ABB_IEP_FS KEEL Preprocess Algorithm

Description

ABB_IEP_FS Preprocess Algorithm from KEEL.

Usage

ABB_IEP_FS(train, test, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::ABB_IEP_FS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

ANR_F KEEL Preprocess Algorithm

Description

ANR_F Preprocess Algorithm from KEEL.

Usage

ANR_F(train, test, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("zoo")
data_test <- RKEEL::loadKeelDataset("zoo")
  
#Create algorithm
algorithm <- RKEEL::ANR_F(data_train, data_test)
  
#Run algorithm
algorithm$run()
  
#See results
algorithm$preprocessed_test

ART_C KEEL Classification Algorithm

Description

ART_C Classification Algorithm from KEEL.

Usage

ART_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::ART_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

AdaBoostNC_C KEEL Classification Algorithm

Description

AdaBoostNC_C Classification Algorithm from KEEL.

Usage

AdaBoostNC_C(train, test, pruned, confidence, instancesPerLeaf,
   numClassifiers, algorithm, trainMethod, lambda, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::AdaBoostNC_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

AdaBoost_I KEEL Imbalanced Classification Algorithm

Description

AdaBoost_I Imbalanced Classification Algorithm from KEEL.

Usage

AdaBoost_I(train, test, pruned, confidence, instancesPerLeaf,
   numClassifiers, algorithm, trainMethod, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::AdaBoost_I(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Alatasetal_A KEEL Association Rules Algorithm

Description

Alatasetal_A Association Rules Algorithm from KEEL.

Usage

Alatasetal_A(dat, seed, NumberofEvaluations, InitialRandomChromosomes,
  rDividingPoints, TournamentSize, ProbabilityofCrossover,
  MinimumProbabilityofMutation, MaximumProbabilityofMutation,
  ImportanceofRulesSupport, ImportanceofRulesConfidence,
  ImportanceofNumberofInvolvedAttributes, ImportanceofIntervalsAmplitude,
  ImportanceofNumberofRecordsAlreadyCovered, AmplitudeFactor)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::Alatasetal_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

Alcalaetal_A KEEL Association Rules Algorithm

Description

Alcalaetal_A Association Rules Algorithm from KEEL.

Usage

Alcalaetal_A(dat, seed, NumberofEvaluations, PopulationSize, NumberofBitsperGene, 
  DecreasingFactorofLthresholdNOTUSED, FactorforParentCentricBLXCrossover, 
  NumberofFuzzyRegionsforNumericAttributes, UseMaxOperatorfor1FrequentItemsets, 
  MinimumSupport, MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::Alcalaetal_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

AllKNN_TSS KEEL Preprocess Algorithm

Description

AllKNN_TSS Preprocess Algorithm from KEEL.

Usage

AllKNN_TSS(train, test, k, distance)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::AllKNN_TSS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

AllPosible_MV KEEL Preprocess Algorithm

Description

AllPosible_MV Preprocess Algorithm from KEEL.

Usage

AllPosible_MV(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::AllPosible_MV(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

Apriori_A KEEL Association Rules Algorithm

Description

Apriori_A Association Rules Algorithm from KEEL.

Usage

Apriori_A(dat, NumberofPartitionsforNumericAttributes, MinimumSupport, 
  MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::Apriori_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

Association Rules Algorithm

Description

Class inheriting of KeelAlgorithm, to common methods for all KEEL Association Rules Algorithms. The specific association rules algorithms must inherit of this class.

The run() method receives three parameters. The folderPath parameter indicates where to place the folder with the experiments if wanted. If it is not indicated, the folder is placen ind a temporary random directory and then removed. If indicated, the experiment folder is not removed. The expUniqueName parameter indicates the name of the experiment folder. If not indicated, it is a random name. If indicated, ensure that the name is unique in the previously indicated folder. The javaOptions parameter indicates, if wanted, extra parameters to the java command line, as for example the maximum memory allowed by java.

Associative Classification Algorithm

Description

Class inheriting of ClassificationAlgorithm, to common methods for Associative Classification Algorithms.

The run() method receives three parameters. The folderPath parameter indicates where to place the folder with the experiments if wanted. If it is not indicated, the folder is placen ind a temporary random directory and then removed. If indicated, the experiment folder is not removed. The expUniqueName parameter indicates the name of the experiment folder. If not indicated, it is a random name. If indicated, ensure that the name is unique in the previously indicated folder. The javaOptions parameter indicates, if wanted, extra parameters to the java command line, as for example the maximum memory allowed by java.

BNGE_C KEEL Classification Algorithm

Description

BNGE_C Classification Algorithm from KEEL.

Usage

BNGE_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::BNGE_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

BSE_C KEEL Classification Algorithm

Description

BSE_C Classification Algorithm from KEEL.

Usage

BSE_C(train, test, k, distance)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::BSE_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Bayesian_D KEEL Preprocess Algorithm

Description

Bayesian_D Preprocess Algorithm from KEEL.

Usage

Bayesian_D(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::Bayesian_D(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

Bojarczuk_GP_C KEEL Classification Algorithm

Description

Bojarczuk_GP_C Classification Algorithm from KEEL.

