In this section, you will use the Support Vector Machine $($SVM$)$ regression model and perform grid search to fine$-$tune its hyperparameters. Follow the steps below to set up the grid search.

Set Up Grid Search for SVM Regression

Define a parameter grid to search over. Review Scikit$-$learn's documentation for the available hyperparameters for this algorithm.

Use GridSearchCV to find the best hyperparameters.

Fit the grid search to both sets $($with and without the G$1/$G$2$ columns$)$ of the transformed training data.

Define Parameter Grid: Set up a parameter grid for the SVM regression model name param$\_$grid.

Initialize Grid Search: Initialize the GridSearchCV and call this grid$\_$search.

Fit the Grid Search: Fit the grid search to both sets $($with and without the G$1/$G$2$ columns$)$ of the transformed training data.

Save & Print Best Parameters: Save the best parameters for each respective fit to best$\_$params$\_$with$\_$grades and best$\_$params$\_$without$\_$grades, and print them.

Print Best Score: Use the best$\_$score$\_$ attribute to view the mean cross$-$validated score for each respective best$\_$estimator