I've developed a machine learning project to predict breast cancer tumor classification using the Wisconsin Breast Cancer dataset. This project aims to contribute to the field of medical diagnostics by leveraging data science techniques.
- Develop a model to classify breast tumors as malignant or benign
- Implement and compare various machine learning algorithms
- Demonstrate practical application of data science in healthcare
I'm using the Wisconsin Breast Cancer dataset, which includes:
- 569 samples of breast masses
- 30 features describing each tumor's characteristics
- Binary classification: malignant or benign
- Language: R
- Libraries: neuralnet
- Data preprocessing and exploratory data analysis
- Feature scaling and selection
- Model training and hyperparameter tuning
- Performance evaluation using metrics such as accuracy, precision, recall, and F1 score
- Model comparison and selection
- Download or clone this repo
- Open it using an IDE supporting jupyter notebook (specifically VS code) with R kernel
- Run all cells
I've implemented multiple models and evaluated their performance. The README will be updated with specific results as the project progresses.
- Explore deep learning approaches, particularly convolutional neural networks
- Investigate the potential of transfer learning using pre-trained models
This repository contains an excerpt of academic assignment shared solely for professional portfolio demonstration and is not to be used as a reference or submission for academic coursework. Any reproduction, copying, or use of this code for educational assignments is strictly prohibited and may constitute academic misconduct.
I'd like to acknowledge the UCI Machine Learning Repository for providing the Wisconsin Breast Cancer dataset, which has been instrumental in this project.
Wolberg, W., Mangasarian, O., Street, N., & Street, W. (1993). Breast Cancer Wisconsin (Diagnostic) [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5DW2B.