Data Mining:

Concepts and Techniques

(3rd ed.)

— Chapter 3 —
• Dr. Raghunath Dey
• School of Computer Engineering
• KIIT Deemed to be University

1
 Chapter 3: Data Preprocessing

• Data Preprocessing: An Overview

– Data Quality

– Major Tasks in Data Preprocessing

• Data Cleaning

• Data Integration

• Data Reduction

• Data Transformation and Data Discretization

• Summary
2
2
Data Quality: Why Preprocess the Data?

• Measures for data quality: A multidimensional view

– Accuracy: correct or wrong, accurate or not
– Completeness: not recorded, unavailable, …
– Consistency: some modified but some not, dangling, …
– Timeliness: timely update?
– Believability: how trustable the data are correct?
– Interpretability: how easily the data can be understood?

3
Major Tasks in Data Preprocessing
• Data cleaning
– Fill in missing values, smooth noisy data, identify or remove
outliers, and resolve inconsistencies
• Data integration
– Integration of multiple databases, data cubes, or files
• Data reduction
– Dimensionality reduction
– Numerosity reduction
– Data compression
• Data transformation and data discretization
– Normalization
– Concept hierarchy generation
4
 Chapter 3: Data Preprocessing

• Data Preprocessing: An Overview

– Data Quality

– Major Tasks in Data Preprocessing

• Data Cleaning

• Data Integration

• Data Reduction

• Data Transformation and Data Discretization

• Summary
5
5
Data Cleaning
• Data in the Real World Is Dirty: Lots of potentially incorrect data, e.g.,
instrument faulty, human or computer error, transmission error
– incomplete: lacking attribute values, lacking certain attributes of
interest, or containing only aggregate data
• e.g., Occupation=“ ” (missing data)
– noisy: containing noise, errors, or outliers
• e.g., Salary=“−10” (an error)
– inconsistent: containing discrepancies in codes or names, e.g.,
• Age=“42”, Birthday=“03/07/2010”
• Was rating “1, 2, 3”, now rating “A, B, C”
• discrepancy between duplicate records
– Intentional (e.g., disguised missing data)
• Jan. 1 as everyone’s birthday?
6
 Incomplete (Missing) Data

• Data is not always available

– E.g., many tuples have no recorded value for several
attributes, such as customer income in sales data
• Missing data may be due to
– equipment malfunction
– inconsistent with other recorded data and thus deleted
– data not entered due to misunderstanding
– certain data may not be considered important at the
time of entry
– not register history or changes of the data
• Missing data may need to be inferred
7
 How to Handle Missing Data?
• Ignore the tuple: usually done when class label is missing
(when doing classification)—not effective when the % of
missing values per attribute varies considerably
• Fill in the missing value manually: tedious + infeasible?
• Fill in it automatically with
– a global constant : e.g., “unknown”, a new class?!
– the attribute mean
– the attribute mean for all samples belonging to the same
class: smarter
– the most probable value: inference-based such as
Bayesian formula or decision tree 8
 Noisy Data
• Noise: random error or variance in a measured variable
• Incorrect attribute values may be due to
– faulty data collection instruments
– data entry problems
– data transmission problems
– technology limitation
– inconsistency in naming convention
• Other data problems which require data cleaning
– duplicate records
– incomplete data
– inconsistent data

9
How to Handle Noisy Data?

• Binning
– first sort data and partition into (equal-frequency) bins
– then one can smooth by bin means, smooth by bin
median, smooth by bin boundaries, etc.
• Regression
– smooth by fitting the data into regression functions
• Clustering
– detect and remove outliers
• Combined computer and human inspection
– detect suspicious values and check by human (e.g.,
deal with possible outliers)

10
Data Cleaning as a Process
• Data discrepancy detection
– Use metadata (e.g., domain, range, dependency, distribution)
– Check field overloading
– Check uniqueness rule, consecutive rule and null rule
– Use commercial tools
• Data scrubbing: use simple domain knowledge (e.g., postal
code, spell-check) to detect errors and make corrections
• Data auditing: by analyzing data to discover rules and
relationship to detect violators (e.g., correlation and clustering to
find outliers)
• Data migration and integration
– Data migration tools: allow transformations to be specified
– ETL (Extraction/Transformation/Loading) tools: allow users to
specify transformations through a graphical user interface
• Integration of the two processes
– Iterative and interactive (e.g., Potter’s Wheels)
11
 Chapter 3: Data Preprocessing

