Solution Manual for Data Mining and Machine Learning: Fundamental Concepts and Algorithms 2nd Edition by Mohammed J. Zaki, Wagner Meira Jr

Solution Manual for Data Mining and Machine Learning:
Fundamental Concepts and Algorithms 2nd Edition by Mohammed
J. Zaki, Wagner Meira Jr A+ LATEST

, lOMoARcPSD|30878495




Contents




Contents 1

1 Data Mining and Analysis . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.7 Exercises 3

PART I DATA ANALYSIS FOUNDATIONS 5

2 Numeric Attributes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.7 Exercises 7

3 Categorical Attributes . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3.7 Exercises 16

4 Graph Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4.6 Exercises 20

5 Kernel Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
5.6 Exercises 26

6 High-dimensional Data . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
6.9 Exercises 29

7 Dimensionality Reduction . . . . . . . . . . . . . . . . . . . . . . . . . 39
7.6 Exercises 39

PART II FREQUENT PATTERN MINING 45

8 Itemset Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47
8.5 Exercises 47

9 Summarizing Itemsets . . . . . . . . . . . . . . . . . . . . . . . . . . . 56
9.6 Exercises 56

1




Downloaded by Irfan Ali ()

, lOMoARcPSD|30878495




2 Contents

10 Sequence Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 63
10.5 Exercises 63

11 Graph Pattern Mining . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75
11.5 Exercises 75

12 Pattern and Rule Assessment . . . . . . . . . . . . . . . . . . . . . . . . 84
12.4 Exercises 84

PART III CLUSTERING 89

13 Representative-based Clustering . . . . . . . . . . . . . . . . . . . . . . 91
13.5 Exercises 91

14 Hierarchical Clustering . . . . . . . . . . . . . . . . . . . . . . . . . . . 99
14.4 Exercises 99

15 Density-based Clustering . . . . . . . . . . . . . . . . . . . . . . . . . . 106
15.5 Exercises 106

16 Spectral and Graph Clustering . . . . . . . . . . . . . . . . . . . . . . . 111
16.5 Exercises 111

17 Clustering Validation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118
17.5 Exercises 118

PART IV CLASSIFICATION 123
18 Probabilistic Classification . . . . . . . . . . . . . . . . . . . . . . . . . 125
18.5 Exercises 125

19 Decision Tree Classifier . . . . . . . . . . . . . . . . . . . . . . . . . . . 129
19.4 Exercises 129

20 Linear Discriminant Analysis . . . . . . . . . . . . . . . . . . . . . . . . 137
20.4 Exercises 137

21 Support Vector Machines . . . . . . . . . . . . . . . . . . . . . . . . . . 141
21.7 Exercises 141

22 Classification Assessment . . . . . . . . . . . . . . . . . . . . . . . . . . 145
22.5 Exercises 145




This book has been published by Cambridge University Press. No unauthorized distribution shall be allowed.




Downloaded by Irfan Ali ()

, lOMoARcPSD|30878495




CHAPTER 1 Data Mining and Analysis




1.7 EXERCISES

Q1. Show that the mean of the centered data matrix Z in Eq. (1.5) is 0.

Answer: Each centered point is given as: zi = xi − µ. Their mean is therefore:
n n
1X 1X
zi = (xi − µ)
n n
i=0 i=0
n
1X 1
= xi − · n · µ
n n
i=0

= µ−µ= 0



Q2. Prove that for the Lp -distance in Eq. (1.2), we have

d 
δ∞ (x, y) = lim δp (x, y) = max |xi − yi |
p→∞ i=1

for x, y ∈ Rd .

Answer: We have to show that

d
! p1
X d 
lim |xi − yi |p = max |xi − yi |
p→∞ i=1
i=1

Assume that dimension a is the max, and let m = |xa − ya |. For simplicity, we
assume that |xi − yi | < m for all i 6= a.
If we divide and multiply the left hand side with mp we get:

! p1  1
d 
X  X  |xi − yi | p
p
|xi − yi | p
m p
= m 1 + 
m m
i=1 i6=a


3




Downloaded by Irfan Ali ()