The aim of this project is to build a machine learning model that is able to leverage metric and kibana log data collected from indy services to detect anomalies. The project is split across three jupyter notebooks which encompass different phases in building the model:

1. RHOSC_EDA.ipynb: Exploratory Data Analysis where we delve into the given log data to gain a better understanding of what we're working with. Basic preprocessing followed by feature selection will also be done in this section.
2. RHOSC_2.ipynb: Testing of a few of the models considered for our anomaly detection task.
3. Results.ipynb: Visualisation of the anomalies detected in the previous notebook, along with analysis of the anomaly points and the logging data leading up to their occurence.