Usage

Bojarczuk_GP_C(train, test, population_size, max_generations,
   max_deriv_size, rec_prob, copy_prob, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::Bojarczuk_GP_C(data_train, data_test)
algorithm <- RKEEL::Bojarczuk_GP_C(data_train, data_test, population_size=5, max_generations=10)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

C45Binarization_C KEEL Classification Algorithm

Description

C45Binarization_C Classification Algorithm from KEEL.

Usage

C45Binarization_C(train, test, pruned, confidence, instancesPerLeaf,
   binarization, scoreFunction, bts)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")
  
#Create algorithm
algorithm <- RKEEL::C45Binarization_C(data_train, data_test)
  
#Run algorithm
algorithm$run()
  
#See results
algorithm$testPredictions

C45Rules_C KEEL Classification Algorithm

Description

C45Rules_C Classification Algorithm from KEEL.

Usage

C45Rules_C(train, test, confidence, itemsetsPerLeaf, threshold,
   seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::C45Rules_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

C45_C KEEL Classification Algorithm

Description

C45_C Classification Algorithm from KEEL.

Usage

C45_C(train, test, pruned, confidence, instancesPerLeaf)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::C45_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CART_C KEEL Classification Algorithm

Description

CART_C Classification Algorithm from KEEL.

Usage

CART_C(train, test, maxDepth)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CART_C(data_train, data_test, maxDepth=3)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CART_R KEEL Regression Algorithm

Description

CART_R Regression Algorithm from KEEL.

Usage

CART_R(train, test, maxDepth)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::CART_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CBA_C KEEL Associative Classification Algorithm

Description

CBA_C Associative Classification Algorithm from KEEL.

Usage

CBA_C(train, test, min_support, min_confidence, pruning, maxCandidates)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data <- loadKeelDataset("breast")

#Create algorithm
algorithm <- RKEEL::CBA_C(data, data)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CFAR_C KEEL Classification Algorithm

Description

CFAR_C Classification Algorithm from KEEL.

Usage

CFAR_C(train, test, min_support, min_confidence, threshold,
   num_labels, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CFAR_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CFKNN_C KEEL Classification Algorithm

Description

CFKNN_C Classification Algorithm from KEEL.

Usage

CFKNN_C(train, test, k, alpha, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CFKNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CHC_C KEEL Classification Algorithm

Description

CHC_C Classification Algorithm from KEEL.

Usage

CHC_C(train, test, pop_size, evaluations, alfa, restart_change,
   prob_restart, prob_diverge, k, distance, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CHC_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CMAR_C KEEL Associative Classification Algorithm

Description

CMAR_C Associative Classification Algorithm from KEEL.

Usage

CMAR_C(train, test, min_confidence, min_support, databaseCoverage)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data <- loadKeelDataset("breast")

#Create algorithm
algorithm <- RKEEL::CMAR_C(data, data)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CNN_C KEEL Classification Algorithm

Description

CNN_C Classification Algorithm from KEEL.

Usage

CNN_C(train, test, k, distance, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CPAR_C KEEL Associative Classification Algorithm

Description

CPAR_C Associative Classification Algorithm from KEEL.

Usage

CPAR_C(train, test, delta, min_gain, alpha, rules_prediction)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data <- loadKeelDataset("breast")

#Create algorithm
algorithm <- RKEEL::CPAR_C(data, data)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CPW_C KEEL Classification Algorithm

Description

CPW_C Classification Algorithm from KEEL.

Usage

CPW_C(train, test, beta, mu, ro, epsilon)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CPW_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CW_C KEEL Classification Algorithm

Description

CW_C Classification Algorithm from KEEL.

Usage

CW_C(train, test, beta, mu, epsilon)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CW_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

C_SVM_C KEEL Classification Algorithm

Description

C_SVM_C Classification Algorithm from KEEL.

Usage

C_SVM_C(train, test, KernelType, C, eps, degree, gamma, coef0,
   nu, p, shrinking, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::C_SVM_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CamNN_C KEEL Classification Algorithm

Description

CamNN_C Classification Algorithm from KEEL.

Usage

CamNN_C(train, test, k)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CamNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

CenterNN_C KEEL Classification Algorithm

Description

CenterNN_C Classification Algorithm from KEEL.

Usage

CenterNN_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::CenterNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Classification Algorithm

Description

Class inheriting of KeelAlgorithm, to common methods for all KEEL Classification Algorithms. The specific classification algorithms must inherit of this class.

The run() method receives three parameters. The folderPath parameter indicates where to place the folder with the experiments if wanted. If it is not indicated, the folder is placen ind a temporary random directory and then removed. If indicated, the experiment folder is not removed. The expUniqueName parameter indicates the name of the experiment folder. If not indicated, it is a random name. If indicated, ensure that the name is unique in the previously indicated folder. The javaOptions parameter indicates, if wanted, extra parameters to the java command line, as for example the maximum memory allowed by java.

Classification Results

Description

Class to calculate and store some results for a ClassificationAlgorithm. It receives as parameter the prediction of a classification algorithm as a data.frame object.

