Project Overview
A curated portfolio of 26 end-to-end machine learning projects β spanning healthcare AI, real-time computer vision, NLP chatbots, time series forecasting, and classical ML prediction tasks.
π Repository at a Glance
| π Projects |
π·οΈ Domains |
π Deployed Apps |
π₯οΈ GUI Apps |
β GitHub Stars |
| 26 |
6 |
5 |
3 |
1.3k+ |
π Table of Contents
Click to expand / collapse
All Projects by Category
Legend: Β π’ Beginner Β π‘ Intermediate Β π΄ Advanced Β |Β π Web App Β π₯οΈ GUI App Β π Notebook
π₯ Healthcare & Medical AI
6 Projects β click to collapse
| Project |
Description |
Tools & Algorithms |
Level |
Type |
| Brain Tumor Detection |
Detects tumors in MRI scans using a CNN. Upload a scan and get a prediction with confidence score. |
CNN, Transfer Learning, Flask |
π΄ |
π |
| Diabetes Prediction |
Predicts diabetes likelihood from 8 health markers (glucose, BMI, age, etc.). |
Random Forest, SVM, Logistic Regression |
π’ |
π |
| Heart Disease Prediction |
Predicts cardiac risk from 13 clinical features using ensemble models. |
XGBoost, Logistic Regression, Random Forest |
π’ |
π |
| Arrhythmia Classification |
Classifies 16 arrhythmia types from 279 ECG features. |
Random Forest, XGBoost, SVM |
π‘ |
π |
| Medical Chatbot |
NLP chatbot mapping user-described symptoms to diagnosis suggestions. |
NLP, NLTK, Flask, ML models |
π΄ |
π |
| MoA Prediction |
Predicts drug biological activity from gene expression and cell viability. |
Deep Learning, TabNet, PyTorch |
π΄ |
π |
π₯ Computer Vision & OpenCV
9 Projects β click to collapse
| Project |
Description |
Tools & Algorithms |
Level |
Type |
| Driver Drowsiness Detection |
Monitors driver eye state via Eye Aspect Ratio (EAR) and triggers alerts on drowsiness. |
OpenCV, Dlib, Flask |
π‘ |
π |
| Distracted Driver Detection |
Classifies 10 distracted behaviors (texting, eating, phone call, etc.) from images. |
CNN, TensorFlow/Keras |
π΄ |
π |
| Lane Line Detection |
Overlays detected road lane lines on images/video using Canny edge detection and Hough transform. |
OpenCV, Hough Transform |
π’ |
π |
| Human Detection & Counting |
Detects and counts people in live video using HOG descriptor. |
OpenCV, HOG, NMS |
π‘ |
π |
| Gender & Age Detection |
Predicts gender and age group from a face image. |
OpenCV, DNN, Caffe Models |
π‘ |
π |
| Image Colorization |
Adds realistic color to grayscale photos using deep learning. |
OpenCV, Deep Learning |
π‘ |
π |
| Smile Selfie Capture |
Auto-captures a photo the instant a smile is detected in the webcam stream. |
OpenCV, Haar Cascades |
π’ |
π |
| Emoji Creator from Emotions |
Detects real-time facial emotions via webcam and overlays emoji reactions. |
OpenCV, Haar Cascades |
π’ |
π |
| Human Activity Recognition |
Classifies activities (walking, sitting, standing) from pose estimation features. |
OpenCV, Pose Estimation |
π‘ |
π |
π Classical ML & Prediction
7 Projects β click to collapse
| Project |
Description |
Tools & Algorithms |
Level |
Type |
| Iris Flower Classification |
Classic benchmark β classifies iris species from petal/sepal measurements. |
Logistic Regression, KNN, SVM |
π’ |
π |
| Wine Quality Prediction |
Predicts wine quality score (3β8) from 11 physicochemical properties. |
XGBoost, Random Forest, SVM |
π’ |
π |
| Loan Repayment Prediction |
Predicts whether a LendingClub borrower will repay based on credit profile. |
Logistic Regression, XGBoost |
π‘ |
π |
| College Admission Prediction |
Estimates graduate admission probability from GRE, TOEFL, GPA, and research experience. |
Linear Regression, Lasso, Random Forest |
π’ |
π |
| Employee Turnover Prediction |
Identifies employees at high risk of leaving the company. |
Random Forest, XGBoost, CatBoost |
π‘ |
π |
| Property Maintenance Fines |
Predicts fine compliance from Detroit's blight data. |
Gradient Boosting, XGBoost |
π΄ |
π |
| Research Topic Prediction |
Classifies academic papers into topic categories using NLP-based features. |
TF-IDF, Naive Bayes, SVM |
π‘ |
π |
π¬ NLP & Conversational AI
2 Projects β click to collapse
| Project |
Description |
Tools & Algorithms |
