This machine learning project predicts the cuisine type and estimates the cooking time of a recipe based on its ingredients and the number of preparation steps. The project features a user-friendly chatbot interface built with Streamlit.

Below is a walkthrough of the chatbot interface. The first image shows the welcome screen, and the second image displays a complete interaction, from user input to the final prediction.

Welcome Screen	Chat Interaction & Prediction

(The images showcase the application's simple UI and the core prediction functionality.)

• Cuisine Prediction: Classifies recipes into one of 6 cuisines (Italian, Mexican, French, Indian, Chinese, and Greek) using the ingredients list.
• Cooking Time Regression: Predicts the total cooking time in minutes based on the number of ingredients, steps, and overall recipe complexity.
• Interactive Chatbot: A simple and intuitive chatbot interface that guides the user to provide the necessary information step-by-step.

• Language: Python
• Data Science & ML: Pandas, NumPy, Scikit-learn, XGBoost, LightGBM, Joblib
• Web Framework: Streamlit
• Dataset: Food.com Recipes and User Interactions from Kaggle.

Follow these steps to run the application on your local machine.

1. Clone the Repository:

   git clone https://github.com/obenadak/recipe-analyzer.git
   cd recipe-analyzer

2. Create and Activate a Virtual Environment: This isolates the project's dependencies from your system's Python installation.

   # Create the virtual environment
   python -m venv venv
   
   # Activate on Windows (PowerShell)
   .\venv\Scripts\Activate.ps1
   
   # Activate on macOS/Linux
   # source venv/bin/activate

3. Install Dependencies: All required libraries are listed in the requirements.txt file.

   pip install -r requirements.txt

4. Run the Streamlit Application:

   streamlit run app.py

   The application will open in your default web browser at http://localhost:8501.

A brief overview of the project's directory structure.

Recipe-Analyzer/
├── assets/         # Contains demo images and other static files
├── models/         # Contains the trained .joblib model files
├── notebooks/      # Jupyter Notebook for data analysis and modeling
├── .gitignore      # Specifies files for Git to ignore
├── app.py          # The main source code for the Streamlit app
├── README.md       # This file
└── requirements.txt# A list of project dependencies

This project was developed as a portfolio piece to showcase skills in data preprocessing, feature engineering, model training and evaluation, and building interactive web applications with Streamlit.