Breast Cancer Classification Project

Breast Cancer Classification using Logistic Regression & Naive Bayes

This project focuses on early breast cancer detection using two classic machine learning models: Logistic Regression and Naive Bayes.

We begin by preprocessing and cleaning a real-world medical dataset to ensure quality inputs. Data features are then standardized using StandardScaler, followed by an efficient Train/Test split strategy.

Each model is trained separately and evaluated through:

Accuracy scores

Confusion matrices

Classification reports

To ensure a clear comparison, results are presented both numerically and visually, allowing for transparent performance insights.

Objectives:

Develop interpretable AI models for medical diagnosis

Analyze and visualize key trends in cancer-related data

Compare model performance to improve detection accuracy