Additional metrics (+tests)
Closed this issue · 2 comments
simonhkswan commented
For the tests of the new metrics, would be good to follow (you can search this approach too):
- Arrange
- Act
- Assert
Let's have a look at pytest.fixtures too.
Hebruwu commented
Metrics: Bhattacharyya distance, Total Variation distance, Ideal number of clusters according to the average silhouette method
Hebruwu commented
As there are many clustering algorithms, I will be limiting the scope to k-means for now as it is a very popular algorithm, but requires the knowledge of an optimal number of clusters in order to perform optimally