This is the repository of group 25 for course DSCI-525 Web and Cloud Computing.
This repository contains a project to build ensemble machine learning models in the cloud to predict the daily rainfall in Australia on a large dataset that is approximately 5GB. Given that we are dealing with Big Data, the best approach would be to deploy any machine learning model to the cloud and utilize the powerful servers to make our predictions. The dataset contains the predictions of rainfall given different models, and our goal is to use these models as features and build an ensemble machine learning model to predict the daily rainfall. After we obtained our predictions using the ensemble method, we will then compare the results with the actual rainfall.
The dataset used by this project is from figshare and put together by Tomas Beuzen.
Jason Chang @jachang0628
Fei Chang @fei-chang
Mengyuan Zhu @Julie-M-Zhu