This repository contains a project aimed at analyzing and predicting the mental health of students, with a focus on depression. The project leverages a dataset from Kaggle to compare various machine learning models and identify the most effective method for mental health prediction.
- Data Preprocessing: Cleaning and preparing raw data for analysis.
- Model Comparison: Evaluating multiple machine learning models for accuracy, precision, recall, and F1-score.
- Predictive Analysis: Generating predictions to identify students at risk of depression.
- Programming Language: Python
- Libraries:
- NumPy & Pandas (Data manipulation)
- Matplotlib & Seaborn (Data visualization)
- Scikit-learn (Machine learning models and evaluation)
The dataset used in this project is sourced from Kaggle and includes information on student mental health. For privacy and ethical reasons, sensitive data has been anonymized.
Dataset Link: Kaggle Student Mental Health Dataset
The project evaluates the performance of various machine learning models, including:
- Logistic Regression
- KNN
- Naive Bayes
Key metrics such as accuracy, precision, recall, and F1-score are used to compare these models and determine the best-performing approach.