CleanAttributes_TR KEEL Preprocess Algorithm

Description

CleanAttributes_TR Preprocess Algorithm from KEEL.

Usage

CleanAttributes_TR(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::CleanAttributes_TR(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

ClusterAnalysis_D KEEL Preprocess Algorithm

Description

ClusterAnalysis_D Preprocess Algorithm from KEEL.

Usage

ClusterAnalysis_D(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::ClusterAnalysis_D(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

DSM_C KEEL Classification Algorithm

Description

DSM_C Classification Algorithm from KEEL.

Usage

DSM_C(train, test, iterations, percentage, alpha_0, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::DSM_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

DT_GA_C KEEL Classification Algorithm

Description

DT_GA_C Classification Algorithm from KEEL.

Usage

DT_GA_C(train, test, confidence, instancesPerLeaf,
   geneticAlgorithmApproach, threshold, numGenerations,
   popSize, crossoverProb, mutProb, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::DT_GA_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

DecimalScaling_TR KEEL Preprocess Algorithm

Description

DecimalScaling_TR Preprocess Algorithm from KEEL.

Usage

DecimalScaling_TR(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::DecimalScaling_TR(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

DecrRBFN_C KEEL Classification Algorithm

Description

DecrRBFN_C Classification Algorithm from KEEL.

Usage

DecrRBFN_C(train, test, percent, num_neurons_ini, alfa, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::DecrRBFN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Deeps_C KEEL Classification Algorithm

Description

Deeps_C Classification Algorithm from KEEL.

Usage

Deeps_C(train, test, beta)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::Deeps_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

EARMGA_A KEEL Association Rules Algorithm

Description

EARMGA_A Association Rules Algorithm from KEEL.

Usage

EARMGA_A(dat, seed, FixedLengthofAssociationRules, PopulationSize, 
  TotalNumberofEvaluations, DifferenceBoundaryNOTUSED, ProbabilityofSelection, 
  ProbabilityofCrossover, ProbabilityofMutation, 
  NumberofPartitionsforNumericAttributes)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::EARMGA_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

EPSILON_SVR_R KEEL Regression Algorithm

Description

EPSILON_SVR_R Regression Algorithm from KEEL.

Usage

EPSILON_SVR_R(train, test, KernelType, C, eps, degree, gamma,
   coef0, nu, p, shrinking, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::EPSILON_SVR_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Eclat_A KEEL Association Rules Algorithm

Description

Eclat_A Association Rules Algorithm from KEEL.

Usage

Eclat_A(dat, NumberofPartitionsforNumericAttributes, MinimumSupport, 
  MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::Eclat_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

FCRA_C KEEL Classification Algorithm

Description

FCRA_C Classification Algorithm from KEEL.

Usage

FCRA_C(train, test, generations, pop_size, length_S_C, WCAR,
   WV, crossover_prob, mut_prob, n1, n2, max_iter,
   linguistic_values, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::FCRA_C(data_train, data_test, generations=10, pop_size=10)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

FPgrowth_A KEEL Association Rules Algorithm

Description

FPgrowth_A Association Rules Algorithm from KEEL.

Usage

FPgrowth_A(dat, NumberofPartitionsforNumericAttributes, MinimumSupport, 
  MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::FPgrowth_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

FRNN_C KEEL Classification Algorithm

Description

FRNN_C Classification Algorithm from KEEL.

Usage

FRNN_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::FRNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

FRSBM_R KEEL Regression Algorithm

Description

FRSBM_R Regression Algorithm from KEEL.

Usage

FRSBM_R(train, test, numrules, sigma, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::FRSBM_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

FURIA_C KEEL Classification Algorithm

Description

FURIA_C Classification Algorithm from KEEL.

Usage

FURIA_C(train, test, optimizations, folds, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::FURIA_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Falco_GP_C KEEL Classification Algorithm

Description

Falco_GP_C Classification Algorithm from KEEL.

Usage

Falco_GP_C(train, test, population_size, max_generations,
   max_deriv_size, rec_prob, mut_prob, copy_prob, alpha, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::Falco_GP_C(data_train, data_test)
algorithm <- RKEEL::Falco_GP_C(data_train, data_test, population_size = 5, max_generations = 10)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

FuzzyApriori_A KEEL Association Rules Algorithm

Description

FuzzyApriori_A Association Rules Algorithm from KEEL.

Usage

FuzzyApriori_A(dat, NumberofPartitionsforNumericAttributes,
  UseMaxOperatorfor1FrequentItemsets, MinimumSupport, MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset 
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::FuzzyApriori_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

FuzzyFARCHD_C KEEL Classification Algorithm

Description

FuzzyFARCHD_C Classification Algorithm from KEEL.

Usage

FuzzyFARCHD_C(train, test, linguistic_values, min_support,
   max_confidence, depth_max, K, max_evaluations, pop_size,
   alpha, bits_per_gen, inference_type, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::FuzzyFARCHD_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

FuzzyKNN_C KEEL Classification Algorithm

Description

FuzzyKNN_C Classification Algorithm from KEEL.

Usage

FuzzyKNN_C(train, test, k, M, initialization, init_k)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::FuzzyKNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

FuzzyNPC_C KEEL Classification Algorithm

Description

FuzzyNPC_C Classification Algorithm from KEEL.

