Data Mining Classification: Alternative Techniques: Lecture Notes For Chapter 5 Introduction To Data Mining

Data Mining
Classification: Alternative Techniques
Lecture Notes for Chapter 5

Introduction to Data Mining
by
Tan, Steinbach, Kumar
Tan,Steinbach, Kumar
4/18/2004
Rule-Based Classifier
O
Classify records by using a collection of

ifthen rules
Rule:
(Condition) y
where
Condition is a conjunctions of attributes
y is the class label
LHS: rule antecedent or condition

RHS: rule consequent
Examples of classification rules:
(Blood Type=Warm) (Lay Eggs=Yes) Birds
(Taxable Income < 50K) (Refund=Yes) Evade=No
4/18/2004
Rule-based Classifier (Example)

Name
Blood Type
human
python
salmon
whale
frog
komodo
bat
pigeon
cat
leopard shark
turtle
penguin
porcupine
eel
salamander
gila monster
platypus
owl
dolphin
eagle
warm
cold
cold
warm
cold
cold
warm
warm
warm
cold
cold
warm
warm
cold
cold
cold
warm
warm
warm
warm
Give Birth
yes
no
no
yes
no
no
yes
no
yes
yes
no
no
yes
no
no
no
no
no
yes
no
Can Fly
no
no
no
no
no
no
yes
yes
no
no
no
no
no
no
no
no
no
yes
no
yes
Live in Water
no
no
yes
yes
sometimes
no
no
no
no
yes
sometimes
sometimes
no
yes
sometimes
no
no
no
yes
no
Class
mammals
reptiles
fishes
mammals
amphibians
reptiles
mammals
birds
mammals
fishes
reptiles
birds
mammals
fishes
amphibians
reptiles
mammals
birds
mammals
birds
R1: (Give Birth = no) (Can Fly = yes) Birds

R2: (Give Birth = no) (Live in Water = yes) Fishes
R3: (Give Birth = yes) (Blood Type = warm) Mammals
R4: (Give Birth = no) (Can Fly = no) Reptiles
R5: (Live in Water = sometimes) Amphibians
4/18/2004
Application of Rule-Based Classifier

O
A rule r covers an instance x if the attributes of

the instance satisfy the condition of the rule
Name
hawk
grizzly bear
Blood Type
warm
warm
Give Birth
Can Fly
Live in Water
Class
no
yes
yes
no
no
no
?
?
The rule R1 covers a hawk => Bird

The rule R3 covers the grizzly bear => Mammal
4/18/2004
Rule Coverage and Accuracy

Tid Refund Marital
Coverage of a rule:
Status
1
Yes
Single
Fraction of records
2
No
Married
that satisfy the
3
No
Single
antecedent of a rule
4
Yes
Married
5
No
Divorced
O Accuracy of a rule:
6
No
Married
Fraction of records
7
Yes
Divorced
that satisfy both the
8
No
Single
9
No
Married
antecedent and
10 No
Single
consequent of a
(Status=Single) No
rule
O
Taxable
Income Class
125K
No
100K
No
70K
No
120K
No
95K
Yes
60K
No
220K
No
85K
Yes
75K
No
90K
Yes
10
Coverage = 40%, Accuracy = 50%

4/18/2004
How does Rule-based Classifier Work?

Name
lemur
turtle
dogfish shark
Blood Type
warm
cold
cold
Give Birth
Can Fly
Live in Water
Class
yes
no
yes
no
no
no
no
sometimes
yes
?
?
?
A lemur triggers rule R3, so it is classified as a mammal

A turtle triggers both R4 and R5
A dogfish shark triggers none of the rules
4/18/2004
Characteristics of Rule-Based Classifier

O
Mutually exclusive rules

Classifier contains mutually exclusive rules if
the rules are independent of each other
Every record is covered by at most one rule
Exhaustive rules
Classifier has exhaustive coverage if it
accounts for every possible combination of
attribute values
Each record is covered by at least one rule
4/18/2004
From Decision Trees To Rules

Classification Rules
(Refund=Yes) ==> No
Refund
Yes
No
NO
{Single,
Divorced}
Marita l
Status
NO
{Married}
(Refund=No, Marital Status={Single,Divorced},

Taxable Income>80K) ==> Yes
(Refund=No, Marital Status={Married}) ==> No
NO
Taxable
Income
< 80K

Taxable Income<80K) ==> No
> 80K
YES
Rules are mutually exclusive and exhaustive

Rule set contains as much information as the
tree
4/18/2004
Rules Can Be Simplified

