Submissions are evaluated on the Log of the Mean Absolute Error, calculated for each scalar coupling type, and then averaged across types, so that a 1% decrease in MAE for one type provides the same improvement in score as a 1% decrease for another type.

$$score = \frac{1}{T} \sum\_{t=1}^{T} \log \left( \frac{1}{n\_{t}} \sum\_{i=1}^{n\_t} \lvert y\_i - \hat{y\_i} \rvert \right) $$

Where:

 - \\( T \\) is the number of scalar coupling types
 - \\( n\_{t}\\) is the number of observations of type \\( t \\) 
 - \\( y\_{i}\\) is the actual scalar coupling constant for the observation
 - \\( \hat{y_i}\\) is the predicted scalar coupling constant for the observation

For this metric, the MAE for any group has a floor of `1e-9`, so that the minimum (best) possible score for perfect predictions is approximately -20.7232.

## Submission File
For each `id` in the test set, you must predict the `scalar_coupling_constant` variable. The file should contain a header and have the following format:

    id,scalar_coupling_constant
    4659076,0.0
    4659077,0.0
    4659078,0.0
    etc.