Supervised Learning Projects

A collection of supervised machine learning projects built with Python and Jupyter notebooks. Each folder contains a self-contained project demonstrating a real ML workflow: data preparation, modeling, and evaluation.

---

📚 Projects Included

1. Employee Turnover Prediction

Folder: Employee_Turnover-LogesticRegression-Model/

• Objective: Predict employee attrition for a company using logistic regression.
• Approach: Baseline Logistic Regression plus L1 (Lasso) and L2 (Ridge) regularization.
• Key features: job satisfaction, work-life balance, monthly income, years at company, performance rating, and more.
• Output: Classification metrics such as accuracy, precision, recall, and F1-score.
• Contents: employee_turnover_project.ipynb, employee_turnover.csv, README.md, requirements.txt

2. House Price Prediction

Folder: House_Price_Predictor/

• Objective: Predict house sale prices using a regression model.
• Approach: Linear regression with data cleaning, missing value handling, one-hot encoding, feature scaling, and evaluation.
• Key features: property characteristics and sale price information from the CSV dataset.
• Output: Regression metrics such as R² score, MAE, RMSE, and MAPE.
• Contents: house_price_predictor.ipynb, HousePricePrediction.csv, README.md, requirements.txt, Supervised_ML_Assignment1.pdf

3. Iris Flower Classification

Folder: Iris_Flower_Classification/

• Objective: Classify Iris species from flower measurements.
• Approach: Compare multiple supervised models including KNN, Logistic Regression, and Naive Bayes.
• Key features: sepal length, sepal width, petal length, petal width, and species label.
• Output: Model comparison with classification metrics and a final recommendation.
• Contents: iris_flower.ipynb, Iris.csv, README.md, requirements.txt

4. Scratch KNN Regressor

Folder: Scratch_implementation_kNN/

• Objective: Build a KNN regressor from scratch using NumPy.
• Approach: Implement Euclidean distance, neighbor selection, and prediction averaging without using scikit-learn.
• Key features: a simple numeric dataset demonstrating model training and inference.
• Output: Predicted values for test samples using the custom KNNRegressor class.
• Contents: knn_regressor_scratch.ipynb, README.md, requirements.txt, Scratch Implementation_Assignment.pdf

---

🔧 How to Use This Repository

Each project folder is designed to run independently. For a given project:

1. Open the folder.
2. Install dependencies from requirements.txt.
3. Run the Jupyter notebook.

Example:

cd House_Price_Predictor
pip install -r requirements.txt
jupyter notebook house_price_predictor.ipynb

Example for the scratch implementation:

cd Scratch_implementation_kNN
pip install -r requirements.txt
jupyter notebook knn_regressor_scratch.ipynb

👤 Author

Afzal
BTech — Computer Science
Supervised ML Project

📝 Notes

• Use project-specific READMEs for detailed setup and implementation notes.
• Keep each dataset and notebook in the same folder.
• The included PDFs provide assignment context and additional documentation.

---

📄 License

This repository is shared under the MIT License.