Group members:

Surya Teja Sista,
Raphael Abba Ekwo

This is a project on Anomalies Detection. This project aim at detecting anomalies in data.

Dataset: we have used the g.csv "https://www.kaggle.com/datasets/caesarlupum/benchmark-labeled-anomaly-detection-ts" dataset from kaggle.

This dataset contains just three columns, the timestamp, value and the label. Here, the label represents the true anomalies of the dataset.

We have used sklearn, pandas, matplotlib libraries to visualize data with anomalies.

The original anomalies percentage was 5.868%.

The notebooks can be found in the project folder