Automatic clustering through HDB-SCAN #6

Closed vrodriguezf closed 3 years ago

In GitLab by @vrodriguezf on Mar 30, 2020, 15:55

From the Timecluster paper: "For validation purpose, we also compare an automatic clustering approach. A hierarchical clustering method (HDB- SCAN) [12,20] is used to generate the most significant clusters as a density-based clustering algorithm. It requires only one parameter which represents the minimum size of the cluster. We use the sklearn package, and we use the hdbscan package as available on PyPi in order to determine the number of clusters"

Implementing this is useful to provide automatic clusters to other PACMEL projects such as the ones devoted to shapelet generation.

In GitLab by @vrodriguezf on Oct 14, 2020, 11:51

assigned to @lgs and unassigned @vrodriguezf

In GitLab by @lgs on Oct 20, 2020, 17:16

We are going to implement this directly into the Shiny app. In this step, the idea is to use the R dbscan library to get the clusters and visualize them in the UI. We will follow the next steps:

[x] Create an numerical input to manually determine the parameter "minPts" of the function hdbscan().
[x] Create a button to calculate the clusters
[x] Calculate clusters from the embedding
[x] Visualize the clusters with different colors in the graph of the embedding tab.

In GitLab by @lgs on Oct 22, 2020, 17:25

mentioned in commit 3a5c293e158d78cf66cfd7f462a3923a02552137

In GitLab by @lgs on Oct 22, 2020, 17:26

mentioned in merge request !11

In GitLab by @lgs on Oct 22, 2020, 17:28

mentioned in commit eb04046e309486477ceb9ebd3d957180d2aceb31

vrodriguezf / deepvats

Automatic clustering through HDB-SCAN #6