Question $7\mathrm{.}0$

$\{$points: $1\}$

Next, we'll use cross$-$validation on our training data to choose $k.$ In $k-$nn classification, we used accuracy to see how well our predictions matched the true labels.

In the context of $k-$nn regression, we will use RMSPE as the scoring instead. Interpreting the RMSPE value can be tricky but generally speaking, if the prediction

values are very close to the true values, the RMSPE will be small. Conversely, if the prediction values are not very close to the true values, the RMSPE will be quite

large.

Let's perform a cross$-$validation and choose the optimal $k!$

First, create a pipeline for $k-$nn$.$ We are still using the $k-$nearest neighbours algorithm, and we will also use the StandardScaler to standardize the numerical

values. Store your pipeline in an object called marathon$\_$pipe. Finally, perform a cross$-$validation with $5$ folds using the cross$\_$validate function. Remember

that since the cross$\_$validate function always maximizes its "score", and here we're using RMSPE $($lower is better!$),$ we need to specify that we're using the

negative RMSPE $($ "neg$\_$root$\_$mean$\_$squared$\_$error" $).$

marathon$\_$cv