Last active
November 25, 2019 05:17
-
-
Save merylldindin/a11d44a97738d3bdefa28e59deaa032c to your computer and use it in GitHub Desktop.
ToMaTo Clustering
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def define_clusters(lst, fil, neighbors): | |
# lst -> ordered list of indexes | |
# fil -> mapped dictionnary of filtration values with indexes | |
# neighbors -> number of closest elements to consider per query | |
unf = UnionFind() | |
for idx in lst: | |
grp, srt = [], np.where(lst == idx)[0][0] | |
# kdt -> neighboring graph defined on x (values) | |
nei = self.kdt.query([self.x[idx]], neighbors, return_distance=False) | |
for ele in nei[0][1:]: | |
if np.where(lst == ele)[0][0] < srt: grp.append(ele) | |
if len(grp) == 0: unf.insert_objects([idx]) | |
else: | |
parent = grp[np.asarray([fil[j] for j in grp]).argmax()] | |
unf.union(parent, idx) | |
for ele in grp: | |
root = unf.find(ele) | |
mini = min(fil[parent], fil[root]) | |
if root != parent and mini < fil[idx] + tau: | |
unf.union(parent, root) | |
parent = unf.find(root) | |
return unf |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment