Luminol is a time series anomaly detection algorithm released by LinkedIn. It uses a bitmap to check how many detection strategies, that are robust in datasets, tend to drift. It is also very lightweight and can handle large amounts of data.
In this example, we are going to use a publicly accessible IoT dataset from the city of Chicago. The city of Chicago has IoT sensors measuring the water quality of their lakes. Because the dataset needs some massaging before we get it into the right format for anomaly detection, we will use the prepdata.py file to extract one data point from one lake.
