I am have a data set with 52 variables. Most of them have zeros, it resembles a sparse matrix. How can I cluster this kind of data and are there any special types of clustering? I am attaching pca plot
-
4$\begingroup$ Have you seen the following posts, 1, 2, 3 and 4? $\endgroup$– mnmSep 27, 2017 at 13:28
-
$\begingroup$ Apparent duplicate of datascience.stackexchange.com/questions/23349/… $\endgroup$– Dave KielpinskiSep 27, 2017 at 17:52
-
$\begingroup$ Do you close duplicate questions? $\endgroup$– EngrStudentOct 24, 2017 at 14:23
-
$\begingroup$ What about using some dimensionality reduction, like PCA? $\endgroup$– JirkaApr 23, 2019 at 21:31
1 Answer
It doesn't require any special method. The algorithm of choice depends on your data if for instance Euclidean distance works for your data or not.
Generally, you can try Kmeans or other methods on your X or PCAs; but Hierarchical Clustering may be a good choice for visualizing the clusters for high dimensional data.
Please check here if you can read/write python code.
-
$\begingroup$ I guess the problem of the poster that it is a high dimensional sparse data. Traditional distance metrics will not work well in this case. $\endgroup$– ViktorJan 15, 2020 at 11:26