Mining Associations with Eclat
Mine frequent itemsets with the Eclat algorithm. This algorithm uses simple intersection operations for equivalence class clustering along with bottom-up lattice traversal.
eclat(data, parameter = NULL, control = NULL)
data |
object of class
|
parameter |
object of class
|
control |
object of class
|
Calls the C implementation of the Eclat algorithm by Christian Borgelt for mining frequent itemsets.
Eclat can also return the transaction IDs for each found itemset using
tidLists=TRUE as a parameter and the result can be retrieved
as a tidLists object with method
tidLists() for class itemsets.
Note that storing transaction ID lists is very memory intensive,
creating transaction ID lists only works for minimum
support values which create a relatively small number of itemsets.
See also supportingTransactions.
ruleInduction can be used to generate rules from the found itemsets.
A weighted version of ECLAT is available as function weclat.
This version can be used to perform weighted association rule mining (WARM).
Returns an object of class itemsets.
Michael Hahsler and Bettina Gruen
Mohammed J. Zaki, Srinivasan Parthasarathy, Mitsunori Ogihara, and Wei Li. (1997) New algorithms for fast discovery of association rules. KDD'97: Proceedings of the Third International Conference on Knowledge Discovery and Data Mining, August 1997, Pages 283-286.
Christian Borgelt (2003) Efficient Implementations of Apriori and Eclat. Workshop of Frequent Item Set Mining Implementations (FIMI 2003, Melbourne, FL, USA).
ECLAT Implementation: https://borgelt.net/eclat.html
data("Adult")
## Mine itemsets with minimum support of 0.1 and 5 or less items
itemsets <- eclat(Adult,
parameter = list(supp = 0.1, maxlen = 5))
itemsets
## Create rules from the itemsets
rules <- ruleInduction(itemsets, Adult, confidence = .9)
rulesPlease choose more modern alternatives, such as Google Chrome or Mozilla Firefox.