DATA MINING

LECTURE 10B
Classification
k-nearest neighbor classifier
Naïve Bayes
Logistic Regression
Support Vector Machines
NEAREST NEIGHBOR
CLASSIFICATION
Illustrating Classification Task
Tid Attrib1 Attrib2 Attrib3 Class
Learning
1 Yes Large 125K No
algorithm
2 No Medium 100K No
3 No Small 70K No
4 Yes Medium 120K No
Induction
5 No Large 95K Yes

6 No Medium 60K No

7 Yes Large 220K No Learn

8 No Small 85K Yes Model
9 No Medium 75K No

10 No Small 90K Yes

Model
10

Training Set
Apply
Tid Attrib1 Attrib2 Attrib3 Class Model
11 No Small 55K ?

12 Yes Medium 80K ?

13 Yes Large 110K ? Deduction

14 No Small 95K ?

15 No Large 67K ?
10

Test Set
Instance-Based Classifiers
Set of Stored Cases • Store the training records

……...
• Use training records to
Atr1 AtrN Class predict the class label of
A unseen cases
B
B
Unseen Case
C
A Atr1 ……... AtrN

C
B
Instance Based Classifiers
• Examples:
• Rote-learner
• Memorizes entire training data and performs classification only
if attributes of record match one of the training examples exactly

• Nearest neighbor classifier

• Uses k “closest” points (nearest neighbors) for performing
classification
 Nearest Neighbor Classifiers
• Basic idea:
• “If it walks like a duck, quacks like a duck, then it’s
probably a duck”

Compute
Distance Test
Record

Training Choose k of the

Records “nearest” records
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:

1. Compute distance to other
training records
2. Identify k nearest neighbors
3. Use class labels of nearest
neighbors to determine the
class label of unknown
record (e.g., by taking
majority vote)
Definition of Nearest Neighbor

X X X

(a) 1-nearest neighbor (b) 2-nearest neighbor (c) 3-nearest neighbor

K-nearest neighbors of a record x are data points

that have the k smallest distance to x
 1 nearest-neighbor
Voronoi Diagram defines the classification boundary

The area takes the

class of the green
point
Nearest Neighbor Classification
• Compute distance between two points:
• Euclidean distance

d ( p, q )   ( pi
i
q )
i
2

• 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
Nearest Neighbor Classification…
• 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

X
Nearest Neighbor Classification…
• 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
Nearest Neighbor Classification…
• Problem with Euclidean measure:
• High dimensional data
• curse of dimensionality
• Can produce counter-intuitive results

111111111110 100000000000
vs
011111111111 000000000001
d = 1.4142 d = 1.4142

 Solution: Normalize the vectors to unit length

Nearest neighbor Classification…
• k-NN classifiers are lazy learners
• It does not build models explicitly
• Unlike eager learners such as decision trees
• Classifying unknown records are relatively
expensive
• Naïve algorithm: O(n)
• Need for structures to retrieve nearest neighbors fast.
• The Nearest Neighbor Search problem.
Nearest Neighbor Search
• Two-dimensional kd-trees
• A data structure for answering nearest neighbor queries
in R2

• kd-tree construction algorithm

• Select the x or y dimension (alternating between the two)
• Partition the space into two with a line passing from the
median point
• Repeat recursively in the two partitions as long as there
are enough points
Nearest Neighbor Search

2-dimensional kd-trees
Nearest Neighbor Search

2-dimensional kd-trees
Nearest Neighbor Search

2-dimensional kd-trees
Nearest Neighbor Search

2-dimensional kd-trees
Nearest Neighbor Search

2-dimensional kd-trees
Nearest Neighbor Search
2-dimensional kd-trees
Nearest Neighbor Search
2-dimensional kd-trees
region(u) – all the black points in the subtree of u
Nearest Neighbor Search
2-dimensional kd-trees

 A binary tree:
 Size O(n)
 Depth O(logn)
 Construction time O(nlogn)
 Query time: worst case O(n), but for many cases O(logn)

Generalizes to d dimensions

 Example of Binary Space Partitioning

SUPPORT VECTOR
MACHINES
Support Vector Machines

• Find a linear hyperplane (decision boundary) that will separate the data
Support Vector Machines
B1

• One Possible Solution

Support Vector Machines

B2

• Another possible solution

Support Vector Machines

B2

• Other possible solutions

Support Vector Machines
B1

B2

• Which one is better? B1 or B2?

