Welcome to my repository where I document my hands-on learning journey in Machine Learning and Data Science through real-world datasets and end-to-end projects.
Each folder represents a self-contained project where I explore algorithms, data preprocessing techniques, model evaluation strategies, and best practices.
Teen Phone Addiction Analysis using Linear Regression
- 📌 Explored and cleaned survey-based dataset
- 📈 Performed EDA and correlation heatmaps
- 🔧 Built and evaluated models: Linear, Ridge, Lasso, ElasticNet
- ✅ Compared model performance and visualized predictions
- 💾 Cleaned data and saved models included
Titanic Survival Prediction using Logistic Regression
- 🧼 Data Cleaning & Null Value Treatment
- 🧠 Feature Engineering (FamilySize, IsAlone)
- 🔍 EDA with visualizations and correlation analysis
- ⚙️ Preprocessing Pipelines with ColumnTransformer
- 🔄 Model Training with Logistic Regression
- 🔍 Hyperparameter Tuning with GridSearchCV
- 🧪 Final predictions tested on Kaggle dataset
- Strengthen core ML concepts through real-world application
- Practice full ML workflows: EDA → Preprocessing → Modeling → Evaluation
- Build a clean and collaborative portfolio on GitHub
- Learn by doing and iterate through trial-and-error
- Python (Pandas, NumPy, Scikit-learn)
- Visualization (Matplotlib, Seaborn)
- Jupyter Notebooks
- Git & GitHub
- Kaggle Datasets
- VS Code
- 🧬 Classification projects with Random Forest, SVM, XGBoost
- 📊 Unsupervised Learning: Clustering (K-Means, DBSCAN)
- 🧰 Feature Selection Techniques (RFE, SHAP)
- 🌐 Deployment with Streamlit & FastAPI
- 🎯 Participation in more Kaggle competitions
I'm actively learning and building in the ML & Data Science space.
If you're working on similar projects or want to collaborate, feel free to reach out or connect on LinkedIn!