Refund
Yes
No
NO
{Single,
Divorced}
Marita l
Status
NO
Taxable
Income
< 80K
{Married}
> 80K
NO
YES
Tid Refund Marital

Status
Taxable
Income Cheat
Yes
Single
125K
No
No
Married
100K
No
No
Single
70K
No
Yes
Married
120K
No
No
Divorced 95K
No
Married
Yes
Divorced 220K
No
No
Single
85K
Yes
No
Married
75K
No
10
No
Single
90K
Yes
60K
Yes
No
10
Initial Rule:
(Refund=No) (Status=Married) No
Simplified Rule: (Status=Married) No

4/18/2004
Effect of Rule Simplification

O
Rules are no longer mutually exclusive

A record may trigger more than one rule
Solution?
Ordered rule set
Unordered rule set use voting schemes
Rules are no longer exhaustive

A record may not trigger any rules
Solution?
Use a default class
4/18/2004
10
Ordered Rule Set

O
Rules are rank ordered according to their priority

An ordered rule set is known as a decision list
When a test record is presented to the classifier

It is assigned to the class label of the highest ranked rule it has
triggered
If none of the rules fired, it is assigned to the default class
Name
turtle
Blood Type
Give Birth
Can Fly
Live in Water
Class
no
no
sometimes
cold
4/18/2004
11
Rule Ordering Schemes

O
Rule-based ordering
Individual rules are ranked based on their quality
Class-based ordering
Rules that belong to the same class appear together
Rule-based Ordering
Class-based Ordering
(Refund=Yes) ==> No
(Refund=Yes) ==> No




4/18/2004
12
Building Classification Rules

O
Direct Method:
Extract rules directly from data
e.g.: RIPPER, CN2, Holtes 1R
Indirect Method:
Extract rules from other classification models (e.g.
decision trees, neural networks, etc).
e.g: C4.5rules
4/18/2004
13
Direct Method: Sequential Covering

1.
2.
3.
4.
Start from an empty rule

Grow a rule using the Learn-One-Rule function
Remove training records covered by the rule
Repeat Step (2) and (3) until stopping criterion
is met
4/18/2004
14
Example of Sequential Covering
(ii) Step 1
(i) Original Data
4/18/2004
15
Example of Sequential Covering
R1
R1
R2
(iii) Step 2
(iv) Step 3
4/18/2004
16
Aspects of Sequential Covering

O
Rule Growing
Instance Elimination
Rule Evaluation
Stopping Criterion
Rule Pruning
4/18/2004
17
Rule Growing
O
Two common strategies
{}
Yes: 3
No: 4
Refund=No,
Status=Single,
Income=85K
(Class=Yes)
Refund=
No
Status =
Single
Status =
Divorced
Status =
Married
Yes: 3
No: 4
Yes: 2
No: 1
Yes: 1
No: 0
Yes: 0
No: 3
...
Income
> 80K
Yes: 3
No: 1
(a) General-to-specific
Refund=No,
Status=Single,
Income=90K
(Class=Yes)
Refund=No,
Status = Single
(Class = Yes)
(b) Specific-to-general
4/18/2004
18
Rule Growing (Examples)

O
CN2 Algorithm:
Start from an empty conjunct: {}
Add conjuncts that minimizes the entropy measure: {A}, {A,B},
Determine the rule consequent by taking majority class of instances
covered by the rule
RIPPER Algorithm:
Start from an empty rule: {} => class
Add conjuncts that maximizes FOILs information gain measure:
R0: {} => class (initial rule)
R1: {A} => class (rule after adding conjunct)
Gain(R0, R1) = t [ log (p1/(p1+n1)) log (p0/(p0 + n0)) ]
where t: number of positive instances covered by both R0 and R1
p0: number of positive instances covered by R0
n0: number of negative instances covered by R0
p1: number of positive instances covered by R1
n1: number of negative instances covered by R1
4/18/2004
19
Instance Elimination
O
Why do we need to
eliminate instances?
R3
Otherwise, the next rule is

identical to previous rule
O
Why do we remove
positive instances?
R1
+
class = +
Ensure that the next rule is

different
O
Why do we remove
negative instances?
class = -
Prevent underestimating
accuracy of rule
Compare rules R2 and R3
in the diagram
+ +
+
+
+
+
++
+
+
+++
+ + +
+ +
-
R2
+
+
+
+ +
-
4/18/2004
20
Rule Evaluation
O
Metrics:
Accuracy
Laplace
nc
n
nc + 1
n+k
n + kp
M-estimate = c
n+k
n : Number of instances
covered by rule
nc : Number of instances
covered by rule
k : Number of classes
p : Prior probability
4/18/2004
21
Stopping Criterion and Rule Pruning