• How do you define better?
Support Vector Machines
B1

B2

b21
b22

margin
b11

b12

• Find hyperplane maximizes the margin => B1 is better than B2

 Support Vector Machines
B1

 
w x b  0
 
  w  x  b  1
w  x  b  1

b11

  b12
 1 if w  x  b  1 2
f ( x)     Margin  
  1 if w  x  b  1 || w ||
Support Vector Machines
2
• We want to maximize: Margin   2
|| w ||
 2
• Which is equivalent to minimizing: L( w) 
|| w ||
2
• But subjected to the following constraints:

  if
if

• This is a constrained optimization problem

• Numerical approaches to solve it (e.g., quadratic programming)
Support Vector Machines
• What if the problem is not linearly separable?
Support Vector Machines
• What if the problem is not linearly separable?

  𝜉𝑖
‖𝑤‖
Support Vector Machines
• What if the problem is not linearly separable?
• Introduce slack variables
• Need to minimize:
 2
|| w ||  N k
L( w)   C   i 
2  i 1 
• Subject to:
 
if
if
Nonlinear Support Vector Machines
• What if decision boundary is not linear?
Nonlinear Support Vector Machines
• Transform data into higher dimensional space

Use the Kernel Trick

LOGISTIC REGRESSION
Classification via regression
• Instead of predicting the class of an record we
want to predict the probability of the class given
the record
• The problem of predicting continuous values is
called regression problem
• General approach: find a continuous function that
models the continuous points.
Example: Linear regression
•  Given a dataset of the
form find a linear
function that given the
vector predicts the
value as
• Find a vector of weights
that minimizes the sum of
square errors

• Several techniques for

solving the problem.
Classification via regression
• Assume a linear classification boundary   ⋅ 𝑥 >0
𝑤
  the positive class the bigger
For
the value of , the further the point
is from the classification boundary,
the higher our certainty for the
membership to the positive class   ⋅ 𝑥 =0
𝑤
• Define as an increasing
function of

 
For the negative class the smaller
the value of , the further the point
is from the classification boundary,
the higher our certainty for the
membership to the negative class
• Define as a decreasing function
of
  ⋅ 𝑥 <0
𝑤
 Logistic Regression
The logistic function
  1
𝑓 ( 𝑡 )= −𝑡
1 +𝑒
  1
𝑃 ( 𝐶 +¿ ¿ 𝑥 )= −𝑤 ⋅ 𝑥
1+𝑒
  𝑒− 𝑤 ⋅ 𝑥
𝑃 ( 𝐶 −|𝑥 )= −𝑤 ⋅ 𝑥
1+𝑒
  𝑃 ( 𝐶 +¿ ¿ 𝑥 )
log =𝑤 ⋅ 𝑥
𝑃 ( 𝐶 −|𝑥 )  LogisticRegression: Find the
vectorthat maximizes the
Linear regression on the log-odds ratio
probability of the observed data
Logistic Regression
• Produces a probability estimate for the class
membership which is often very useful.
• The weights can be useful for understanding the
feature importance.
• Works for relatively large datasets
• Fast to apply.
NAÏVE BAYES CLASSIFIER
Bayes Classifier
• A probabilistic framework for solving classification
problems
• A, C random variables
• Joint probability: Pr(A=a,C=c)
• Conditional probability: Pr(C=c | A=a)
• Relationship between joint and conditional
probability distributions
Pr(C , A)  Pr(C | A)  Pr( A)  Pr( A | C )  Pr(C )

