Inspiration
The motivation was to experiment with end to end machine learning project and get some idea about deployment platform like Heroku and offcourse this " Diabetes is an increasingly growing health issue due to our inactive lifestyle. If it is detected in time then through proper medical treatment, adverse effects can be prevented. To help in early detection, technology can be used very reliably and efficiently. Using machine learning we have built a predictive model that can predict whether the patient is diabetes positive or not.". This is also sort of fun to work on a project like this which could be beneficial for the society.
What it does
The objective of this project is to classify whether someone has diabetes or not. Dataset consists of several Medical Variables(Independent) and one Outcome Variable(Dependent) The independent variables in this data set are :-'Pregnancies', 'Glucose', 'BloodPressure', 'SkinThickness', 'Insulin','BMI', 'DiabetesPedigreeFunction', 'Age' The outcome variable value is either 1 or 0 indicating whether a person has diabetes(1) or not(0).
How we built it
In this project, our objective is to predict whether the patient has diabetes or not based on various features like Glucose level, Insulin, Age, BMI. We will perform all the steps from Data gathering to Model deployment. During Model evaluation, we compare various machine learning algorithms on the basis of accuracy_score metric and find the best one. Then we create a web app using Flask which is a python micro framework.
Challenges we ran into
Data preprocessing wasn't quite intuitive with null values being replaced with 0 in numerical variables making it difficult to analyze.
Accomplishments that we're proud of
The following points were the objective of the project . If you are looking for all the following points in this repo then i have not covered all in this repo. I'm working on blog about this mini project and I'll update the link of blog about all the points in details later . (The main intention was to create an end-to-end ML project.)
Data gathering Descriptive Analysis Data Visualizations Data Preprocessing Data Modelling Model Evaluation Model Deployment
What we learned
Learnes how to create an end to end ML pipeline and deploy it online.
What's next for DIabetes Prediction Web App
Providing Healthcare centres after improving the interfacing and connecting it with their databases.
Log in or sign up for Devpost to join the conversation.