YureiYuri/stressUp

🎓 Student Stress Level Predictor

A machine learning app that predicts a student's stress level — Low, Medium, or High — based on 20 psychosocial and academic factors.

How It Works

Adjust the sliders to describe a student's situation and click Predict Stress Level. The model returns a probability score for each stress category.

Input Features

Category	Features
Psychological	Anxiety Level, Self-Esteem, Mental Health History, Depression
Physical	Headache Frequency, Blood Pressure, Sleep Quality, Breathing Problem
Environment	Noise Level, Living Conditions, Safety, Basic Needs
Academic	Academic Performance, Study Load, Teacher-Student Relationship, Future Career Concerns
Social	Social Support, Peer Pressure, Extracurricular Activities, Bullying

Output

The model predicts one of three stress levels:

• 🟢 Low — Student is managing well across most factors
• 🟡 Medium — Moderate stress present in some areas
• 🔴 High — Significant stress across multiple dimensions

Model Details

Property	Value
Architecture	Feedforward Neural Network (PyTorch)
Hidden Layers	3 (256 → 128 → 64)
Activation	ReLU + Batch Normalization + Dropout (0.3)
Input Dimensions	20
Output Classes	3 (Low, Medium, High)
Preprocessing	StandardScaler (mean/variance normalization)

Files

├── app.py               # Gradio interface
├── config.json          # Feature names, label mapping, model hyperparameters
├── scaler.json          # Normalization statistics (mean & scale)
└── model_weights.pt     # Trained PyTorch weights
```---
title: Student Stress Level Predictor
emoji: 🎓
colorFrom: blue
colorTo: indigo
sdk: gradio
sdk_version: 6.10.0
app_file: app.py
pinned: false
license: mit
---

# 🎓 Student Stress Level Predictor

A machine learning app that predicts a student's stress level — **Low**, **Medium**, or **High** — based on 20 psychosocial and academic factors.

## How It Works

Adjust the sliders to describe a student's situation and click **Predict Stress Level**. The model returns a probability score for each stress category.

## Input Features

| Category | Features |
|---|---|
| **Psychological** | Anxiety Level, Self-Esteem, Mental Health History, Depression |
| **Physical** | Headache Frequency, Blood Pressure, Sleep Quality, Breathing Problem |
| **Environment** | Noise Level, Living Conditions, Safety, Basic Needs |
| **Academic** | Academic Performance, Study Load, Teacher-Student Relationship, Future Career Concerns |
| **Social** | Social Support, Peer Pressure, Extracurricular Activities, Bullying |

## Output

The model predicts one of three stress levels:

- 🟢 **Low** — Student is managing well across most factors
- 🟡 **Medium** — Moderate stress present in some areas
- 🔴 **High** — Significant stress across multiple dimensions

## Model Details

| Property | Value |
|---|---|
| **Architecture** | Feedforward Neural Network (PyTorch) |
| **Hidden Layers** | 3 (256 → 128 → 64) |
| **Activation** | ReLU + Batch Normalization + Dropout (0.3) |
| **Input Dimensions** | 20 |
| **Output Classes** | 3 (Low, Medium, High) |
| **Preprocessing** | StandardScaler (mean/variance normalization) |

## Files

├── app.py # Gradio interface ├── config.json # Feature names, label mapping, model hyperparameters ├── scaler.json # Normalization statistics (mean & scale) └── model_weights.pt # Trained PyTorch weights ```