P ( A | C ) P (C )
• Bayes Theorem: P (C | A) 
P ( A)
 Bayesian Classifiers
• Consider each
a l attribute
a l
u s and class label as random
c c i i o
variables or o r u
te
g e g tin s s
ca c at c on cl
a
Evade C
Tid Refund Marital Taxable Event space: {Yes, No}
Status Income Evade
P(C) = (0.3, 0.7)
1 Yes Single 125K No
Refund A1
2 No Married 100K No
Event space: {Yes, No}
3 No Single 70K No P(A1) = (0.3,0.7)
4 Yes Married 120K No
5 No Divorced 95K Yes Martial Status A2
No
Event space: {Single, Married, Divorced}
6 No Married 60K
P(A2) = (0.4,0.4,0.2)
7 Yes Divorced 220K No
8 No Single 85K Yes
Taxable Income A3
9 No Married 75K No Event space: R
10 No Single 90K Yes P(A3) ~ Normal(,)
10
Bayesian Classifiers
• Given a record X over attributes (A1, A2,…,An)
• E.g., X = (‘Yes’, ‘Single’, 125K)

• The goal is to predict class C

• Specifically, we want to find the value c of C that maximizes
P(C=c| X)
• Maximum Aposteriori Probability estimate

• Can we estimate P(C| X) directly from data?

• This means that we estimate the probability for all possible
values of the class variable.
Bayesian Classifiers
• Approach:
• compute the posterior probability P(C | A1, A2, …, An) for all
values of C using the Bayes theorem
P ( A A  A | C ) P (C )
P (C | A A  A )  1 2 n

P( A A  A )
1 2 n

1 2 n

• 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)

• How to estimate P(A1, A2, …, An | C )?

Naïve Bayes Classifier
•  Assume independence among attributes Ai when class is
given:

• We can estimate P(Ai| C) for all values of Ai and C.

• New point X is classified to class c if

is maximum over all possible values of C.

 How to Estimate
l l
Probabilities from Data?
a a u s
r ic r ic o
o o u
eg eg it n s s
at at n
cl
a • Class
  Prior Probability:
c c co
Tid Refund Marital Taxable
Status Income Evade
e.g., P(C = No) = 7/10,
1 Yes Single 125K No
P(C = Yes) = 3/10
2 No Married 100K No
3 No Single 70K No
• For discrete attributes:
4 Yes Married 120K No
5 No Divorced 95K Yes
6 No Married 60K No where is number of instances
7 Yes Divorced 220K No having attribute and belongs to
8 No Single 85K Yes class
9 No Married 75K No • Examples:
10 No Single 90K Yes
10
P(Status=Married|No) = 4/7
P(Refund=Yes|Yes)=0
How to Estimate Probabilities from Data?

• 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
(i.e., mean  and standard deviation )
• Once probability distribution is known, we can use it to estimate
the conditional probability P(Ai|c)
 l l s
How togoEstimate
go it n
uProbabilities from Data?
s
ric
a
ric
a
o u

t e t e
on las
ca ca c c
Tid Refund Marital Taxable
Evade
• Normal distribution:
Status Income
( a   ij ) 2

1 Yes Single 125K No 1 2 ij2
P ( Ai  a | c j )  e
2 No Married 100K No 2 ij2
3 No Single 70K No
4 Yes Married 120K No
5 No Divorced 95K Yes • One for each (ai,ci) pair
6 No Married 60K No
7 Yes Divorced 220K No
• For (Income, Class=No):
8 No Single 85K Yes
• If Class=No
9 No Married 75K No
10 No Single 90K Yes
• sample mean = 110
• sample variance = 2975
10

1 
( 120110 ) 2

P( Income  120 | No)  e 2 ( 2975)

 0.0072
2 (54.54)
Example of Naïve Bayes Classifier
• Creating a Naïve Bayes Classifier, essentially
means to compute counts:
Total number of records: N = 10

Class No: Class Yes:

