🤖 AI/ML Projects Master Hub

A curated collection of end-to-end Machine Learning projects covering classification, regression, clustering, NLP, and time series forecasting. Each project follows a structured approach: EDA → Preprocessing → Baseline Model → Model Selection → Hyperparameter Tuning → Evaluation → Inference.

---

📂 Projects

#	Project	Type	Algorithm	Dataset
1	Sonar Rock vs Mine Classification	Binary Classification	SVM	Sonar signals (208 samples, 60 features)
2	Breast Cancer Diagnosis	Binary Classification	SVM + PCA	Wisconsin Breast Cancer (569 samples)
3	Credit Card Fraud Detection	Imbalanced Classification	Random Forest	Credit Card Transactions (284K samples)
4	California House Price Prediction	Regression	HistGradientBoosting	California Housing (20K samples)
5	Medical Insurance Cost Prediction	Regression	Random Forest	Insurance Dataset (1.3K samples)
6	Customer Segmentation	Clustering	K-Means	Mall Customers (200 samples)
7	Fake News Detection	NLP Classification	Logistic Regression + TF-IDF	WELFake Dataset (72K articles)
8	Airline Passengers Forecasting	Time Series	ARIMA / SARIMAX	Airline Passengers (144 months)

---

🛠️ Tech Stack

• Languages: Python 3.x
• Core Libraries: NumPy, Pandas, Matplotlib, Seaborn
• ML Framework: Scikit-learn
• Specialized: XGBoost, Statsmodels (time series)
• Environment: Jupyter Notebooks

---

🚀 Getting Started

Each project is self-contained with its own virtual environment setup.

# Clone the repository
git clone https://github.com/yourusername/AL-ML-Projects-Master-Hub.git
cd AL-ML-Projects-Master-Hub

# Navigate to a project
cd sonar-rock-vs-mine-classification

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

# Launch Jupyter
jupyter notebook

---

📊 Project Categories

Classification

• Sonar Classification — Classify sonar returns as rocks or mines using frequency energy features
• Breast Cancer Diagnosis — Predict malignant vs benign tumors from cell nuclei measurements
• Credit Card Fraud — Detect fraudulent transactions in highly imbalanced data
• Fake News Detection — NLP-based classification of news articles as real or fake

Regression

• House Price Prediction — Predict California housing prices from geographic and demographic features
• Insurance Cost Prediction — Estimate medical insurance charges based on patient attributes

Unsupervised Learning

• Customer Segmentation — Segment mall customers by income and spending patterns using K-Means

Time Series

• Airline Forecasting — Forecast monthly passenger counts using ARIMA/SARIMAX models

---

📁 Project Structure

AL-ML-Projects-Master-Hub/
├── README.md                              # This file
├── sonar-rock-vs-mine-classification/
│   ├── sonar-rock-vs-mine-classification.ipynb
│   ├── README.md
│   ├── requirements.txt
│   └── sonar_data.csv
├── breast-cancer-diagnosis/
│   ├── breast-cancer-diagnosis.ipynb
│   ├── README.md
│   ├── requirements.txt
│   └── breast_cancer_dataset.csv
├── credit-card-fraud-detection/
│   └── ...
├── california-house-price-prediction/
│   └── ...
├── medical-insurance-cost-prediction/
│   └── ...
├── customer-segmentation-kmeans/
│   └── ...
├── fake-news-detection-nlp/
│   └── ...
└── airline-passengers-forecasting/
    └── ...

---

🔮 Future Plans

• Migrate each project to its own mono-repo for independent versioning
• Add model deployment examples (FastAPI / Streamlit)
• Include deep learning variants for applicable projects
• Add MLOps pipelines (MLflow, DVC)

---

📝 License

This project is for educational purposes. Datasets are sourced from Kaggle and UCI ML Repository.

---

🤝 Contributing

Contributions welcome! Feel free to open issues or submit PRs for improvements.