Usage

FuzzyNPC_C(train, test, M)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::FuzzyNPC_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GANN_C KEEL Classification Algorithm

Description

GANN_C Classification Algorithm from KEEL.

Usage

GANN_C(train, test, hidden_layers, hidden_nodes, transfer, eta,
   alpha, lambda, test_data, validation_data, cross_validation,
   BP_cycles, improve, tipify_inputs, save_all, elite,
   num_individuals, w_range, connectivity, P_bp, P_param,
   P_struct, max_generations, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::GANN_C(data_train, data_test, hidden_layers=1, 
  hidden_nodes=5, max_generations=5)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GAR_A KEEL Association Rules Algorithm

Description

GAR_A Association Rules Algorithm from KEEL.

Usage

GAR_A(dat, seed, NumberofItemsets, TotalNumberofEvaluations, PopulationSize,
  ProbabilityofSelection, ProbabilityofCrossover, ProbabilityofMutation,
  ImportanceofNumberofRecordsAlreadyCovered, ImportanceofIntervalsAmplitude,
  ImportanceofNumberofInvolvedAttributes, AmplitudeFactor, MinimumSupport,
  MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("glass")

#Create algorithm
algorithm <- RKEEL::GAR_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

GENAR_A KEEL Association Rules Algorithm

Description

GENAR_A Association Rules Algorithm from KEEL.

Usage

GENAR_A(dat, seed, NumberofAssociationRules, TotalNumberofEvaluations, 
  PopulationSize, ProbabilityofSelection, ProbabilityofMutation, 
  PenalizationFactor, AmplitudeFactor)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("glass")

#Create algorithm
algorithm <- RKEEL::GENAR_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

GFS_AdaBoost_C KEEL Classification Algorithm

Description

GFS_AdaBoost_C Classification Algorithm from KEEL.

Usage

GFS_AdaBoost_C(train, test, numLabels, numRules, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::GFS_AdaBoost_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GFS_GP_R KEEL Regression Algorithm

Description

GFS_GP_R Regression Algorithm from KEEL.

Usage

GFS_GP_R(train, test, numLabels, numRules, popSize, numisland,
   steady, numIter, tourSize, mutProb, aplMut, probMigra,
   probOptimLocal, numOptimLocal, idOptimLocal, nichinggap,
   maxindniche, probintraniche, probcrossga, probmutaga,
   lenchaingap, maxtreeheight, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::GFS_GP_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GFS_GSP_R KEEL Regression Algorithm

Description

GFS_GSP_R Regression Algorithm from KEEL.

Usage

GFS_GSP_R(train, test, numLabels, numRules, deltafitsap,
   p0sap, p1sap, amplMut, nsubsap, probOptimLocal,
   numOptimLocal, idOptimLocal, probcrossga, probmutaga,
   lenchaingap, maxtreeheight, numItera, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::GFS_GSP_R(data_train, data_test)
algorithm <- RKEEL::GFS_GSP_R(data_train, data_test, numRules=2, numItera=10, maxtreeheight=2)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GFS_LogitBoost_C KEEL Classification Algorithm

Description

GFS_LogitBoost_C Classification Algorithm from KEEL.

Usage

GFS_LogitBoost_C(train, test, numLabels, numRules, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::GFS_LogitBoost_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GFS_RB_MF_R KEEL Regression Algorithm

Description

GFS_RB_MF_R Regression Algorithm from KEEL.

Usage

GFS_RB_MF_R(train, test, numLabels, popSize, generations,
   crossProb, mutProb, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::GFS_RB_MF_R(data_train, data_test)
algorithm <- RKEEL::GFS_RB_MF_R(data_train, data_test, popSize = 5, generations = 10)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

GeneticFuzzyAprioriDC_A KEEL Association Rules Algorithm

Description

GeneticFuzzyAprioriDC_A Association Rules Algorithm from KEEL.

Usage

GeneticFuzzyAprioriDC_A(dat, seed, NumberofEvaluations, PopulationSize, 
  ProbabilityofMutation, ProbabilityofCrossover, ParameterdforMMACrossover, 
  NumberofFuzzyRegionsforNumericAttributes, UseMaxOperatorfor1FrequentItemsets, 
  MinimumSupport, MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::GeneticFuzzyAprioriDC_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

GeneticFuzzyApriori_A KEEL Association Rules Algorithm

Description

GeneticFuzzyApriori_A Association Rules Algorithm from KEEL.

Usage

GeneticFuzzyApriori_A(dat, seed, NumberofEvaluations, PopulationSize, 
  ProbabilityofMutation, ProbabilityofCrossover, ParameterdforMMACrossover, 
  NumberofFuzzyRegionsforNumericAttributes, UseMaxOperatorfor1FrequentItemsets, 
  MinimumSupport, MinimumConfidence)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::GeneticFuzzyApriori_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

ID3_C KEEL Classification Algorithm

Description

ID3_C Classification Algorithm from KEEL.

Usage

ID3_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::ID3_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

ID3_D KEEL Preprocess Algorithm

Description

ID3_D Preprocess Algorithm from KEEL.

