random.transactions {arules}R Documentation

Create a Random Transaction Data Set

Description

Creates a random transactions object where all items occur independently of each other.

Usage

random.transactions(nitems, ntrans, prob = 0.1)

Arguments

nitems "integer"; number of items.
ntrans "integer"; number of transactions.
prob "numeric"; occurrence probabilities for items in the transactions. If prob is a vector of length nitems, each value is interpreted as the occurrence probability of the corresponding item. If prob is a scalar, the same given probability is used for all items.

Details

The function generates a nitems times ntrans transaction database. All items are treated as independent. Each transaction is the result of nitems independent Bernoulli trials, one for each item with success probabilities given by prob.

Value

Returns an object of class transactions.

References

Michael Hahsler, Kurt Hornik, and Thomas Reutterer. Implications of probabilistic data modeling for mining association rules. In Proceedings of the 29th Annual Conference of the Gesellschaft fuer Klassifikation e.V., University of Magdeburg, March 9-11, 2005, Studies in Classification, Data Analysis, and Knowledge Organization. Springer-Verlag, 2005. Accepted for publication.

See Also

transactions-class.

Examples

 # generate random 1000 transactions for 200 items with 
 # a success probability decreasing from 0.2 to 0.0001
 trans <- random.transactions(200, 1000, seq(0.2,0.0001, length=200))
 
 # display random data set
 image(trans)

[Package arules version 0.3-0 Index]