• Data Preprocessing: An Overview

– Data Quality

– Major Tasks in Data Preprocessing

• Data Cleaning

• Data Integration

• Data Reduction

• Data Transformation and Data Discretization

• Summary
12
12
 Data Integration
• Data integration:
– Combines data from multiple sources into a coherent store
• Schema integration: e.g., A.cust-id  B.cust-#
– Integrate metadata from different sources
• Entity identification problem:
– Identify real world entities from multiple data sources, e.g., Bill
Clinton = William Clinton
• Detecting and resolving data value conflicts
– For the same real world entity, attribute values from different
sources are different
– Possible reasons: different representations, different scales, e.g.,
metric vs. British units
13
13
Handling Redundancy in Data Integration

• Redundant data occur often when integration of multiple

databases
– Object identification: The same attribute or object may
have different names in different databases
– Derivable data: One attribute may be a “derived”
attribute in another table, e.g., annual revenue
• Redundant attributes may be able to be detected by
correlation analysis and covariance analysis
• Careful integration of the data from multiple sources may
help reduce/avoid redundancies and inconsistencies and
improve mining speed and quality
14
14
Correlation Analysis (Nominal Data)

 Χ2 (chi-square) test
2
(Observed  Expected)
2  
Expected
 The larger the Χ2 value, the more likely the variables are
related
 The cells that contribute the most to the Χ2 value are
those whose actual count is very different from the
expected count
 Correlation does not imply causality
 # of hospitals and # of car-theft in a city are correlated
 Both are causally linked to the third variable: population

15
Chi-Square Calculation: An Example
Observed Data
Play chess Not play chess Sum (row)
Like science fiction 250 200 450

Not like science fiction 50 1000 1050

Sum(col.) 300 1200 1500

• Null Hypothesis: There is no significance relationship between

two variables.
• Alternate Hypothesis: There is a significance relationship
among the two variables.
• Expected Data=(450*300)/1500=90 and so on...

Play chess Not play chess Sum (row)

Like science fiction 90 360 450

Not like science fiction 210 840 1050

Sum(col.) 300 1200 1500 16

The expected value in a chi-square test
is calculated using the formula:

8/14/2024
 (Observed  Expected) 2
 
2

Expected

 Χ2 (chi-square) calculation
2 2 2 2
( 250  90 ) (50  210 ) ( 200  360 ) (1000  840 )
2      507.93
90 210 360 840

 It shows that like_science_fiction and play_chess are

correlated in the group
Degrees of freedom (df)

• The degrees of freedom (df) for a chi-

square test are calculated using the
formula:

Here row=2 and column=2, so df=1*1=1

Table of percentage points for chi-
square
• The table of percentage points for chi-square distributions shows
the critical values of the chi-square statistic for different degrees
of freedom (df) and significance levels (α).

8/14/2024
• These values indicate the chi-square statistic beyond
which the null hypothesis is rejected for the given
significance level. For example, with 3 degrees of
freedom and a significance level of 0.05, the critical
value is 7.81. If your chi-square test statistic is
greater than 7.81, you would reject the null
hypothesis at the 0.05 significance level.

Here 507.93> 3.84 ( Reject H0)

Hence, It shows that like_science_fiction and play_chess
are correlated in the group
8/14/2024
Exercise

8/14/2024
8/14/2024
8/14/2024
8/14/2024
8/14/2024
8/14/2024 Conclusion:
Accept H0 as X^2 < 5.99
Relationships Among Numerical
&
Numerical Variables

8/14/2024
Correlation and Covariance

• Correlation and covariance measure the strength

and direction of a linear relationship between two
numerical variables. (Bi-Variate Measures)
– The relationship is “strong” if the points in a
scatterplot cluster tightly around some straight line.
• If this straight line rises from left to right, the relationship is
positive and the measures will be positive numbers.
• If it falls from left to right, the relationship is negative and the
measures will be negative numbers.

