Data Organization for Data Analysts
Data Mining Concepts
1. On describing discovered knowledge using association rules
One of the major techniques in data mining involves the discovery of association rules. These rules correlate the presence of a set of items with another range of values for another set of variables. The database in this context is regarded as a collection of transactions, each involving a set of items, as shown below.
Trans ID Items Purchased
101 milk, bread, eggs
102 milk, juice
103 juice, butter
104 milk, bread, eggs
105 coffee, eggs
106 coffee
107 coffee, juice
108 milk, bread, cookies, eggs
109 cookies, butter
110 milk, bread
1.1 Apply the Apriori algorithm on this dataset.
Note that, the set of items is {milk, bread, cookies, eggs, butter, coffee, juice}. You may use 0.2 for the minimum support value.
1.2 Show two rules that have a conftdence of 0.7 or greater for an itemset containing three items.
2. On describing discovered knowledge using classiftcation
Classiftcation is the process of learning a model that describes different classes of data and the classes should be pre-determined. Consider the following set of data records:
|
RID
|
Age
|
City
|
Gender
|
Education
|
Repeat Customer
|
|
101
|
20..30
|
NY
|
F
|
College
|
YES
|
|
102
|
20..30
|
SF
|
M
|
Graduate
|
YES
|
|
103
|
31..40
|
NY
|
F
|
College
|
YES
|
|
104
|
51..60
|
NY
|
F
|
College
|
NO
|
|
105
|
31..40
|
LA
|
M
|
High school
|
NO
|
|
106
|
41..50
|
NY
|
F
|
College
|
YES
|
|
107
|
41..50
|
NY
|
F
|
Graduate
|
YES
|
|
108
|
20..30
|
LA
|
M
|
College
|
YES
|
|
109
|
20..30
|
NY
|
F
|
High school
|
NO
|
|
110
|
20..30
|
NY
|
F
|
college
|
YES
|
2.1 Assuming that the class attribute is Repeat Customer, apply a classiftcation algorithm to this dataset.
3. On describing discovered knowledge using clustering
Consider the following set of two-dimensional records:
|
RID
|
Dimension 1
|
Dimension 2
|
|
1
|
8
|
4
|
|
2
|
5
|
4
|
|
3
|
2
|
4
|
|
4
|
2
|
6
|
|
5
|
2
|
8
|
|
6
|
8
|
6
|
3.1 Use the K-means algorithm to cluster this dataset. You can use a value of 3 for K and can assume that the records with RIDs 1, 3, and 5 are used for the initial cluster centroids (means).
3.2 What is the difference between describing discovered knowledge using clustering and describing it using classiftcation.