Heart-Disease-Prediction

Description:

Project Description:

This project is presented a prediction of the Heart Disease for young patients using Data Minings techniques.

Files Description:

• Main.ipynb - main Jupyter notebook, where is presented main prediction work.
• outliers - in this folder is Outliers Jupyter notebook, Stat_outliers notebook and dataset file of outliers.
• stats - in this folder are presented three different Jupyter notebooks where visulize dependecies target values with other attributes.
• data.csv - collected data in one dataset from different country
• heart.csv - processed data

Data description:

The data reviewed in this study was taken from the UCI Archive. The main data have about 900 rows, and processed data - about 300 rows. Its dataset was collected from different country, such as USA, Hungarian, Switzerland and Vatican

Atrribute description:

• AGE - age
• SEX - gender
• CP - chest pain type
• TRESTBPS - resting blood pressure (in mm HG on admission to the hospital)
• CHOL - serum chorestoral in mg/dl
• FBS - fasting blood sugar >120
• RESTECG - resting electrographic result
• THALACH - maximum heart rate achieved
• EXANG - exercise induced angina
• OLDPEAR - ST depression induced by exercise relative to rest
• CA - number of major vessels colored by flouroscopy
• THAL - “thalium”, the blood disorder

Getting Started:

Clone project to computer:

To clone project to your computer, from console run:

$ git clone https://github.com/anastasiatraverse/Heart-Disease-Prediction.git

Install packages:

All the necessary libraries to run the project are in the file: requirements.txt. To install them, you should go through the terminal to the folder where the downloaded project is located and write the following:

$pip3 install -r requirements.txt

Run Jupyter Notebooks:

Jupyter Notebooks are used throughout the project. To open them, you can use the Jupyter Lab website or launch notepad from the console using the following instructions:

$jupyter notebook

Built With:

• pandas - pandas is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language.
• sklearn - simple and efficient tools for data mining and data analysis
• marplotlib - Python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms

Authors & License:

• Traverse Anastasia - UCU student, Faculty of Applied Science, Computer Science