The purpose of this project is to build and deploy ensemble machine learning models in the cloud to predict daily rainfall in Australia on a relatively large data set (~ 5.5 GB). The data can be found on figshare. We are using the output of different climate models as a feature and the actual rainfall recordings as a target.
There are four milestones for this project:
- Downloading the data using API
- Combining data CSVs into a single CSV using
DASK
andPandas
libraries. - Loading the combined CSV to memory and perform a simple EDA
- Performing a simple EDA in R
Name | Github ID |
---|---|
Heidi Ye | @heidi-ye |
Junting He | @JuntingHe |
Kamal Moravej | @Kmoravej |
Tanmay Sharma | @tanmaysharma19 |