Unanswered
luifrancgom
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
When using
n_clusters
in the documentation it is mention that " ... The mainn_clusters
function proposes to run all of them, and find out the number of clusters that is suggested by the majority of methods ..." But there is not a description about what methods are used.Using the example pointed out you can extract all the methods used in the following way:
Created on 2024-06-23 with reprex v2.1.0
However, there is not a direct reference for each method. For example in the case of Elbow I was curious about how this method was implemented because Elbow method is a visual heuristic without a strict mathematical formula.
Checking the source code of
n_clusters
this is the way it is calculated:Created on 2024-06-23 with reprex v2.1.0
However, in
factoextra
the following plot is pointed out:And in the
fviz_nbclust
documentation the following reference is pointed out but there is not a description about a strict mathematical formula.I understand in the case of Elbow the logic used in
n_clusters
but without a description in the function documentation it is difficult to understand the method without checking the source code.¿Where can I find the references for the rest of the 28 methods used in
n_clusters
without checking the source code?Beta Was this translation helpful? Give feedback.
All reactions