# F1 _Racer Diet planning — Data

来源：https://www.kaggle.com/competitions/f-1-racer-diet-planning/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Files

- **train.csv** – the training set (35 MB, 600 000 rows, 9 columns). Contains all feature columns plus the target `Calories`.  
- **test.csv** – the test set (same 8 feature columns, no `Calories`). Use this to generate your predictions.  
- **sample_submission.csv** – a sample submission in the correct format. Two columns: `id` and `Calories`.

## Columns

| Column       | Type    | Description                                       |
|--------------|---------|---------------------------------------------------|
| `id`         | int     | Unique session identifier                         |
| `Sex`        | string  | Driver’s sex (`male` or `female`)                 |
| `Age`        | int     | Driver’s age in years                             |
| `Height`     | float   | Driver’s height in centimeters (cm)               |
| `Weight`     | float   | Driver’s weight in kilograms (kg)                 |
| `Duration`   | float   | Session duration in minutes                       |
| `Heart_Rate` | float   | Average heart rate during session (beats per min) |
| `Body_Temp`  | float   | Average body temperature during session (°C)      |
| `Calories`   | float   | Total calories burned in session (target)         |

## What to expect

- **train.csv** includes all 9 columns above.  
- **test.csv** includes the first 8 columns—your model must predict `Calories`.  
- **sample_submission.csv** has two columns (`id`, `Calories`); make sure your submission uses exactly these column names and order.  

## Prediction Task

You are predicting the continuous target `Calories` for each `id` in `test.csv`.

---

Feel free to refer back to this section for quick reference on file names, formats, and column meanings. Good luck!