Data Preprocessing

Question 1

7 DATA PROCESSING TASKS / METHODS

Answer 1

1. Aggregation
2. Sampling
3. Dimensionality Reduction
4. Feature Subset Selection
5. Feature Creation
6. Discretization and Binarization
7. Attribute Transformation

Question 2

combining two or more attributes into a single attribute.

Answer 2

Aggregation

Question 3

3 PURPOSE OF AGGREGATION

Answer 3

• Data Reduction
• Change of Scale
• More Stable Data

Question 4

is the main technique employe for data selection.

Answer 4

Sampling

Question 5

4 TYPES OF SAMPLING

Answer 5

• Sampling without replacement
• Sampling with replacement
• Simple Random Sampling
• Stratified Sampling

Question 6

a type of sampling where each item is selected, it is removed from the population.

Answer 6

Sampling with replacement

Question 7

a type of sampling where objects are not removed from the population as they are selected.

Answer 7

Sampling without replacement

Question 8

a type of sampling where there is an equal probability of selecting any particular items.

Answer 8

Simple Random Sampling

Question 9

a type of sampling where it splits the data into several partitions, then drawn random samples from each partition.

Answer 9

Stratified Sampling

Question 10

is the number of samples in a data set.

Answer 10

SAMPLE SIZE

Question 11

2 SAMPLE SIZE DETERMINATION

Answer 11

• Statistics
• Machine Learning

Question 12

a determination where it implies the confidence interval, for parameter estimate or desires statistical power of test.

Answer 12

Statistics

Question 13

a determination where it implies that often more is better, cross-validated accuracy.

Answer 13

Machine Learning

Question 14

when dimensionality increases, the size of the data space grows exponentially.

Answer 14

Curse of Dimensionality

Question 15

its purpose of to avoid the curse of dimensionality.

Answer 15

Dimensionality Reduction

Question 16

Reduces the amount of time and memory required by data mining algorithms.

Answer 16

Dimensionality Reduction

Question 17

3 TECHNIQUES FOR DIMENSION REDUCTION

Answer 17

1. Principal Component Analysis
2. ISOMAP
3. Low Dimensional Embedding

Question 18

is another way to reduce dimensionality of data.

Answer 18

Feature Subset Selection

Question 19

2 TYPES OF FEATURES

Answer 19

1. Redundant Features
2. Irrelevant Features

Question 20

is a type of feature where there are many duplicate or all of the information contained in one or more other attribute.

Answer 20

Redundant Features

Question 21

is a type of feature where it contains no information that is useful foe the data mining task at hand.

Answer 21

Irrelevant Features

Question 22

4 APPROACHES IN FEATURE SUBSET SELECTION

Answer 22

1. Embedded Approach
2. Filter Approach
3. Brute-force Approach
4. Wrapper Approach

Question 23

feature selection occurs naturally as part of the data mining algorithm,

Answer 23

Embedded Approach

Question 24

features are selected before data mining algorithm is run.

Answer 24

Filter Approach

Question 25

try all possible feature subsets as input to data mining algorithm and choose the best.

Answer 25

Brute-force Approach

Question 26

use the data mining algorithm as a black box to find bests subsets of attributes.

Answer 26

Wrapper Approach

Question 27

creates new attributes that can capture the important information in a data set much more efficiently than the original attributes.

Answer 27

Feature Creation

Question 28

3 GENERAL METHODOLOGIES FOR FEATURE CREATION

Answer 28

1. Feature Extraction
2. Feature Construction / Feature Engineering
3. Mapping Data to New Space

Question 29

is a methodology in feature selection where it is domain specific.

Answer 29

Feature Extraction

Question 30

is a methodology in feature extraction where it combines features.

Answer 30

Feature Construction / Feature Engineering

Question 31

2 WAYS OF MAPPING DATA TO NEW SPACE

Answer 31

• Fourier Transform
• Wavelet Transfor

Question 32

a function that maps the entire set of values of a given attributes to a new set of replacement values such that each old value can be identifies with one of the new values.

Answer 32

Attribute Transformation

Question 33

are numerical measure of how alike two data objects are.

Answer 33

Similarity

Question 34

numerical measure of how different two data objects are.

Answer 34

Dissimilarity

Question 35

refers to a similarity or dissimilarity.

Answer 35

Proximity

Question 36

6 METHODS TO KNOW THE SIMILARITY OR DISSIMILARITY:

Answer 36

• Euclidean Distance
• Mikowski Distance
• Mahalanobis Distance
• Cosine Similarity
• Correlation
• Rank Correlation

Question 37

is the generalization of Euclidean.

Answer 37

Mikowski Distance

Question 38

measures the linear relationship between two variables.

Answer 38

Correlation

Question 39

measures the degree of similarity between two ratings.

Answer 39

Rank Correlation

Question 40

describes the likelihood of a random variable taking a given value.

Answer 40

Probability Density (Function)

Question 41

is a non-parametric way to estimate the probability density function of a random variable.

Answer 41

Kernel Desnity Estimation

Question 42

implies that the simplest approach is to divide region into a number of rectangular cells of equal volume and define density as # of points the cell contains.

Answer 42

Euclidean Density - Cell-Based

Question 43

implies that the Euclidean density is the number of points within a specified radius of the point.

Answer 43

Euclidean Density - Center-Based