Usage

ID3_D(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::ID3_D(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

IF_KNN_C KEEL Classification Algorithm

Description

IF_KNN_C Classification Algorithm from KEEL.

Usage

IF_KNN_C(train, test, K, mA, vA, mR, vR, k)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::IF_KNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Ignore_MV KEEL Preprocess Algorithm

Description

Ignore_MV Preprocess Algorithm from KEEL.

Usage

Ignore_MV(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::Ignore_MV(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

ImbalancedClassification Algorithm

Description

Class inheriting of ClassificationAlgorithm, to common methods for all KEEL Imbalanced Classification Algorithms. The specific imbalanced-classification algorithms must inherit of this class.

IncrRBFN_C KEEL Classification Algorithm

Description

IncrRBFN_C Classification Algorithm from KEEL.

Usage

IncrRBFN_C(train, test, epsilon, alfa, delta, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::IncrRBFN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

IterativePartitioningFilter_F KEEL Preprocess Algorithm

Description

IterativePartitioningFilter_F Preprocess Algorithm from KEEL.

Usage

IterativePartitioningFilter_F(train, test, numPartitions,
   filterType, confidence, itemsetsPerLeaf, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::IterativePartitioningFilter_F(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

JFKNN_C KEEL Classification Algorithm

Description

JFKNN_C Classification Algorithm from KEEL.

Usage

JFKNN_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::JFKNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

KMeans_MV KEEL Preprocess Algorithm

Description

KMeans_MV Preprocess Algorithm from KEEL.

Usage

KMeans_MV(train, test, k, error, iterations, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::KMeans_MV(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

KNN-C KEEL Classification Algorithm

Description

KNN-C Classification Algorithm from KEEL.

Usage

KNN_C(train, test, k, distance)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::KNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

KNN_MV KEEL Preprocess Algorithm

Description

KNN_MV Preprocess Algorithm from KEEL.

Usage

KNN_MV(train, test, k)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::KNN_MV(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

KSNN_C KEEL Classification Algorithm

Description

KSNN_C Classification Algorithm from KEEL.

Usage

KSNN_C(train, test, k)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::KSNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

KStar_C KEEL Classification Algorithm

Description

KStar_C Classification Algorithm from KEEL.

Usage

KStar_C(train, test, selection_method, blend, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::KStar_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Keel Algorithm

Description

Principal class for implementing KEEL Algorithms. The distinct types of algorithms must inherit of this class.

Kernel_C KEEL Classification Algorithm

Description

Kernel_C Classification Algorithm from KEEL.

Usage

Kernel_C(train, test, sigma, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::Kernel_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

LDA_C KEEL Classification Algorithm

Description

LDA_C Classification Algorithm from KEEL.

Usage

LDA_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::LDA_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

LVF_IEP_FS KEEL Preprocess Algorithm

Description

LVF_IEP_FS Preprocess Algorithm from KEEL.

Usage

LVF_IEP_FS(train, test, paramKNN, maxLoops, inconAllow, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::LVF_IEP_FS(data_train, data_test)
algorithm <- RKEEL::LVF_IEP_FS(data_train, data_test, maxLoops = 30, 
  inconAllow=2)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

LinearLMS_C KEEL Classification Algorithm

Description

LinearLMS_C Classification Algorithm from KEEL.

Usage

LinearLMS_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::LinearLMS_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

LinearLMS_R KEEL Regression Algorithm

Description

LinearLMS_R Regression Algorithm from KEEL.

Usage

LinearLMS_R(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::LinearLMS_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Logistic_C KEEL Classification Algorithm

Description

Logistic_C Classification Algorithm from KEEL.

Usage

Logistic_C(train, test, ridge, maxIter)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::Logistic_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

M5Rules_R KEEL Regression Algorithm

Description

M5Rules_R Regression Algorithm from KEEL.

Usage

M5Rules_R(train, test, pruningFactor, heuristic)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::M5Rules_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

M5_R KEEL Regression Algorithm

Description

M5_R Regression Algorithm from KEEL.

Usage

M5_R(train, test, type, pruningFactor, unsmoothed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::M5_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

MLP_BP_C KEEL Classification Algorithm

Description

MLP_BP_C Classification Algorithm from KEEL.

Usage

MLP_BP_C(train, test, hidden_layers, hidden_nodes, transfer,
   eta, alpha, lambda, test_data, validation_data,
   cross_validation, cycles, improve, tipify_inputs,
   save_all, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::MLP_BP_C(data_train, data_test, )

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

MLP_BP_R KEEL Regression Algorithm

Description

MLP_BP_R Regression Algorithm from KEEL.

Usage

MLP_BP_R(train, test, hidden_layers, hidden_nodes, transfer,
   eta, alpha, lambda, test_data, validation_data,
   cross_validation, cycles, improve, tipify_inputs,
   save_all, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::MLP_BP_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

MODENAR_A KEEL Association Rules Algorithm

Description

MODENAR_A Association Rules Algorithm from KEEL.