Level |
Type |
| AI Room Booking Chatbot |
Hotel room booking chatbot using IBM Watson. Handles booking requests and sends email notifications. |
IBM Watson, Flask, Python |
π‘ |
π |
| Medical Chatbot |
Symptom-to-diagnosis NLP chatbot with multi-turn conversation support. |
NLP, LSTM, Flask |
π΄ |
π |
π Time Series & Business Analytics
2 Projects β click to collapse
| Project |
Description |
Tools & Algorithms |
Level |
Type |
| Multi-Store Sales Prediction |
Forecasts daily sales for 50 items across 10 stores using time series features. |
XGBoost, Lag Features, Seasonal Patterns |
π‘ |
π |
| IPL Score Prediction |
Predicts first-innings T20 scores from ball-by-ball match data with deep EDA. |
Random Forest, XGBoost |
π‘ |
π |
πΊοΈ Geospatial & Data Science
1 Project β click to collapse
| Project |
Description |
Tools & Algorithms |
Level |
Type |
| The Battle of Neighborhoods |
IBM Capstone β clusters city neighborhoods to recommend better business locations. |
K-Means, Folium, Foursquare API |
π‘ |
π |
π οΈ Tech Stack
Languages & Environments :
Machine Learning & Deep Learning :
Computer Vision & NLP :
Data & Visualization :
Deployment :
π Project Structure
Every project follows a consistent layout for easy navigation and reuse:
ProjectName/
β
βββ π data/ # Raw and processed datasets
βββ π notebooks/ # Jupyter notebooks (EDA β Training β Evaluation)
βββ π models/ # Saved weights (.pkl / .h5 / .pt)
βββ π static/ # CSS, JS, images (Flask apps)
βββ π templates/ # Jinja2 HTML templates (Flask apps)
βββ π src/
β βββ preprocess.py # Data cleaning & feature engineering
β βββ train.py # Model training pipeline
β βββ predict.py # Inference logic
βββ app.py # Flask entry point (web apps)
βββ requirements.txt # Python dependencies
βββ README.md # Project-specific documentation
π Getting Started
Prerequisites
Python 3.7+ | pip | Git
Clone & Run
# Clone the repository
git clone https://github.com/shsarv/Machine-Learning-Projects.git
cd Machine-Learning-Projects
# Navigate to any project
cd "Heart Disease Prediction [END 2 END]"
# (Recommended) Create a virtual environment
python -m venv venv
source venv/bin/activate # Linux / macOS
venv\Scripts\activate # Windows
# Install dependencies
pip install -r requirements.txt
# For Flask web apps
python app.py
# β Open http://127.0.0.1:5000
# For notebooks
jupyter notebook
Deploy to Heroku
heroku login
heroku create your-app-name
echo "web: gunicorn app:app" > Procfile
git push heroku main
heroku open
Contributions π±
We welcome contributions to this project! If you would like to improve the existing codebase or contribute new features, feel free to submit a pull request. Before submitting, please ensure that your changes align with the repository's style and structure.
- Fork this repo
- Branch:
git checkout -b feature/YourProjectName
- Structure your folder with a
README.md and requirements.txt
- Commit:
git commit -m "Add: YourProjectName"
- Push:
git push origin feature/YourProjectName
- Open a Pull Request β target
main
Please read CONTRIBUTING.md and follow the Code of Conduct.
Future Enhancements:
- Integrate Explainable AI (XAI) models for better understanding of predictions in complex models.
- Add Docker support for easy containerization of all projects.
- Incorporate CI/CD pipelines using GitHub Actions for automated testing and deployment.
- Migrate some projects to use streamlit for interactive dashboards.
- Explore Reinforcement Learning for game-based AI projects.
- Expand the NLP section to include text summarization, translation, and more chatbot capabilities.
π Resources and References
For a deeper understanding of AI, machine learning, and data science, I recommend the following courses:
- Coursera - Machine Learning by Andrew Ng
- Udacity - AI for Everyone
- Kaggle Learn - Data Science
β Acknowledgments
- The wonderful Kaggle community, which provided open datasets and insightful discussions.
- Udemy, Coursera, and edX instructors who have helped me build a solid foundation in AI.
License
Distributed under the MIT License. See LICENSE for more information.
Maintained By