<|im_start|>system
You are given a machine learning task. You must solve the task by training a model and running the model on the test set to produce a submission file.<|im_end|>
<|im_start|>user
First outline your proposed solution in natural language (3-5 sentences), followed by a single markdown code block (wrapped in ```). Note:

- Datasets train.csv and test.csv are available in `/workdir/spaceship-titanic/prepared/public/`.
- You MUST produce a submission file at `./submission.csv` by running your model on the test split.
- Achieve the best classification accuracy on the test split.
- Your can use pre-installed packages such as: `statsmodels`, `pandas`, `bayesian-optimization`, `scikit-learn`, `xgboost`, `numpy`, `torch`, `torchvision`, `lightGBM`, `torch-geometric`.
- You can't access the internet so don't use any pre-trained models need downloading.
- `submission.csv` should have the following format:

```
PassengerId,Transported
0013_01,False
0018_01,False
etc.
```

Train and test data snippet:
-> /workdir/spaceship-titanic/prepared/public/train.csv has 7823 rows and 14 columns.
Age (float64) has range: 0.00 - 79.00
Cabin (object) has 5992 unique values. Some example values: ['B/201/P', 'B/11/S', 'F/1194/P', 'F/1411/P']
CryoSleep (object) has 2 unique values: [True, False, nan]
Destination (object) has 3 unique values: ['TRAPPIST-1e', 'PSO J318.5-22', '55 Cancri e', nan]
FoodCourt (float64) has range: 0.00 - 27723.00
HomePlanet (object) has 3 unique values: ['Mars', 'Europa', 'Earth', nan]
Name (object) has 7625 unique values. Some example values: ['Anton Woody', 'Ankalik Nateansive', 'Dia Cartez', 'Asch Stradick']
PassengerId (object) has 7823 unique values. Some example values: ['2930_01', '4408_01', '7710_01', '7709_02']
RoomService (float64) has range: 0.00 - 14327.00
ShoppingMall (float64) has range: 0.00 - 23492.00
Spa (float64) has range: 0.00 - 22408.00
Transported (bool) is 50.44% True, 49.56% False
VIP (object) has 2 unique values: [False, True, nan]
VRDeck (float64) has range: 0.00 - 24133.00
<|im_end|>
<|im_start|>assistant
