ASparameter-class {arules}R Documentation

Classes “ASparameter”, “APparameter”, “ECparameter” - Specifying the 'parameter' Argument of apriori() and eclat()

Description

The ASparameter class holds the mining parameters (e.g., minimum support) for the used mining algorithms. APparameter and ECparameter directly extend ASparameter with additional slots for parameters only suitable for the Apriori (APparameter) or the Eclat algorithms (ECparameter).

Objects from the Class

A suitable default parameter object will be automatically created by the apriori or the eclat function. By specifying a named list (names equal to slots) as parameter argument for the apriori or the eclat function, default values can be replaced by the values in the list. Objects can be created by calls of the form new("APparameter", ...) or new("ECparameter", ...).

Slots

Common slots defined in ASparameter:

support:
"numeric"; minimal support of an item set (default: 0.1)
minlen:
"integer"; minimal number of items per item set (default: 1)
maxlen:
"integer"; maximal number of items per item set (default: 5)
target:
"character"; indicates the type of association mined. One of
ext:
"logical"; produce extended information on quality measures (e.g., lhs.support) (default: FALSE)

Additional slots for Apriori in APparameter:

confidence:
"numeric"; minimal confidence of rules/association hyperedges (default: 0.8)
smax:
"numeric"; maximal support of itemsets/rules/hyperedgesets (default: 1)
arem:
"character"; additional rule evaluation measure (default: none) given by one of
"none":
no additional evaluation measure
"diff":
absolute confidence difference
"quot":
difference of confidence quotient to 1
"aimp":
absolute difference of improvement to 1
"info":
information difference to prior
"chi2":
normalized chi^2 measure
aval:
"logical"; return the additional rule evaluation measure selected with arem.
minval:
"numeric"; minimal value of additional evaluation measure selected with arem (default: 0.1)
originalSupport:
"logical"; use for minimum support the original definition of the support of a rule (lhs and rhs) instead of lhs support. Make sure to use ext = TRUE if originalSupport is set to FALSE (default: TRUE)

Additional slots for Eclat in ECparameter:

tidList:
"logical"; return also a list of supporting transactions (transaction IDs) (default: FALSE)

Methods

coerce
signature(from = "NULL", to = "APparameter")
coerce
signature(from = "list", to = "APparameter")
coerce
signature(from = "NULL", to = "ECparameter")
coerce
signature(from = "list", to = "ECparameter")
show
signature(object = "ASparameter")

Author(s)

Bettina Gruen and Michael Hahsler

References

Christian Borgelt (2004). Apriori — Finding Association Rules/Hyperedges with the Apriori Algorithm. http://fuzzy.cs.uni-magdeburg.de/~borgelt/apriori.html

See Also

apriori, eclat


[Package arules version 0.1-1 Index]