This repository contains a comprehensive collection of machine learning and data science capstone projects, showcasing various applications including recommendation systems, computer vision, MLOps, and natural language processing.

A machine learning-powered web application that provides personalized product recommendations based on user sentiment analysis from product reviews.

• Sentiment Analysis: Analyzes user reviews to understand sentiment patterns
• Collaborative Filtering: User-based recommendation system using similarity metrics
• Real-time Recommendations: Flask web application providing instant recommendations
• Pre-trained Models: Optimized ML models with pickle serialization
• Responsive UI: Bootstrap-powered frontend for seamless user experience

• Backend: Python, Flask
• Machine Learning: Scikit-learn, NLTK, Spacy
• Data Processing: Pandas, NumPy
• Frontend: HTML, CSS, Bootstrap
• Deployment: Heroku
• Model Storage: Pickle files

The application is deployed on Heroku: Live Demo

Senitment Based Product Recommendation System/
├── sentiment_based_product_recommendation_system-main/
│   ├── app.py                              # Flask web application
│   ├── model.py                            # ML model and recommendation logic
│   ├── requirements.txt                    # Python dependencies
│   ├── Procfile                           # Heroku deployment configuration
│   ├── sample30.csv                       # Sample dataset
│   ├── pickle_file/                       # Trained models
│   │   ├── count_vector.pkl               # Count vectorizer
│   │   ├── tfidf_transformer.pkl          # TF-IDF transformer
│   │   ├── model.pkl                      # Classification model
│   │   ├── RandomForest_classifier.pkl    # Random Forest model
│   │   └── user_final_rating.pkl          # User recommendation matrix
│   └── templates/
│       └── index.html                     # Frontend template
├── Recommendation+System+Notebook.ipynb   # Jupyter notebook with analysis
├── Data+Attribute+Description.csv         # Dataset description
└── colab_user_guide-converted.pdf         # User guide

1. Clone the repository

   git clone https://github.com/mrchandrayee/Course11-Capstone.git
   cd Course11-Capstone

2. Navigate to the main project

   cd "Senitment Based Product Recommendation System/sentiment_based_product_recommendation_system-main"

3. Install dependencies

   pip install -r requirements.txt

4. Download Spacy model

   python -m spacy download en_core_web_sm

5. Run the application

   python app.py

6. Access the application Open your browser and navigate to http://localhost:5000

1. Enter a valid username from the system
2. Click "Get Recommendations"
3. View the top 5 recommended products based on sentiment analysis

Valid Test Users: 00sab00, 1234, zippy, zburt5, joshua, dorothy w, rebecca, walker557, samantha, raeanne, kimmie, cassie, moore222

1. Data Preprocessing: Text cleaning, tokenization, and normalization
2. Feature Extraction: TF-IDF vectorization and count vectorization
3. Sentiment Analysis: Classification model to predict sentiment polarity
4. Recommendation Engine: User-based collaborative filtering
5. Model Deployment: Flask API with pickle model serialization

This repository also includes several other capstone projects:

• Deep learning project implementing Generative Adversarial Networks for artistic style transfer

• Computer vision project for assistive technology

• NLP-based news recommendation engine

• Predictive analytics for sales forecasting

• Car Damage Detection with MLOps pipeline
• EdTech Lead Scoring Classification with MLOps implementation

Note: Large project files (>50MB) are excluded from this repository due to GitHub size limitations. The main working code and documentation are available in the project folders.

• ✅ Successfully deployed ML model to production
• ✅ Implemented end-to-end recommendation pipeline
• ✅ Created responsive web interface
• ✅ Achieved real-time performance with optimized models
• ✅ Implemented comprehensive MLOps practices

• Model Accuracy: Optimized for sentiment classification
• Response Time: < 2 seconds for recommendations
• Scalability: Deployed on cloud platform with auto-scaling

1. Fork the repository
2. Create a feature branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

Chandrayee

• GitHub: @mrchandrayee
• Project Link: Course11-Capstone

• Machine Learning course instructors and mentors
• Open source community for libraries and frameworks
• Heroku for deployment platform
• Bootstrap for responsive UI components

⭐ Star this repository if you found it helpful! ⭐