## Background

Formula 1 is as much a test of human endurance as it is of engineering. Drivers experience sustained high G-forces, rapid accelerations and decelerations, and cockpit temperatures exceeding 50 °C. To stay sharp and avoid fatigue or heat exhaustion, teams meticulously plan each driver’s diet and hydration.

## Problem Statement

In this competition, you will predict the number of calories an F1 driver burns during a simulated training session, given biometric and workout data. Accurate calorie estimates allow teams to:

- ✔️ Tailor pre- and post-session meals  
- ✔️ Optimize hydration strategies  
- ✔️ Monitor recovery and recovery needs  

Your model must generalize across drivers with different physiologies, session intensities, and durations.

## Data Details

You are provided three files:

- **train.csv** (35.46 MB, 9 columns, 600 000 rows)  
- **test.csv** (same 8 feature columns, no `Calories`)  
- **sample_submission.csv** (`id`, `Calories`)

**train.csv columns**  
| Column       | Type    | Description                               |
|--------------|---------|-------------------------------------------|
| `id`         | int     | Unique session identifier                 |
| `Sex`        | string  | `male` or `female`                        |
| `Age`        | int     | Driver’s age (years)                      |
| `Height`     | float   | Driver’s height (cm)                      |
| `Weight`     | float   | Driver’s weight (kg)                      |
| `Duration`   | float   | Session length (minutes)                  |
| `Heart_Rate` | float   | Average heart rate (beats per minute)     |
| `Body_Temp`  | float   | Average body temperature (°C)             |
| `Calories`   | float   | Total calories burned (target variable)   |

**sample_submission.csv**  
| Column   | Description                      |
|----------|----------------------------------|
| `id`     | Session identifier (matches train/test) |
| `Calories` | Your predicted calories burned |

## Feature Insights

- **Sex, Age, Height, Weight** capture physiological baselines.  
- **Duration** and **Heart_Rate** drive most of the metabolic estimate.  
- **Body_Temp** reflects thermal stress—higher temperatures correlate with extra calorie expenditure.