public class Apriori extends AbstractAssociator implements OptionHandler, CARuleMiner, TechnicalInformationHandler
@inproceedings{Agrawal1994, author = {R. Agrawal and R. Srikant}, booktitle = {20th International Conference on Very Large Data Bases}, pages = {478-499}, publisher = {Morgan Kaufmann, Los Altos, CA}, title = {Fast Algorithms for Mining Association Rules in Large Databases}, year = {1994} } @inproceedings{Liu1998, author = {Bing Liu and Wynne Hsu and Yiming Ma}, booktitle = {Fourth International Conference on Knowledge Discovery and Data Mining}, pages = {80-86}, publisher = {AAAI Press}, title = {Integrating Classification and Association Rule Mining}, year = {1998} }Valid options are:
-N <required number of rules output> The required number of rules. (default = 10)
-T <0=confidence | 1=lift | 2=leverage | 3=Conviction> The metric type by which to rank rules. (default = confidence)
-C <minimum metric score of a rule> The minimum confidence of a rule. (default = 0.9)
-D <delta for minimum support> The delta by which the minimum support is decreased in each iteration. (default = 0.05)
-U <upper bound for minimum support> Upper bound for minimum support. (default = 1.0)
-M <lower bound for minimum support> The lower bound for the minimum support. (default = 0.1)
-S <significance level> If used, rules are tested for significance at the given level. Slower. (default = no significance testing)
-I If set the itemsets found are also output. (default = no)
-R Remove columns that contain all missing values (default = no)
-V Report progress iteratively. (default = no)
-A If set class association rules are mined. (default = no)
-c <the class index> The class index. (default = last)
Modifier and Type | Field and Description |
---|---|
static Tag[] |
TAGS_SELECTION
Metric types.
|
Constructor and Description |
---|
Apriori()
Constructor that allows to sets default values for the minimum confidence
and the maximum number of rules the minimum confidence.
|
Modifier and Type | Method and Description |
---|---|
void |
buildAssociations(Instances instances)
Method that generates all large itemsets with a minimum support, and from
these all association rules with a minimum confidence.
|
java.lang.String |
carTipText()
Returns the tip text for this property
|
java.lang.String |
classIndexTipText()
Returns the tip text for this property
|
java.lang.String |
deltaTipText()
Returns the tip text for this property
|
FastVector[] |
getAllTheRules()
returns all the rules
|
Capabilities |
getCapabilities()
Returns default capabilities of the classifier.
|
boolean |
getCar()
Gets whether class association ruels are mined
|
int |
getClassIndex()
Gets the class index
|
double |
getDelta()
Get the value of delta.
|
Instances |
getInstancesNoClass()
Gets the instances without the class atrribute.
|
Instances |
getInstancesOnlyClass()
Gets only the class attribute of the instances.
|
double |
getLowerBoundMinSupport()
Get the value of lowerBoundMinSupport.
|
SelectedTag |
getMetricType()
Get the metric type
|
double |
getMinMetric()
Get the value of minConfidence.
|
int |
getNumRules()
Get the value of numRules.
|
java.lang.String[] |
getOptions()
Gets the current settings of the Apriori object.
|
boolean |
getOutputItemSets()
Gets whether itemsets are output as well
|
boolean |
getRemoveAllMissingCols()
Returns whether columns containing all missing values are to be removed
|
java.lang.String |
getRevision()
Returns the revision string.
|
double |
getSignificanceLevel()
Get the value of significanceLevel.
|
TechnicalInformation |
getTechnicalInformation()
Returns an instance of a TechnicalInformation object, containing detailed
information about the technical background of this class, e.g., paper
reference or book this class is based on.
|
double |
getUpperBoundMinSupport()
Get the value of upperBoundMinSupport.
|
boolean |
getVerbose()
Gets whether algorithm is run in verbose mode
|
java.lang.String |
globalInfo()
Returns a string describing this associator
|
java.util.Enumeration |
listOptions()
Returns an enumeration describing the available options.
|
java.lang.String |
lowerBoundMinSupportTipText()
Returns the tip text for this property
|
static void |
main(java.lang.String[] args)
Main method.
|
java.lang.String |
metricString()
Returns the metric string for the chosen metric type
|
java.lang.String |
metricTypeTipText()
Returns the tip text for this property
|
FastVector[] |
mineCARs(Instances data)
Method that mines all class association rules with minimum support and with
a minimum confidence.
|
java.lang.String |
minMetricTipText()
Returns the tip text for this property
|
java.lang.String |
numRulesTipText()
Returns the tip text for this property
|
java.lang.String |
outputItemSetsTipText()
Returns the tip text for this property
|
java.lang.String |
removeAllMissingColsTipText()
Returns the tip text for this property
|
void |
resetOptions()
Resets the options to the default values.
|
void |
setCar(boolean flag)
Sets class association rule mining
|
void |
setClassIndex(int index)
Sets the class index
|
void |
setDelta(double v)
Set the value of delta.
|
void |
setLowerBoundMinSupport(double v)
Set the value of lowerBoundMinSupport.
|
void |
setMetricType(SelectedTag d)
Set the metric type for ranking rules
|
void |
setMinMetric(double v)
Set the value of minConfidence.
|
void |
setNumRules(int v)
Set the value of numRules.
|
void |
setOptions(java.lang.String[] options)
Parses a given list of options.
