ETL (extract, transform, load) + Database

Initially we looked at using Wine.com’s API, but unfortunately it is not longer accessible as of September of this year. Then we looked into scraping data from a few different websites, unfortunately that did not seem possible either; for many of these…

Conclusion

Although there are many wine recommenders, we created two unique ones. Most other recommender systems have bottle recognition systems where the user will take a photo of a bottle of wine and the recommender will suggest other bottles that are similar to this. Some of them give in depth detail about the wine…

Reporting / Visualizations

In order to visualize our results we used a few different techniques

Word Clouds

We found a word cloud library online created by Andreas Mueller and can use this to create word clouds of each of our wines. For our top…

Machine Learning/Statistical Models

Since we are not trying to predict anything, the only machine learning techniques that would be applicable to our project would be unsupervised machine learning techniques, however, clustering is not a natural concept because we are building our model on words, which…

Post Exploratory Statistics

The database we created from the cellar tracker data has the following statistics:

Interactive Applet

We were able to create very basic applets to utilize the recommendation system using the python library Tkinter. The first applet takes the string of “Wine Name” and returns the Top 10 most similar wines based on their cosine similarity scores. The second Applet takes in a string of words…

Introduction

For our project we decided to look at wine data in order to create a wine recommender. We are aiming to generate wine recommendations based on text reviews of wines. Ideally, we would like to create a more effective method of recommending wines that is based on tasting notes and not user preference or…