###############################################################
#                                                             #
#  Config file for hamlet's pre-processing engine             #
#                                                             #
###############################################################


# number of clusters to generate
numClusters=500

# percentage of dataset size to use as number of clusters
# (ex. if there are 100 data points and clusterPercent=0.8, 
#    then 80 clusters will be generated)
clusterPercent=0.8

# When dealing with feature subset selection, this number tells how many 
#features (terms) we want to keep
numKeyTerms=100

# The type of clustering algorithm to instantiate
# possible values: 
# kmeans - in house k-means implementation
# canopy - in house canopy implementation using k-means
# genic - in house GenIc implementation
clusterer=genic

# The type of classification algorithm to instantiate
# possible values: 
# weka_BayesNet
# weka_DMNBtext
# weka_NaiveBayes
# weka_NaiveBayesMultinomial
# weka_NaiveBayesMultinomialUpdateable
# weka_IBk
# weka_KStar
# weka_LWL
# weka_HyperPipes
# weka_VFI
# weka_ConjunctiveRule
# weka_DecisionTable
# weka_JRip
# weka_PART
# weka_ZeroR
# weka_DecisionStump
# weka_J48
# weka_J48graft
# weka_RandomForest
# weka_RandomTree
# weka_REPTree
# weka_SimpleCart
classifier=weka_NaiveBayes

# The maximum number of iterations to use for kmeans.  Default is 500.
maxKMeansIterations=500