A repository containing all the most recent files related to the material design project
The goal of this project is to predict consumer perception metrics, such as star ratings, using product ingrediients and product reviews.
Toothpaste products scraped from Walmart
Ingredients and Reviews is featurized using off-the-shell Python libraries such as RDkit and nltk
Contains Python scripts created to
- Ingredient String Cleaning
- Convert Ingredients to SMILES
- Convert SMILES to RDkit features
Contains data used for data scraping, featurization and machine learning
Contains important plots or graphics created from data analysis
Contains Jupyter Notebooks created for data analysis
Contains Powerpoint slides that helped explain and update the progress of the project at different stages
Contains Python script that featurizes product reviews
Contains Python scripts used for data scraping