🍽️ Recipe Recommender

A machine learning-based application to recommend recipes personalized to your taste! This project combines data science, interactive web apps, and user-friendly design to help you discover new dishes quickly and intuitively.

---

🚀 Features

• Personalized Recipe Recommendations:
  Enter your preferences or available ingredients, and get tailored recipe suggestions.

• Large Recipe Database:
  Powered by an extensive dataset (all_recipes_final_df_v2.csv) covering diverse cuisines and dietary needs.

• ML-Driven Suggestions:
  Utilizes PCA, TF-IDF, and a trained recipe recommendation model for accurate results.

• Intuitive Web Interface:
  Simple, clean UI for easy recipe exploration (built with Python).

• Recipe Details:
  Get the ingredients, instructions, and key info for every recommended recipe.

• Visual Appeal:
  Includes images and a user-friendly layout (style.css, chef.jpg, project_logo.jpeg).

• Notebooks for EDA & Modeling:
  Explore the modeling process and data analysis in the Notebooks/ directory.

---

🗂 Project Structure

Recipe-Recommender/
├── App/
│   ├── application.py               # Main web app backend
│   ├── recipe_v1.py                 # Recipe recommendation logic
│   ├── style.css                    # Custom styles
│   ├── all_recipes_final_df_v2.csv  # Recipe dataset
│   ├── pca_model.pkl                # PCA model
│   ├── tfidf_vectorizer.pkl         # TF-IDF model
│   ├── recipe_recommendation_model.pkl # Main recommendation model
│   ├── chef.jpg, project_logo.jpeg  # Images for the UI
├── Notebooks/
│   └── Modeling/                    # Jupyter notebooks for modeling and EDA
├── README.md                        # You are here!

---

🛠️ Tech Stack

• Backend & Logic: Python 3.x
• Web Framework: (Likely Flask or Streamlit – check application.py)
• ML/DS Libraries: scikit-learn, pandas, numpy (see Notebooks)
• Frontend: HTML/CSS via templates or Streamlit UI
• Visualization: Matplotlib, Seaborn (in Notebooks)
• Model Artifacts: Pre-trained .pkl files for fast recommendations

---

⚡ Getting Started

1. Clone the Repository

   git clone https://github.com/yvishwas40/Recipe-Recommender.git
   cd Recipe-Recommender/App

2. Install Dependencies
   (You may want to use a virtual environment)

   pip install -r requirements.txt

   If requirements.txt is missing, install: pandas, numpy, scikit-learn, flask or streamlit, etc.

3. Run the Application

   # For Flask:
   python application.py
   
   # For Streamlit (if applicable):
   streamlit run application.py

4. Access the App
   Open your browser at http://localhost:5000 for Flask or as indicated by Streamlit.

---

📊 Jupyter Notebooks

Explore the Notebooks/Modeling/ directory for EDA, model training, and evaluation steps used to build the recommender.

---

🤝 Contributing

Contributions are welcome!

• Fork the repo
• Create your feature branch
• Commit your changes
• Open a Pull Request

---

📄 License

Distributed under the MIT License.

---

Recipe Recommender – Unlock new flavors, one suggestion at a time!