O
Stopping criterion
Compute the gain
If gain is not significant, discard the new rule
Rule Pruning
Similar to post-pruning of decision trees
Reduced Error Pruning:
Remove one of the conjuncts in the rule
Compare error rate on validation set before and
after pruning
If error improves, prune the conjunct
4/18/2004
22
Summary of Direct Method

O
Grow a single rule
Remove Instances from rule
Prune the rule (if necessary)
Add rule to Current Rule Set
Repeat
4/18/2004
23
Direct Method: RIPPER

O
For 2-class problem, choose one of the classes as

positive class, and the other as negative class
Learn rules for positive class
Negative class will be default class
For multi-class problem
Order the classes according to increasing class
prevalence (fraction of instances that belong to a
particular class)
Learn the rule set for smallest class first, treat the rest
as negative class
Repeat with next smallest class as positive class
4/18/2004
24

O
Growing a rule:
Start from empty rule
Add conjuncts as long as they improve FOILs
information gain
Stop when rule no longer covers negative examples
Prune the rule immediately using incremental reduced
error pruning
Measure for pruning: v = (p-n)/(p+n)
p: number of positive examples covered by the rule in
the validation set
n: number of negative examples covered by the rule in
the validation set
Pruning method: delete any final sequence of

conditions that maximizes v
4/18/2004
25

O
Building a Rule Set:

Use sequential covering algorithm
Finds the best rule that covers the current set of
positive examples
Eliminate both positive and negative examples
covered by the rule
Each time a rule is added to the rule set,

compute the new description length
stop adding new rules when the new description
length is d bits longer than the smallest description
length obtained so far
4/18/2004
26

O
Optimize the rule set:

For each rule r in the rule set R
Consider 2 alternative rules:

Replacement rule (r*): grow new rule from scratch
Revised rule(r): add conjuncts to extend the rule r
Compare the rule set for r against the rule set for r*
and r
Choose rule set that minimizes MDL principle
Repeat rule generation and rule optimization

for the remaining positive examples
4/18/2004
27
Indirect Methods
P
No
Yes
Q
No
Rule Set
R
Yes
No
Yes
Q
No
Yes
r1: (P=No,Q=No) ==> r2: (P=No,Q=Yes) ==> +

r3: (P=Yes,R=No) ==> +
r4: (P=Yes,R=Yes,Q=No) ==> r5: (P=Yes,R=Yes,Q=Yes) ==> +
4/18/2004
28
Indirect Method: C4.5rules

Extract rules from an unpruned decision tree
O For each rule, r: A y,
consider an alternative rule r: A y where A
is obtained by removing one of the conjuncts
in A
Compare the pessimistic error rate for r
against all rs
Prune if one of the rs has lower pessimistic
error rate
Repeat until we can no longer improve
generalization error
O
4/18/2004
29
Indirect Method: C4.5rules

O
Instead of ordering the rules, order subsets of

rules (class ordering)
Each subset is a collection of rules with the
same rule consequent (class)
Compute description length of each subset
Description length = L(error) + g L(model)
g is a parameter that takes into account the
presence of redundant attributes in a rule set
(default value = 0.5)
4/18/2004
30
Example
Name
Give Birth
human
python
salmon
whale
frog
komodo
bat
pigeon
cat
leopard shark
turtle
penguin
porcupine
eel
salamander
gila monster
platypus
owl
dolphin
eagle
yes
no
no
yes
no
no
yes
no
yes
yes
no
no
yes
no
no
no
no
no
yes
no
Lay Eggs
no
yes
yes
no
yes
yes
no
yes
no
no
yes
yes
no
yes
yes
yes
yes
yes
no
yes
Can Fly
no
no
no
no
no
no
yes
yes
no
no
no
no
no
no
no
no
no
yes
no
yes
Live in Water Have Legs
no
no
yes
yes
sometimes
no
no
no
no
yes
sometimes
sometimes
no
yes
sometimes
no
no
no
yes
no
yes
no
no
no
yes
yes
yes
yes
yes
no
yes
yes
yes
no
yes
yes
yes
yes
no
yes
Class
mammals
reptiles
fishes
mammals
amphibians
reptiles
mammals
birds
mammals
fishes
reptiles
birds
mammals
fishes
amphibians
reptiles
mammals
birds
mammals
birds
4/18/2004
31
C4.5 versus C4.5rules versus RIPPER

C4.5rules:
Give
Birth?
(Give Birth=No, Can Fly=Yes) Birds

(Give Birth=No, Live in Water=Yes) Fishes
No
Yes
(Give Birth=Yes) Mammals

(Give Birth=No, Can Fly=No, Live in Water=No) Reptiles
Live In
Water?
Mammals
Yes
( ) Amphibians
RIPPER:
No
(Live in Water=Yes) Fishes