8/14/2024
Visually Evaluating Correlation

Scatter plots
showing the
similarity from
–1 to 1.

30
Covariance

• Covariance is essentially an average of

products of deviations from means.

• With this in mind, let Xi and Yi be the paired

values for observation i, and let n be the
number of observations. Then the covariance
between X and Y, denoted by Covar(X, Y).
8/14/2024
Covariance
• It is a statistical measure that shows whether two variables are
related by measuring how the variances change relation to each
other. It is essentially an average of products of deviations from
means.
• If two variables increases/decreases together, covariance will be a
large positive value and the relationship is called positive. If one
variable increases and other decreases and vice versa then
covariance is large negative value and the relationship is called
negative. If two variables are unrelated, the covariance may be a
small number.
• However, how much large is large and how much small is small is
undefined, or it is usually difficult to provide any guideline about how
much large covariance shows a strong relationship and how much
small covariance shows no relationship.

8/14/2024
Example

• Calculate the covariance between two

stocks returns (%)

8/14/2024
8/14/2024
8/14/2024
Correlation
Correlation is a unitless quantity that is unaffected by the
measurement scale.
• For example, the correlation is the same regardless of
whether the variables are measured in dollars, thousands
of dollars, or millions of dollars.

The correlation is defined by Equation, where Stdev(X) and

Stdev(Y) denote the standard deviations of X & Y, and
Covar(X,Y) denote the covariance of X & Y.

8/14/2024
8/14/2024
Exercise
Sl StockX StockY

1 1 6
2 2 1
3 3 8
4 4 3
5 5 2

Find out the co-variance and co-relation between two

variables StockX and StockY
Exercise
Sl StockX StockY

1 1 6
2 2 1
3 3 8
4 4 3
5 5 2

8/14/2024
8/14/2024
Excercize(With 3 variables)
Sl StockX StockY StockZ Means:

1 1 2 3
2 4 5 6
3 7 8 9

8/14/2024
8/14/2024
8/14/2024
Chapter 3: Data Preprocessing

 Data Preprocessing: An Overview

 Data Quality

 Major Tasks in Data Preprocessing

 Data Cleaning

 Data Integration

 Data Reduction

 Data Transformation and Data Discretization

 Summary
46
46
 Data Reduction Strategies
• Data reduction: Obtain a reduced representation of the data set that is
much smaller in volume but yet produces the same (or almost the
same) analytical results
• Why data reduction? — A database/data warehouse may store
terabytes of data. Complex data analysis may take a very long time to
run on the complete data set.
• Data reduction strategies
– Dimensionality reduction, e.g., remove unimportant attributes
• Wavelet transforms
• Principal Components Analysis (PCA)
• Feature subset selection, feature creation
– Numerosity reduction (some simply call it: Data Reduction)
• Regression and Log-Linear Models
• Histograms, clustering, sampling
• Data cube aggregation
– Data compression
47
Principal Component Analysis (PCA)
• Find a projection that captures the largest amount of variation in data
• The original data are projected onto a much smaller space, resulting
in dimensionality reduction. We find the eigenvectors of the
covariance matrix, and these eigenvectors define the new space

x2

x1
48
Principal Component Analysis (Steps)
• Given N data vectors from n-dimensions, find k ≤ n orthogonal vectors
(principal components) that can be best used to represent data
– Normalize input data: Each attribute falls within the same range
– Compute k orthonormal (unit) vectors, i.e., principal components
– Each input data (vector) is a linear combination of the k principal
component vectors
– The principal components are sorted in order of decreasing
“significance” or strength
– Since the components are sorted, the size of the data can be
reduced by eliminating the weak components, i.e., those with low
variance (i.e., using the strongest principal components, it is
possible to reconstruct a good approximation of the original data)
• Works for numeric data only
49
Attribute Subset Selection

• Another way to reduce dimensionality of data

• Redundant attributes
– Duplicate much or all of the information contained in
one or more other attributes
– E.g., purchase price of a product and the amount of
sales tax paid
• Irrelevant attributes
– Contain no information that is useful for the data
mining task at hand
– E.g., students' ID is often irrelevant to the task of
predicting students' GPA

