The aim of the whole project was to detect anomalies in the supercomputer logs based on certain events and messages, extracting critical features using feature engineering and running Random Forest Machine Learning model to evaluate the performance. Achieved overall test accuracy to around 99% using all the classification criteria - confusion matrix, precision, recall etc
sajuptpm/Anamoly_Detection_Supercomputer_Logs_Machine_Learning
The aim of the whole project was to detect anomalies in the supercomputer logs based
Jupyter Notebook