Usage

MODENAR_A(dat, seed, PopulationSize, NumberofEvaluations, CrossoverrateCR, 
  Thresholdforthenumberofnondominatedsolutions, 
  Thefactorofamplitudeforeachattributeofthedataset, WeightforSupport, 
  WeightforConfidence, WeightforComprehensibility, 
  WeightforAmplitudeoftheIntervals)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::MODENAR_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

MOEA_Ghosh_A KEEL Association Rules Algorithm

Description

MOEA_Ghosh_A Association Rules Algorithm from KEEL.

Usage

MOEA_Ghosh_A(dat, seed, NumberofObjetives, NumberofEvaluations, PopulationSize, 
  PointCrossover, ProbabilityofCrossover, ProbabilityofMutation, 
  Thefactorofamplitudeforeachattributeofthedataset)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::MOEA_Ghosh_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

MOPNAR_A KEEL Association Rules Algorithm

Description

MOPNAR_A Association Rules Algorithm from KEEL.

Usage

MOPNAR_A(dat, seed, objetives, evaluations, parameter, weightNeighborhood, 
  wrobabilitySolutionsNeighborhood, maxSolutions, probabilityMutation, 
  amplitude, threshold)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::MOPNAR_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

MinMax_TR KEEL Preprocess Algorithm

Description

MinMax_TR Preprocess Algorithm from KEEL.

Usage

MinMax_TR(train, test, newMin, newMax)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::MinMax_TR(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

ModelCS_TSS KEEL Preprocess Algorithm

Description

ModelCS_TSS Preprocess Algorithm from KEEL.

Usage

ModelCS_TSS(train, test, k, distance)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::ModelCS_TSS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

MostCommon_MV KEEL Preprocess Algorithm

Description

MostCommon_MV Preprocess Algorithm from KEEL.

Usage

MostCommon_MV(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::MostCommon_MV(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

NB_C KEEL Classification Algorithm

Description

NB_C Classification Algorithm from KEEL.

Usage

NB_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::NB_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

NICGAR_A KEEL Association Rules Algorithm

Description

NICGAR_A Association Rules Algorithm from KEEL.

Usage

NICGAR_A(dat, seed, NumberofEvaluations, PopulationSize, ProbabilityofMutation, 
  Thefactorofamplitudeforeachattributeofthedataset, NichingThreshold, 
  QualityThreshold, PercentUpdate)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::NICGAR_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

NM_C KEEL Classification Algorithm

Description

NM_C Classification Algorithm from KEEL.

Usage

NM_C(train, test)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::NM_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

NNEP_C KEEL Classification Algorithm

Description

NNEP_C Classification Algorithm from KEEL.

Usage

NNEP_C(train, test, hidden_nodes, transfer, generations, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::NNEP_C(data_train, data_test)
algorithm <- RKEEL::NNEP_C(data_train, data_test, generations = 5)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

NU_SVM_C KEEL Classification Algorithm

Description

NU_SVM_C Classification Algorithm from KEEL.

Usage

NU_SVM_C(train, test, KernelType, C, eps, degree, gamma, coef0,
   nu, p, shrinking, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::NU_SVM_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

NU_SVR_R KEEL Regression Algorithm

Description

NU_SVR_R Regression Algorithm from KEEL.

Usage

NU_SVR_R(train, test, KernelType, C, eps, degree, gamma,
   coef0, nu, p, shrinking, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::NU_SVR_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Nominal2Binary_TR KEEL Preprocess Algorithm

Description

Nominal2Binary_TR Preprocess Algorithm from KEEL.

Usage

Nominal2Binary_TR(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::Nominal2Binary_TR(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

PART_C KEEL Classification Algorithm

Description

PART_C Classification Algorithm from KEEL.

Usage

PART_C(train, test, confidence, itemsetsPerLeaf)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PART_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PDFC_C KEEL Classification Algorithm

Description

PDFC_C Classification Algorithm from KEEL.

Usage

PDFC_C(train, test, C, d, tolerance, epsilon, PDRFtype,
   nominal_to_binary, preprocess_type, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PDFC_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PFKNN_C KEEL Classification Algorithm

Description

PFKNN_C Classification Algorithm from KEEL.

Usage

PFKNN_C(train, test, k, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PFKNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PNN_C KEEL Classification Algorithm

Description

PNN_C Classification Algorithm from KEEL.

Usage

PNN_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PNN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

POP_TSS KEEL Preprocess Algorithm

Description

POP_TSS Preprocess Algorithm from KEEL.

Usage

POP_TSS(train, test)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::POP_TSS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

PRISM_C KEEL Classification Algorithm

Description

PRISM_C Classification Algorithm from KEEL.

Usage

PRISM_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::PRISM_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PSO_ACO_C KEEL Classification Algorithm

Description

PSO_ACO_C Classification Algorithm from KEEL.

Usage

PSO_ACO_C(train, test, max_uncovered_samples, min_saples_by_rule,
   max_iterations_without_converge, enviromentSize, numParticles,
   x, c1, c2, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PSO_ACO_C(data_train, data_test, 
  max_iterations_without_converge=2, numParticles=5)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PSRCG_TSS KEEL Preprocess Algorithm

Description

PSRCG_TSS Preprocess Algorithm from KEEL.

