Data Preprocessing
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
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
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
Measures for data quality
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 are the data, are they
correct?
Interpretability: how easily the data can be understood?
Value added
Accessibility
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
Data Cleaning
Importance
“Data cleaning is the number one problem in data
warehousing”
Data cleaning tasks – this routine attempts to
Fill in missing values
Identify outliers and smooth out noisy data
Correct inconsistent data
Resolve redundancy caused by data integration
Missing Data
Data is not always available
E.g., many tuples have no recorded values 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
No registered history or changes of the data
Missing data may need to be inferred.
How to Handle Missing Data
1. Ignore the tuple
2. Fill in missing values manually: tedious + infeasible
3. Fill in automatically with a global constant.
4. Fill in with the attribute mean
5. Fill in with the attribute mean for all samples
belonging to the same class as the given tuple
6. Fill in with the most probable value determined with
regression, inference-based such as Bayesian
formula, decision tree.
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
Other data problems which requires data cleaning
duplicate records
incomplete data
inconsistent data
How to Handle Noisy Data
Binning method:
first sort data and partition into (equi-depth) bins
then one can smooth by bin means, smooth by bin median,
smooth by bin boundaries, etc.
Clustering
Similar values are organized into groups (clusters).
Values that fall outside of clusters are considered outliers.
Combined computer and human inspection
detect suspicious values and check by human (e.g., deal with
possible outliers)
Regression
Data can be smoothed by fitting the data to a function such as
with regression. (linear regression/multiple linear regression)
Discretization Method: 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
Binning Methods for Data Smoothing
Sorted data for price : 4, 8, 15, 21, 21, 24, 25, 28, 34
Partition into (equi-depth) bins:
Bin 1: 4, 8, 15
Bin 2: 21, 21, 24
Bin 3: 25, 28, 34
Smoothing by bin means:
Bin 1: 9, 9, 9
Bin 2: 22, 22, 22
Bin 3: 29, 29, 29
Smoothing by bin boundaries:
Bin 1: 4, 4, 15
Bin 2: 21, 21, 24
Bin 3: 25, 25, 34
Data Integration
Data integration:
Combines data from multiple sources(data cubes, multiple db
or flat files)
Issues during data integration
Schema integration
Integrate metadata (about the data) from different sources
Entity identification problem: identify real world entities from
multiple data sources
Detecting and resolving data value conflicts
For the same real world entity, attribute values from different
sources are different, e.g., different scales, metric vs. British
units
Removing duplicates and redundant data
An attribute can be derived from another table (annual revenue)
Inconsistencies in attribute naming
Data Transformation
Smoothing: remove noise from data (binning, clustering,
regression)
Normalization: scaled to fall within a small, specified
range such as –1.0 to 1.0 or 0.0 to 1.0
Attribute/feature construction
New attributes constructed / added from the given ones
Aggregation: summarization or aggregation operations
apply to data
Generalization: concept hierarchy climbing
Low level/ primitive/raw data are replace by higher level
concepts
Data Transformation: Normalization
Useful for classification algorithms involving
Neural networks
Distance measurements (nearest neighbor)
Backpropagation algorithm (NN) – normalizing helps to
speed up the learning phase
Distance-based methods – normalization prevents
attributes with initially large range (i.e. income) from
outweighing attributes with initially smaller ranges (i.e.
binary attribute)
Data Transformation: Normalization
Min-max normalization: to [new_minA, new_maxA]
v minAA
v' (new _ maxAA new _ minAA) new _ minAA
maxAA minAA
Ex. Let income range 12,000 to 98,000 normalized to [0.0,
1.0]. Then 73,000 is mapped to 73,600 12,000 (1.0 0) 0 0.716
98,000 12,000
Z-score normalization (μ: mean, σ: standard deviation):
v A
v'
A
73,600 54,000
Ex. Let μ = 54,000, σ = 16,000. Then 1.225
16,000
Normalization by decimal scaling
v
v' j v'
Where j is the smallest integer such that Max(|
10 |)<1
Data Reduction Strategies
Data is too big to work with – may take time, impractical or
infeasible analysis
Data reduction techniques
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 – apply aggregation operations (data cube)
Dimensionality reduction—remove unimportant attributes
Data compression – encoding mechanism used to reduce data size
Numerosity reduction – data replaced or estimated by alternative,
smaller data representation - parametric model (store model parameter
instead of actual data), non-parametric (clustering sampling,
histogram)
Discretization and concept hierarchy generation – replaced by ranges
or higher conceptual levels
Dimensionality Reduction
Problem: Feature selection (i.e., attribute subset
selection):
Select a minimum set of attributes (features) that is
sufficient for the data mining task.
Best/worst attributes are determined using test of
statistical significance – information gain (building
decision tree for classification)
Solution: Heuristic methods (due to exponential # of
choices – 2d):
step-wise forward selection
step-wise backward elimination
combining forward selection and backward elimination
Data Compression
String compression
There are extensive theories and well-tuned algorithms
Typically lossless
But only limited manipulation is possible without
expansion
Audio/video, image 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
Data Compression
Original Data Compressed
Data
lossless
s s y
lo
Original Data
Approximated
Numerosity Reduction
Reduce the data volume by choosing alternative ‘smaller’
forms of data representation
Two type:
Parametric – a model is used to estimate the data, only
the data parameters is stored instead of actual data
regression
log-linear model
Nonparametric –storing reduced representation of the
data
Histograms
Clustering
Sampling
Histograms
A popular data reduction technique
Divide data into buckets and store average (sum) for each
bucket
Use binning to approximate data distributions
Bucket – horizontal axis, height (area) of bucket – the
average frequency of the values represented by the
bucket
Bucket for single attribute-value/frequency pair –
singleton buckets
Continuous ranges for the given attribute
Clustering
Partition data set into clusters, and one can store cluster
representation only.
Can be very effective if data is clustered but not if data
is “smeared”/ spread.
Can have hierarchical clustering and be stored in multi-
dimensional index tree structures.
There are many choices of clustering definitions and
clustering algorithms
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
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.
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
Discretization and Concept Hierarchy
Discretization
reduce the number of values for a given continuous
attribute by dividing the range of the attribute into
intervals. Interval labels can then be used to replace
actual data values
Concept hierarchies
reduce the data by collecting and replacing low level
concepts (such as numeric values for the attribute age) by
higher level concepts (such as young, middle-aged, or
senior)
Discretization
Three types of attributes:
Nominal — values from an unordered set
Ordinal — values from an ordered set
Continuous — real numbers
Discretization:
divide the range of a continuous attribute into intervals
because some data mining algorithms only accept
categorical attributes.
Some techniques:
Binning methods – equal-width, equal-frequency
Histogram
Entropy-based methods
References
J. Han and M. Kamber. Data Mining: Concepts and
Techniques. Morgan Kaufmann, 2000.
T. Dasu and T. Johnson. Exploratory Data Mining and
Data Cleaning. John Wiley & Sons, 2003
V. Raman and J. Hellerstein. Potters Wheel: An
Interactive Framework for Data Cleaning and
Transformation, VLDB’2001
Jagadish et al., Special Issue on Data Reduction
Techniques. Bulletin of the Technical Committee on
Data Engineering, 20(4), December 1997.
H.V. Jagadish et al., Special Issue on Data Reduction
Techniques. Bulletin of the Technical Committee on
Data Engineering, 20(4), December 1997
