neohosseinism / bsp-machine-learning

BSP-Machine-Learning: Patient Survival Prediction

Overview

This repository contains the code and resources for a machine learning project conducted as part of a course at Jahrom University, under the guidance of Dr. Mohsen Rahmanian. The project's objective is to design a predictive model that can determine whether patients will survive for more than one year or not based on clinical data.

Dataset

We used the 'clinical_with_header.csv' dataset, which is included in this repository. This dataset contains various clinical features and a target variable indicating patient survival.

Project Structure

The project is organized as follows:

• Project/: This folder contains the project codes and dataset.
• Project/huseyn_huseyni.ipynb: This Jupyter Notebook file contains the main code for data preprocessing, model training, and evaluation.
• Project/clinical_with_header.csv: The dataset used for this project.
• Pre-written codes/: This folder contains some pre-written codes for data preprocessing and model evaluation.
• README.md: This readme file.

Requirements

To run the code in the Jupyter Notebook, you need to have the following libraries and dependencies installed:

• Python 3.x
• Jupyter Notebook
• NumPy
• pandas
• scikit-learn
• matplotlib
• seaborn

You can install these dependencies using pip:

pip install numpy pandas scikit-learn matplotlib seaborn

Usage

1. Clone this repository to your local machine:

git clone <https://github.com/HuseynHuseyni/BSP-Machine-Learning>
cd <BSP-Machine-Learning>

2. Open and run the Jupyter Notebook Project/huseyn_huseyni.ipynb. This notebook contains step-by-step instructions for data loading, preprocessing, model training, and evaluation.

3. Follow the code in the notebook to train and evaluate the survival prediction model.

Results

The project aims to build a machine learning model that can predict whether patients will survive for more than one year or not. The performance of the model will be evaluated using appropriate metrics such as accuracy, precision, recall, and F1-score.

Contact

If you have any questions or suggestions regarding this project, please feel free to contact me.

• [email protected]

I hope you find this project informative and useful!