- Dataset was obtained from an online kaggle source Food.com Recipes and Interactions, where we preprocessed datasets: "RAW_interactions.csv" and "RAW_recipes.csv", which were then used for training.
- FeedMe_Preprocessing.ipynb contains the code where we preprocessed both online datasets to obtain a much useful dataset to train and test.
- FeedMe_NN.ipynb contains the code where we trained a Neural Network on the preprocessed data using two different optimizers and visualized train and validation accuracy and loss.
- FeedMe_Similarity.ipynb contains the code where we used the Jaccard Similarity Metric to find the closest recipes to 1 recipe based on its ingredients.
-
Notifications
You must be signed in to change notification settings - Fork 0
Machine Learning project that recommends recipes based on user preference for previous recipes using Neural Networks. Data was preprocessed to make it suitable for training, after training we used evaluation metrics to test accuracy, loss, and predict optimal recipes based on ingredients given by the user.
andrewbejjani/AI-Recipe-Recommender-System
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Machine Learning project that recommends recipes based on user preference for previous recipes using Neural Networks. Data was preprocessed to make it suitable for training, after training we used evaluation metrics to test accuracy, loss, and predict optimal recipes based on ingredients given by the user.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published