def buildClassifier(self, data: Instances):
data = Instances(data)
data.deleteWithMissingClass()
self.buildTree(data, self.m_subtreeRaising or not self.m_cleanup)
if self.m_collapseTheTree:
self.collapse()
if self.m_pruneTheTree:
self.prune()
if self.m_cleanup:
self.cleanup(Instances(data, 0))
def buildClassifier(self, data: Instances):
data = Instances(data)
data.deleteWithMissingClass()
data.stratify(self.numSets)
self.buildTree(
data.trainCV(self.numSets, self.numSets - 1, self.m_seed),
not self.m_cleanup, data.testCV(self.numSets, self.numSets - 1))
if self.pruneTheTree:
self.prune()
if self.m_cleanup:
self.cleanup(Instances(data, 0))
def buildClassifier(self,data:Instances):
self.getCapabilities().testWithFail(data)
instances=Instances(data)
instances.deleteWithMissingClass()
self.m_NumClasses=instances.numClasses()
self.m_ClassType=instances.classAttribute().type()
self.m_Train=Instances(instances,0,instances.numInstances())
#只保存了样本集
if self.WindowSize > 0 and instances.numInstances() > self.WindowSize:
self.m_Train=Instances(self.m_Train,self.m_Train.numInstances()-self.WindowSize,self.WindowSize)
self.m_NumAttributesUsed=0
for i in range(self.m_Train.numAttributes()):
if i != self.m_Train.classIndex() and (self.m_Train.attribute(i).isNominal() or self.m_Train.attribute(i).isNumeric()):
self.m_NumAttributesUsed+=1
self.m_NNSearch.setInstances(self.m_Train)
self.m_kNNValid=False
self.m_defaultModel=ZeroR()
self.m_defaultModel.buildClassifier(instances)
def buildClassifier(self, data: Instances):
self.m_ModelBuilt = False
self.m_isZeroR = False
if data.numInstances() == 1:
self.m_Coefficients = [data.instance(0).classValue()]
self.m_SelectedAttributes = [False] * data.numAttributes()
self.m_isZeroR = True
return
if not self.m_checksTurnedOff:
self.getCapabilities().testWithFail(data)
if self.outputAdditionalStats:
ok = True
for i in range(data.numInstances()):
if data.instance(i).weight() != 1:
ok = False
break
if not ok:
raise Exception(
"Can only compute additional statistics on unweighted data"
)
data = Instances(data)
data.deleteWithMissingClass()
self.m_TransformFilter = NominalToBinary()
self.m_TransformFilter.setInputFormat(data)
data = Filter.useFilter(data, self.m_TransformFilter)
self.m_MissingFilter = ReplaceMissingValues()
self.m_MissingFilter.setInputFormat(data)
data = Filter.useFilter(data, self.m_MissingFilter)
data.deleteWithMissingClass()
else:
self.m_TransformFilter = None
self.m_MissingFilter = None
self.m_ClassIndex = data.classIndex()
self.m_TransformedData = data
self.m_Coefficients = None
self.m_SelectedAttributes = [False] * data.numAttributes()
self.m_Means = [0] * data.numAttributes()
self.m_StdDevs = [0] * data.numAttributes()
for j in range(data.numAttributes()):
if j != self.m_ClassIndex:
self.m_SelectedAttributes[j] = True
self.m_Means[j] = data.meanOrMode(j)
self.m_StdDevs[j] = math.sqrt(data.variance(j))
if self.m_StdDevs[j] == 0:
self.m_SelectedAttributes[j] = False
self.m_ClassStdDev = math.sqrt(
data.variance(self.m_TransformedData.classIndex()))
self.m_ClassMean = data.meanOrMode(self.m_TransformedData.classIndex())
self.findBestModel()
if self.outputAdditionalStats:
k = 1
for i in range(data.numAttributes()):
if i != data.classIndex():
if self.m_SelectedAttributes[i]:
k += 1
self.m_df = self.m_TransformedData.numInstances() - k
se = self.calculateSE(self.m_SelectedAttributes,
self.m_Coefficients)
self.m_RSquared = RegressionAnalysis.calculateRSquared(
self.m_TransformedData, se)
self.m_RSquaredAdj = RegressionAnalysis.calculateAdjRSquared(
self.m_RSquared, self.m_TransformedData.numInstances(), k)
self.m_FStat = RegressionAnalysis.calculateFStat(
self.m_RSquared, self.m_TransformedData.numInstances(), k)
self.m_StdErrorOfCoef = RegressionAnalysis.calculateStdErrorOfCoef(
self.m_TransformedData, self.m_SelectedAttributes, se,
self.m_TransformedData.numInstances(), k)
self.m_TStats = RegressionAnalysis.calculateTStats(
self.m_Coefficients, self.m_StdErrorOfCoef, k)
if self.Minimal:
self.m_TransformedData = None
self.m_Means = None
self.m_StdDevs = None
else:
self.m_TransformedData = Instances(data, 0)
self.m_ModelBuilt = True
def buildClassifier(self, data: Instances):
data = Instances(data)
data.deleteWithMissingClass()
self.buildTree(data, False)