Data Mining:

Concepts and Techniques

Jianlin Cheng
Department of Computer Science
University of Missouri, Columbia
Adapted from
©2006 Jiawei Han and Micheline Kamber, All rights reserved
June 19, 2025 Data Mining: Concepts and Techniques 1
 Chapter 2: Data Preprocessing

Why preprocess the data?

Descriptive data summarization

Data cleaning

Data integration and transformation

Data reduction

Discretization and concept hierarchy generation

Summary
June 19, 2025 Data Mining: Concepts and Techniques 2
 Why Data Preprocessing?
• Data in the real world is dirty
• incomplete: lacking attribute values, lacking certain
attributes of interest, or containing only aggregate data
• e.g., occupation=“ ”
• noisy: containing errors or outliers
• e.g., Salary=“-10”
• inconsistent: containing discrepancies in codes or names
• e.g., Age=“42” Birthday=“03/07/1997”
• e.g., Was rating “1,2,3”, now rating “A, B, C”
• e.g., discrepancy between duplicate records

June 19, 2025 Data Mining: Concepts and Techniques 3

 Why Is Data Dirty?
• Incomplete data may come from
• “Not applicable” data value when collected
• Different considerations between the time when the data was collected
and when it is analyzed.
• Human/hardware/software problems
• Noisy data (incorrect values) may come from
• Faulty data collection instruments
• Human or computer error at data entry
• Errors in data transmission
• Inconsistent data may come from
• Different data sources
• Functional dependency violation (e.g., modify some linked data)
• Duplicate records also need data cleaning
June 19, 2025 Data Mining: Concepts and Techniques 4
 Why Is Data Preprocessing
Important?

No quality data, no quality mining results!

Quality decisions must be based on quality data
 e.g., duplicate or missing data may cause incorrect or even
misleading statistics.
Data warehouse needs consistent integration of quality data
Data extraction, cleaning, and transformation comprises the
majority of the work of building a data warehouse

June 19, 2025 Data Mining: Concepts and Techniques 5

 Multi-Dimensional Measure of Data
Quality
A well-accepted multidimensional view:
Accuracy
Completeness
Consistency
Timeliness
Believability
Value added
Interpretability
Accessibility

June 19, 2025 Data Mining: Concepts and Techniques 6

 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 transformation
 Normalization and aggregation
Data reduction
 Obtains reduced representation in volume but produces the same or
similar analytical results
Data discretization
 Part of data reduction but with particular importance, especially for
numerical data

June 19, 2025 Data Mining: Concepts and Techniques 7

 Forms of Data Preprocessing

June 19, 2025 Data Mining: Concepts and Techniques 8

 Chapter 2: Data Preprocessing

Why preprocess the data?

Descriptive data summarization

Data cleaning

Data integration and transformation

Data reduction

Discretization and concept hierarchy generation

Summary
June 19, 2025 Data Mining: Concepts and Techniques 9
 Mining Data Descriptive
Characteristics
 Motivation
 To better understand the data: central tendency, variation and
spread
 Data dispersion characteristics
 median, mean, max, min, quantiles, outliers, variance, etc.
 Numerical dimensions correspond to sorted intervals
 Data dispersion
 Boxplot or quantile analysis on sorted intervals

June 19, 2025 Data Mining: Concepts and Techniques 10

Measuring the Central Tendency

 
1 n x
 Mean (algebraic measure) (sample vs. population): x   xi
n i 1 N
n
 Weighted arithmetic mean: w x i i

 x i 1
Trimmed mean: chopping extreme values n

w
i 1
i

 Median: A holistic measure

 Middle value if odd number of values, or average of the middle two
values otherwise
 Mode
 Value that occurs most frequently in the data
 Unimodal, bimodal, trimodal
 Empirical formula:
mean  mode 3 (mean  median)
June 19, 2025 Data Mining: Concepts and Techniques 11
 Visualization of Data Dispersion: Boxplot
Analysis