50
Sampling

• Sampling: obtaining a small sample s to represent the

whole data set N
• Allow a mining algorithm to run in complexity that is
potentially sub-linear to the size of the data
• Key principle: Choose a representative subset of the data
– Simple random sampling may have very poor
performance in the presence of skew
– Develop adaptive sampling methods, e.g., stratified
sampling:
• Note: Sampling may not reduce database I/Os (page at a
time) 51
Types of Sampling

• Simple random sampling

– There is an equal probability of selecting any particular
item
• Sampling without replacement
– Once an object is selected, it is removed from the
population
• Sampling with replacement
– A selected object is not removed from the population
• Stratified sampling:
– Partition the data set, and draw samples from each
partition (proportionally, i.e., approximately the same
percentage of the data)
– Used in conjunction with skewed data
52
Sampling: Cluster or Stratified Sampling

Raw Data Cluster/Stratified Sample

53
Data Compression
• String compression
– There are extensive theories and well-tuned algorithms
– Typically lossless, but only limited manipulation is
possible without expansion
• Audio/video compression
– Typically lossy compression, with progressive refinement
– Sometimes small fragments of signal can be
reconstructed without reconstructing the whole
• Time sequence is not audio
– Typically short and vary slowly with time
• Dimensionality and numerosity reduction may also be
considered as forms of data compression
54
Data Compression

Original Data Compressed

Data
lossless

s s y
lo
Original Data
Approximated

55
Chapter 3: Data Preprocessing

 Data Preprocessing: An Overview

 Data Quality

 Major Tasks in Data Preprocessing

 Data Cleaning

 Data Integration

 Data Reduction

 Data Transformation and Data Discretization

 Summary
56
 Data Transformation
• A function that maps the entire set of values of a given attribute to a
new set of replacement values s.t. each old value can be identified
with one of the new values
• Methods
– Smoothing: Remove noise from data
– Attribute/feature construction
• New attributes constructed from the given ones
– Aggregation: Summarization
– Normalization: Scaled to fall within a smaller, specified range
• min-max normalization
• z-score normalization
• normalization by decimal scaling
– Discretization: Concept hierarchy climbing 57
Normalization
 Min-max normalization:

 Z-score normalization

 Normalization by decimal scaling

58
Min-max normalization
Min-max normalization: to [new_minA, new_maxA]
v  minA
v'  (new _ maxA  new _ minA)  new _ minA
maxA  minA

Example: Let income range $12,000 to $98,000 normalized to

[0.0, 1.0]. Then $73,600 is mapped to

73,600  12,000
(1.0  0)  0  0.716
98,000  12,000

8/14/2024
Example

8/14/2024
Z-Score Normalization
Z-score normalization (or standardization) is a technique that transforms data into a
distribution with a mean of 0 and a standard deviation of 1. This method is
particularly useful when the data follows a normal distribution and you want to
compare data points from different distributions.

Z-scores are commonly used to detect outliers in a dataset. Data

points with z-scores that are very high or very low (e.g., greater
than 3 or less than -3) are considered outliers, as they are far from
8/14/2024
the mean.
8/14/2024
Decimal scaling normalization
• Decimal scaling normalization is a method of
normalizing data by moving the decimal point of
values in a dataset. The number of decimal places
moved depends on the maximum absolute value of
the dataset. This technique ensures that all the
normalized values fall within a specific range, typically
between -1 and 1.

8/14/2024
8/14/2024
 Discretization

• Three types of attributes

– Nominal—values from an unordered set, e.g., color, profession
– Ordinal—values from an ordered set, e.g., military or academic
rank
– Numeric—real numbers, e.g., integer or real numbers
• Discretization: Divide the range of a continuous attribute into intervals
– Interval labels can then be used to replace actual data values
– Reduce data size by discretization
– Supervised vs. unsupervised
– Split (top-down) vs. merge (bottom-up)
– Discretization can be performed recursively on an attribute
– Prepare for further analysis, e.g., classification
66
Data Discretization Methods
• Typical methods: All the methods can be applied recursively
– Binning
• Top-down split, unsupervised
– Histogram analysis
• Top-down split, unsupervised
– Clustering analysis (unsupervised, top-down split or
bottom-up merge)
– Decision-tree analysis (supervised, top-down split)
– Correlation (e.g., 2) analysis (unsupervised, bottom-up
merge)