(Have Legs=No) Reptiles
Sometimes
Fishes
Yes
Birds
(Give Birth=No, Can Fly=No, Live In Water=No)

Reptiles
Can
Fly?
Amphibians
(Can Fly=Yes,Give Birth=No) Birds
No
() Mammals
Reptiles
4/18/2004
32
C4.5 versus C4.5rules versus RIPPER

C4.5 and C4.5rules:
PREDICTED CLASS
Amphibians Fishes Reptiles Birds
2
0
0
ACTUAL Amphibians
0
2
0
CLASS Fishes
1
0
3
Reptiles
1
0
0
Birds
0
0
1
Mammals
0
0
0
3
0
Mammals
0
1
0
0
6
0
0
0
2
0
Mammals
2
0
1
1
4
RIPPER:
PREDICTED CLASS
Amphibians Fishes Reptiles Birds
0
0
0
ACTUAL Amphibians
0
3
0
CLASS Fishes
0
0
3
Reptiles
0
0
1
Birds
0
2
1
Mammals
4/18/2004
33
Advantages of Rule-Based Classifiers

As highly expressive as decision trees
O Easy to interpret
O Easy to generate
O Can classify new instances rapidly
O Performance comparable to decision trees
O
4/18/2004
34
Instance-Based Classifiers
Set of Stored Cases
Atr1
...
AtrN
Class
A
Store the training records

Use training records to
predict the class label of
unseen cases
B
B
C
A
Unseen Case
Atr1
...
AtrN
C
B
4/18/2004
35
Instance Based Classifiers

O
Examples:
Rote-learner
Memorizes entire training data and performs
classification only if attributes of record match one of
the training examples exactly
Nearest neighbor
Uses k closest points (nearest neighbors) for
performing classification
4/18/2004
36
Nearest Neighbor Classifiers

O
Basic idea:
If it walks like a duck, quacks like a duck, then
its probably a duck
Compute
Distance
Training
Records
Test
Record
Choose k of the
nearest records
4/18/2004
37
Nearest-Neighbor Classifiers
Unknown record
Requires three things

The set of stored records
Distance Metric to compute
distance between records
The value of k, the number of
nearest neighbors to retrieve
To classify an unknown record:

Compute distance to other
training records
Identify k nearest neighbors
Use class labels of nearest
neighbors to determine the
class label of unknown record
(e.g., by taking majority vote)
4/18/2004
38
Definition of Nearest Neighbor
(b) 2-nearest neighbor
(c) 3-nearest neighbor
(a) 1-nearest neighbor
K-nearest neighbors of a record x are data points

that have the k smallest distance to x
4/18/2004
39
4/18/2004
40
1 nearest-neighbor
Voronoi Diagram
Nearest Neighbor Classification

O
Compute distance between two points:

Euclidean distance
d ( p, q ) =
O
q )
( pi
Determine the class from nearest neighbor list

take the majority vote of class labels among
the k-nearest neighbors
Weigh the vote according to distance
weight factor, w = 1/d2
4/18/2004
41

O
Choosing the value of k:

If k is too small, sensitive to noise points
If k is too large, neighborhood may include points from
other classes
4/18/2004
42

O
Scaling issues
Attributes may have to be scaled to prevent
distance measures from being dominated by
one of the attributes
Example:
height of a person may vary from 1.5m to 1.8m
weight of a person may vary from 90lb to 300lb
income of a person may vary from $10K to $1M
4/18/2004
43

O
Problem with Euclidean measure:

High dimensional data
curse of dimensionality
Can produce counter-intuitive results

111111111110
vs
100000000000
011111111111
000000000001
d = 1.4142
d = 1.4142
Solution: Normalize the vectors to unit length
4/18/2004
44
Nearest neighbor Classification

O
k-NN classifiers are lazy learners

It does not build models explicitly
Unlike eager learners such as decision tree
induction and rule-based systems
Classifying unknown records are relatively
expensive
4/18/2004
45
Example: PEBLS
O
PEBLS: Parallel Examplar-Based Learning

System (Cost & Salzberg)
Works with both continuous and nominal
features
For
nominal features, distance between two

nominal values is computed using modified value
difference metric (MVDM)
Each record is assigned a weight factor

