Example of running pGAPPUM algorithm

This example explains how to run pGAPPUM algorithm using PPSF open-source privacy-preserving library.

How to run this example?

  • If you are using the graphical interface, (1) choose the “pGAPPUM” algorithm, (2) select the corresponding input database file and sensitive itemsets fileĀ  , (3) set the output file name (e.g. “output_pGAPPUM.txt”) (4) set w1, w2, w3 to a decimal respectively so that sum of them is 1.(e.g. 0.8, 0.1, 0.1)(5) click “Run algorithm”. Note that the parameters “upper_min” and “sensitive percentage” are set according to the choosed sensitive itemsets file. It means if you input the sensitive itemsets file, these parameters are set automatically according to your input file.
  • If you are using the source code version of SPMF, launch the file “main.java” in the package “PPSF/src/gui”, the next steps are the same as above.

What is the input of pGAPPUM?

The input is a transaction and utility database , a sensitive itemsets database, a minimum utility threshold, a sensitive percentage threshold and three weight numbers w1, w2 and w3.

A transaction and utility database is a set of transactions and total utility of this transaction and total utility of each item. Each transaction is a set of items.The total utility of item is equal to the product of quantity of this item and its utility. The total utility of this tansaction is the sum of utility of itemsets in the transaction. For example, consider the following transaction database.The characters before the first “:” is the name of the items. The number behind the first “:” is the total utility of the transaction. The numbers behind the second “:” is the total utility of each item. In this example, the total utility of transaction is 12285. The total utility if item “1” in “t1” is 76. The total utility of item “2” in “t1” is 175. It is important to note that an item is not allowed to appear twice in the same transaction and that items are assumed to be sorted by lexicographical order in a transaction.

Transaction id Items and total utility
t1 1 3 5 7 … 74:12285:76 175 590 132 … 64
t2 1 3 5 7 … 74:11383:380 35 472 176 … 160
t3 1 3 5 7 … 74:10399:380 140 236 132 … 32
t4 1 3 5 7 … 74:9016:76 175 118 176 … 160
t5 1 3 5 7 … 74:12061:304 35 118 132 … 128

A sensitive itemsets file lists the sensitive itemsets of this dataset. An example is given below.The numbers is the names of items. Each line represents a set of sensitive itemsets.

Sensitive itemsets