67
 Simple Discretization: Binning

• Equal-width (distance) partitioning

– Divides the range into N intervals of equal size: uniform grid
– if A and B are the lowest and highest values of the attribute, the
width of intervals will be: W = (B –A)/N.
– The most straightforward, but outliers may dominate presentation
– Skewed data is not handled well

• Equal-depth (frequency) partitioning

– Divides the range into N intervals, each containing approximately
same number of samples
– Good data scaling
– Managing categorical attributes can be tricky
68
Binning Methods for Data Smoothing
q Sorted data for price (in dollars): 4, 8, 9, 15, 21, 21, 24, 25, 26, 28,
29, 34
* Partition into equal-frequency (equi-depth) bins:
- Bin 1: 4, 8, 9, 15
- Bin 2: 21, 21, 24, 25
- Bin 3: 26, 28, 29, 34
* Smoothing by bin means:
- Bin 1: 9, 9, 9, 9
- Bin 2: 23, 23, 23, 23
- Bin 3: 29, 29, 29, 29
* Smoothing by bin boundaries:
- Bin 1: 4, 4, 4, 15
- Bin 2: 21, 21, 25, 25
- Bin 3: 26, 26, 26, 34
69
Dision Without Using Class Labels
(Binning vs. Clustering)

Data Equal interval width

(binning)

Equal frequency (binning) K-means clustering leads to better results

70
Discretization by Classification &
Correlation Analysis
• Classification (e.g., decision tree analysis)
– Supervised: Given class labels, e.g., cancerous vs. benign
– Using entropy to determine split point (discretization point)
– Top-down, recursive split
– Details to be covered in Chapter 7
• Correlation analysis (e.g., Chi-merge: χ2-based discretization)
– Supervised: use class information
– Bottom-up merge: find the best neighboring intervals (those
having similar distributions of classes, i.e., low χ2 values) to merge
– Merge performed recursively, until a predefined stopping condition

71
 Concept Hierarchy Generation

• Concept hierarchy organizes concepts (i.e., attribute values)

hierarchically and is usually associated with each dimension in a data
warehouse
• Concept hierarchies facilitate drilling and rolling in data warehouses to
view data in multiple granularity
• Concept hierarchy formation: Recursively reduce the data by collecting
and replacing low level concepts (such as numeric values for age) by
higher level concepts (such as youth, adult, or senior)
• Concept hierarchies can be explicitly specified by domain experts
and/or data warehouse designers
• Concept hierarchy can be automatically formed for both numeric and
nominal data. For numeric data, use discretization methods shown.

72
Concept Hierarchy Generation
for Nominal Data
• Specification of a partial/total ordering of attributes
explicitly at the schema level by users or experts
– street < city < state < country
• Automatic generation of hierarchies (or attribute levels) by
the analysis of the number of distinct values
– E.g., for a set of attributes: {street, city, state, country}

73
Automatic Concept Hierarchy Generation
• Some hierarchies can be automatically generated based on
the analysis of the number of distinct values per attribute in
the data set
– The attribute with the most distinct values is placed at
the lowest level of the hierarchy
– Exceptions, e.g., weekday, month, quarter, year

country 15 distinct values

province_or_ state 365 distinct values

city 3567 distinct values

street 674,339 distinct values

74
Outliers
• An outlier is a value or an entire observation (row) that
lies well outside of the norm.
• Some statisticians define an outlier as any value more
than three standard deviations from the mean, but this is
only a rule of thumb.
• Even if values are not unusual by themselves, there still
might be unusual combinations of values.
• When dealing with outliers, it is best to run the analyses
two ways: with the outliers and without them.
• Let’s just agree to define outliers as extreme values, and
then for any particular data set, you can decide how
extreme a value needs to be to qualified.