Number of nearest neighbor, k = 1
4/18/2004
46
Example: PEBLS
Tid Refund Marital
Status
Taxable
Income Cheat
Yes
Single
125K
No
d(Single,Married)
No
Married
100K
No
= | 2/4 0/4 | + | 2/4 4/4 | = 1
No
Single
70K
No
Yes
Married
120K
No
d(Single,Divorced)
No
Divorced 95K
Yes
No
Married
No
d(Married,Divorced)
Yes
Divorced 220K
No
= | 0/4 1/2 | + | 4/4 1/2 | = 1
No
Single
85K
Yes
d(Refund=Yes,Refund=No)
No
Married
75K
No
10
No
Single
90K
Yes
= | 0/3 3/7 | + | 3/3 4/7 | = 6/7
60K
Distance between nominal attribute values:
= | 2/4 1/2 | + | 2/4 1/2 | = 0
10
Refund
Marital Status
Class
Single
Married
Divorced
Yes
No
Class
Yes
No
Yes
No
d (V1 ,V2 ) =
n1i n 2 i
n1 n 2
4/18/2004
47
Example: PEBLS
Tid Refund Marital
Status
Taxable
Income Cheat
Yes
Single
125K
No
No
Married
100K
No
10
Distance between record X and record Y:

d
( X , Y ) = w X wY d ( X i , Yi ) 2
i =1
where:
wX =
Number of times X is used for prediction

Number of times X predicts correctly
wX 1 if X makes accurate prediction most of the time

wX > 1 if X is not reliable for making predictions
4/18/2004
48
Bayes Classifier
A probabilistic framework for solving classification
problems
O Conditional Probability:
P( A, C )
P (C | A) =
P ( A)
O
P( A | C ) =
O
P( A, C )
P (C )
Bayes theorem:
P (C | A) =
P ( A | C ) P (C )
P ( A)
4/18/2004
49
Example of Bayes Theorem

O
Given:
A doctor knows that meningitis causes stiff neck 50% of the
time
Prior probability of any patient having meningitis is 1/50,000
Prior probability of any patient having stiff neck is 1/20
If a patient has stiff neck, whats the probability

he/she has meningitis?
P( M | S ) =
P ( S | M ) P ( M ) 0.5 1 / 50000
=
= 0.0002
P( S )
1 / 20
4/18/2004
50
Bayesian Classifiers
O
Consider each attribute and class label as random

variables
Given a record with attributes (A1, A2,,An)

Goal is to predict class C
Specifically, we want to find the value of C that
maximizes P(C| A1, A2,,An )
Can we estimate P(C| A1, A2,,An ) directly from

data?
4/18/2004
51
Bayesian Classifiers
O
Approach:
compute the posterior probability P(C | A1, A2, , An) for
all values of C using the Bayes theorem
P (C | A A K A ) =
1
P ( A A K A | C ) P (C )
P(A A K A )
1
Choose value of C that maximizes

P(C | A1, A2, , An)
Equivalent to choosing value of C that maximizes
P(A1, A2, , An|C) P(C)
O
How to estimate P(A1, A2, , An | C )?
4/18/2004
52
Nave Bayes Classifier

O
Assume independence among attributes Ai when class is

given:
P(A1, A2, , An |C) = P(A1| Cj) P(A2| Cj) P(An| Cj)
Can estimate P(Ai| Cj) for all Ai and Cj.
New point is classified to Cj if P(Cj) P(Ai| Cj) is
maximal.
4/18/2004
53
How to Estimate Probabilities from Data?

c
Tid
Refund
Marital
Status
Taxable
Income
Evade
Yes
Single
125K
No
No
Married
100K
No
No
Single
70K
No
Yes
Married
120K
No
No
Divorced
95K
Yes
No
Married
60K
No
Yes
Divorced
220K
No
No
Single
85K
Yes
No
Married
75K
No
10
No
Single
90K
Yes
Class: P(C) = Nc/N

e.g., P(No) = 7/10,
P(Yes) = 3/10
For discrete attributes:

P(Ai | Ck) = |Aik|/ Nc k
where |Aik| is number of
instances having attribute
Ai and belongs to class Ck
Examples:
10
P(Status=Married|No) = 4/7
P(Refund=Yes|Yes)=0
4/18/2004
54

O
For continuous attributes:

Discretize the range into bins
one ordinal attribute per bin
violates independence assumption
Two-way split: (A < v) or (A > v)
choose only one of the two splits as new attribute
Probability density estimation:

Assume attribute follows a normal distribution
Use data to estimate parameters of distribution
(e.g., mean and standard deviation)
Once probability distribution is known, can use it to
estimate the conditional probability P(Ai|c)
4/18/2004
55

