def buildClassifier(self, instances):
"""
builds the ZeroR classifier with the given data
Parameter(s):
'instances' -- the data to build the classifier from
"""
self.getCapabilities().testWithFail(instances)
# remove instances with missing class
instances = Instances(instances)
instances.deleteWithMissingClass()
sumOfWeights = 0
self.__Class = instances.classAttribute()
self.__ClassValue = 0
self.__Counts = None
if (instances.classAttribute().isNumeric()):
self.__Counts = None
elif (instances.classAttribute().isNominal()):
self.__Counts = jarray.zeros(instances.numClasses(), 'd')
for i in range(len(self.__Counts)):
self.__Counts[i] = 1
sumOfWeights = instances.numClasses()
enu = instances.enumerateInstances()
while (enu.hasMoreElements()):
instance = enu.nextElement()
if (not instance.classIsMissing()):
if (instances.classAttribute().isNominal()):
self.__Counts[int(
instance.classValue())] += instance.weight()
else:
self.__ClassValue += instance.weight(
) * instance.classValue()
sumOfWeights += instance.weight()
if (instances.classAttribute().isNumeric()):
if (Utils.gr(sumOfWeights, 0)):
self.__ClassValue /= sumOfWeights
else:
self.__ClassValue = Utils.maxIndex(self.__Counts)
Utils.normalize(self.__Counts, sumOfWeights)
return
def buildClassifier(self, instances):
"""
builds the ZeroR classifier with the given data
Parameter(s):
'instances' -- the data to build the classifier from
"""
self.getCapabilities().testWithFail(instances)
# remove instances with missing class
instances = Instances(instances)
instances.deleteWithMissingClass()
sumOfWeights = 0
self.__Class = instances.classAttribute()
self.__ClassValue = 0
self.__Counts = None
if (instances.classAttribute().isNumeric()):
self.__Counts = None
elif (instances.classAttribute().isNominal()):
self.__Counts = jarray.zeros(instances.numClasses(), 'd')
for i in range(len(self.__Counts)):
self.__Counts[i] = 1
sumOfWeights = instances.numClasses()
enu = instances.enumerateInstances()
while (enu.hasMoreElements()):
instance = enu.nextElement()
if (not instance.classIsMissing()):
if (instances.classAttribute().isNominal()):
self.__Counts[int(instance.classValue())] += instance.weight()
else:
self.__ClassValue += instance.weight() * instance.classValue()
sumOfWeights += instance.weight()
if (instances.classAttribute().isNumeric()):
if (Utils.gr(sumOfWeights, 0)):
self.__ClassValue /= sumOfWeights
else:
self.__ClassValue = Utils.maxIndex(self.__Counts)
Utils.normalize(self.__Counts, sumOfWeights)
return
def load_model(self, model, arff):
try:
j48 = J48()
options = ('-i', '-l', model, '-T', arff)
objectInputFileName = Utils.getOption('l', options);
if len(objectInputFileName) == 0:
print "No training file and no object input file given."
raise
inputStream = InputStream
inputStream = FileInputStream(objectInputFileName)
objectInputStream = ObjectInputStream(inputStream)
j48 = objectInputStream.readObject()
return j48
except:
raise
class JeroR(AbstractClassifier, JythonSerializableObject):
"""
JeroR is a Jython implementation of the Weka classifier ZeroR
'author' -- FracPete (fracpete at waikato dot ac dot nz)
'version' -- $Revision: 10229 $
"""
# the documentation can be generated with HappyDoc:
# http://happydoc.sourceforge.net/
# Example command:
# happydoc --title Weka -d ./doc ./src
# the chosen class value
__ClassValue = Utils.missingValue()
# the class attribute
__Class = None
# the counts for each class label
__Counts = None
def listOptions(self):
"""
Returns an enumeration describing the available options.
Return:
an enumeration of all the available options.
"""
return AbstractClassifier.listOptions(self)
def setOptions(self, options):
"""
Parses a given list of options.
Parameter(s):
'options' -- the list of options as an array of strings
"""
AbstractClassifier.setOptions(self, options)
return
def getOptions(self):
"""
Gets the current settings of the Classifier as string array.
Return:
an array of strings suitable for passing to setOptions
"""
return AbstractClassifier.getOptions(self)
def getCapabilities(self):
"""
returns the capabilities of this classifier
Return:
the capabilities of this classifier
"""
result = AbstractClassifier.getCapabilities(self)
# attributes
result.enable(Capability.NOMINAL_ATTRIBUTES)
result.enable(Capability.NUMERIC_ATTRIBUTES)
result.enable(Capability.DATE_ATTRIBUTES)
result.enable(Capability.STRING_ATTRIBUTES)
result.enable(Capability.RELATIONAL_ATTRIBUTES)
result.enable(Capability.MISSING_VALUES)
# class
result.enable(Capability.NOMINAL_CLASS)
result.enable(Capability.NUMERIC_CLASS)
result.enable(Capability.DATE_CLASS)
result.enable(Capability.MISSING_CLASS_VALUES)
# instances
result.setMinimumNumberInstances(0)
return result
def buildClassifier(self, instances):
"""
builds the ZeroR classifier with the given data
Parameter(s):
'instances' -- the data to build the classifier from
"""
self.getCapabilities().testWithFail(instances)
# remove instances with missing class
instances = Instances(instances)
instances.deleteWithMissingClass()
sumOfWeights = 0
self.__Class = instances.classAttribute()
self.__ClassValue = 0
self.__Counts = None
if (instances.classAttribute().isNumeric()):
self.__Counts = None
elif (instances.classAttribute().isNominal()):
self.__Counts = jarray.zeros(instances.numClasses(), 'd')
for i in range(len(self.__Counts)):
self.__Counts[i] = 1
sumOfWeights = instances.numClasses()
enu = instances.enumerateInstances()
while (enu.hasMoreElements()):
instance = enu.nextElement()
if (not instance.classIsMissing()):
if (instances.classAttribute().isNominal()):
self.__Counts[int(
instance.classValue())] += instance.weight()
else:
self.__ClassValue += instance.weight(
) * instance.classValue()
sumOfWeights += instance.weight()
if (instances.classAttribute().isNumeric()):
if (Utils.gr(sumOfWeights, 0)):
self.__ClassValue /= sumOfWeights
else:
self.__ClassValue = Utils.maxIndex(self.__Counts)
Utils.normalize(self.__Counts, sumOfWeights)
return
def classifyInstance(self, instance):
"""
returns the prediction for the given instance
Parameter(s):
'instance' -- the instance to predict the class value for
Return:
the prediction for the given instance
"""
return self.__ClassValue
def distributionForInstance(self, instance):
"""
returns the class distribution for the given instance
Parameter(s):
'instance' -- the instance to calculate the class distribution for
Return:
the class distribution for the given instance
"""
result = None
if (self.__Counts == None):
result = jarray.zeros(1, 'd')
result[0] = self.__ClassValue
else:
result = self.__Counts[:]
return result
def toString(self):
"""
Prints a string representation of the classifier
Return:
string representation of the classifier
"""
if (self.__Class == None):
return "JeroR: No model built yet."
if (self.__Counts == None):
return "JeroR predicts class value: " + str(self.__ClassValue)
else:
return "JeroR predicts class value: " + str(
self.__Class.value(int(self.__ClassValue)))