Usage

PSRCG_TSS(train, test, distance)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::PSRCG_TSS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

PUBLIC_C KEEL Classification Algorithm

Description

PUBLIC_C Classification Algorithm from KEEL.

Usage

PUBLIC_C(train, test, nodesBetweenPrune, estimateToPrune)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PUBLIC_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PW_C KEEL Classification Algorithm

Description

PW_C Classification Algorithm from KEEL.

Usage

PW_C(train, test, beta, ro, epsilon)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PW_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PolQuadraticLMS_C KEEL Classification Algorithm

Description

PolQuadraticLMS_C Classification Algorithm from KEEL.

Usage

PolQuadraticLMS_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::PolQuadraticLMS_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

PolQuadraticLMS_R KEEL Regression Algorithm

Description

PolQuadraticLMS_R Regression Algorithm from KEEL.

Usage

PolQuadraticLMS_R(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::PolQuadraticLMS_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Preprocess Algorithm

Description

Class inheriting of KeelAlgorithm, to common methods for all KEEL Preprocess Algorithms. The specific preprocessing algorithms must inherit of this class.

The run() method receives three parameters. The folderPath parameter indicates where to place the folder with the experiments if wanted. If it is not indicated, the folder is placen ind a temporary random directory and then removed. If indicated, the experiment folder is not removed. The expUniqueName parameter indicates the name of the experiment folder. If not indicated, it is a random name. If indicated, ensure that the name is unique in the previously indicated folder. The javaOptions parameter indicates, if wanted, extra parameters to the java command line, as for example the maximum memory allowed by java.

Proportional_D KEEL Preprocess Algorithm

Description

Proportional_D Preprocess Algorithm from KEEL.

Usage

Proportional_D(train, test, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::Proportional_D(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

QAR_CIP_NSGAII_A KEEL Association Rules Algorithm

Description

QAR_CIP_NSGAII_A Association Rules Algorithm from KEEL.

Usage

QAR_CIP_NSGAII_A(dat, seed, NumberofObjetives, NumberofEvaluations, 
  PopulationSize, ProbabilityofMutation, 
  Thefactorofamplitudeforeachattributeofthedataset, Differencethreshold)

Arguments

Details

$run() Run algorith

$showRules(numRules) Show a number of rules. By default all rules.

$getInterestMeasures() Return a data.frame with all interest measures of set rules.

$sortBy(interestMeasure) Order set rules by interest measure.

$writeCSV(fileName, sep) Create CSV file with set rules. Default fileName="rules" sep=","

$writePMML(fileName) Create PMML file with set rules. Default fileName="rules"

$addInterestMeasure(name, colName) Add interest measures to set rules. Some interest measures supported:

"allConfidence" (Omiencinski, 2003)

"crossSupportRatio", cross-support ratio (Xiong et al., 2003)

"lift", interest factor (Brin et al. 1997)

"support", supp (Agrawal et al., 1996)

"addedValue", added Value, AV, Pavillon index, centered confidence (Tan et al., 2002)

"chiSquared", X^2 (Liu et al., 1999)

"certainty", certainty factor, CF, Loevinger (Berzal et al., 2002)

"collectiveStrength"

"confidence", conf (Agrawal et al., 1996)

"conviction" (Brin et al. 1997)

"cosine" (Tan et al., 2004)

"coverage", cover, LHS-support

"confirmedConfidence", descriptive confirmed confidence (Kodratoff, 1999)

"casualConfidence", casual confidence (Kodratoff, 1999)

"casualSupport", casual support (Kodratoff, 1999)

"counterexample", example and counterexample rate

"descriptiveConfirm", descriptive-confirm (Kodratoff, 1999)

"doc", difference of confidence (Hofmann and Wilhelm, 2001)

"fishersExactTest", Fisher's exact test (Hahsler and Hornik, 2007)

"gini", Gini index (Tan et al., 2004)

"hyperLift" (Hahsler and Hornik, 2007)

"hyperConfidence" (Hahsler and Hornik, 2007)

"imbalance", imbalance ratio, IR (Wu, Chen and Han, 2010)

"implicationIndex", implication index (Gras, 1996)

"improvement" (Bayardo et al., 2000)

"jaccard", Jaccard coefficient (Tan and Kumar, 2000)

"jMeasure", J-measure, J (Smyth and Goodman, 1991)

"kappa" (Tan and Kumar, 2000)

"klosgen", Klosgen (Tan and Kumar, 2000)

"kulczynski" (Wu, Chen and Han, 2007; Kulczynski, 1927)

"lambda", Goodman-Kruskal lambda, predictive association (Tan and Kumar, 2000)

"laplace", L (Tan and Kumar 2000)

"leastContradiction", least contradiction (Aze and Kodratoff, 2004

"lerman", Lerman similarity (Lerman, 1981)

"leverage", PS (Piatetsky-Shapiro 1991)

"mutualInformation", uncertainty, M (Tan et al., 2002)

"oddsRatio", odds ratio alpha (Tan et al., 2004)

"phi", correlation coefficient phi (Tan et al. 2004)

"ralambrodrainy", Ralambrodrainy Measure (Ralambrodrainy, 1991)

"RLD", relative linkage disequilibrium (Kenett and Salini, 2008)

"sebag", Sebag measure (Sebag and Schoenauer, 1988)

"support", supp (Agrawal et al., 1996)

"varyingLiaison", varying rates liaison (Bernard and Charron, 1996)

"yuleQ", Yule's Q (Tan and Kumar, 2000)

"yuleY", Yule's Y (Tan and Kumar, 2000)

For more information see ?arules::interestMeasure

Value

A arules class with the Association Rules for both dat dataset.

