Data Mining:

Concepts and Techniques

— Chapter 6 —

Jianlin Cheng
Department of Computer Science
University of Missouri
Slides Adapted from
©2006 Jiawei Han and Micheline Kamber, All rights reserved

November 22, 2019 Data Mining: Concepts and Techniques 1

 Chapter 6. Classification and Prediction

 What is classification and  Support Vector Machines (SVM)

regression (prediction)?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction and random forest  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 2
 Prediction: Classification vs.
Regression
 Classification
 predicts categorical class labels (discrete or nominal)

 classifies data (constructs a model) based on the

training set and the values (class labels) in a
classifying attribute and uses it in classifying new data
 Regression
 models continuous-valued functions, i.e., predicts
unknown or missing values
 Typical applications
 Credit approval

 Target marketing

 Medical diagnosis

 Fraud detection

November 22, 2019 Data Mining: Concepts and Techniques 3

 Classification—A Two-Step Process
 Model construction: describing a set of predetermined classes
 Each tuple/sample is assumed to belong to a predefined class,
as determined by the class label attribute
 The set of tuples used for model construction is training set

 The model is represented as classification rules, decision trees,

or mathematical formulae
 Model usage: for classifying future or unknown objects
 Estimate accuracy of the model

 The known label of test sample is compared with the

classified result from the model

 Accuracy rate is the percentage of test set samples that are

correctly classified by the model

 Test set is independent of training set, otherwise over-fitting

will occur
 If the accuracy is acceptable, use the model to classify data
tuples whose class labels are not known
November 22, 2019 Data Mining: Concepts and Techniques 4
 Process (1): Model Construction

Classification
Algorithms
Training
Data

NAME RANK YEARS TENURED Classifier

Mike Assistant Prof 3 no (Model)
Mary Assistant Prof 5 yes
Bill Professor 2 yes
Jim Associate Prof 6 yes
IF rank = ‘professor’
Dave Assistant Prof 4 no
OR years >= 5
Anne Associate Prof 3 no
THEN tenured = ‘yes’
November 22, 2019 Data Mining: Concepts and Techniques 5
Process (2): Using the Model in Prediction

Classifier

Testing
Data Unseen Data

(Jeff, Professor, 4)
NAME RANK YEARS TENURED
T om A ssistant P rof 2 no Tenured?
M erlisa A ssociate P rof 7 no
G eorge P rofessor 5 yes
Joseph A ssistant P rof 7 yes
November 22, 2019 Data Mining: Concepts and Techniques 6
 Supervised vs. Unsupervised Learning

 Supervised learning (classification)

 Supervision: The training data (observations,
measurements, etc.) are accompanied by labels
indicating the class of the observations
 New data is classified based on the model built on
training set
 Unsupervised learning (clustering)
 The class labels of training data is unknown
 Given a set of measurements, observations, etc. with
the aim of establishing the existence of classes or
clusters in the data
November 22, 2019 Data Mining: Concepts and Techniques 7
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 8
 Issues: Data Preparation

 Data cleaning
 Preprocess data in order to reduce noise and handle
missing values
 Relevance analysis (feature selection)
 Remove the irrelevant or redundant attributes
 Data transformation
 Generalize and/or normalize data

November 22, 2019 Data Mining: Concepts and Techniques 9

Issues: Evaluating Classification Methods

 Accuracy
 classifier accuracy: predicting class label

 regression accuracy: guessing value of predicted

attributes
 Speed
 time to construct the model (training time)

 time to use the model (classification/prediction time)

 Robustness: handling noise and missing values

 Scalability: efficiency on large databases
 Interpretability
 understanding and insight provided by the model

 Other measures, e.g., goodness of rules, such as decision

tree size or compactness of classification rules
November 22, 2019 Data Mining: Concepts and Techniques 10
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 11
Decision Tree Induction: Training Dataset

age income student credit_rating buys_computer

<=30 high no fair no
<=30 high no excellent no
31…40 high no fair yes
>40 medium no fair yes
>40 low yes fair yes
>40 low yes excellent no
31…40 low yes excellent yes
<=30 medium no fair no
<=30 low yes fair yes
>40 medium yes fair yes
<=30 medium yes excellent yes
31…40 medium no excellent yes
31…40 high yes fair yes
>40 medium no excellent no

November 22, 2019 Data Mining: Concepts and Techniques 12

 Output: A Decision Tree for “buys_computer”

age?

<=30 overcast
31..40 >40

student? yes credit rating?

no yes excellent fair

no yes yes

November 22, 2019 Data Mining: Concepts and Techniques 13

Algorithm for Decision Tree Induction
 Basic algorithm (a greedy algorithm)
 Tree is constructed in a top-down recursive divide-and-conquer

manner
 At start, all the training examples are at the root

 Attributes are categorical (if continuous-valued, they are

discretized in advance)
 Examples are partitioned recursively based on selected attributes

 Test attributes are selected on the basis of a heuristic or

statistical measure (e.g., information gain)

 Conditions for stopping partitioning
 All (or most) samples for a given node belong to the same class

 There are no remaining attributes for further partitioning –

majority voting is employed for classifying the leaf

November 22, 2019 Data Mining: Concepts and Techniques 14

 Attribute Selection Measure:
Information Gain (ID3/C4.5)
 Select the attribute with the highest information gain
 Let pi be the probability that an arbitrary tuple in D
belongs to class Ci, estimated by |Ci, D|/|D|
Initial entropy: m
Entropy( D)   pi log 2 ( pi )


i 1

 New entropy (after using A to split D into v partitions) to

classify D: v
| Dj |
EntropyA (D) = å ´ E(D j )
j=1 |D|

 Information gained by branching on attribute A

Gain(A)  Entropy(D)  EntropyA(D)

November 22, 2019 Data Mining: Concepts and Techniques 15
 Attribute Selection: Information Gain

 Class P: buys_computer = Entropyage ( D ) 

5
E (2,3) 
4
E (4,0)
“yes” 14 14
 Class N: buys_computer = “no” 5
9 9 5 5  E (3,2)  0.694
Entropy( D)  E (9,5)   log 2 ( )  log 2 ( ) 0.940 14
14 14 14 14
5
age pi ni I(pi, ni) E (2,3) means “age <=30” has 5
14
<=30 2 3 0.971 out of 14 samples, with 2
31…40 4 0 0 yes’es and 3 no’s. Hence
>40 3 2 0.971 Gain(age)  Entropy( D)  Entropyage ( D)  0.246
age income student credit_rating buys_computer
<=30 high no fair no
<=30 high no excellent no
31…40 high
>40 medium
no
no
fair
fair
yes
yes
Similarly,
>40 low yes fair yes
>40 low
31…40 low
yes
yes
excellent
excellent
no
yes Gain(income)  0.029
Gain( student )  0.151
<=30 medium no fair no
<=30 low yes fair yes
>40 medium yes fair yes
<=30 medium
31…40 medium
yes
no
excellent
excellent
yes
yes
Gain(credit _ rating )  0.048
31…40 high yes fair yes
>40November 22, 2019 no
medium excellent Data no
Mining: Concepts and Techniques 16
 Decision Boundary ?

Class B

Class A
X
Class C

Y
November 22, 2019 Data Mining: Concepts and Techniques 17
 Decision Boundary ?

Class B

Class A
X
Class C

Y
November 22, 2019 Data Mining: Concepts and Techniques 18
 Decision Boundary ?

