The test data provided in this competition contains a list of **hand-crafted geometries**. Use your trained model to predict the properties of each geometry !

### Submission format

The submission file should be a CSV file with 2 fields :`id` and `value`.

`id` has the following format : **`<geometry_id>_<task_name>`**

*For tasks that uses several values (for example for centroid prediction, there is the x-value and the y-value), each value should appear on a different line, with an index in the task name.*

Example of submission file : 

```
id,value
0_area,0.0
0_perimeter,0.0
0_size_0,0.0
0_size_1,0.0
0_convexity,0.0
0_min_clear,0.0
0_centroid_0,0.0
0_centroid_1,0.0
0_ombr_ratio,0.0
0_aspect_ratio,0.0
0_opening_ratio,0.0
1_area,0.0
1_perimeter,0.0
...
```

### Scoring

This competition is evaluated on the weighted mean absolute error (WMAE):

![](https://user-images.githubusercontent.com/78339260/145503169-ed2c3436-e89d-4da9-b5f1-e50665b5c7d3.jpg)

Where :
* \\( n \\) is the number of rows
* \\( \hat{y}_i \\) is the predicted sales
* \\( y_i \\) is the actual sales
* \\( w_i \\) are weights