Skip to content

Pinktober – Breast Cancer Classification (Datathon Project) Built a machine learning pipeline for breast cancer prediction using tabular health data. Achieved 98.2% accuracy in a 48-hour internal datathon organized by Micro Club.

Notifications You must be signed in to change notification settings

ryma-tharouma/Pinktober

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

🎗️ Pinktober: Breast Cancer Classification Challenge

This notebook was developed for Pinktober, a Micro Club internal datathon held in October during Breast Cancer Awareness Month.

🧠 Objective

To build a robust machine learning model to classify breast cancer cases based on anonymized patient data.

🧩 Workflow

  • Data Exploration: Statistical summaries and visualizations
  • Preprocessing: Feature selection, normalization with MinMaxScaler
  • Modeling: Tried Logistic Regression, KNN, Decision Trees, and Random Forests
  • Evaluation: Confusion matrix, classification report, and metrics (Precision, Recall, F1)

🎯 Final Results

  • Accuracy: 0.98246
  • Precision: 0.97872
  • Recall: 0.97872
  • F1-score: 0.97872

🛠️ Tech Stack

Python, Pandas, Seaborn, Scikit-learn, Matplotlib

🤝 Context

Created and submitted during a 48-hour ML datathon organized by Micro Club.

About

Pinktober – Breast Cancer Classification (Datathon Project) Built a machine learning pipeline for breast cancer prediction using tabular health data. Achieved 98.2% accuracy in a 48-hour internal datathon organized by Micro Club.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published