Breast Cancer Prediction in Python using Machine Learning

By Nihal Chandra

This project is used to predict whether the Breast Cancer is Benign or Malignant using various ML algorithms.

Breast cancer is a cancer in which the cells of breast tissue get altered and undergo uncontrolled division, resulting in a lump or mass in that region. It is generally diagnosed as one of the two types:

- Benign (Non-cancerous)

- Malignant (Cancerous)

An early diagnosis is found to have remarkable results in saving lives. With this objective in mind, a project has been developed to predict weather the tumor is cancerous or not so that required remdial actions can be taken up to cure it at the earliest.

The aim of this project is to hence identify and predict the cancer as either malignant or benign using 30 features from the dataset. We use different algorithms for this purpose including:

- Logistic Regression

- K-Nearest Neighbours Classifier

- Naive Bayes Classifier

- Support Vector Machine Classifier

- Light Gradient Boosted Machine Classifier

For each algorithm, we obtain the performance metrics, confusion matrix, Receiver Operating Characteristic Curve and the importance of of each feature. 

 

The dataset for this project is the Breast Cancer Wisconsin (Diagnostic) dataset that contains 30 features spanning over 569 instances with 357 benign and 212 malignant records.

 

Requirements

This project has been implemented in Python 3.6 environment using Jupyter Notebook by making use of the following libraries:

- Numpy                   v1.19.1

- Matplotlib               v3.3.1

- Plotly                     v4.9.0

- Seaborn                 v0.10.1

- Sci-kit learn            v0.23.2

Implementation:

Open the 'Breast Cancer Prediction using Machine Learning.ipynb' file using Jupyter Notebook and click on the Run button |>>|