Challenge $4$

Now we would like to test our model on the testing data that we produced in Exercise $2.$ This test will give the Root Mean Squared Logarithmic Error $($RMSLE$),$ which is determined by:

$$

RMSLE $=\backslash$sqrt$\{\backslash$frac$\{1\}\{$N$\}\backslash$sum$\_\{$i$=1\}^$N $[$log$(1+$p$\_$i$)-$ log$(1+$y$\_$i$)]^2\}$

$$

$**$$p$\_$i$ refers to the $i$^\{\backslash$rm th$\}$$ prediction made from $`$X$\_$test$`$

$*$ $y$\_$i$ refers to the $i$^\{\backslash$rm th$\}$$ value in $`$y$\_$test$`$

$*$ $N$ is the length of $`$y$\_$test$`$

$\_**$Function Specifications:$**\_$

$*$ Should take a trained model and two $`$arrays$`$ as input. This will be the $`$X$\_$test$`$ and $`$y$\_$test$`$ variables from Question $2.$

$*$ Should calculate and return the Root Mean Squared Logarithmic Error $($RMSLE$)$ between the predicted values from $`$X$\_$test$`$ and the actual values in $`$y$\_$test$`.$

$*$ The output should be a $`$float$`$ rounded to $3$ decimal places.