https://github.com/amruthpillai/ml-breast-cancer-classification

Technicians can use a microscope to observe tissue samples that were taken from patients who are suspected to have breast cancer. By looking at the size and shape of the nuclei present within these tissue samples, one can then predict whether a given sample appears to be cancerous. In this document I demonstrate an automated methodology to predict if a sample is benign or malignant given measurements of nuclear shape that were made from digital images of fine needle aspirates of breast tissue masses from clinical samples.
https://github.com/amruthpillai/ml-breast-cancer-classification

Last synced: 8 months ago
JSON representation

Technicians can use a microscope to observe tissue samples that were taken from patients who are suspected to have breast cancer. By looking at the size and shape of the nuclei present within these tissue samples, one can then predict whether a given sample appears to be cancerous. In this document I demonstrate an automated methodology to predict if a sample is benign or malignant given measurements of nuclear shape that were made from digital images of fine needle aspirates of breast tissue masses from clinical samples.

• Host: GitHub
• URL: https://github.com/amruthpillai/ml-breast-cancer-classification
• Owner: AmruthPillai
• Created: 2018-12-03T18:13:15.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2024-04-22T19:19:40.000Z (over 1 year ago)
• Last Synced: 2024-05-02T05:37:17.512Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 666 KB
• Stars: 2
• Watchers: 2
• Forks: 2
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Machine Learning - Breast Cancer Classification

Technicians can use a microscope to observe tissue samples that were taken from patients who are suspected to have breast cancer. By looking at the size and shape of the nuclei present within these tissue samples, one can then predict whether a given sample appears to be cancerous. In this document I demonstrate an automated methodology to predict if a sample is benign or malignant given measurements of nuclear shape that were made from digital images of fine needle aspirates of breast tissue masses from clinical samples.

#### Dataset Used: [Breast Cancer Wisconsin (Diagnostic)](https://www.kaggle.com/uciml/breast-cancer-wisconsin-data)

## Methods

* Data Prep using Pandas DataFrames

* Data Visualization using Seaborn (matplotlib)

* Using Support Vector Machine (SVM) from scikit-learn

* Improving the model, by employing MinMaxScaler

* Using GridSearchCV to fine-tune hyper parameters

## Screenshot