3. Consider the decision tree shown in Figure 2a, and the corresponding training and test sets shown in thetable below. The decision tree in Figure 2b is a pruned version of the original decision tree.22BB1Figure 2aFigure 2bTraining set# of (+) instances # of (-) instancesTest set# of (+) instances# of (-) instancesAB4.1134312276.32315222162.5a. Estimate the generalization error rate of both trees shown in Figures 2a and 2b using both theoptimistic approach and the pessimistic approach. To account for model complexity with thepessimistic approach, use a penalty value of 2 for each leaf node.b. Compute the error rate of the two trees on the test set shown in the table.HOHO1.

3. Consider the decision tree shown in Figure 2a, and the corresponding training and test sets shown in the table below. The decision tree in Figure 2b is a pruned version of the original decision tree. 2 2 1 Figure 2a Figure 2b Training set Test set A B # of (+) instances # of (-) instances # of (+) instances # of (-) instances 3 4 1 3. 4 1 22 7 6. 3 7 32 3. 15 2. 2. 2 2. 1. 6. 4 2 5 a. Estimate the generalization error rate of both trees shown in Figures 2a and 2b using both the optimistic approach and the pessimistic approach. To account for model complexity with the pessimistic approach, use a penalty value of 2 for each leaf node. b. Compute the error rate of the two trees on the test set shown in the table, O

3. Consider the decision tree shown in Figure 2a, and the corresponding training and test sets shown in the table below. The decision tree in Figure 2b is a pruned version of the original decision tree. 2 2 1 Figure 2a Figure 2b Training set Test set A B # of (+) instances # of (-) instances # of (+) instances # of (-) instances 3 4 1 3. 4 1 22 7 6. 3 7 32 3. 15 2. 2. 2 2. 1. 6. 4 2 5 a. Estimate the generalization error rate of both trees shown in Figures 2a and 2b using both the optimistic approach and the pessimistic approach. To account for model complexity with the pessimistic approach, use a penalty value of 2 for each leaf node. b. Compute the error rate of the two trees on the test set shown in the table, O

Database System Concepts

7th Edition

ISBN:9780078022159

Author:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Publisher:Abraham Silberschatz Professor, Henry F. Korth, S. Sudarshan

Chapter1: Introduction

Section: Chapter Questions

Problem 1PE

See similar textbooks

Similar questions

The accuracy on an unpruned decision tree is 40% on the test data, while that on the training data is close to 60%. Write the accuracy expression of this using 0.632 bootstrap?
Data Mining Briefly outline the major steps of decision tree classification. 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)?
Consider a node, t, in a decision tree. The set of training records in node t is Dt, which contains records from three different classes C1, C2, and C3. The class distribution is as follow: Class Number of records C1 x C2 x C3 2x What are the impurity measures of this node using Gini index and misclassification error? Gini index = Misclassification error =
Construct a decision tree toclassify the given data.
Discretized values in a decision tree may be combined into a single branch if order is not preserved. Having trouble understanding why this is true ?
Implement a graphical system for employee management that includes an employee id, employee name, and years of service. Employees should be stored in the system using a B-tree of order 7, and they should be able to be added and removed. Your system must refresh a sorted list of workers sorted by name on the screen after each operation. Implement a graphical system for employee management that includes an employee id, employee name, and years of service. Employees should be stored in the system using a B-tree of order 7, and they should be able to be added and removed. Your system must refresh a sorted list of workers sorted by name on the screen after each operation.
2. Determine using a tree whether the following propositions are jointly satisfiable. If they are, read off from your tree a model on which they are both true (and be sure to indicate which path you are reading it off from). (Lbb∧Lda)↔∀xLcx ∃x(Lbx→Lxx)
Q2:Explain the connection between potential overfitting of a decision tree model and the minimum entropy required to determine that a node is a leaf.
Implement a graphical system to manage employees using an employee id, employee name, and years of service. The system should usea B-tree of order 7 to store employees, and it must provide the abilityto add and remove employees. After each operation, your system mustupdate a sorted list of employees sorted by name on the screen.
Develop a simple table of examples in some domain, such as classifying plants by species, and trace the construction of a decision tree by the ID3 algorithm. Construct a decision tree using py
Generalize the missing attribute problem to the case of several missing features, and to several deficient patterns. Specifically, write pseudocode for creating a binary decision tree where each d-dimensional pattern can have multiple missing features.
Write the decision tree model class that uses training accuracy to make splits from scratch. The class should be able to handle other splitting criteria, namely entropy and Gini index as well.