Skip to content

This research work summarized different machine learning algorithms to create models for predicting diabetes patients utilizing the Diabetes Dataset (PIDD) from the UCI repository. The classifiers were K-Nearest Neighbors, Naïve Bayes, Support Vector, Decision Tree, Random Forest, Logistic Regression and Ensemble Model using a voting classifier.

Notifications You must be signed in to change notification settings

sumaaan/Diabetes-Predection-using-Ensemble-Learning

Repository files navigation

Diabetes_Ensemble

The predictivesystem.py is just for testing purpose kindly don't use the file.

You don't need to re-run the Diabeties_predection _using_ensemble_methods.ipynb file as the required model is saved and exported as diabetes_model.sav

For running the Webapp.py

Install the following package
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- 
- pip install -U scikit-learn scipy matplotlib
- pip install numpy  
- pip install streamlit
- pip install networkx

After the installation : Run the following code in the terminal -> streamlit run .\Webapp.py NOTE : WHILE ENTERING THE VALUE THE VALUE SHOULD BE INTEGER OR FLOAT.

Some Example to check the system is working or not:
(6,148,35,33.6,50) Expected output --> 1(YES)
(10,139,0,27.1,57) Expected output --> 0(NO)
(11,143,33,36.6,51) Expected output --> 1(YES)
(5,109,26,36,60) Expected output --> 0(NO)

About

This research work summarized different machine learning algorithms to create models for predicting diabetes patients utilizing the Diabetes Dataset (PIDD) from the UCI repository. The classifiers were K-Nearest Neighbors, Naïve Bayes, Support Vector, Decision Tree, Random Forest, Logistic Regression and Ensemble Model using a voting classifier.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published