Class B

Class A
X
Class C

Y
November 22, 2019 Data Mining: Concepts and Techniques 19
 Computing Information-Gain for
Continuous-Value Attributes
 Let attribute A be a continuous-valued attribute
 Must determine the best split point for A
 Sort the value A in increasing order
 Typically, the midpoint between each pair of adjacent
values is considered as a possible split point
 (ai+ai+1)/2 is the midpoint between the values of ai and ai+1
 The point yielding maximum information gain for A is
selected as the split-point for A
 Split:
 D1 is the set of tuples in D satisfying A ≤ split-point, and
D2 is the set of tuples in D satisfying A > split-point
November 22, 2019 Data Mining: Concepts and Techniques 20
 Gain Ratio for Attribute Selection (C4.5)

 Information gain measure is biased towards attributes

with a large number of values
 C4.5 (a successor of ID3) uses gain ratio to overcome the
problem (normalization to information gain)
v | Dj | | Dj |
SplitEntropy A ( D)    log 2 ( )
j 1 |D| |D|

 GainRatio(A) = Gain(A)/SplitEntropy(A)
4 4 6 6 4 4
 Ex. SplitEntropy A ( D)  
14
 log 2 ( )   log 2 ( )   log 2 ( )  0.926
14 14 14 14 14
 gain_ratio(income) = 0.029/0.926 = 0.031
 The attribute with the maximum gain ratio is selected as
the splitting attribute
November 22, 2019 Data Mining: Concepts and Techniques 21
Gini index (CART, IBM IntelligentMiner)
 If a data set D contains examples from n classes, gini index, gini(D) is
defined as n
gini( D) 1  p 2j
j 1
where pj is the relative frequency (proportion) of class j in D
 If a data set D is split on A into two subsets D1 and D2, the gini index
gini(D) is defined as
|D1| |D |
gini A (D)  gini(D1)  2 gini(D2)
|D| |D|
 Reduction in Impurity:
gini( A)  gini(D)  giniA(D)
 The attribute provides the largest reduction in impurity is chosen to
split the node (need to enumerate all the possible splitting points for
each attribute)
November 22, 2019 Data Mining: Concepts and Techniques 22
Gini index (CART, IBM IntelligentMiner)
 Ex. D has 9 tuples in buys_computer = “yes” and 5 in “no”
2 2
9 5
gini ( D)  1        0.459
 14   14 
 Suppose the attribute income partitions D into 10 in D1: {low,
medium} and 4 in D2  10  4
giniincome{low,medium} ( D)   Gini ( D1 )   Gini ( D1 )
 14   14 

but gini{medium,high} is 0.30 and thus the best since it is the lowest

November 22, 2019 Data Mining: Concepts and Techniques 23

 Weka Demo of A Decision Tree
http://www.cs.waikato.ac.nz/ml/weka/
Breast Cancer Data
Attribute Information:
1. Class: no-recurrence-events, recurrence-events
2. age: 10-19, 20-29, 30-39, 40-49, 50-59, 60-69, 70-79, 80-89, 90-99.
3. menopause: lt40, ge40, premeno.
4. tumor-size: 0-4, 5-9, 10-14, 15-19, 20-24, 25-29, 30-34, 35-39, 40-44,
45-49, 50-54, 55-59.
5. inv-nodes: 0-2, 3-5, 6-8, 9-11, 12-14, 15-17, 18-20, 21-23, 24-26,
27-29, 30-32, 33-35, 36-39.
6. node-caps: yes, no.
7. deg-malig: 1, 2, 3.
8. breast: left, right.
9. breast-quad: left-up, left-low, right-up, right-low, central.
10. irradiat: yes, no.
Class Distribution:
1. no-recurrence-events: 201 instances
2. recurrence-events: 85 instances
November 22, 2019 Data Mining: Concepts and Techniques 24
Comparing Attribute Selection Measures

 The three measures, in general, return good results but

 Information gain:
 biased towards multivalued attributes
 Gain ratio:
 tends to prefer unbalanced splits in which one
partition is much smaller than the others
 Gini index:
 biased to multivalued attributes
 has difficulty when # of classes is large
 tends to favor tests that result in equal-sized
partitions and purity in both partitions
November 22, 2019 Data Mining: Concepts and Techniques 25
 Overfitting and Tree Pruning

 Overfitting: An induced tree may overfit the training data

 Too many branches, some may reflect anomalies due to noise or
outliers
 Poor accuracy for unseen samples
 Two approaches to avoid overfitting
 Prepruning: Halt tree construction early—do not split a node if this
would result in the goodness measure falling below a threshold
 Difficult to choose an appropriate threshold
 Postpruning: Remove branches from a “fully grown” tree—get a
sequence of progressively pruned trees
 Use a set of data different from the training data to decide
which is the “best pruned tree”
November 22, 2019 Data Mining: Concepts and Techniques 26
Enhancements to Basic Decision Tree Induction

 Allow for continuous-valued attributes

 Dynamically define new discrete-valued attributes that
partition the continuous attribute value into a discrete
set of intervals
 Handle missing attribute values
 Assign the most common value of the attribute
 Assign probability to each of the possible values

November 22, 2019 Data Mining: Concepts and Techniques 27

 Classification in Large Databases

 Classification—a classical problem extensively studied by

statisticians and machine learning researchers
 Scalability: Classifying data sets with millions of examples
and hundreds of attributes with reasonable speed
 Why decision tree induction in data mining?
 relatively faster learning speed (than other classification
methods)
 convertible to simple and easy to understand
classification rules
 can use SQL queries for accessing databases
 comparable classification accuracy with other methods

November 22, 2019 Data Mining: Concepts and Techniques 28

 Scalable Decision Tree Induction Methods

 PUBLIC (VLDB’98 — Rastogi & Shim)

 Integrates tree splitting and tree pruning: stop growing

the tree earlier

 RainForest (VLDB’98 — Gehrke, Ramakrishnan & Ganti)
 Builds an AVC-list (attribute, value, class label)

 BOAT (PODS’99 — Gehrke, Ganti, Ramakrishnan & Loh)

 Uses bootstrapping to create several small samples

Random Forest – creates a large number of

trees with a random selection of features

November 22, 2019 Data Mining: Concepts and Techniques 29

 Scalability Framework for RainForest

 Builds an AVC-list: AVC (Attribute, Value, Class_label)

 AVC-set (of an attribute X )
 Projection of training dataset onto the attribute X and
class label where counts of individual class label are
aggregated

November 22, 2019 Data Mining: Concepts and Techniques 30

 Rainforest: Training Set and Its AVC Sets

Training Examples AVC-set on Age AVC-set on income

age income studentcredit_rating
buys_computerAge Buy_Computer income Buy_Computer

<=30 high no fair no yes no

<=30 high no excellent no yes no
high 2 2
31…40 high no fair yes <=30 3 2
31..40 4 0 medium 4 2
>40 medium no fair yes
>40 low yes fair yes >40 3 2 low 3 1
>40 low yes excellent no
31…40 low yes excellent yes
AVC-set on
<=30 medium no fair no AVC-set on Student
credit_rating
<=30 low yes fair yes
student Buy_Computer
>40 medium yes fair yes Credit
Buy_Computer

<=30 medium yes excellent yes yes no rating yes no

31…40 medium no excellent yes yes 6 1 fair 6 2
31…40 high yes fair yes no 3 4 excellent 3 3
>40 medium no excellent no
November 22, 2019 Data Mining: Concepts and Techniques 31
 BOAT (Bootstrapped Optimistic Algorithm
for Tree Construction)

 Use a statistical technique called bootstrapping to create

several smaller samples (subsets), each fits in memory
 Each subset is used to create a tree, resulting in several
trees
 These trees are examined and used to construct a new
tree T’
 It turns out that T’ is very close to the tree that would
be generated using the whole data set together
 Adv: requires fewer scans of DB, an incremental alg.

