Linear SVM Hinge Loss

Compute the mean hinge loss of a linear classifier. Labels y are in $\{-1,+1\}\backslash \{-1,+1\backslash \}$ and scores are the real-valued model outputs.

Implement solve(y,scores).

Returns. Return a non-negative Python float $\frac{1}{n}{\sum }_i\max (0,1-y_i{s}_i)\backslash ;\backslash frac1n\backslash sum\_i\backslash max(0,\backslash ,1-y\_is\_i)$.

Examples

Example 1

Input:

solve([1, -1, 1], [1.0, -1.0, -1.0])

Output:

0.666667

Example 2

Input:

solve([1, -1], [3.0, -0.5])

Output:

0.25