This project contains an implementation of an Anomaly Detector using the Polars library. Polars is a DataFrame library implemented in Rust and it is blazingly fast. This project aims to demonstrate the power and flexibility of the Polars library.
The PolarsAnomalyDetector is capable of processing large datasets efficiently.
It uses a rolling mean and standard deviation to detect anomalies in the data, based on a user-defined threshold. These anomalies are then plotted for a more intuitive understanding of the data.
The PolarsAnomalyDetector class also includes an interactive plot method using the plotly library, which allows users to visualize data and anomaly detection results in a more dynamic way.
The functionality of this project is demonstrated in a Jupyter notebook, which you can find in this repository. The notebook shows how to use the PolarsAnomalyDetector class and visualizes its output with both static and interactive plots.
-
Clone this repository to your local machine.
-
Open the notebook file to see how the class is used and how the output is visualized.
This project is part of a larger effort to showcase the capabilities of the Polars library. We encourage you to explore the other projects in this series and contribute to enhancing the functionality of this anomaly detector.