November 22, 2019 Data Mining: Concepts and Techniques 32

 Visualization of a Decision Tree in SGI/MineSet 3.0

November 22, 2019 Data Mining: Concepts and Techniques 33

 Random Forest
 Randomly select a sub set of features
 Create a fully grown decision tree on the n data
points, with the sub feature set, sampled with
replacement.
 Repeat the two steps to create a large number of
trees forming a random forest.
 Apply each tree in the forest on test data and use
majority vote of all trees as final prediction.
 The random forest may work better than a tree
constructed from all features.
 Why does it work better? Reduce variance, bias, no
feature selection, two parameters (#feature, #tree)
November 22, 2019 Data Mining: Concepts and Techniques 34
 Advantages and Disadvantages
 It is one of the most accurate learning algorithms available.
 It runs efficiently on large databases.
 It can handle thousands of input variables without variable deletion.
 It gives estimates of what variables are important in the classification.
 It generates an internal unbiased estimate of the generalization error
as the forest building progresses.
 It has an effective method for estimating missing data and maintains
accuracy when a large proportion of the data are missing.
 It computes proximities between pairs of cases that can be used in
clustering, locating outliers, or (by scaling) give interesting views of
the data.
 The capabilities of the above can be extended to unlabeled data,
leading to unsupervised clustering, data views and outlier detection.
 It offers an experimental method for detecting variable interactions.
 Disadvantages: overfitting

November 22, 2019 Data Mining: Concepts and Techniques

Wikipedia 35
 Mining Data with Random Forest

• Classification
• Clustering
• Regression
• Feature Selection
• Outlier detection
Review paper:
http://www.sciencedirect.com/science/article/pii/S003
1320310003973
November 22, 2019 Data Mining: Concepts and Techniques 36
 An Example

Two Gaussian point clouds Random Forest Logistic regression

Wikipedia

November 22, 2019 Data Mining: Concepts and Techniques 37

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 38
 Bayesian Classification: Why?
 A statistical classifier: performs probabilistic prediction,
i.e., predicts class membership probabilities
 Foundation: Based on Bayes’ Theorem.
 Performance: A simple Bayesian classifier, naïve Bayesian
classifier, has comparable performance with decision tree
and selected neural network classifiers
 Incremental: Each training example can incrementally
increase/decrease the probability that a hypothesis is
correct — prior knowledge can be combined with observed
data
 Standard: Even when Bayesian methods are
computationally intractable, they can provide a standard
of optimal decision making against which other methods
can be measured
November 22, 2019 Data Mining: Concepts and Techniques 39
 Bayesian Theorem: Basics
 Let X be a data sample (“evidence”), class label is
unknown
 Let H be a hypothesis that X belongs to class C
 Classification is to determine P(C|X), the probability that
the hypothesis holds given the observed data sample X
 P(C) (prior probability), the initial probability of C
 E.g., X will buy computer, regardless of age, income, …
 P(X): probability that sample data is observed
 P(X|C) (likelihood), the probability of observing the sample
X, given that the hypothesis H holds
 E.g., Given that X will buy computer, the prob. that X is
31..40, medium income
November 22, 2019 Data Mining: Concepts and Techniques 40
 Bayesian Theorem

 Given training data X, posteriori probability of a

hypothesis H, P(C|X), follows the Bayes theorem

P(C | X)  P(X | C)P(C)

P(X)
 Informally, this can be written as
posteriori = prior x likelihood / evidence
 Predicts X belongs to Ci iff the probability P(Ci|X) is the
highest among all the P(Ck|X) for all the k classes
 Practical difficulty: require initial knowledge of many
probabilities, significant computational cost
November 22, 2019 Data Mining: Concepts and Techniques 41
 Towards Naïve Bayesian Classifier
 Let D be a training set of tuples and their associated class
labels, and each tuple is represented by an n-D attribute
vector X = (x1, x2, …, xn)
 Suppose there are m classes C1, C2, …, Cm.
 Classification is to derive the maximum posteriori, i.e., the
maximal P(Ci|X)
 This can be derived from Bayes’ theorem (1<= i <= m)
P(X | C )P(C )
P(C | X)  i i
i P(X)
 Since P(X) is constant for all classes, only
P(X | C )P(C )
i i
needs to be maximized

November 22, 2019 Data Mining: Concepts and Techniques 42

Derivation of Naïve Bayes Classifier
 A simplified assumption: attributes are conditionally
independent (i.e., no dependence relation between
attributes): n
P( X | C i )   P( x | C i )  P( x | C i )  P( x | C i )  ...  P( x | C i )
k 1 2 n
k 1
 This greatly reduces the computation cost: Only counts
the class distribution
 If Ak is categorical, P(xk|Ci) is the # of tuples in Ci having
value xk for Ak divided by |Ci, D| (# of tuples of Ci in D)
 If Ak is continuous-valued, P(xk|Ci) is usually computed
based on Gaussian distribution with a mean μ and
standard deviation σ 
( x ) 2
1
g ( x,  ,  )  e 2 2

2 
and P(xk|Ci) is
P(Xk | Ci) = g(xk , mCi , s Ci )
November 22, 2019 Data Mining: Concepts and Techniques 43
Naïve Bayesian Classifier: Training Dataset
age income studentcredit_rating
buys_compu
<=30 high no fair no
<=30 high no excellent no
Class: 31…40 high no fair yes
C1:buys_computer = ‘yes’ >40 medium no fair yes
C2:buys_computer = ‘no’ >40 low yes fair yes
>40 low yes excellent no
Data sample
31…40 low yes excellent yes
X = (age <=30,
Income = medium, <=30 medium no fair no
Student = yes <=30 low yes fair yes
Credit_rating = Fair) >40 medium yes fair yes
<=30 medium yes excellent yes
31…40 medium no excellent yes
31…40 high yes fair yes
>40 medium no excellent no
November 22, 2019 Data Mining: Concepts and Techniques 44
Naïve Bayesian Classifier: An Example
 P(Ci): P(buys_computer = “yes”) = 9/14 = 0.643
P(buys_computer = “no”) = 5/14= 0.357

 Compute P(X|Ci) for each class

P(age = “<=30” | buys_computer = “yes”) = 2/9 = 0.222
P(age = “<= 30” | buys_computer = “no”) = 3/5 = 0.6
P(income = “medium” | buys_computer = “yes”) = 4/9 = 0.444
P(income = “medium” | buys_computer = “no”) = 2/5 = 0.4
P(student = “yes” | buys_computer = “yes) = 6/9 = 0.667
P(student = “yes” | buys_computer = “no”) = 1/5 = 0.2
P(credit_rating = “fair” | buys_computer = “yes”) = 6/9 = 0.667
P(credit_rating = “fair” | buys_computer = “no”) = 2/5 = 0.4

 X = (age <= 30 , income = medium, student = yes, credit_rating = fair)

P(X|Ci) : P(X|buys_computer = “yes”) = 0.222 x 0.444 x 0.667 x 0.667 = 0.044

P(X|buys_computer = “no”) = 0.6 x 0.4 x 0.2 x 0.4 = 0.019
P(X|Ci)*P(Ci) : P(X|buys_computer = “yes”) * P(buys_computer = “yes”) = 0.028
P(X|buys_computer = “no”) * P(buys_computer = “no”) = 0.007

Therefore, X belongs to class (“buys_computer = yes”)

November 22, 2019 Data Mining: Concepts and Techniques 45
 Avoiding the 0-Probability Problem
 Naïve Bayesian prediction requires each conditional prob. be non-
zero. Otherwise, the predicted prob. will be zero
n
P( X | C i )   P( x k | C i)
k 1

 Ex. Suppose a dataset with 1000 tuples, income=low (0), income=

medium (990), and income = high (10)

November 22, 2019 Data Mining: Concepts and Techniques 46

 Avoiding the 0-Probability Problem
 Naïve Bayesian prediction requires each conditional prob. be non-
zero. Otherwise, the predicted prob. will be zero
n
P( X | C i )   P( x k | C i)
k 1

 Ex. Suppose a dataset with 1000 tuples, income=low (0), income=

medium (990), and income = high (10),
 Use Laplacian correction (or Laplacian estimator)
 Adding 1 to each case

Prob(income = low) = 1/1003

Prob(income = medium) = 991/1003
Prob(income = high) = 11/1003
 The “corrected” prob. estimates are close to their “uncorrected”

counterparts

November 22, 2019 Data Mining: Concepts and Techniques 47

Naïve Bayesian Classifier: Comments
 Advantages
 Easy to implement

 Good results obtained in most of the cases

 Disadvantages
 Assumption: class conditional independence, therefore

loss of accuracy
 Practically, dependencies exist among variables

 E.g., salary and age.

