To evaluate your results, we first calculate the absolute difference between your predicted and the ground truth heart rates for each 30-second window (Error). Afterward, we calculate your final score (FinalScore) as the mean of the mean error and the median error between your predictions and the ground truth heart rates:

$$ \text{Error} = \text{abs}(\text{PredictedHR} - \text{GroundTruthHR}) $$

$$ \text{FinalScore} = 0.5 \text{mean}(\text{Error}) + 0.5 \text{median}(\text{Error}) $$

Note that the HR may not be constant throughout the 30–second window you compute it for. The ground truth HR is equivalent to the average HR over the window.


## Submission File
To obtain a score on the leaderboard, at least one of your team has to submit a *submission.csv* file, which consists of two columns with the names "Id" and "Predicted". The column "Id" contains the name of the phase and a counter of your predicted windows in the format displayed below. The column "Predicted" contains your predicted heart rate for the corresponding window as a float. **The displayed heart rates below are only examples and are not the correct heart rates!**

In the *example_notebook.ipynb*, we have prepared an example of how to create a correct *submission.csv* file so that you do not have to code that yourself.

    Id, Predicted
    phase0_0, 70.12
    phase0_1, 130.5
    phase0_2, 51.3
    etc.