Obesity_Prediction

Obesity AI - Machine Learning Classification Project

? Project Overview

This project implements a comprehensive machine learning solution for obesity classification using various algorithms. The system analyzes lifestyle and health data to predict obesity levels, providing insights for health professionals and individuals.

? Problem Statement

Obesity is a significant global health concern. This project aims to:

Classify individuals into different obesity categories based on lifestyle factors

Provide accurate predictions using machine learning algorithms

Help healthcare professionals assess obesity risk factors

Enable individuals to understand their obesity classification

? Features

Core Functionality

Multi-class Classification: Predicts 7 different obesity categories

Multiple ML Algorithms: Implements 4 different machine learning models

Interactive Prediction: Command-line interface for real-time predictions

Model Persistence: Saves trained models for future use

Comprehensive Evaluation: Detailed performance metrics and analysis

Obesity Categories

Insufficient_Weight - Underweight individuals

Normal_Weight - Healthy weight range

Overweight_Level_I - Slightly overweight

Overweight_Level_II - Moderately overweight

Obesity_Type_I - Class I obesity

Obesity_Type_II - Class II obesity

Obesity_Type_III - Class III obesity (severe)

? Dataset Features

The model uses 16 input features to predict obesity levels:

Physical Attributes

Age - Individual's age in years

Height - Height in meters

Weight - Weight in kilograms

Lifestyle Factors

FAVC - Frequent consumption of high caloric food (yes/no)

FCVC - Frequency of consumption of vegetables (1-3 scale)

NCP - Number of main meals (1-4)

CAEC - Consumption of food between meals (Never/Sometimes/Frequently/Always)

CH2O - Daily consumption of water (liters)

FAF - Physical activity frequency (0-3 scale)

TUE - Time using technology devices (hours)

Health & Family History

family_history_with_overweight - Family history of overweight (yes/no)

SMOKE - Smoking habit (yes/no)

SCC - Calorie consumption monitoring (yes/no)

CALC - Consumption of alcohol (Never/Sometimes/Frequently)

Transportation

MTRANS - Transportation used (Automobile/Bike/Public_Transportation/Walking/Motorbike)

?️ Architecture

Data Pipeline

Data Loading - Training and test datasets

Data Preprocessing - Handling missing values, encoding categorical variables

Feature Engineering - BMI calculation, outlier handling

Data Scaling - Standardization of numerical features

Model Training - Multiple algorithm implementation

Evaluation - Performance metrics and comparison

Model Persistence - Saving trained models