Machine-Learning-and-Big-Data

Analysis of data from an environmental sensor network using Spark

The goal of the project is to analyse air quality data captured from a network of small environmental sensors, using Apache Spark data processing framework.

The data can be accessed in JSON format from:

Averaged data from last 24 hours for each sensor: https://data.sensor.community/static/v2/data.24h.json

Averaged data from last 5 minutes for each sensor (for testing): https://data.sensor.community/static/v2/data.json