Words: 306 English lu.s) Ask me anything Ask me anything Qi. Given a decision tr

Question

Words: 306 English lu.s) Ask me anything Ask me anything Qi. Given a decision tree, you have the option of (a) converting the decision tree to rules and then pruning the resulting rules, or b) pruning the decision tree and then converting the pruned tree to rules. What advantage does (a) have Over (b) CO. 75 Marko Q2. See the following Figure and compute the true positive rate .TPR. false positive rate FPR. Precision and Accuracy. i Marks Predicted Predicted n 165 NO YES Actual: NO 10 Actual: 100 There are two possible predicted classes "yes" and "no". If we predict the presence of a disease, for example, "yes" would mean they have the disease, and "no" would mean they don't have the disease. The classifier made a total of 165 predictions (e. 165 patients were being tested for the presence of that disease). Out of those 165 cases, the classifier predicted "yes" 110 times, and "no" 55 times. In reality, 105 patients in the sample have the disease, and 60 patients do not. E EA R 100% C A m 01:54 ENG 02:24 ENG 2/1/2016

Explanation / Answer

Q1. Given a decision tree, you have the option of (a) converting the decision tree to rules and then pruning the resulting rules, or (b) pruning the decision tree and then converting the pruned tree to rules. What advantage does (a) have over (b)?

Ans: If pruning a subtree,we would remove the subtree completely with method (b).However, with method(a), if pruning a rule, we may remove any precondition of it.The latter is less restrictive. The main difference is that rule pruning is more flexible than tree pruningsince the latter is restricted by tree structures because the pruning canonly be done on the leave nodes, while rule pruning can be doneany where so that virtually we can perform pruning near the root of the tree.

Q2. See the following Figure and compute the true positive rate .TPR/ , false positive rate .FPR/, Precision and Accuracy. (1 Marks) • There are two possible predicted classes: "yes" and "no". If we predict the presence of a disease, for example, "yes" would mean they have the disease, and "no" would mean they don't have the disease. • The classifier made a total of 165 predictions (e.g., 165 patients were being tested for the presence of that disease). • Out of those 165 cases, the classifier predicted "yes" 110 times, and "no" 55 times. • In reality, 105 patients in the sample have the disease, and 60 patients do not.

Ans. We know 165 patients were being tested for the presence of that disease.

There are total 4 cases that are as follows

Q3. Compare the advantages and disadvantages of eager classification (e.g., decision tree, Bayesian, neural network) versus lazy classification (e.g., k-nearest neighbor, case-based reasoning).

Ans.
1. Eager classification is Speedy at the time of classification as compared to lazy at the time of lassification.
2. Eager classification create a generalization model before receiving any new record to classify where as lazy does not.
3. In case of Eager classification Weights can be assigned to attributes, which can improve classification accuracy where as no Weights can be assigned in case of Lazy.

Main disadvantage of Eager classification is due to requirements of commit to a single hupothesis, which cover entire instance space it can decrease classification, and more time is needed for training.

In case of Lazy classification it use a richer hypothesis space, which can improve classification accuracy.   It requires less time for training than eager classification.  

A disadvantages of lazy classification is that all training records need to be stored, which leads to expensive storage costs and requires efficient indexing techniques. Another disadvantage is that it is slower at classification because classifiers are not built until new tuples need to be classified.

Q4. The following decision tree has been created to predict what someone can do. a. Convert this tree to if then rules (0.25 Mark) b. Using the following testing data: i. Predict the class of each record (0.25 Mark) Parents Visiting Weather Money class Prediction 1 Yes Sunny Rich Shopping 2 Yes Windy Poor Cinema 3 No Windy Poor Play tennis 4 No Rainy Rich Stay in 5 Yes Rainy Poor Stay in 6 No Windy Rich Cinema ii. Calculate the accuracy of this model. (0.25 Mark) iii. Interpret the obtained result (0.25 Mark) iv. How we can improve the performance of the obtained model? (0.25Mark)

Ans.
a.
if parentvisit=yes
then
cinema
else if Weather=sunny
then
play tennis

else if Weather=windy
then
   if money=rich
   then
   shopping
else
   cinema
   end if
else if Weather=Rainy
then
   stay away
end if

b. 1. Cinema
2. Cinema
3. Cinema
4. Stay in
5. Cinema
6. Shopping

c. Interpret the obtained result (0.25 Mark)

1. if parent visit = yes then it moves to cinema
2. if parent visit = yes then it moves to cinema
3. if parent visit =no it moves to check Weather which is=windy it check money which is =poor so it moves to cinema class
4. if parent visit =no it moves to check Weather which is = rainy so it moves to stay in class
5. if parent visit = yes then it moves to cinema
6.if parent visit =no it moves to check Weather which is =windy it check money which is =rich so it moves to shopping class

d. How we can improve the performance of the obtained model? (0.25Mark)

We can improve the perfrmance of the model by implementing the proper cases of the table.

Related Questions

Navigate

• Browse (All)
• Browse W
• Subjects

---

---

Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.