In this project we aim to predict the amount of monthly average precipitation in various locations throughtout Germany and Sweden.
The project is split into three parts:
- ETL - Streaming weather data using Kafka, transforming it using PySpark and eventually storing it in MSSQL Database.
- Data Analysis - Using our stored data to preform evalutations, feature selection and feature engineering on our data in preparation of fitting a model to it.
- Learning - Fitting a few models onto our data and getting final predictions.