Tid
1
Refund
Yes
Marital
Status
Single
Taxable
Income
125K
Evade
Normal distribution:
1
P( A | c ) =
e
2
No
No
Married
100K
No
No
Single
70K
No
Yes
Married
120K
No
No
Divorced
95K
Yes
No
Married
60K
No
Yes
Divorced
220K
No
No
Single
85K
Yes
No
Married
75K
No
10
No
Single
90K
Yes
( Ai ij ) 2
2 ij2
ij
One for each (Ai,ci) pair

O
For (Income, Class=No):

If Class=No
sample mean = 110
sample variance = 2975
10
1
P ( Income = 120 | No) =
e
2 (54.54)
( 120 110 ) 2
2 ( 2975 )
= 0.0072
4/18/2004
56
Example of Nave Bayes Classifier

Given a Test Record:
X = (Refund = No, Married, Income = 120K)
naive Bayes Classifier:

P(Refund=Yes|No) = 3/7
P(Refund=No|No) = 4/7
P(Refund=Yes|Yes) = 0
P(Refund=No|Yes) = 1
P(Marital Status=Single|No) = 2/7
P(Marital Status=Divorced|No)=1/7
P(Marital Status=Married|No) = 4/7
P(Marital Status=Single|Yes) = 2/7
P(Marital Status=Divorced|Yes)=1/7
P(Marital Status=Married|Yes) = 0
For taxable income:
If class=No:
sample mean=110
sample variance=2975
If class=Yes: sample mean=90
sample variance=25
P(X|Class=No) = P(Refund=No|Class=No)
P(Married| Class=No)
P(Income=120K| Class=No)
= 4/7 4/7 0.0072 = 0.0024
P(X|Class=Yes) = P(Refund=No| Class=Yes)

P(Married| Class=Yes)
P(Income=120K| Class=Yes)
= 1 0 1.2 10-9 = 0
Since P(X|No)P(No) > P(X|Yes)P(Yes)

Therefore P(No|X) > P(Yes|X)
=> Class = No
4/18/2004
57
Nave Bayes Classifier

If one of the conditional probability is zero, then
the entire expression becomes zero
O Probability estimation:
O
Original : P ( Ai | C ) =
N ic
Nc
N +1
Laplace : P( Ai | C ) = ic
Nc + c
N + mp
m - estimate : P( Ai | C ) = ic
Nc + m
c: number of classes
p: prior probability
m: parameter
4/18/2004
58
Example of Nave Bayes Classifier

Name
human
python
salmon
whale
frog
komodo
bat
pigeon
cat
leopard shark
turtle
penguin
porcupine
eel
salamander
gila monster
platypus
owl
dolphin
eagle
Give Birth
yes
Give Birth
yes
no
no
yes
no
no
yes
no
yes
yes
no
no
yes
no
no
no
no
no
yes
no
Can Fly
no
no
no
no
no
no
yes
yes
no
no
no
no
no
no
no
no
no
yes
no
yes
Can Fly
no
no
no
yes
yes
sometimes
no
no
no
no
yes
sometimes
sometimes
no
yes
sometimes
no
no
no
yes
no
Class
yes
no
no
no
yes
yes
yes
yes
yes
no
yes
yes
yes
no
yes
yes
yes
yes
no
yes
mammals
non-mammals
non-mammals
mammals
non-mammals
non-mammals
mammals
non-mammals
mammals
non-mammals
non-mammals
non-mammals
mammals
non-mammals
non-mammals
non-mammals
mammals
non-mammals
mammals
non-mammals
yes
no
A: attributes
M: mammals
N: non-mammals
6 6 2 2
P ( A | M ) = = 0.06
7 7 7 7
1 10 3 4
P ( A | N ) = = 0.0042
13 13 13 13
7
P ( A | M ) P( M ) = 0.06 = 0.021
20
13
P ( A | N ) P( N ) = 0.004 = 0.0027
20
Class
P(A|M)P(M) > P(A|N)P(N)

=> Mammals
4/18/2004
59
Nave Bayes (Summary)

O
Robust to isolated noise points
Handle missing values by ignoring the instance

during probability estimate calculations
Robust to irrelevant attributes
Independence assumption may not hold for some

attributes
Use other techniques such as Bayesian Belief
Networks (BBN)
4/18/2004
60
Artificial Neural Networks (ANN)
X1 X2 X3
1
1
1
1
0
0
0
0
0
0
1
1
0
1
1
0
0
1
0
1
1
0
1
0
Input
0
1
1
1
0
0
1
0
X1
Black box
Output
X2
X3
Output Y is 1 if at least two of the three inputs are equal to 1.
4/18/2004
61
X1 X2 X3
1
1
1
1
0
0
0
0
0
0
1
1
0
1
1
0
0
1
0
1
1
0
1
0
Y
0
1
1
1
0
0
1
0
Input
nodes
Black box
X1
Output
node
0.3
0.3
X2
X3
0.3
t=0.4
Y = I ( 0 .3 X 1 + 0 .3 X 2 + 0 .3 X 3 0 .4 > 0 )
1
where I ( z ) =
0
if z is true
otherwise
4/18/2004
62

