Search for question
Question

Assignment #4:

1. This problem uses the data table provided. Consider the first 5 records as the entirety of the table. (The

main purpose of part (a) of this problem is to explain the relation between the file of "items" that Apriori

and FP-growth work on, and data files such as this one.)

Interpreting the records of a file as sets of items: the set of all items is the union of the sets of values

appearing in the attributes.

Note 1: RecordID is not to be considered an attribute.

Note 2: Because columns 3 and 5 have values in common, recode values in column 3 as "no3" and "yes3"

and values in column 5 as "no5" and "yes5".

Thus the set of items is (youth, mid-aged, senior; high, ...; no5, yes5}.

(a) The first record, as a set of items, is {youth, high, no3, fair, no5}. Write the remaining 4 records of the

(truncated) file as sets of items. (16 pts)

(b) Letting the minimum support be 3 records, find F1, C2, F2, C3, and F3 (or, using the notation of pages

249-253 of the text, L1;C2; L2;C3;L3). (20 pts)

Fig: 1