Breast-Cancer-Classification

Breast Cancer Classification Using Machine Learning

Project Overview

This project implements machine learning algorithms to classify breast tumor samples as benign or malignant using the Breast Cancer Wisconsin Diagnostic Dataset.

The project demonstrates the application of data science and supervised machine learning techniques in oncology-related data analysis.

Technologies Used

• Python
• NumPy
• Pandas
• Matplotlib
• Seaborn
• Scikit-learn
• Joblib
• Visual Studio Code

Machine Learning Algorithms

1. Logistic Regression
2. Random Forest Classifier
3. Support Vector Machine (SVM)

Dataset

Breast Cancer Wisconsin Diagnostic Dataset

• Total Samples: 569
• Features: 30
• Benign Samples: 357
• Malignant Samples: 212

Project Features

• Dataset loading and analysis
• Data preprocessing
• Exploratory data analysis
• Machine learning model training
• Model performance comparison
• Classification report
• Confusion matrix
• Correlation heatmap
• Feature importance analysis
• Sample classification

Installation

Clone the repository:

git clone https://github.com/SK-do/Breast-Cancer-Classification.git

Navigate to the project:

cd Breast-Cancer-Classification

Create a virtual environment:

python -m venv .venv

Install the required libraries:

python -m pip install -r requirements.txt

Run the Project

Option 1: Command Line Script

Execute:

python main.py

Option 2: Streamlit Web App (Recommended)

Run the interactive web interface:

streamlit run streamlit_app.py

The Streamlit app provides:

• Interactive model training interface
• Real-time predictions with custom input
• Visualizations and results dashboard
• User-friendly navigation

Expected Results

The program trains and evaluates three machine learning algorithms and generates visualizations and performance metrics.

Disclaimer

This project is intended for educational and research purposes only. It is not a clinically validated medical diagnostic tool.