Mental_health predictor
completedDeveloped an end-to-end Machine Learning web application that predicts a student's Mental Health Score based on daily habits and lifestyle factors. Performed comprehensive Exploratory Data Analysis (EDA) and data preprocessing on a dataset containing 5,000 records and 13 columns using Pandas and NumPy. Trained and evaluated multiple regression models, including Linear Regression (baseline), Random Forest Regressor, and a hyperparameter-tuned Random Forest. Selected the standard Random Forest model based on its performance and serialized it using Joblib for deployment. Built a REST API using FastAPI with Pydantic for request validation and integrated it with a responsive frontend developed using HTML, CSS, and JavaScript. Enabled secure frontend-backend communication using FastAPI CORS middleware and deployed the complete application on Render.