Symptoms: fever, cough etc., Disease: lung cancer, diabetes, etc.
 Dependencies among these cannot be modeled by Naïve

Bayesian Classifier
 How to deal with these dependencies?
 Bayesian Belief Networks
November 22, 2019 Data Mining: Concepts and Techniques 48
 Weka Demo

Vote Classification

November 22, 2019 Data Mining: Concepts and Techniques 49

 Graphical Model for Naïve Bayes
Classifier

http://people.csail.mit.edu/kersting/profile/PROFILE_nb.html

November 22, 2019 Data Mining: Concepts and Techniques 50

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 51
 Using IF-THEN Rules for Classification
 Represent the knowledge in the form of IF-THEN rules
R: IF age = youth AND student = yes THEN buys_computer = yes
 Rule antecedent/precondition vs. rule consequent
 Assessment of a rule: coverage and accuracy
 ncovers = # of data points covered by R
 ncorrect = # of data points correctly classified by R
coverage(R) = ncovers /|D| /* D: training data set */
accuracy(R) = ncorrect / ncovers
 If more than one rule is triggered, need conflict resolution
 Size ordering: assign the highest priority to the triggering rules that has
the “toughest” requirement (i.e., with the most attribute test)
 Rule-based ordering (decision list): rules are organized into one long
priority list, according to some measure of rule quality (accuracy) or by
experts

November 22, 2019 Data Mining: Concepts and Techniques 52

 Rule Extraction from a Decision Tree
age?

<=30 31..40 >40

 Rules are easier to understand than large trees
student? credit rating?
yes
 One rule is created for each path from the root
no yes excellent fair
to a leaf
no yes yes
 Each attribute-value pair along a path forms a
conjunction: the leaf holds the class prediction
 Rules are mutually exclusive and exhaustive
 Example: Rule extraction from our buys_computer decision-tree
IF age = young AND student = no THEN buys_computer = no
IF age = young AND student = yes THEN buys_computer = yes
IF age = mid-age THEN buys_computer = yes
IF age = old AND credit_rating = excellent THEN buys_computer = yes
IF age = young AND credit_rating = fair THEN buys_computer = no

November 22, 2019 Data Mining: Concepts and Techniques 53

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 54
 Classification: A Mathematical Mapping

 Classification:
 predicts categorical class labels

 E.g., Personal homepage classification

 xi = (x1, x2, x3, …), yi = +1 or –1

 x1 : # of a word “homepage”

 x2 : # of a word “welcome”

 Mathematically
 x  X =  , y  Y = {+1, –1}
n

 We want a function f: X  Y

November 22, 2019 Data Mining: Concepts and Techniques 55

 Linear Classification
 Binary Classification
problem
 The data above the red
line belongs to class ‘x’
x  The data below red line
x x
x x belongs to class ‘o’
x  Examples: SVM,
x x o
x Perceptron
o
x o o
ooo
o o
o o o o

November 22, 2019 Data Mining: Concepts and Techniques 56

 Generative VS Discriminative

Generative Classifier: develop a model to

simulate the generation of data of each class
(Naïve Bayes, HMM)
Discriminative Classifier: find a function to
separate different groups of data
(decision tree, perceptron, neural networks,
support vector machines, etc)

November 22, 2019 Data Mining: Concepts and Techniques 57

 Discriminative Classifiers
 Advantages
 prediction accuracy is generally high

 As compared to Bayesian methods – in general

 robust, works when training examples contain errors
 fast evaluation of the learned target function
 Bayesian networks are normally slow
 Criticism
 Cannot simulate data generation

 long training time

 difficult to understand the learned function (weights)

 Bayesian networks can be used easily for pattern discovery

 not easy to incorporate domain knowledge
 Easy in the form of priors on the data or distributions
November 22, 2019 Data Mining: Concepts and Techniques 58
 Perceptron
• Vector: x, w
x2
• Scalar: x, y, w
Input: {(x1, t1), …}
Output: classification function f(x)
f(xi) > 0 for ti = +1
f(xi) < 0 for ti = -1
f(x) = w1x1+w2x2+b = 0

• Perceptron: update W
additively

x1

November 22, 2019 Data Mining: Concepts and Techniques 59

November 22, 2019 Data Mining: Concepts and Techniques 60
November 22, 2019 Data Mining: Concepts and Techniques 61
November 22, 2019 Data Mining: Concepts and Techniques 62
 Perceptron Learning Movie

 https://www.youtube.com/watch?v=vGwemZhPls
A

November 22, 2019 Data Mining: Concepts and Techniques 63

November 22, 2019 Data Mining: Concepts and Techniques 64
November 22, 2019 Data Mining: Concepts and Techniques 65
 Extend to Neural Networks

 Started by psychologists and neurobiologists to develop

and test computational analogues of neurons
 A neural network: A set of connected input/output units
where each connection has a weight associated with it
 During the learning phase, the network learns by
adjusting the weights so as to be able to predict the
correct class label of the input tuples
 Also referred to as connectionist learning due to the
connections between units

November 22, 2019 Data Mining: Concepts and Techniques 66

 Brain

Images.google.com
November 22, 2019 Data Mining: Concepts and Techniques 67
November 22, 2019 Data Mining: Concepts and Techniques 68
November 22, 2019 Data Mining: Concepts and Techniques 69
 A Neuron (= a perceptron)

1 w0
x1

w1
f
output y
xn wn
For Example
n
Input weight weighted Activation y  sign(  wi xi  w0 )
vector x vector w sum function i 1

 The n-dimensional input vector x is mapped into variable y by

means of the scalar product and a nonlinear function mapping

November 22, 2019 Data Mining: Concepts and Techniques 70

A Multi-Layer Feed-Forward Neural Network

Output vector

Output layer

Hidden layer

wij

Input layer

Input vector: X
November 22, 2019 Data Mining: Concepts and Techniques 71
November 22, 2019 Data Mining: Concepts and Techniques 72
November 22, 2019 Data Mining: Concepts and Techniques 73
 Activation / Transfer Function

 Sigmoid function:

 Tanh function What is derivative of f(x)?

November 22, 2019 Data Mining: Concepts and Techniques 74

November 22, 2019 Data Mining: Concepts and Techniques 75
November 22, 2019 Data Mining: Concepts and Techniques 76
November 22, 2019 Data Mining: Concepts and Techniques 77
November 22, 2019 Data Mining: Concepts and Techniques 78
November 22, 2019 Data Mining: Concepts and Techniques 79
 Matrix View of Propagation
w11 w12 w13 … w1d

W21 W22 … …. w2d

* (X1, x2, …, Xd) = (a1, a2, …, am)

….
Apply
Wm1 Wm2 wmd Transfer
w11 w12 w13 … w1m function

W21 W22 … …. w2c

* (z1, z2, …, zm)

(b1, b2, …, bc) =
….

Apply transfer function Wc1 Wm2 wcm

(O1, O2, …, Oc)

November 22, 2019 Data Mining: Concepts and Techniques 80

 Chain Rule of Calculating Derivatives

November 22, 2019 Data Mining: Concepts and Techniques 81

 Chain Rule of Calculating Derivatives

November 22, 2019 Data Mining: Concepts and Techniques 82

 Backpropagation
 Iteratively present a set of training tuples & compare the network's
prediction with the actual known target value.
 An iteration on all tuples is called an Epoch.
 For each training tuple, the weights are modified to minimize the
mean squared error between prediction and the actual target value
 Modifications are made in the “backwards” direction
backpropagation
 Steps
 Initialize weights (to small random #s) and biases in the network

 Propagate the inputs forward (by applying activation function)

 Backpropagate the error (by updating weights and biases)

 Repeat propagation and back-propagation until terminating

condition is reached (when error is very small, etc.)

