Presentation on theme: "A Brief Tour of Rs arules package July 2012 Stu Rodgers."— Presentation transcript:
A Brief Tour of Rs arules package July 2012 Stu Rodgers
Package arules Mining frequent itemsets and association rules is a popular and well researched approach for discovering interesting relationships between variables in large databases. –provides a basic infrastructure for creating and manipulating input data sets and for analyzing the resulting itemsets and rules. > library(arules) Loading required package: Matrix Loading required package: lattice Attaching package: Matrix The following object(s) are masked from package:base: det Attaching package: arules The following object(s) are masked from package:base: %in% Warning message: package arules was built under R version
Data in arules > data() Data sets in package arules: Adult Adult Data Set AdultUCI Adult Data Set Epub Epub Data Set Groceries Groceries Data Set Income Income Data Set IncomeESL Income Data Set...
Using arules > data("Epub") > ls()  "Epub" > summary(Epub) transactions as itemMatrix in sparse format with rows (elements/itemsets/transactions) and 936 columns (items) and a density of most frequent items: doc_11d doc_813 doc_4c6 doc_955 doc_698 (Other) element (itemset/transaction) length distribution: sizes Notes – Epub contains downloads of documents from the Electronic Publication platform of the Vienna University of Economics and Business available via from January 2003 to December 2008.http://epub.wu-wien.ac.at
Using arules > summary(Epub) -- continued Min. 1st Qu. Median Mean 3rd Qu. Max includes extended item information - examples: labels 1 doc_11d 2 doc_13d 3 doc_14c includes extended transaction information - examples: transactionID TimeStamp session_ :59: session_ :46: session_479a :50:38
Using arules > year <- strftime(as.POSIXlt(transactionInfo(Epub)[["TimeStamp"]]), "%Y") > table(year) year > Epub2003 <- Epub[year == "2003"] > length(Epub2003)  987 > image(Epub2003) Notes –strftime - converts between strings and POSIXlt class objects –POSIXlt - objects for representing calendar dates and times (to nearest second) –"%Y" – 4 digit year
Visualizing transactions > image(Epub2003)
Using arules > data(AdultUCI") > dim(AdultUCI)  > R demo... Notes – AdultUCI - UCI machine learning repository (Asuncion and Newman 2007) of U.S. census bureau database. Contains attributes like age, work class, education, etc. In the original applications of the data, the attributes were used to predict the income level of individuals.