QUESTION 28 10 points Save Answer Consider again the TopUniversities data used in class. In addition to the existing attributes, U. S. News & World Report also provided rankings for the 25 universities. The rank order is the same as the position of the university in the dataset, e.g., Harvard is ranked #1, Princeton #2, ..., and Texas A&M #25 (see the list on the horizontal axis in the last screen in Question 29). The first output screen below is generated by Weka's SVR algorithm (SMOreg), using the university's rank as the target attribute. Then, we replaced the numeric ranking attribute with a 2-class attribute by grouping the first 15 universities to class A and the remaining 10 universities to class B. Based on this grouped dataset, the second output screen is generated by Weka's SVM algorithm (SMO) and the third output screen is generated by Weka's decision tree algorithm (J48). Answer questions (a), (b), (c) and (d) following the output screens. Weka Explorer X Preprocess Classify Cluster Associate Select attributes Visualize Classifier Choose SMoreg -C 1.0-NO-I"weka.classifiers.functions.supportVector.RegSMOImproved -T 0.001 -V-P 1.0E-12-L 0.001 -W Test options Classifier output Use training set Attributes: Supplied test set Set AvgSAT PetTop10Student Cross-validation Folds 10 PotAccept StuFacRatio Percentage split 66 Expenses GradRate More options. Rank Test mode: 10-fold cross-validation (Num) Rank mm Classifier model (full training set) .mm Start Stop SHOreg Result list (right-click for options) weights (not support vectors) : 15:57:56 - functions SMOreg 0.5489 * (normalized) AvgSAT 0.1014 * (normalized) PetTop10Student 0.3414 * (normalized) PetAccept 0.2047 * (normalized) StuFacRatio 0.3871 * (normalized) Expenses 0.2656 * (normalized) GradRate 1.0324 Number of kernel evaluations: 325 (93.1691 cached) Time taken to build model: 0.01 seconds mmm Cross-validation mmm am. Summary sum Correlation coefficient 0.8499 Mean absolute error 3.4401 Root mean squared error 4.2907Weka Explorer X Preprocess Classify Cluster Associate | Select attributes | Visualize Classifier Choose SMO -C 1.5 -L 0.001 -P 1.0E-12-NO-V-1 -W1 -K"weka.classifiers.functions.supportvector.PolyKernel -E 1.0-C 250007" -ce Test options Classifier output O Use training set Accribuses: 7 O Supplied test set Set AVISAT PetTop10Student O Cross-validation Folds 10 PetAccept StuFacRatio Percentage split 9% 66 Expenses GradRate More options. Class Tent mode: 10-fold cross-validation (Nom) Class www Classifier model (full training get) mmm Start Stop Result list (right-click for options) Kernel used: 15:57:56 - functions.SMOreg Linear Kernel: K(x, Y) = (x, Y) 16:04:03 - functions.SMO Classifier for classes: A, B BinarySHO Machine linear: showing accribuce weights, not support vectors. -1.0853 . (normalized) AvgSAT -0. 6185 * (normalized) PotTop10Student 1.2777 * (normalized) PotAccept + 0.589 * (normalized) StuFacRatio -1. 7641 . (normalized) Expenses -1. 1692 " (normalized) GradRace 1. 4922 Number of kernel evaluations: 48 (56.7574 cached) Time taken to build model: 0 seconds wow Stratified cross-validation mmm own Summary mom Correctly Classified Instances 21 Incorrectly Classified Instances Status LO OKWeka Explorer 0 X Preprocess Classify Cluster |Associate |Select attributes Visualize Classifier Choose J48 -C 0.25 -M 1 Test options Classifier output O Use training set Attributes: O Supplied test set Set AvgSAT PetTop10Student O Cross-validation Folds 10 PetAccept StuFacRatio Percentage split 1 56 Expenses GradRate More options Class Test mode: 10-fold cross-validation (Nom) Class was Classifier model (full training set) mmm Start Stop 348 pruned tree Result list (right-click for options) 15 57:56 - functions.SMOreg AvgSAT 25.026: A (1.0) 16:07:30 - 1700s.J48 AvgSAT > 12. 6: A (14.0) Number of Leaves : Size of the tree : Time taken to build model: 0 seconds wen Stratified cross-validation mmm man Summary com Correctly Classified Instances 21 Incorrectly Classified Instances Status OK Log a. Based on the SVR model (first screen), what two attributes are the most important predictors? b. Why is the coefficient of the AvgSAT attribute a negative number? c. Based on the SVM model (second screen), What two attributes are the most important predictors? d. Based on the decision tree model (third screen), what two attributes are the most important predictors