Diabetes Prediction

Objective

Original dataset : https://archive.ics.uci.edu/ml/datasets/diabetes

Kaggle Competitions : https://www.kaggle.com/uciml/pima-indians-diabetes-database

Overview

This dataset is originally from the National Institute of Diabetes and Digestive and Kidney Diseases. The objective of the dataset is to diagnostically predict whether or not a patient has diabetes, based on certain diagnostic measurements included in the dataset. Several constraints were placed on the selection of these instances from a larger database.

Techniques Used

• Data Cleaning
• Data Visualization
• Machine Learning Modeling

Algortihms Used

1. Logistic Regression
2. KNN
3. Support Vector Machine
4. Random Forest Classifier
5. Decision Tree
6. XGboost

Accuracy We got

1. Logistic Regression : 77.92%
2. KNN : 74.92%
3. Support Vector Machine : 78.57%
4. Random Forest Classifier : 80.52%
5. Decision Tree : 79.22%
6. XGboost : 75.32%

Screenshot

Installation

• Clone this repository and unzip it.

• After downloading, cd into the Deployment directory.

• Begin a new virtual environment with Python 3 and activate it.

• Install the required packages using pip install -r requirements.txt

• Execute the command: python manage.py runserver

• Open http://127.0.0.1:8000/ in your browser.

• Upload the csv of PPG signal.

• Enter the physiological data.

Guide Lines

Packages and Tools Required:

Pandas 
Matplotlib
Seaborn
Scikit Learn
Jupyter Notebook
Django

Package Installation

pip3 install -r requirements.txt