Number of records: 7 Number of records: 3
Attribute Refund: Attribute Refund:
Yes: 3 Yes: 0
No: 4 No: 3
Attribute Marital Status: Attribute Marital Status:
Single: 2 Single: 2
Divorced: 1 Divorced: 1
Married: 4 Married: 0
Attribute Income: Attribute Income:
mean: 110 mean: 90
variance: 2975 variance: 25
 Example of Naïve Bayes Classifier
Given a Test Record:
X  ( Refund  No, Married, Income  120K)
naive Bayes Classifier:
P(Refund=Yes|No) = 3/7  P(X|Class=No) = P(Refund=No|Class=No)
P(Refund=No|No) = 4/7  P(Married| Class=No)
P(Refund=Yes|Yes) = 0  P(Income=120K| Class=No)
P(Refund=No|Yes) = 1
= 4/7  4/7  0.0072 = 0.0024
P(Marital Status=Single|No) = 2/7
P(Marital Status=Divorced|No)=1/7  P(X|Class=Yes) = P(Refund=No| Class=Yes)
P(Marital Status=Married|No) = 4/7  P(Married| Class=Yes)
P(Marital Status=Single|Yes) = 2/7  P(Income=120K| Class=Yes)
P(Marital Status=Divorced|Yes)=1/7 = 1  0  1.2  10-9 = 0
P(Marital Status=Married|Yes) = 0

For taxable income: P(No) = 0.3, P(Yes) = 0.7

If class=No: sample mean=110
Since P(X|No)P(No) > P(X|Yes)P(Yes)
sample variance=2975
If class=Yes: sample mean=90 Therefore P(No|X) > P(Yes|X)
sample variance=25
=> Class = No
Naïve Bayes Classifier
• If one of the conditional probability is zero, then
the entire expression becomes zero
• Probability estimation:
N ac
Original : P( Ai  a | C  c) 
Nc Ni: number of attribute
values for attribute Ai
N ac  1
Laplace : P( Ai  a | C  c )  p: prior probability
Nc  Ni
m: parameter
N ac  mp
m - estimate : P( Ai  a | C  c) 
Nc  m
 Example of Naïve Bayes Classifier
Given a Test Record: With Laplace Smoothing
X  ( Refund  No, Married, Income  120K)
naive Bayes Classifier:
P(Refund=Yes|No) = 4/9  P(X|Class=No) = P(Refund=No|Class=No)
P(Refund=No|No) = 5/9  P(Married| Class=No)
P(Refund=Yes|Yes) = 1/5  P(Income=120K| Class=No)
P(Refund=No|Yes) = 4/5
= 5/9  5/10  0.0072
P(Marital Status=Single|No) = 3/10
P(Marital Status=Divorced|No)=2/10  P(X|Class=Yes) = P(Refund=No| Class=Yes)
P(Marital Status=Married|No) = 5/10  P(Married| Class=Yes)
P(Marital Status=Single|Yes) = 3/6  P(Income=120K| Class=Yes)
P(Marital Status=Divorced|Yes)=2/6 = 4/5  1/6  1.2  10-9
P(Marital Status=Married|Yes) = 1/6

For taxable income: P(No) = 0.7, P(Yes) = 0.3

If class=No: sample mean=110
Since P(X|No)P(No) > P(X|Yes)P(Yes)
sample variance=2975
If class=Yes: sample mean=90 Therefore P(No|X) > P(Yes|X)
sample variance=25
=> Class = No
Implementation details
•  Computing the conditional probabilities involves
multiplication of many very small numbers
• Numbers get very close to zero, and there is a danger
of numeric instability
• We can deal with this by computing the logarithm
of the conditional probability
Naïve Bayes for Text Classification
•  Naïve Bayes is commonly used for text
classification
• For a document

• = Fraction of terms from all documents in c that

are.

• Easy to implement and works relatively well

• Limitation: Hard to incorporate additional features
(beyond words).
Naïve Bayes (Summary)
• 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)

• Naïve Bayes can produce a probability estimate, but it is

usually a very biased one
• Logistic Regression is better for obtaining probabilities.
Generative vs Discriminative models
• Naïve Bayes is a type of a generative model
• Generative process:
• First pick the category of the record
• Then given the category, generate the attribute values from the
distribution of the category

C
• Conditional independence given C

𝐴  1 𝐴  2 𝐴  𝑛
• We use the training data to learn the distribution of
the values in a class
Generative vs Discriminative models
• Logistic Regression and SVM are discriminative
models
• The goal is to find the boundary that discriminates
between the two classes from the training data

• In order to classify the language of a document,

you can
• Either learn the two languages and find which is more
likely to have generated the words you see
• Or learn what differentiates the two languages.