November 22, 2019 Data Mining: Concepts and Techniques 83

 Training Error

November 22, 2019 Data Mining: Concepts and Techniques 84

 Defining a Network Topology
 First decide the network topology: # of units in the
input layer, # of hidden layers (if > 1), # of units in each
hidden layer, and # of units in the output layer
 Normalizing the input values for each attribute measured in
the training tuples to [0.0—1.0]
 Output, if for classification and more than two classes,
one output unit per class is used
 Once a network has been trained and its accuracy is
unacceptable, repeat the training process with a different
network topology or a different set of initial weights

November 22, 2019 Data Mining: Concepts and Techniques 85

 Test Phase and Prediction

• Weights are known

• Given an input x, neural network generates
an output O
• Binary classification: O > 0.5  positive, O
<= 0.5  negative
• Multi-classification: Choose the class of the
output node with highest value
• Regression: O is the predicted value

November 22, 2019 Data Mining: Concepts and Techniques 86

 Neural Network as a Classifier
 Weakness
 Long training time
 Require a number of parameters typically best determined
empirically, e.g., the network topology
 Poor interpretability: Difficult to interpret the symbolic meaning
behind the learned weights and of ``hidden units" in the network
 Strength
 High tolerance to noisy data
 Ability to classify untrained patterns
 Well-suited for continuous-valued inputs and outputs
 Successful on a wide array of real-world data
 Algorithms are inherently parallel
 Techniques have recently been developed for the extraction of
rules from trained neural networks
November 22, 2019 Data Mining: Concepts and Techniques 87
 Neural Network Demo - NNClass

On sysbio.rnet.missouri.edu server
In /home/chengji/nnrank1.2

November 22, 2019 Data Mining: Concepts and Techniques 88

 Neural Network Software

 Weka (Java)
 NNClass in NNRank package (C++, good
performance, very fast):
http://sysbio.rnet.missouri.edu/multicom_toolbox/
tools.html
 Matlab

November 22, 2019 Data Mining: Concepts and Techniques 89

 Most Recent Development – Deep
Learning

November 22, 2019 Data Mining: Concepts and Techniques 90

 Deep Learning Tools

 Pylearn2
 Theano
 Caffe
 Torch
 Cuda-convnet
 Deeplearning4j

November 22, 2019 Data Mining: Concepts and Techniques 91

 Six Top General Data Mining Tools

 RapidMiner
 Weka
 R-programming
 Orange (python)
 KNIME
 NLTK

November 22, 2019 Data Mining: Concepts and Techniques 92

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 93
 SVM—Support Vector Machines
 A new classification method for both linear and nonlinear
data
 It uses a nonlinear mapping to transform the original
training data into a higher dimension
 With the new dimension, it searches for the linear optimal
separating hyperplane (i.e., “decision boundary”)
 With an appropriate nonlinear mapping to a sufficiently
high dimension, data from two classes can always be
separated by a hyperplane
 SVM finds this hyperplane using support vectors
(“essential” training tuples) and margins (defined by the
support vectors)
November 22, 2019 Data Mining: Concepts and Techniques 94
 SVM—History and Applications
 Vapnik and colleagues (1992)—groundwork from Vapnik
& Chervonenkis’ statistical learning theory in 1960s
 Features: training can be slow but accuracy is high owing
to their ability to model complex nonlinear decision
boundaries (margin maximization)
 Used both for classification and prediction
 Applications:
 handwritten digit recognition, object recognition,
speaker identification, benchmarking time-series
prediction tests
November 22, 2019 Data Mining: Concepts and Techniques 95
 SVM—General Philosophy

Small Margin Large Margin

Support Vectors

November 22, 2019 Data Mining: Concepts and Techniques 96

 SVM—Linearly Separable
 A separating hyperplane can be written as
W●X+b=0
where W={w1, w2, …, wn} is a weight vector and b a scalar (bias)
 For 2-D it can be written as
w0 + w1 x1 + w2 x2 = 0
 The hyperplane defining the sides of the margin:
H1: w0 + w1 x1 + w2 x2 ≥ 1 for yi = +1, and
H2: w0 + w1 x1 + w2 x2 ≤ – 1 for yi = –1
 Any training tuples that fall on hyperplanes H1 or H2 (i.e., the
sides defining the margin) are support vectors
 This becomes a constrained (convex) quadratic optimization
problem: Quadratic objective function and linear constraints 
Quadratic Programming (QP)  Lagrangian multipliers

November 22, 2019 Data Mining: Concepts and Techniques 97

SVM—When Data Is Linearly Separable

Let data D be (X1, y1), …, (X|D|, y|D|), where Xi is the set of training tuples
associated with the class labels yi
There are infinite lines (hyperplanes) separating the two classes but we want to
find the best one (the one that minimizes classification error on unseen data)
SVM searches for the hyperplane with the largest margin, i.e., maximum
marginal hyperplane (MMH)

November 22, 2019 Data Mining: Concepts and Techniques 98

November 22, 2019 Data Mining: Concepts and Techniques 99
 Quadratic Optimization

November 22, 2019 Data Mining: Concepts and Techniques 100

 Primal Optimization

November 22, 2019 Data Mining: Concepts and Techniques 101

 Dual Optimization

November 22, 2019 Data Mining: Concepts and Techniques 102

November 22, 2019 Data Mining: Concepts and Techniques 103
November 22, 2019 Data Mining: Concepts and Techniques 104
 How to calculate b?

November 22, 2019 Data Mining: Concepts and Techniques 105

 How to calculate b?

 Take a positive (resp. negative) support vector

 Given W ● X + b = 1
 b= 1-W●X
 Good practice is to use all the support vectors to
caculate b and take the average

November 22, 2019 Data Mining: Concepts and Techniques 106

 Prediction

How to interpret it?

November 22, 2019 Data Mining: Concepts and Techniques 107

Why Is SVM Effective on High Dimensional Data?

 The complexity of trained classifier is characterized by the # of

support vectors rather than the dimensionality of the data
 The support vectors are the essential or critical training examples —
they lie closest to the decision boundary (MMH)
 If all other training examples are removed and the training is
repeated, the same separating hyperplane would be found
 The number of support vectors found can be used to compute an
(upper) bound on the expected error rate of the SVM classifier, which
is independent of the data dimensionality
 Thus, an SVM with a small number of support vectors can have good
generalization, even when the dimensionality of the data is high

November 22, 2019 Data Mining: Concepts and Techniques 108

 Connection between SVM and NN?

November 22, 2019 Data Mining: Concepts and Techniques 109

 Connection Between SVM and NN

November 22, 2019 Data Mining: Concepts and Techniques 110

November 22, 2019 Data Mining: Concepts and Techniques 111
 SVM Kernel Mapping Demo

 http://www.youtube.com/watch?v=3liCbRZPrZA

November 22, 2019 Data Mining: Concepts and Techniques 112

 Dual Optimization

November 22, 2019 Data Mining: Concepts and Techniques 113

November 22, 2019 Data Mining: Concepts and Techniques 114
November 22, 2019 Data Mining: Concepts and Techniques 115
November 22, 2019 Data Mining: Concepts and Techniques 116
November 22, 2019 Data Mining: Concepts and Techniques 117
November 22, 2019 Data Mining: Concepts and Techniques 118
November 22, 2019 Data Mining: Concepts and Techniques 119
November 22, 2019 Data Mining: Concepts and Techniques 120
 SVM vs. Neural Network
 SVM  Neural Network
 Hot in late 1990s and  Relatively old, but hot

early 2000 again

 Nondeterministic
 Deterministic algorithm algorithm
 Nice Generalization  Generalizes well
properties  Can easily be learned in

 Hard to learn – learned incremental fashion

in batch mode using  To learn complex

quadratic programming functions—use multilayer

perceptron (not that
techniques trivial)
 Using kernels can learn  Local minima

very complex functions

November 22, 2019 Data Mining: Concepts and Techniques 121
 SVM Tools

 SVM-light: http://svmlight.joachims.org/
 LIBSVM:
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
 Gist: http://bioinformatics.ubc.ca/gist/
 Weka

November 22, 2019 Data Mining: Concepts and Techniques 122

 SVM Related Links

 SVM Website

 http://www.kernel-machines.org/

 Representative implementations

 LIBSVM: an efficient implementation of SVM, multi-class

classifications, nu-SVM, one-class SVM, including also various
interfaces with java, python, etc.