June 19, 2025 Data Mining: Concepts and Techniques 12

 Histogram Analysis

Graph displays of basic statistical class descriptions

Frequency histograms
 A univariate graphical method
 Consists of a set of rectangles that reflect the counts or
frequencies of the classes present in the given data

June 19, 2025 Data Mining: Concepts and Techniques 13

Quantile Plot
Displays all of the data (allowing the user to assess both the
overall behavior and unusual occurrences)
Plots quantile information
For a data xi data sorted in increasing order, fi in range [0, 1]
indicates that approximately 100 fi% of the data are below
or equal to the value xi

June 19, 2025 Data Mining: Concepts and Techniques 14

Quantile-Quantile (Q-Q) Plot
Graphs the quantiles of one univariate distribution against the
corresponding quantiles of another
Allows the user to view whether there is a shift in going from
one distribution to another

June 19, 2025 Data Mining: Concepts and Techniques 15

Scatter plot
Provides a first look at bivariate data to see clusters of points,
outliers, etc
Each pair of values is treated as a pair of coordinates and
plotted as points in the plane

June 19, 2025 Data Mining: Concepts and Techniques 16

Loess Curve
Adds a smooth curve to a scatter plot in order to provide
better perception of the pattern of dependence
Loess curve is fitted by setting two parameters: a smoothing
parameter, and the degree of the polynomials that are fitted
by the regression

June 19, 2025 Data Mining: Concepts and Techniques 17

Positively and Negatively Correlated Data

June 19, 2025 Data Mining: Concepts and Techniques 18

June 19, 2025 Data Mining: Concepts and Techniques 19
 Not Correlated Data

June 19, 2025 Data Mining: Concepts and Techniques 20

 Graphic Displays of Basic Statistical
Descriptions

 Histogram
 Boxplot
 Quantile plot:each value xi is paired with fi indicating that approximately 100 fi %
of data are  xi
 Quantile-quantile (q-q) plot: graphs the quantiles of one univariant distribution
against the corresponding quantiles of another
 Scatter plot: each pair of values is a pair of coordinates and plotted as points in
the plane
 Loess (local regression) curve: add a smooth curve to a scatter plot to provide
better perception of the pattern of dependence

June 19, 2025 Data Mining: Concepts and Techniques 21

 Chapter 2: Data Preprocessing

Why preprocess the data?

Descriptive data summarization

Data cleaning

Data integration and transformation

Data reduction

Discretization and concept hierarchy generation

Summary
June 19, 2025 Data Mining: Concepts and Techniques 22
 Data Cleaning
• Importance
• “Data cleaning is one of the three biggest problems in
data warehousing”—Ralph Kimball
• “Data cleaning is the number one problem in data
warehousing”—DCI survey

• Data cleaning tasks

• Fill in missing values
• Identify outliers and smooth out noisy data
• Correct inconsistent data
• Resolve redundancy caused by data integration
June 19, 2025 Data Mining: Concepts and Techniques 23
 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

 Missing data may need to be inferred.

June 19, 2025 Data Mining: Concepts and Techniques 24

Customer Data
Name Age Sex Income Class
Mike 40 Male 150k Big spender
Jenny 20 Female ? Regular
…

June 19, 2025 Data Mining: Concepts and Techniques 25

 How to Handle Missing
Data?
• Ignore the tuple: usually done when class label is missing (assuming the tasks
in classification—not effective when the percentage 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 (e.g., predict my age based on the info at my web site?)

June 19, 2025 Data Mining: Concepts and Techniques 26

 Noisy Data
Noise: random error or variance in a measured variable
Incorrect attribute values may due to
faulty data collection instruments
data entry problems
data transmission problems
technology limitation
inconsistency in naming convention

June 19, 2025 Data Mining: Concepts and Techniques 27

 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)

June 19, 2025 Data Mining: Concepts and Techniques 28

 Data Cleaning as a Process
 Data discrepancy detection
 Use metadata (e.g., domain, range, dependency, distribution) (How
many people are there in Nebraska?)
 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)

June 19, 2025 Data Mining: Concepts and Techniques 29

 Chapter 2: Data Preprocessing

Why preprocess the data?

