Topic Modeling



No file uploaded.Loading data...
Model loaded successfully.
KMeans model fitted successfully.

First 10 Keywords:
['root', 'user', 'login']

Nearest keyword to cluster centroid:
('user', 2.1736214346885974)
('user', 0.5123351667984772)
('root', 1.6326386493786684)
('root', 1.1001319049448395)
('user', 2.405748742084026)

Top TF-IDF scores on each cluster:
Cluster 0:
(check,0.58) (pass,0.58) (unknown,0.58) (authentication,0.32) (euid,0.32) (failure,0.32) (logname,0.32) (nodevssh,0.32) (rhost,0.32) (root,0.32)
Cluster 1:
(root,5.00) (closed,1.41) (session,1.41) (check,1.15) (pass,1.15) (unknown,1.15) (eventtemplate,1.00)
Cluster 2:
(opened,0.71) (session,0.71)
Cluster 3:
(user,1.03) (root,0.79) (check,0.53) (pass,0.53) (unknown,0.53)
Cluster 4:
(abnormally,0.58) (alert,0.58) (exited,0.58) (opened,0.50) (session,0.50) (uid,0.50) (user,0.50)

Nearest keyword to comment:
('EventTemplate', 'user', 0.06253632)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*>', 'root', 1.3332263)
('check pass; user unknown', 'user', 1.4118712)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*>', 'root', 1.3332263)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*> user=root', 'root', 1.1507246)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*> user=root', 'root', 1.1507246)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*> user=root', 'root', 1.1507246)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*> user=root', 'root', 1.1507246)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*> user=root', 'root', 1.1507246)
('authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=<*> user=root', 'root', 1.1507246)