 SVM-light: simpler but performance is not better than LIBSVM,

support only binary classification and only C language

 SVM-torch: another recent implementation also written in C.

November 22, 2019 Data Mining: Concepts and Techniques 123

 SVM Demo (Weka)

November 22, 2019 Data Mining: Concepts and Techniques 124

 SVM—Introduction Literature
 “Statistical Learning Theory” by Vapnik: extremely hard to understand,
containing many errors too.
 C. J. C. Burges. A Tutorial on Support Vector Machines for Pattern
Recognition. Knowledge Discovery and Data Mining, 2(2), 1998.
 The book “An Introduction to Support Vector Machines” by N.
Cristianini and J. Shawe-Taylor
 The neural network book by Haykins
 Contains one nice chapter of SVM introduction

November 22, 2019 Data Mining: Concepts and Techniques 125

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 126
 Associative Classification
 Associative classification
 Association rules are generated and analyzed for use in classification
 Search for strong associations between frequent patterns
(conjunctions of attribute-value pairs) and class labels
 Classification: Based on evaluating a set of rules in the form of
P1 ^ p2 … ^ pl  “Aclass = C” (conf, sup)
 Why effective?
 It explores highly confident associations among multiple attributes
and may overcome some constraints introduced by decision-tree
induction, which considers only one attribute at a time
 In many studies, associative classification has been found to be more
accurate than some traditional classification methods, such as C4.5
November 22, 2019 Data Mining: Concepts and Techniques 127
Typical Associative Classification Methods

 CBA (Classification By Association: Liu, Hsu & Ma, KDD’98)

 Mine association possible rules in the form of
 Cond-set (a set of attribute-value pairs)  class label
 Build classifier: Organize rules according to decreasing
precedence based on confidence and then support
 CMAR (Classification based on Multiple Association Rules: Li,
Han, Pei, ICDM’01)
 Classification: Statistical analysis on multiple rules

November 22, 2019 Data Mining: Concepts and Techniques 128

 A Closer Look at CMAR

 CMAR (Classification based on Multiple Association Rules: Li, Han, Pei, ICDM’01)
 Efficiency: Uses an enhanced FP-tree that maintains the distribution of
class labels among tuples satisfying each frequent itemset
 Rule pruning whenever a rule is inserted into the tree
 Given two rules, R1 and R2, if the antecedent of R1 is more general

than that of R2 and conf(R1) ≥ conf(R2), then R2 is pruned

 Prunes rules for which the rule antecedent and class are not

positively correlated, based on a χ2 test of statistical significance

 Classification based on generated/pruned rules
 If only one rule satisfies tuple X, assign the class label of the rule

 If a rule set S satisfies X, CMAR

 divides S into groups according to class labels

 uses a weighted χ measure to find the strongest group of rules,

2

based on the statistical correlation of rules within a group

 assigns X the class label of the strongest group
November 22, 2019 Data Mining: Concepts and Techniques 129
 Associative Classification May Achieve High
Accuracy and Efficiency (Cong et al. SIGMOD05)

November 22, 2019 Data Mining: Concepts and Techniques 130

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 131
 Lazy vs. Eager Learning
 Lazy vs. eager learning
 Lazy learning (e.g., instance-based learning): Simply
stores training data (or only minor processing) and
waits until it is given a test tuple
 Eager learning (the above discussed methods): Given a
set of training set, constructs a classification model
before receiving new (e.g., test) data to classify
 Lazy: less time in training but more time in predicting
 Accuracy
 Lazy method effectively uses a richer hypothesis space
since it uses many local linear functions to form its
implicit global approximation to the target function
 Eager: must commit to a single hypothesis that covers
the entire instance space
November 22, 2019 Data Mining: Concepts and Techniques 132
 Lazy Learner: Instance-Based Methods

 Instance-based learning:
 Store training examples and delay the processing
(“lazy evaluation”) until a new instance must be
classified
 Typical approaches
 k-nearest neighbor approach

 Instances represented as points in a Euclidean

space.
 Locally weighted regression

 Constructs local approximation

November 22, 2019 Data Mining: Concepts and Techniques 133

 The k-Nearest Neighbor Algorithm
 All instances correspond to points in the n-D space
 The nearest neighbor are defined in terms of
Euclidean distance, dist(X1, X2)
 Target function could be discrete- or real- valued
 For discrete-valued, k-NN returns the most common
value among the k training examples nearest to xq
 Vonoroi diagram: the decision surface induced by 1-
NN for a typical set of training examples

_
_
_ _
.
+
_ .
+
xq + . . .
November 22, 2019
_ + .
Data Mining: Concepts and Techniques 134
 Discussion on the k-NN Algorithm

 k-NN for real-valued prediction for a given unknown tuple

 Returns the mean values of the k nearest neighbors
 Distance-weighted nearest neighbor algorithm
 Weight the contribution of each of the k neighbors
according to their distance to the query xq 1 w
 Give greater weight to closer neighbors d ( xq , x )2
i
 Robust to noisy data by averaging k-nearest neighbors
 Curse of dimensionality: distance between neighbors could
be dominated by irrelevant attributes
 To overcome it, elimination of the least relevant
attributes
November 22, 2019 Data Mining: Concepts and Techniques 135
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 136
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Regression
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 137
 What Is Regression?
 (Numerical) prediction / regression is similar to classification
 construct a model

 use model to predict continuous or ordered value for a given input

 Regression is different from classification

 Classification refers to predict categorical class label

 Regression models continuous-valued functions

 Major method for prediction of real value: regression

 model the relationship between one or more independent or

predictor variables and a dependent or response variable

 Regression analysis
 Linear and multiple regression

 Non-linear regression (neural networks, support vector machines,

KNN)
 Other regression methods: generalized linear model, Poisson

regression, log-linear models, regression trees

November 22, 2019 Data Mining: Concepts and Techniques 138
 Linear Regression
 Linear regression: involves a response variable y and a single
predictor variable x
y = w0 + w1 x
where w0 (y-intercept) and w1 (slope) are regression coefficients
 Method of least squares: estimates the best-fitting straight line
| D|

 (x  x )( yi  y )
w  w  y w x
i
i 1

1 | D|
0 1
 (x
i 1
i  x )2

 Multiple linear regression: involves more than one predictor variable

 Training data is of the form (X1, y1), (X2, y2),…, (X|D|, y|D|)
 Solvable by extension of least square method or using R, SAS, S-
Plus

November 22, 2019 Data Mining: Concepts and Techniques 139

November 22, 2019 Data Mining: Concepts and Techniques 140
November 22, 2019 Data Mining: Concepts and Techniques 141
 Nonlinear Regression
 Some nonlinear models can be modeled by a polynomial
function
 A polynomial regression model can be transformed into
linear regression model. For example,
y = w0 + w1 x + w2 x2 + w3 x3
convertible to linear with new variables: x2 = x2, x3= x3
y = w0 + w1 x + w2 x2 + w3 x3

November 22, 2019 Data Mining: Concepts and Techniques 142

 Other Regression-Based Models
 Generalized linear model:
 Foundation on which linear regression can be applied to modeling
categorical response variables
 Logistic regression: models the prob. of some event occurring as a
linear function of a set of predictor variables
 Regression trees and model trees
 Trees to predict continuous values rather than class labels

November 22, 2019 Data Mining: Concepts and Techniques 143

November 22, 2019 Data Mining: Concepts and Techniques 144
 Logistic Regression

X1 X2 … Die / Live
0.01 0.004 1
0.001 0.02 0
…
…
0.003 0.005 1

Binomial distribution:
For one dose level xi, yi = P(die|xi), likelihood = yiti(1-yi)(1-ti)

Maximize likelihood is equivalent to minimize negative log-likelihood:

-tilog(yi) – (1 - ti)log(1 – yi)

November 22, 2019 Data Mining: Concepts and Techniques 145

 Logistic Regression As One Layer
Neural Network – Gradient Descent

November 22, 2019 Data Mining: Concepts and Techniques 146

November 22, 2019 Data Mining: Concepts and Techniques 147
 Regression Trees and Model Trees
 Regression tree: proposed in CART system (Breiman et al. 1984)
 CART: Classification And Regression Trees
 Each leaf stores a continuous-valued prediction
 It is the average value of the predicted attribute for the training
tuples that reach the leaf
 Model tree: proposed by Quinlan (1992)
 Each leaf holds a regression model—a multivariate linear equation
for the predicted attribute
 A more general case than regression tree
 Regression and model trees tend to be more accurate than linear
regression when the data are not represented well by a simple linear
model
November 22, 2019 Data Mining: Concepts and Techniques 148
 How to Partition Data

 Minimize Square Errors

www.stat.cmu.edu/~cshalizi/350-2006/lecture-10.pdf

November 22, 2019 Data Mining: Concepts and Techniques 149

 Algorithm
1. Start with a single node containing all points. Calculate mc and S.

