Predict calories burned for every workout, log exercise sessions, and explore your fitness data on an interactive dashboard — all powered by Python + Flask, SQLite, and a machine‑learning model.
Deployed: https://caloriepredictionproject.onrender.com/
| Module | Highlights |
|---|---|
| Calorie Predictor | • XGBoost regression model (final_model.pkl) trained on gender, age, height, duration, heart‑rate, body‑temperature.• Instant prediction on the home page or via API. |
| User Auth | • Register / log in with SQLite credentials. • Sessions handled with Flask’s session object. |
| Exercise Logger | • After each prediction the workout is auto‑stored: exercise name, duration, date, BPM, temperature, calories. |
| Analytics Dashboard | • Bar: total calories per exercise • Line: calories over time • Pie: exercise share vs. calories • Scatter: heart‑rate vs. calories • Heat‑map: feature correlation • Bonus charts: violin, temp vs exercise, heart‑rate timeline & pie. |
| Secure & Portable | • Single‑file Flask backend. • No external DB server — just Calorie.db.• Secret key stored in app config for session protection. |
# 1 Clone repo & enter folder
git clone https://github.com/your‑org/ignifit.git
cd ignifit
# 2 Create virtual env
python -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
# 3 Install deps
pip install -r requirements.txt
# (Flask, pandas, plotly, xgboost, etc.)###Screenshots