O
Model is an assembly of
inter-connected nodes
and weighted links
Output node sums up
each of its input value
according to the weights
of its links
Input
nodes
Black box
X1
Output
node
w1
w2
X2
w3
X3
Perceptron Model
Y = I ( wi X i t )
Compare output node

against some threshold t
or
Y = sign( wi X i t )
i
4/18/2004
63
General Structure of ANN

x1
x2
x3
Input
Layer
x4
x5
Input
I1
I2
Hidden
Layer
I3
Neuron i
wi1
wi2
wi3
Si
Activation
function
g(Si )
Output
Oi
Oi
threshold, t
Output
Layer
Training ANN means learning

the weights of the neurons
y
4/18/2004
64
Algorithm for learning ANN

O
Initialize the weights (w0, w1, , wk)
Adjust the weights in such a way that the output

of ANN is consistent with class labels of training
examples
2
Objective function: E = [Yi f ( wi , X i )]
i
Find the weights wis that minimize the above

objective function
e.g., backpropagation algorithm (see lecture notes)
4/18/2004
65
Support Vector Machines
Find a linear hyperplane (decision boundary) that will separate the data
4/18/2004
66

B1
One Possible Solution
4/18/2004
67
4/18/2004
68
B2
Another possible solution
B2
Other possible solutions
4/18/2004
69
4/18/2004
70

B1
B2
O
O
Which one is better? B1 or B2?

How do you define better?

B1
B2
b21
b22
margin
b11
b12
O
Find hyperplane maximizes the margin => B1 is better than B2
4/18/2004
71

B1
r r
w x + b = 0
r r
w x + b = +1
r r
w x + b = 1
b11
1
r
f (x) =
1
r r
if w x + b 1
r r
if w x + b 1
b12
Margin =
4/18/2004
2
r 2
|| w ||
72

O
2
We want to maximize: Margin = r 2
|| w ||
r
|| w ||2
Which is equivalent to minimizing: L( w) =
2
But subjected to the following constraints:

r r
if w x i + b 1
1
r
f ( xi ) =
r r
1 if w x i + b 1
This is a constrained optimization problem

Numerical approaches to solve it (e.g., quadratic programming)
4/18/2004
73

O
What if the problem is not linearly separable?
4/18/2004
74

O
What if the problem is not linearly separable?

Introduce slack variables
r
Need to minimize:
|| w ||2
N k
+ C i
L( w ) =
2
i =1
Subject to:
1
r
f ( xi ) =
1
r r
if w x i + b 1 - i
r r
if w x i + b 1 + i
4/18/2004
75
Nonlinear Support Vector Machines

O
What if decision boundary is not linear?
4/18/2004
76
Nonlinear Support Vector Machines

O
Transform data into higher dimensional space
4/18/2004
77
Ensemble Methods
O
Construct a set of classifiers from the training

data
Predict class label of previously unseen records

by aggregating predictions made by multiple
classifiers
4/18/2004
78
General Idea
D
Step 1:
Create Multiple
Data Sets
Step 2:
Build Multiple
Classifiers
D1
D2
C1
C2
Step 3:
Combine
Classifiers
....
Original
Training data
Dt-1
Dt
Ct -1
Ct
C*
4/18/2004
79
Why does it work?

O
Suppose there are 25 base classifiers

Each classifier has error rate, = 0.35
Assume classifiers are independent
Probability that the ensemble classifier makes
a wrong prediction:
25 i
(1 ) 25i = 0.06
i =13
25
4/18/2004
80
Examples of Ensemble Methods

O
How to generate an ensemble of classifiers?