|
void |
setOutputItemSets(boolean flag)
Sets whether itemsets are output as well
|
void |
setRemoveAllMissingCols(boolean r)
Remove columns containing all missing values.
|
void |
setSignificanceLevel(double v)
Set the value of significanceLevel.
|
void |
setUpperBoundMinSupport(double v)
Set the value of upperBoundMinSupport.
|
void |
setVerbose(boolean flag)
Sets verbose mode
|
java.lang.String |
significanceLevelTipText()
Returns the tip text for this property
|
java.lang.String |
toString()
Outputs the size of all the generated sets of itemsets and the rules.
|
java.lang.String |
upperBoundMinSupportTipText()
Returns the tip text for this property
|
java.lang.String |
verboseTipText()
Returns the tip text for this property
|
forName, makeCopies, makeCopy
public static final Tag[] TAGS_SELECTION
public Apriori()
public java.lang.String globalInfo()
public TechnicalInformation getTechnicalInformation()
getTechnicalInformation
in interface TechnicalInformationHandler
public void resetOptions()
public Capabilities getCapabilities()
getCapabilities
in interface Associator
getCapabilities
in interface CapabilitiesHandler
getCapabilities
in class AbstractAssociator
Capabilities
public void buildAssociations(Instances instances) throws java.lang.Exception
buildAssociations
in interface Associator
instances
- the instances to be used for generating the associationsjava.lang.Exception
- if rules can't be built successfullypublic FastVector[] mineCARs(Instances data) throws java.lang.Exception
mineCARs
in interface CARuleMiner
data
- the instances for which class association rules should be minedjava.lang.Exception
- if rules can't be built successfullypublic Instances getInstancesNoClass()
getInstancesNoClass
in interface CARuleMiner
public Instances getInstancesOnlyClass()
getInstancesOnlyClass
in interface CARuleMiner
public java.util.Enumeration listOptions()
listOptions
in interface OptionHandler
public void setOptions(java.lang.String[] options) throws java.lang.Exception
-N <required number of rules output> The required number of rules. (default = 10)
-T <0=confidence | 1=lift | 2=leverage | 3=Conviction> The metric type by which to rank rules. (default = confidence)
-C <minimum metric score of a rule> The minimum confidence of a rule. (default = 0.9)
-D <delta for minimum support> The delta by which the minimum support is decreased in each iteration. (default = 0.05)
-U <upper bound for minimum support> Upper bound for minimum support. (default = 1.0)
-M <lower bound for minimum support> The lower bound for the minimum support. (default = 0.1)
-S <significance level> If used, rules are tested for significance at the given level. Slower. (default = no significance testing)
-I If set the itemsets found are also output. (default = no)
-R Remove columns that contain all missing values (default = no)
-V Report progress iteratively. (default = no)
-A If set class association rules are mined. (default = no)
-c <the class index> The class index. (default = last)
setOptions
in interface OptionHandler
options
- the list of options as an array of stringsjava.lang.Exception
- if an option is not supportedpublic java.lang.String[] getOptions()
getOptions
in interface OptionHandler
public java.lang.String toString()
toString
in class java.lang.Object
public java.lang.String metricString()
metricString
in interface CARuleMiner
public java.lang.String removeAllMissingColsTipText()
public void setRemoveAllMissingCols(boolean r)
r
- true if cols are to be removed.public boolean getRemoveAllMissingCols()
public java.lang.String upperBoundMinSupportTipText()
public double getUpperBoundMinSupport()
public void setUpperBoundMinSupport(double v)
v
- Value to assign to upperBoundMinSupport.public void setClassIndex(int index)
setClassIndex
in interface CARuleMiner
index
- the class indexpublic int getClassIndex()
public java.lang.String classIndexTipText()
public void setCar(boolean flag)
flag
- if class association rules are mined, false otherwisepublic boolean getCar()
public java.lang.String carTipText()
public java.lang.String lowerBoundMinSupportTipText()
public double getLowerBoundMinSupport()
public void setLowerBoundMinSupport(double v)
v
- Value to assign to lowerBoundMinSupport.public SelectedTag getMetricType()
public java.lang.String metricTypeTipText()
public void setMetricType(SelectedTag d)
d
- the type of metricpublic java.lang.String minMetricTipText()
public double getMinMetric()
public void setMinMetric(double v)
v
- Value to assign to minConfidence.public java.lang.String numRulesTipText()
public int getNumRules()
public void setNumRules(int v)
v
- Value to assign to numRules.public java.lang.String deltaTipText()
public double getDelta()
public void setDelta(double v)
v
- Value to assign to delta.public java.lang.String significanceLevelTipText()
public double getSignificanceLevel()
public void setSignificanceLevel(double v)
v
- Value to assign to significanceLevel.public void setOutputItemSets(boolean flag)
flag
- true if itemsets are to be output as wellpublic boolean getOutputItemSets()
public java.lang.String outputItemSetsTipText()
public void setVerbose(boolean flag)
flag
- true if algorithm should be run in verbose modepublic boolean getVerbose()
public java.lang.String verboseTipText()
public FastVector[] getAllTheRules()
m_allTheRules
public java.lang.String getRevision()
getRevision
in interface RevisionHandler
getRevision
in class AbstractAssociator
public static void main(java.lang.String[] args)
args
- the commandline options