This dataset contains 587,187 days of food diary records logged by 9.9K MyFitnessPal (MFP) users from September 2014 through April 2015. Each line is a tab-separated list of:
- Anonymized user ID
- Diary date
- List of food entries and nutrients (as JSON objects)
- Daily aggregate of nutrient intake and goal (as JSON objects).
The dataset was collected via web scraping of publicly accessible MyFitnessPal food diary pages. First, an initial list of 100K MFP usernames was extracted from the 10 most popular groups. Then, for each user, we retrieved up to the last 180 days of food diary pages until March 2015. Next, for each food diary page, we parsed relevant information such as date, meal entries, actual nutrient intake, and nutrient intake goals from the HTML content.
Kindly cite the following paper if you use the dataset:
Ingmar Weber and Palakorn Achananuparp. 2016. Insights from Machine-Learned Diet Success Prediction. In Proceedings of Pacific Symposium on Biocomputing (PSB).
Last updated on 03 Apr 2019 .