Problem & Context
A collection of machine learning exercises covering core supervised learning workflows for classification and regression.
Goal
Build foundational understanding of data preprocessing, model training, feature handling, and evaluation.
Approach
Implemented multiple classification and regression workflows using structured datasets.
Technical Implementation
Handled missing values during preprocessing, performed feature selection, applied categorical encoding, built classification models including MLPClassifier and regression models using Linear Regression, evaluated classification using Accuracy/Precision/Recall/F1/Confusion Matrix, evaluated regression using MSE/RMSE/R², and used Matplotlib for visualization.
Outcome
Developed practical understanding of complete supervised learning workflows from preprocessing to evaluation.
Lessons Learned
Practiced the full supervised learning pipeline end-to-end — preprocessing, feature handling, model training, and evaluation across both classification and regression tasks.