2. If all the points in the node have the same value for all the
independent variables, stop. Otherwise, search over the splits of all
variables for the one which will reduce S as much as possible. If the
largest decrease in S would be less than some threshold , or one of
the resulting nodes would contain less than q points, stop.
Otherwise, take that split, creating two new nodes.

3. In each new node, go back to step 1.

www.stat.cmu.edu/~cshalizi/350-2006/lecture-10.pdf

November 22, 2019 Data Mining: Concepts and Techniques 150

 Regression tree for prices of 1993 model cars. All values are standardized in [-1, 1]
November 22, 2019 Data Mining: Concepts and Techniques 151
 www.stat.cmu.edu/~cshalizi/350-2006/lecture-10.pdf
November 22, 2019 Data Mining: Concepts and Techniques 152
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 153
 C1(Pre) C2(pre)

Classifier Accuracy Measures C1 True positive False negative

C2 False positive True negative

classes buy_computer = yes buy_computer = no total recognition(%)

buy_computer = yes 6954 46 7000 99.34
buy_computer = no 412 2588 3000 86.27
total 7366 2634 10000 95.52
 Accuracy of a classifier M, acc(M): percentage of test set tuples that are
correctly classified by the model M
 Error rate (misclassification rate) of M = 1 – acc(M)

 Given m classes, CMi,j, an entry in a confusion matrix, indicates #

of tuples in class i that are labeled by the classifier as class j

 Alternative accuracy measures (e.g., for cancer diagnosis)
sensitivity = t-pos/pos /* true positive recognition rate */
specificity = t-neg/neg /* true negative recognition rate */
precision = t-pos/(t-pos + f-pos)
accuracy = sensitivity * pos/(pos + neg) + specificity * neg/(pos + neg)
 This model can also be used for cost-benefit analysis
November 22, 2019 Data Mining: Concepts and Techniques 154
 Predictor Error Measures
 Measure predictor accuracy: measure how far off the predicted value is
from the actual known value
 Loss function: measures the error betw. yi and the predicted value yi’
 Absolute error: | yi – yi’|
 Squared error: (yi – yi’)2
 Test error (generalization error):
d
the average loss over the test
d
set
 Mean absolute error: | y
i 1
i  yi ' | Mean squared error: ( y  y ')
i 1
i i
2

d d
d

 Relative absolute error:  | y

d

i  yi ' | Relative squared error:  ( yi  yi ' ) 2

i 1
i 1
d d
| y
i 1
i y|
(y
i 1
i  y)2
The mean squared-error exaggerates the presence of outliers
Popularly use (square) root mean-square error, similarly, root relative
squared error
November 22, 2019 Data Mining: Concepts and Techniques 155
 Evaluating the Accuracy of a Classifier
or Predictor (I)
 Holdout method
 Given data is randomly partitioned into two independent sets

 Training set (e.g., 2/3) for model construction

 Test set (e.g., 1/3) for accuracy estimation

 Random sampling: a variation of holdout

 Repeat holdout k times, accuracy = avg. of the accuracies

obtained
 Cross-validation (k-fold, where k = 10 is most popular)
 Randomly partition the data into k mutually exclusive subsets,

each approximately equal size

 At i-th iteration, use Di as test set and others as training set

 Leave-one-out: k folds where k = # of tuples, for small sized data

 Stratified cross-validation: folds are stratified so that class dist. in

each fold is approx. the same as that in the initial data

November 22, 2019 Data Mining: Concepts and Techniques 156

 Evaluating the Accuracy of a Classifier
or Predictor (II)
 Bootstrap
 Works well with small data sets
 Samples the given training tuples uniformly with replacement
 i.e., each time a tuple is selected, it is equally likely to be
selected again and re-added to the training set
 Several boostrap methods, and a common one is .632 boostrap
 Suppose we are given a data set of d tuples. The data set is sampled d
times, with replacement, resulting in a training set of d samples. The data
tuples that did not make it into the training set end up forming the test set.
About 63.2% of the original data will end up in the bootstrap, and the
remaining 36.8% will form the test set (since (1 – 1/d)d ≈ e-1 = 0.368)
 Repeat the sampling procedue k times, overall accuracy of the
model: k
acc( M )   (0.632  acc( M i )test _ set 0.368  acc( M i )train_ set )
i 1

November 22, 2019 Data Mining: Concepts and Techniques 157

 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 158
Ensemble Methods: Increasing the Accuracy

 Ensemble methods
 Use a combination of models to increase accuracy

 Combine a series of k learned models, M1, M2, …, Mk,

with the aim of creating an improved model M*

 Popular ensemble methods
 Bagging: averaging the prediction over a collection of

classifiers (e.g. Random Forest)

 Boosting: weighted vote with a collection of classifiers

 Ensemble: combining a set of heterogeneous classifiers

November 22, 2019 Data Mining: Concepts and Techniques 159

 Bagging: Boostrap Aggregation
 Analogy: Diagnosis based on multiple doctors’ majority vote
 Training
 Given a set D of d tuples, at each iteration i, a training set Di of d

tuples is sampled with replacement from D (i.e., boostrap)

 A classifier model Mi is learned for each training set Di

 Classification: classify an unknown sample X

 Each classifier Mi returns its class prediction

 The bagged classifier M* counts the votes and assigns the class

with the most votes to X

 Prediction: can be applied to the prediction of continuous values by
taking the average value of each prediction for a given test tuple
 Accuracy
 Often significant better than a single classifier derived from D

 For noise data: not considerably worse, more robust

 Proved improved accuracy in prediction

November 22, 2019 Data Mining: Concepts and Techniques 160
 Boosting
 Analogy: Consult several doctors, based on a combination of weighted
diagnoses—weight assigned based on the previous diagnosis accuracy
 How boosting works?
 Weights are assigned to each training tuple
 A series of k classifiers is iteratively learned
 After a classifier Mi is learned, the weights are updated to allow the
subsequent classifier, Mi+1, to pay more attention to the training
tuples that were misclassified by Mi
 The final M* combines the votes of each individual classifier, where
the weight of each classifier's vote is a function of its accuracy
 The boosting algorithm can be extended for the prediction of
continuous values
 Comparing with bagging: boosting tends to achieve greater accuracy,
but it also risks overfitting the model to misclassified data
November 22, 2019 Data Mining: Concepts and Techniques 161
Adaboost (Freund and Schapire, 1997)
 Given a set of d class-labeled tuples, (X1, y1), …, (Xd, yd)
 Initially, all the weights of tuples are set the same (1/d)
 Generate k classifiers in k rounds. At round i,
 Tuples from D are sampled (with replacement) to form a
training set Di of the same size
 Each tuple’s chance of being selected is based on its weight
 A classification model Mi is derived from Di
 Its error rate is calculated using Di as a test set
 If a tuple is misclssified, its weight is increased, o.w. it is
decreased
 Error rate: err(Xj) is the misclassification error of tuple Xj. Classifier
Mi error rate is the sum of the weights of the misclassified tuples:
d
error ( M i )   w j  err ( X j )
j
1  error ( M i )
 The weight of classifier Mi’s vote is log
error ( M i )
November 22, 2019 Data Mining: Concepts and Techniques 162
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 163
Model Selection: ROC Curves
 ROC (Receiver Operating Characteristics)
curves: for visual comparison of
classification models
 Originated from signal detection theory
 Shows the trade-off between the true
positive rate and the false positive rate
 Vertical axis represents
 The area under the ROC curve is a
the true positive rate
measure of the accuracy of the model
 Horizontal axis rep. the
 The closer to the diagonal line (i.e., the false positive rate
closer the area is to 0.5), the less accurate
 The plot also shows a
is the model diagonal line
 A model with perfect
accuracy will have an
area of 1.0
November 22, 2019 Data Mining: Concepts and Techniques 164
 Chapter 6. Classification and Prediction

