Skip to content

A robust framework to predict diabetes based different independent attributes. Outlier rejection, filling the missing values, data standardization, K-fold validation, and different Machine Learning (ML) classifiers were used to create optimal model.Finally, optimal model was deployed on a PaaS .

Notifications You must be signed in to change notification settings

mayurraj876/Diabetes-Prediction

Repository files navigation

Table of Contents

About the Project

This is built to predict probality of having diabetes using predefined paramter with the help of Machine Learning.
Objective of the project are :
    * To build an efficient model that can predict the probability of having Diabetes.
    * To visualize various independent variables like the number of pregnancies the patient has had, their BMI, insulin level, age, and dependent variable
    * To increase the model efficiency of the model with help of data processing and hyperparameter tuning.
    * To build a cloud-based user-friendly interface.

Publication link

Project work has been published in International Research Journal of Engineering and Technology (IRJET) Volume 8, Issue 8,  August 2021 
Refer to https://www.irjet.net/volume8-issue8 S.No: 82 for detailed explanations.

Getting Started

Clone the repo and extract it ....

Prerequisites

All the results reported in the project were produced using the following version Python and Python API:

    * python 3.7.6
    * numpy 1.18.1
    * pandas 1.0.1
    * matplotlib 3.1.3
    * seaborn 0.10.0
    * scikit-learn 0.22.1
    * xgboost 1.3.0post0
    * Keras 2.4.3 

Setup

1. Clone the repository 
```
git clone https://github.com/mayurraj876/Diabetes-Prediction.git
```
2. Install Python Libraries
```
pip install pandas,numpy,matplotlib,sklearn,xgboost,keras,flask

```

Contributers

* mayurraj876 
* manoj281998
* paurush0506

Contact

Name - Mayur Raj Singh Chouhan 
Email - mayurrajsinghc.ec17@rvce.edu.in

Cloud interface Link: https://diabetes-prediction-rvce.herokuapp.com/

References

* flask
* sklearn 
* Stackoverflow

About

A robust framework to predict diabetes based different independent attributes. Outlier rejection, filling the missing values, data standardization, K-fold validation, and different Machine Learning (ML) classifiers were used to create optimal model.Finally, optimal model was deployed on a PaaS .

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages