# Predict the occurrence of diabetes

This project is the result of a Kaggle competition promoted by [Data Science Academy](https://www.datascienceacademy.com.br/) in January of 2019.

The goal of the competition was to create a Machine Learning model to predict the occurrence of diabetes.

Data source: National Institute of Diabetes and Digestive and Kidney Diseases

Competition page: https://www.kaggle.com/c/competicao-dsa-machine-learning-jan-2019/


### Problem

The goal is to predict, based on diagnostic measures, whether a patient has diabetes. 

### Task

Create a Machine Learning model to estimate the probability of the occurrence of diabetes.

### Solution

I've used Python to perform an **Exploratory Data Analysis (EDA)** using visual and quantitative methods to understand and summarize a dataset without making any assumptions about its contents. Then I've performed Data Cleaning and built several **Machine Learning** models to compute the probability of occurrence of diabetes. The Logistic Regression model presented the best results.

### Results

In this competition, I've reached the accuracy of **76.27%** and I got **position 41 on the leaderboard**.

---
# Solution details

I've written a  [blog post with details](https://cpatrickalves.hashnode.dev/kaggle-predict-the-occurrence-of-diabetes) about the solution. 

The code is also available at GitHub.

[![github](https://user-images.githubusercontent.com/22003608/127739408-c499e7b2-5a1d-4f44-a028-dc46eb8e900d.jpg)](https://github.com/cpatrickalves/kaggle-diabetes-prediction)