A cheese recommendation website

This web application recommends cheeses based on user input and uses TF-IDF vectorization and cosine similarity to find similar cheeses. The application then returns the top recommendations, excluding any cheeses with qualities specified by the user to be excluded.

This project could be useful for a cheese retailer or distributor to provide personalized recommendations to their customers. By asking customers about their preferences and excluding any qualities they do not like, the retailer can provide a curated list of cheeses that are more likely to be appealing to the customer. This could increase customer satisfaction and potentially lead to higher sales.

The code is implementing a cheese recommendation system using the TF-IDF algorithm and cosine similarity.

The CheeseRecommender class initializes with a file path for a tab-separated values (tsv) file containing information on various cheeses. The data is loaded into a pandas DataFrame, and a TfidfVectorizer is created to transform the cheese descriptions into a matrix of TF-IDF (Term Frequency-Inverse Document Frequency) values.

The get_recommendations method takes in user input, number of recommendations, starting index, and a list of words to exclude from the recommendation. If the user does not provide any input or exclusion words, the method generates a random sample of cheese recommendations. If the user provides input, the user's input is transformed into a vector using the same TfidfVectorizer used on the cheese descriptions, and the cosine similarity between the user input vector and the cheese matrix is calculated. The method returns the top recommendations with the highest cosine similarity scores. If exclude words are provided, the method removes any cheeses containing the excluded words from the recommendations.

1. Clone the repository:

   git clone https://github.com/psibir/chz-recs.git
   

2. Navigate to the project directory:

   cd chz-recs
   

3. Create a virtual environment:

   python3 -m .venv venv
   

4. Activate the virtual environment:

   • For macOS/Linux:

     source .venv/bin/activate
     

   • For Windows:

     venv\Scripts\activate
     

5. Install the required dependencies:

   pip install -r requirements.txt
   

6. Run the application:

   python3 app.py
   

7. Open a web browser and visit http://localhost:8080 to access the Cheese Recommender.

• Home Page: The home page displays a form where you can enter user preferences for cheese recommendations. Fill in the required fields and click the "Submit" button to get personalized recommendations.

• Results Page: After submitting the form on the home page, you will be redirected to the results page, which shows a list of recommended cheeses based on your preferences. Click on a cheese name to view more details about that cheese.

• Cheese Details: The cheese details page provides information about a specific cheese. It includes details such as the cheese name, country of origin, region, family, rind type, milk type, fat content, kind, description, producer, and synonyms.

• Cheese Library: The website also includes a full database of over 1800 cheeses available so you can find your favorites on your own.

Contributions to the Cheese Recommender project are welcome! If you find any issues or have suggestions for improvements, please submit a pull request or open an issue on the project's GitHub repository.

This project is licensed under the MIT License. Feel free to use and modify it for your own purposes.