Data Mining
Buddhaland
TakeTest_FinalExamFall2019Fall2019-Introto.._.pdf
12/10/2019 Take Test: Final Exam (Fall 2019) – Fall 2019 - Intro to...
https://ucumberlands.blackboard.com/webapps/assessment/take/launch.jsp?course_assessment_id=_123225_1&course_id=_110905_1&content_id=_1996737_1&ste… 1/3
F ll Content Final Exam Take Test: Final Exam (Fall 2019)H
Take Test: Final Exam (Fall 2019)Take Test: Final Exam (Fall 2019)
Test Information Description Instructions Timed Test This test has a time limit of 1 hour and 30 minutes.You will be notified when time expires, and you may continue or
submit. Warnings appear when half the time, 5 minutes, 1 minute, and 30 seconds remain.
Multiple Attempts
Not allowed. This test can only be taken once.
Force Completion
This test can be saved and resumed later. The timer will continue to run if you leave the test.
Question Completion Status:
1 2 3 4 5 6 7 8
Q U E S T I O N 1
For the data points below, show the order of merging at each step using MAX as the similarity measure
Proximity Matrix
20 points Save AnswerSave Answer
??
Home CoursesCourses
Remaining Time: 51 minutes, 21 seconds.
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
Save All AnswersSave All Answers SaSa
SHRAVAN KUMAR POSHALA
12/10/2019 Take Test: Final Exam (Fall 2019) – Fall 2019 - Intro to...
https://ucumberlands.blackboard.com/webapps/assessment/take/launch.jsp?course_assessment_id=_123225_1&course_id=_110905_1&content_id=_1996737_1&ste… 2/3
Path: p Words:0
(example: Step 1: Merge p1 & p2 --> Cluster 1.... Step 2: merge Cluster 1 & p3 --> Cluster 2 Step 3: merge Cluster 1 & Cluster 2 ....)
Please type your answer in steps similar to example above: Step 1: Step 2: Step 3: Step 4: Step 5: (more steps)
Paragraph Arial 3 (12pt)
a.
b.
c.
d.
Q U E S T I O N 2
The method where you split your data into k segments and build model using k-1 segments for training data and the rest as test data is:
Holdout
Stra�fied Training
Bootstrap
Cross Valida�on
10 points SavedSaved
a.
b.
c.
d.
Q U E S T I O N 3
K-means is :
Centroid -based Par��onal clustering approach
Medoid-based Par��onal clustering approach
Medoid-based Hierarchical clustering
Centroid-based Hierarchical clustering
10 points SavedSaved
I.
II.
III.
IV.
Q U E S T I O N 4
Consider the following plot of two variables X and Y. Which 2 of the following statements are true? (only 2 of them are true)
The two variables are independent
The two variables are positively correlated.
The two variables are dependent.
The two variables are uncorrelated.
15 points SavedSaved
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
Save All AnswersSave All Answers SaSa
12/10/2019 Take Test: Final Exam (Fall 2019) – Fall 2019 - Intro to...
https://ucumberlands.blackboard.com/webapps/assessment/take/launch.jsp?course_assessment_id=_123225_1&course_id=_110905_1&content_id=_1996737_1&ste… 3/3
V. The two variables are negatively correlated
a.
b.
c.
d.
Q U E S T I O N 5
___________________measures how closely related are objects in a cluster
___________________measures how distinct or well-separated a cluster is from other clusters
Cluster Cohesion - Cluster Separa�on
Cluster Separa�on - Cluster Cohesion
Cluster Similarity - Cluster Distance
Cluster Distance – Cluster Similarity
10 points SavedSaved
a.
b.
c.
d.
Q U E S T I O N 6
Which one is the most common measure to evaluate K-Means Clusters:
Cluster Mean
Cohesion
Separa�on
SSE
10 points SavedSaved
a.
b.
c.
d.
Q U E S T I O N 7
For the tree above, what is the Pessimistic Error after splitting:
20/40
10/40
12/40
14/40
10 points SavedSaved
a.
b.
c.
d.
Q U E S T I O N 8
Assigned me you have a dataset that has 95% class label as "healthy" and 5% as "sick"
Which one is used to make sure that the classification model does not always predicts "healty" to achieve 95% accuracy.
Principal Component Analysis
Confusion Matrix
Objective Function
Classification Accuracy
15 points SavedSaved
Click Save and Submit to save and submit. Click Save All Answers to save all answers.
Save All AnswersSave All Answers SaSa