 What is classification? What is  Support Vector Machines (SVM)

prediction?  Associative classification
 Issues regarding classification  Lazy learners (or learning from
and prediction your neighbors)
 Classification by decision tree  Other classification methods
induction  Prediction
 Bayesian classification  Accuracy and error measures
 Rule-based classification  Ensemble methods
 Classification by back  Model selection
propagation
 Summary
November 22, 2019 Data Mining: Concepts and Techniques 165
 Summary (I)
 Classification and regression are two forms of data analysis that can
be used to extract models describing important data classes or to
predict future data trends.
 Effective and scalable methods have been developed for decision
trees induction, Naive Bayesian classification, Bayesian belief
network, rule-based classifier, Backpropagation, Support Vector
Machine (SVM), associative classification, nearest neighbor classifiers.
 Linear, nonlinear, and generalized linear models of regression can be
used for prediction. Many nonlinear problems can be converted to
linear problems by performing transformations on the predictor
variables. Regression trees are also used for prediction.

November 22, 2019 Data Mining: Concepts and Techniques 166

 Summary (II)
 Stratified k-fold cross-validation is a recommended method for
accuracy estimation. Bagging and boosting can be used to increase
overall accuracy by learning and combining a series of individual
models.
 Significance tests and ROC curves are useful for model selection
 There have been numerous comparisons of the different classification
and prediction methods, and the matter remains a research topic
 No single method has been found to be superior over all others for all
data sets
 Issues such as accuracy, training time, robustness, interpretability, and
scalability must be considered and can involve trade-offs, further
complicating the quest for an overall superior method
November 22, 2019 Data Mining: Concepts and Techniques 167
 Course Project

 Rule: up to 4 students in a group

 Select one of five standard projects or come up
your own project
 Project presentation during the last few classes
 Project report by the end of the semester
 Contact me if you are not sure if your project is
suitable
 Email [email protected] the name of
students in your group by March 15.
 Review of five standard projects
November 22, 2019 Data Mining: Concepts and Techniques 168
 References (1)
 C. Apte and S. Weiss. Data mining with decision trees and decision rules. Future
Generation Computer Systems, 13, 1997.
 C. M. Bishop, Neural Networks for Pattern Recognition. Oxford University Press,
1995.
 L. Breiman, J. Friedman, R. Olshen, and C. Stone. Classification and Regression
Trees. Wadsworth International Group, 1984.
 C. J. C. Burges. A Tutorial on Support Vector Machines for Pattern Recognition.
Data Mining and Knowledge Discovery, 2(2): 121-168, 1998.
 P. K. Chan and S. J. Stolfo. Learning arbiter and combiner trees from partitioned
data for scaling machine learning. KDD'95.
 W. Cohen. Fast effective rule induction. ICML'95.
 G. Cong, K.-L. Tan, A. K. H. Tung, and X. Xu. Mining top-k covering rule groups for
gene expression data. SIGMOD'05.
 A. J. Dobson. An Introduction to Generalized Linear Models. Chapman and Hall,
1990.
 G. Dong and J. Li. Efficient mining of emerging patterns: Discovering trends and
differences. KDD'99.

November 22, 2019 Data Mining: Concepts and Techniques 169

 References (2)
 R. O. Duda, P. E. Hart, and D. G. Stork. Pattern Classification, 2ed. John Wiley and
Sons, 2001
 U. M. Fayyad. Branching on attribute values in decision tree generation. AAAI’94.
 Y. Freund and R. E. Schapire. A decision-theoretic generalization of on-line
learning and an application to boosting. J. Computer and System Sciences, 1997.
 J. Gehrke, R. Ramakrishnan, and V. Ganti. Rainforest: A framework for fast decision
tree construction of large datasets. VLDB’98.
 J. Gehrke, V. Gant, R. Ramakrishnan, and W.-Y. Loh, BOAT -- Optimistic Decision Tree
Construction. SIGMOD'99.
 T. Hastie, R. Tibshirani, and J. Friedman. The Elements of Statistical Learning: Data
Mining, Inference, and Prediction. Springer-Verlag, 2001.
 D. Heckerman, D. Geiger, and D. M. Chickering. Learning Bayesian networks: The
combination of knowledge and statistical data. Machine Learning, 1995.
 M. Kamber, L. Winstone, W. Gong, S. Cheng, and J. Han. Generalization and decision
tree induction: Efficient classification in data mining. RIDE'97.
 B. Liu, W. Hsu, and Y. Ma. Integrating Classification and Association Rule. KDD'98.
 W. Li, J. Han, and J. Pei, CMAR: Accurate and Efficient Classification Based on
Multiple Class-Association Rules, ICDM'01.
November 22, 2019 Data Mining: Concepts and Techniques 170
 References (3)
 T.-S. Lim, W.-Y. Loh, and Y.-S. Shih. A comparison of prediction accuracy,
complexity, and training time of thirty-three old and new classification
algorithms. Machine Learning, 2000.
 J. Magidson. The Chaid approach to segmentation modeling: Chi-squared
automatic interaction detection. In R. P. Bagozzi, editor, Advanced Methods of
Marketing Research, Blackwell Business, 1994.
 M. Mehta, R. Agrawal, and J. Rissanen. SLIQ : A fast scalable classifier for data
mining. EDBT'96.
 T. M. Mitchell. Machine Learning. McGraw Hill, 1997.
 S. K. Murthy, Automatic Construction of Decision Trees from Data: A Multi-
Disciplinary Survey, Data Mining and Knowledge Discovery 2(4): 345-389, 1998
 J. R. Quinlan. Induction of decision trees. Machine Learning, 1:81-106, 1986.
 J. R. Quinlan and R. M. Cameron-Jones. FOIL: A midterm report. ECML’93.
 J. R. Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993.
 J. R. Quinlan. Bagging, boosting, and c4.5. AAAI'96.

November 22, 2019 Data Mining: Concepts and Techniques 171

 References (4)
 R. Rastogi and K. Shim. Public: A decision tree classifier that integrates building
and pruning. VLDB’98.
 J. Shafer, R. Agrawal, and M. Mehta. SPRINT : A scalable parallel classifier for
data mining. VLDB’96.
 J. W. Shavlik and T. G. Dietterich. Readings in Machine Learning. Morgan Kaufmann,
1990.
 P. Tan, M. Steinbach, and V. Kumar. Introduction to Data Mining. Addison Wesley,
2005.
 S. M. Weiss and C. A. Kulikowski. Computer Systems that Learn: Classification
and Prediction Methods from Statistics, Neural Nets, Machine Learning, and
Expert Systems. Morgan Kaufman, 1991.
 S. M. Weiss and N. Indurkhya. Predictive Data Mining. Morgan Kaufmann, 1997.
 I. H. Witten and E. Frank. Data Mining: Practical Machine Learning Tools and
Techniques, 2ed. Morgan Kaufmann, 2005.
 X. Yin and J. Han. CPAR: Classification based on predictive association rules.
SDM'03
 H. Yu, J. Yang, and J. Han. Classifying large data sets using SVM with
hierarchical clusters. KDD'03.
November 22, 2019 Data Mining: Concepts and Techniques 172