Bagging
Boosting
4/18/2004
81
Bagging
O
Sampling with replacement

Original Data
Bagging (Round 1)
Bagging (Round 2)
Bagging (Round 3)
1
7
1
1
2
8
4
8
3
10
9
5
4
8
1
10
5
2
2
5
6
5
3
5
7
10
2
9
8
10
7
6
9
5
3
3
10
9
2
7
Build classifier on each bootstrap sample
Each sample has probability (1 1/n)n of being

selected
4/18/2004
82
Boosting
O
An iterative procedure to adaptively change

distribution of training data by focusing more on
previously misclassified records
Initially, all N records are assigned equal
weights
Unlike bagging, weights may change at the
end of boosting round
4/18/2004
83
Boosting
Records that are wrongly classified will have their
weights increased
O Records that are classified correctly will have
their weights decreased
O
Original Data
Boosting (Round 1)
Boosting (Round 2)
Boosting (Round 3)
1
7
5
4
2
3
4
4
3
2
9
8
4
8
4
10
5
7
2
4
6
9
5
5
7
4
1
4
8
10
7
6
9
6
4
3
10
3
2
4
Example 4 is hard to classify

Its weight is increased, therefore it is more
likely to be chosen again in subsequent rounds
4/18/2004
84
Example: AdaBoost
O
Base classifiers: C1, C2, , CT
Error rate:
1
i =
N
O
w (C ( x ) y )
N
j =1
Importance of a classifier:
1 1 i
i = ln
2 i
4/18/2004
85
Example: AdaBoost
O
Weight update:
exp j if C j ( xi ) = yi
wi
exp j if C j ( xi ) yi
where Z j is the normalization factor
( j +1)
wi( j )
=
Zj
If any intermediate rounds produce error rate

higher than 50%, the weights are reverted back
to 1/n and the resampling procedure is repeated
O Classification:
T
O
C * ( x ) = arg max j (C j ( x ) = y )
y
j =1
4/18/2004
86
Illustrating AdaBoost
Initial weights for each data point
0.1
Original
Data
0.1
0.1
0.0094
0.4623
Data points
for training
- - - - - ++
+++
B1
Boosting
Round 1
0.0094
- - - - - - -
+++
= 1.9459
4/18/2004
87
Illustrating AdaBoost
B1
Boosting
Round 1
0.0094
0.0094
+++
0.4623
- - - - - - -
= 1.9459
B2
Boosting
Round 2
0.0009
0.3037
- - -
0.0422
- - - - - ++
= 2.9323
B3
0.0276
0.1819
0.0038
Boosting
Round 3
+++
++ ++ + ++
Overall
+++
- - - - - ++
= 3.8744
4/18/2004
88

Data Mining Classification: Alternative Techniques: Lecture Notes For Chapter 5 Introduction To Data Mining

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Data Mining Classification: Alternative Techniques: Lecture Notes For Chapter 5 Introduction To Data Mining

Uploaded by

Copyright:

Available Formats

Data Mining

Classification: Alternative Techniques

Lecture Notes for Chapter 5

Introduction to Data Mining

Classify records by using a collection of

Condition is a conjunctions of attributes

y is the class label

LHS: rule antecedent or condition

(Blood Type=Warm) (Lay Eggs=Yes) Birds

(Taxable Income < 50K) (Refund=Yes) Evade=No

Introduction to Data Mining

Rule-based Classifier (Example)

R1: (Give Birth = no) (Can Fly = yes) Birds

Introduction to Data Mining

Application of Rule-Based Classifier

A rule r covers an instance x if the attributes of

The rule R1 covers a hawk => Bird

Introduction to Data Mining

Rule Coverage and Accuracy

Coverage = 40%, Accuracy = 50%

Introduction to Data Mining

How does Rule-based Classifier Work?

A lemur triggers rule R3, so it is classified as a mammal

Introduction to Data Mining

Characteristics of Rule-Based Classifier

Mutually exclusive rules

Introduction to Data Mining

From Decision Trees To Rules

(Refund=No, Marital Status={Single,Divorced},

(Refund=No, Marital Status={Single,Divorced},

Rules are mutually exclusive and exhaustive

Introduction to Data Mining

Rules Can Be Simplified

Tid Refund Marital

Simplified Rule: (Status=Married) No

Introduction to Data Mining

Effect of Rule Simplification

Rules are no longer mutually exclusive

Rules are no longer exhaustive

Use a default class

Introduction to Data Mining

Ordered Rule Set

Rules are rank ordered according to their priority

When a test record is presented to the classifier

Introduction to Data Mining

Rule Ordering Schemes

(Refund=No, Marital Status={Single,Divorced},

(Refund=No, Marital Status={Single,Divorced},

(Refund=No, Marital Status={Single,Divorced},

(Refund=No, Marital Status={Married}) ==> No

(Refund=No, Marital Status={Married}) ==> No

(Refund=No, Marital Status={Single,Divorced},

Introduction to Data Mining

Building Classification Rules

Introduction to Data Mining

Direct Method: Sequential Covering

Start from an empty rule

Introduction to Data Mining

Example of Sequential Covering

(i) Original Data

Introduction to Data Mining

Example of Sequential Covering

Introduction to Data Mining