I have a dataset:

enter image description here

How can I apply kmeans algorithm to find clusters based on "date" column . So that I can retrieve tweeting/retweeting activity every hour and generate a pattern.

It would be great if someone can help me out.

Thank you.

  • $\begingroup$ Your question appears very general to me. What exactly the problem you got stuck on applying k-means to this data? $\endgroup$ – Sammy May 9 at 9:26
  • $\begingroup$ I am still in the learning phase, I tried to cluster the tweets based on Jaccard Similarity but I could detect a tweeting/ retweeting pattern. So I need a way to form clusters based on time and I have no idea about executing it. $\endgroup$ – Chirag Atha May 9 at 10:10