Hey there! Check out my project on Predicting Differentiated Thyroid Cancer Recurrence. This repository shows how I dug into and broke down a dataset to predict if well-differentiated thyroid cancer might come back.
This project is a part of my journey to enhance my skills in Python and data analysis. Using a dataset collected over 15 years and featuring 13 clinicopathologic attributes, my goal is to practice and deepen my understanding of data analysis and machine learning techniques.
- Data Exploration: Get hands-on practice to clean and preprocess data using pandas.
- Feature Analysis: Learn to evaluate and interpret how important different features are.
- Model Building: Try out various machine learning models and understand how to assess and enhance them.
- Visualization: Make and improve visuals to share insights .
- Documentation: Get better at writing up and showing my analysis steps and results.
- Improve my Python skills for data analysis with pandas.
- Figure out how to use machine learning algorithms and check how well they work.(I'm new to all this!)
- Developing the ability to work with medical data and derive actionable insights.
- Get better at making data visuals to show complex info .
The dataset used in this project can be accessed here. It includes 13 clinicopathologic features related to thyroid cancer recurrence.
-
Clone the Repository:
git clone https://github.com/yourusername/differentiated-thyroid-cancer-recurrence.git -
Explore the Data: Begin by examining the data in the provided Jupyter notebooks.
-
Run Analysis: Follow the notebooks to perform data preprocessing, model building, and evaluation.
As I am still learning, I welcome any feedback, suggestions, or contributions. Feel free to submit issues or pull requests!
This dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0) license, see https://creativecommons.org/licenses/by/4.0/legalcode for details This allows for the sharing and adaptation of the datasets for any purpose, provided that the appropriate credit is given.
Please cite the original article if you use the data set for secondary research and/or public demonstrations: https://doi.org/10.1007/s00405-023-08299-w