Examples

#Load KEEL dataset
dat<-RKEEL::loadKeelDataset("car")

#Create algorithm
algorithm <- RKEEL::QAR_CIP_NSGAII_A(dat)

#Run algorithm
algorithm$run()

#Rules in format arules
algorithm$rules

#Show a number of rules
algorithm$showRules(2)

#Return a data.frame with all interest measures of set rules
algorithm$getInterestMeasures()

#Add interst measure YuleY to set rules
algorithm$addInterestMeasure("YuleY","yulesY")

#Sort by interest measure lift
algorithm$sortBy("lift")

#Save rules in CSV file
algorithm$writeCSV(paste0(tempdir(), "/myrules"))

QDA_C KEEL Classification Algorithm

Description

QDA_C Classification Algorithm from KEEL.

Usage

QDA_C(train, test, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::QDA_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

RBFN_C KEEL Classification Algorithm

Description

RBFN_C Classification Algorithm from KEEL.

Usage

RBFN_C(train, test, neurons, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::RBFN_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

RBFN_R KEEL Regression Algorithm

Description

RBFN_R Regression Algorithm from KEEL.

Usage

RBFN_R(train, test, neurons, seed)

Arguments

Value

A data.frame with the actual and predicted values for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("autoMPG6_train")
data_test <- RKEEL::loadKeelDataset("autoMPG6_test")

#Create algorithm
algorithm <- RKEEL::RBFN_R(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

RISE_C KEEL Classification Algorithm

Description

RISE_C Classification Algorithm from KEEL.

Usage

RISE_C(train, test, Q, S)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::RISE_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

Regression Algorithm

Description

Class inheriting of KeelAlgorithm, to common methods for all KEEL Regression Algorithms. The specific regression algorithms must inherit of this class.

The run() method receives three parameters. The folderPath parameter indicates where to place the folder with the experiments if wanted. If it is not indicated, the folder is placen ind a temporary random directory and then removed. If indicated, the experiment folder is not removed. The expUniqueName parameter indicates the name of the experiment folder. If not indicated, it is a random name. If indicated, ensure that the name is unique in the previously indicated folder. The javaOptions parameter indicates, if wanted, extra parameters to the java command line, as for example the maximum memory allowed by java.

Regression Results

Description

Class to calculate and store some results for a RegressionAlgorithm. It receives as parameter the prediction of a regression algorithm as a data.frame object.

Relief_FS KEEL Preprocess Algorithm

Description

Relief_FS Preprocess Algorithm from KEEL.

Usage

Relief_FS(train, test, paramKNN, relevanceThreshold,
   numInstancesSampled, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::Relief_FS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

Ripper_C KEEL Classification Algorithm

Description

Ripper_C Classification Algorithm from KEEL.

Usage

Ripper_C(train, test, grow_pct, k, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::Ripper_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

SFS_IEP_FS KEEL Preprocess Algorithm

Description

SFS_IEP_FS Preprocess Algorithm from KEEL.

Usage

SFS_IEP_FS(train, test, threshold, seed)

Arguments

Value

A data.frame with the preprocessed data for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("car_train")
data_test <- RKEEL::loadKeelDataset("car_test")

#Create algorithm
algorithm <- RKEEL::SFS_IEP_FS(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$preprocessed_test

SGA_C KEEL Classification Algorithm

Description

SGA_C Classification Algorithm from KEEL.

Usage

SGA_C(train, test, mut_prob_1to0, mut_prob_0to1, cross_prob,
   pop_size, evaluations, alfa, selection_type, k,
   distance, seed)

Arguments

Value

A data.frame with the actual and predicted classes for both train and test datasets.

Examples

data_train <- RKEEL::loadKeelDataset("iris_train")
data_test <- RKEEL::loadKeelDataset("iris_test")

#Create algorithm
algorithm <- RKEEL::SGA_C(data_train, data_test)

#Run algorithm
algorithm$run()

#See results
algorithm$testPredictions

SMO_C KEEL Classification Algorithm

Description

SMO_C Classification Algorithm from KEEL.

Usage

SMO_C(train, test, C, toleranceParameter, epsilon,
   RBFKernel_gamma, normalized_PolyKernel_exponent,
   normalized_PolyKernel_useLowerOrder, PukKernel_omega,
   PukKernel_sigma, StringKernel_lambda,
   StringKernel_subsequenceLength,
   StringKernel_maxSubsequenceLength, StringKernel_normalize,
   StringKernel_pruning, KernelType, FitLogisticModels,
   ConvertNominalAttributesToBinary, PreprocessType, seed)

Arguments