8/14/2024
 Boxplot Analysis: (Finding the Outliers)

Five-number summary as follows: Minimum Value, Q1, Median, Q3, Maximum Value

Data is represented with a box

• The ends of the box are at the first and third quartiles, i.e., the height of the box
is IQR. IQR(Interquartile Range) is the basic mathematics behind boxplots.
• The median is marked by a line within the box
• Two lines (called whiskers) outside the box extend to the smallest (Minimum)
and largest (Maximum) observations. The top and bottom whiskers can be
understood as the boundaries of data, and any data lying outside it will be an outlier.
• Outliers: points beyond a specified outlier threshold, plotted individually
Ex:-1 Finding the Outliers
• Consider the data set: 52, 57, 85, 88, 64, 72, 76, 48, 61, 77, 81
• Order of Data Set: 48, 52, 57, 61, 64, 72, 76, 77, 81, 85, 88
• Median (Q2) = 72, Q1 = 57, Q3 = 81
• Therefore IQR =Q3- Q1= 81-57 = 24
• Lower Outlier = Q1 - 1.5 X IQR = 57 - 1.5 X 24 = 21
• Higher Outlier = Q3 + 1.5 X IQR =81 + 1.5 X 24 = 117

• No Outlier, Min Value= 48, Max Value=88

• Q1=1x(n+1)/4
• median=2x(n+1)/4
• Q3=3x(n+1)/4

8/14/2024
Ex:-2 Finding the Outliers
• Consider the data set: 19, 52, 81, 85, 57, 61, 64, 72, 76, 77, 188
• Order of Data Set: 19, 52, 57, 61, 64, 72, 76, 77, 81, 85, 188
• Median (Q2) = 72, Q1 = 57, Q3 = 81,
• Therefore IQR =Q3- Q1= 81-57 = 24
• Lower Outlier = Q1 - 1.5 X IQR = 57 - 1.5 X 24 = 21
• Loower Outlier < 21
• Higher Outlier = Q3 + 1.5 X IQR =81 + 1.5 X 24 = 117
• Higher Outlier> 117
• Outlier = 19, 188, Min Value= 52 , Max Value=85

8/14/2024
Chapter 3: Data Preprocessing

 Data Preprocessing: An Overview

 Data Quality

 Major Tasks in Data Preprocessing

 Data Cleaning

 Data Integration

 Data Reduction

 Data Transformation and Data Discretization

 Summary
79
Summary
• Data quality: accuracy, completeness, consistency, timeliness,
believability, interpretability
• Data cleaning: e.g. missing/noisy values, outliers
• Data integration from multiple sources:
– Entity identification problem
– Remove redundancies
– Detect inconsistencies
• Data reduction
– Dimensionality reduction
– Numerosity reduction
– Data compression
• Data transformation and data discretization
– Normalization
– Concept hierarchy generation
80
 References

• D. P. Ballou and G. K. Tayi. Enhancing data quality in data warehouse environments. Comm. of ACM,
42:73-78, 1999
• A. Bruce, D. Donoho, and H.-Y. Gao. Wavelet analysis. IEEE Spectrum, Oct 1996
• T. Dasu and T. Johnson. Exploratory Data Mining and Data Cleaning. John Wiley, 2003
• J. Devore and R. Peck. Statistics: The Exploration and Analysis of Data. Duxbury Press, 1997.
• H. Galhardas, D. Florescu, D. Shasha, E. Simon, and C.-A. Saita. Declarative data cleaning: Language,
model, and algorithms. VLDB'01
• M. Hua and J. Pei. Cleaning disguised missing data: A heuristic approach. KDD'07
• H. V. Jagadish, et al., Special Issue on Data Reduction Techniques. Bulletin of the Technical
Committee on Data Engineering, 20(4), Dec. 1997
• H. Liu and H. Motoda (eds.). Feature Extraction, Construction, and Selection: A Data Mining
Perspective. Kluwer Academic, 1998
• J. E. Olson. Data Quality: The Accuracy Dimension. Morgan Kaufmann, 2003
• D. Pyle. Data Preparation for Data Mining. Morgan Kaufmann, 1999
• V. Raman and J. Hellerstein. Potters Wheel: An Interactive Framework for Data Cleaning and
Transformation, VLDB’2001
• T. Redman. Data Quality: The Field Guide. Digital Press (Elsevier), 2001
• R. Wang, V. Storey, and C. Firth. A framework for analysis of data quality research. IEEE Trans.
Knowledge and Data Engineering, 7:623-640, 1995
81