README.md

title: Book Recommender 01 # Your Space's title emoji: 📊 # An emoji for your Space (optional) colorFrom: red # Color for the Space's theme (optional) colorTo: gray # Color for the Space's theme (optional) sdk: gradio # Important: Specifies the Gradio SDK app_file: app.py # The name of your main Python file (case-sensitive!)

sdk_version: 5.14.0 # Remove this line unless you have a VERY specific reason to pin an older version

Book Recommender App

This is a book recommendation app built using Python, scikit-learn, and Gradio. It uses TF-IDF vectorization and cosine similarity to recommend books based on their summaries.

Functionality

• File Upload and Processing: Users can upload CSV or Excel files containing book data (title and summary). This uses the pandas library.
• Data Preprocessing: Handles missing values and removes duplicates using pandas.
• TF-IDF Vectorization: Converts book summaries to numerical vectors using scikit-learn's TfidfVectorizer.
• Similarity Calculation: Calculates cosine similarity between TF-IDF vectors using scikit-learn.
• Book Recommendation: Recommends similar books based on a user-provided title.
• User Interface: Provides an interactive interface using gradio.

Dependencies

• pandas: For data loading, manipulation, and preprocessing (CSV and Excel file handling).
• scikit-learn: For TF-IDF vectorization and cosine similarity calculation.
• gradio: For creating the interactive user interface.

How to Run Locally

1. Clone the repository:

   git clone [https://github.com/](https://github.com/)<your_username>/<your_repo_name>.git  # Replace with your repo URL
   cd <your_repo_name>
   

2. Create a virtual environment (recommended):

   python3 -m venv .venv       # Create a virtual environment (Linux/macOS)
   source .venv/bin/activate  # Activate the environment (Linux/macOS)
   .venv\Scripts\activate    # Activate the environment (Windows)
   

3. Install the dependencies:

   pip install -r requirements.txt
   

4. Run the app:

   python app.py
   

5. Open the app in your browser: Gradio will provide a URL (usually http://127.0.0.1:7860/).

How to Deploy on Hugging Face Spaces

1. Create a Hugging Face account: If you don't have one, sign up at huggingface.co.

2. Create a new Space:

   • Click on "New Space."
   • Give your Space a name.
   • Select the "Gradio" SDK.
   • Choose a hardware and storage upgrade if needed.
   • Select a license (e.g., MIT).
   • Click "Create Space."

3. Push your code to the Space:

   • Clone the newly created Git repository:

     git clone [https://huggingface.co/spaces/](https://huggingface.co/spaces/)<your_username>/<your_space_name>
     cd <your_space_name>
     

   • Copy all the necessary files (app.py, requirements.txt, your data file, README.md, config.yaml) into the cloned repository.

   • Commit and push your changes:

     git add .
     git commit -m "Initial commit"
     git push origin main
     

4. Wait for the build: Hugging Face Spaces will automatically build your app. Monitor the build progress on your Space page.

5. Access your deployed app: Once the build is successful, your app will be live at a URL provided by Hugging Face.

Data File

The app requires a CSV or Excel file containing book data, including at least the title and summary columns. The file should be named (e.g., books.csv) and placed in the same directory as app.py. The path to the file is specified in the load_data method of the BookRecommender class within app.py.

Example Usage

1. Upload your book data file.
2. Enter the title of a book you like.
3. The app will recommend similar books.

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

MIT License (Or your chosen license)