EDA and ML of Wine Reviews Dataset from Kaggle
This project makes use of the Wine Reviews Dataset found on Kaggle, created by user zackthoutt.
I was interested in this dataset when I saw what the inspiration for creating it was - finding out whether one could create a predictive
model that would determine what wine variety based on a wine’s description/review (from Wine Enthusiast). I was less interested in
determining variety and more interested in finding out region, since I thought that would be more difficult as there are far more regions
than varieties. You could certainly tweak the ML portion of this report to use varieties against the description review but I have gone
with ‘province in this case.
For more information about what data was used, please refer to the dataset on Kaggle.
I used RStudio to create this report. All libraries used are mentioned in the reports and rmd file.
This project is licensed under the CC BY-NC-SA 4.0 License - see CC BY-NC-SA 4.0 for details