Data cleaning

Data integration and transformation

Data reduction

Discretization and concept hierarchy generation

Summary

June 19, 2025 Data Mining: Concepts and Techniques 30

 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 (e.g., GPA in US and China)

June 19, 2025 Data Mining: Concepts and Techniques 31

 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
• Careful integration of the data from multiple sources may help
reduce/avoid redundancies and inconsistencies and improve
mining speed and quality
June 19, 2025 Data Mining: Concepts and Techniques 32
 Correlation Analysis (Numerical
Data)

• Correlation coefficient (also called Pearson’s product moment

coefficient)

rA, B 
 (A  A)( B  B )

 ( AB)  n AB
( n  1)AB ( n  1)AB

A B
where n is the number of tuples, and are the respective means of A
and B, σA and σB are the respective standard deviation of A and B, and
Σ(AB) is the sum of the AB cross-product.

• If rA,B > 0, A and B are positively correlated (A’s values increase as

B’s). The higher, the stronger correlation.
• rA,B = 0: independent;DatarA,B
June 19, 2025
< 0: negatively correlated
Mining: Concepts and Techniques 33
Correlation Analysis (Categorical Data)

• Χ2 (chi-square) test (Example: Grade and Sex)

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

June 19, 2025 Data Mining: Concepts and Techniques 34

 Data Transformation

Smoothing: remove noise from data

Aggregation: summarization
Generalization: concept hierarchy climbing
Normalization: scaled to fall within a small, specified range
min-max normalization
z-score normalization
normalization by decimal scaling
Attribute/feature construction
New attributes constructed from the given ones

June 19, 2025 Data Mining: Concepts and Techniques 35

Data Transformation: Normalization
• Min-max normalization: to [new_minA, new_maxA]
v  minA
v'  (new _ maxA  new _ minA)  new _ minA
maxA  minA
• Ex. Let income range $12,000 to $98,000 normalized to [0.0, 1.0]. Then
73,600  12,000
(1.0  0)  0 0.716
$73,000 is mapped to 98,000  12,000

• Z-score normalization (μ: mean, σ: standard deviation):

v  A
v' 
 A

73,600  54,000
1.225
• Ex. Let μ = 54,000, σ = 16,000. Then 16,000

• Normalization
v by decimal scaling
v'  Where j is the smallest integer such that Max(|ν’|) < 1
10 j
June 19, 2025 Data Mining: Concepts and Techniques 36
 Chapter 2: Data Preprocessing

Why preprocess the data?

Data cleaning

Data integration and transformation

Data reduction

Discretization and concept hierarchy generation

Summary

June 19, 2025 Data Mining: Concepts and Techniques 37

 Data Reduction Strategies

• Why data reduction?

• A database/data warehouse may store terabytes of data
• Complex data analysis/mining may take a very long time to run on the
complete data set
• Data reduction
• Obtain a reduced representation of the data set that is much smaller in
volume but yet produce the same (or almost the same) analytical
results
• Data reduction strategies
• Data cube aggregation:
• Dimensionality reduction — e.g., remove unimportant attributes
• Data Compression
• Numerosity reduction — e.g., fit data into models
• Discretization and concept hierarchy generation

June 19, 2025 Data Mining: Concepts and Techniques 38

 Data Cube Aggregation
 The lowest level of a data cube (base
cuboid)
 The aggregated data for an individual
entity of interest
 Multiple levels of aggregation in data cubes
 Further reduce the size of data to deal
with

June 19, 2025 Data Mining: Concepts and Techniques 39

 Attribute Subset Selection
Feature selection (i.e., attribute subset selection):
Select a minimum set of features such that the probability
distribution of different classes given the values for those
features is as close as possible to the original distribution
given the values of all features
reduce # of patterns in the patterns, easier to understand
Heuristic methods (due to exponential # of choices):
Step-wise forward selection
Step-wise backward elimination
Combining forward selection and backward elimination
Decision-tree induction

June 19, 2025 Data Mining: Concepts and Techniques 40