def copyStringValues(cls, inst:Instance, a0=None, a1=None, a2:AttributeLocator=None, a3:Instances=None, a4:AttributeLocator=None):
if isinstance(a0,Instances) and isinstance(a1,AttributeLocator):
if inst.dataset() is None:
raise Exception("Instance has no dataset assigned!!")
elif inst.dataset().numAttributes() != a0.numAttributes():
raise Exception("Src and Dest differ in # of attributes: "
+ str(inst.dataset().numAttributes()) + " != "
+ str(a0.numAttributes()))
cls.copyStringValuesFromSrc(inst,True,inst.dataset(),a1,a0,a1)
else:
if a1 == a3:
return
if len(a2.getAttributeIndices()) != len(a4.getAttributeIndices()):
raise Exception("Src and Dest string indices differ in length: "
+ str(len(a2.getAttributeIndices())) + " != "
+ str(len(a4.getAttributeIndices())))
if len(a2.getLocatorIndices()) != len(a4.getLocatorIndices()):
raise Exception("Src and Dest locator indices differ in length: "
+ str(len(a2.getLocatorIndices())) + " != "
+ str(len(a4.getLocatorIndices())))
for i in range(len(a2.getAttributeIndices())):
if a0:
instIndex = a2.getActualIndex(a2.getAttributeIndices()[i])
else:
instIndex = a4.getActualIndex(a4.getAttributeIndices()[i])
src = a1.attribute(a2.getActualIndex(a2.getAttributeIndices()[i]))
dest = a3.attribute(a4.getActualIndex(a4.getAttributeIndices()[i]))
if not inst.isMissing(instIndex):
valIndex = dest.addStringValue(src, int(inst.value(instIndex)))
inst.setValue(instIndex, valIndex)
def convertInstanceNumeric(self, instance: Instance):
if not self.m_needToTransform:
self.push(instance, False)
return
vals = [0] * self.outputFormatPeek().numAttributes()
attSoFar = 0
for j in range(self.getInputFormat().numAttributes()):
att = self.getInputFormat().attribute(j)
if not att.isNominal() or j == self.getInputFormat().classIndex():
vals[attSoFar] = instance.value(j)
attSoFar += 1
else:
if instance.isMissing(j):
for k in range(att.numValues() - 1):
vals[attSoFar + k] = instance.value(j)
else:
k = 0
while int(instance.value(j)) != self.m_Indices[j][k]:
vals[attSoFar + k] = 1
k += 1
while k < att.numValues() - 1:
vals[attSoFar + k] = 0
k += 1
attSoFar += att.numValues() - 1
inst = Instance(instance.weight(), vals)
self.copyValues(inst, False, instance.dataset(),
self.outputFormatPeek())
self.push(inst)
def convertInstanceNominal(self, instance: Instance):
if not self.m_needToTransform:
self.push(instance, False)
return
vals = [0] * self.outputFormatPeek().numAttributes()
attSoFar = 0
for j in range(self.getInputFormat().numAttributes()):
att = self.getInputFormat().attribute(j)
if not att.isNominal() or j == self.getInputFormat().classIndex():
vals[attSoFar] = instance.value(j)
attSoFar += 1
else:
if att.numValues() <= 2 and not self.m_TransformAll:
vals[attSoFar] = instance.value(j)
attSoFar += 1
else:
if instance.isMissing(j):
for k in range(att.numValues()):
vals[attSoFar + k] = instance.value(j)
else:
for k in range(att.numValues()):
if k == int(instance.value(j)):
vals[attSoFar + k] = 1
else:
vals[attSoFar + k] = 0
attSoFar += att.numValues()
inst = Instance(instance.weight(), vals)
self.copyValues(inst, False, instance.dataset(),
self.outputFormatPeek())
self.push(inst)
def push(self, instance: Instance, copyInstance: bool = True):
if instance is not None:
if instance.dataset() is not None:
if copyInstance:
instance = copy.deepcopy(instance)
self.copyValues(instance, False)
instance.setDataset(self.m_OutputFormat)
self.m_OutputQueue.put(instance)
def convertInstance(self,instance:Instance):
inst=instance
hasMissing=instance.hasMissingValue()
if hasMissing:
vals=[0]*self.getInputFormat().numAttributes()
for j in range(instance.numAttributes()):
if instance.isMissing(j) and self.getInputFormat().classIndex()!=j \
and (self.getInputFormat().attribute(j).isNominal() or self.getInputFormat().attribute(j).isNumeric()):
vals[j]=self.m_ModesAndMeans[j]
else:
vals[j]=instance.value(j)
inst=Instance(instance.weight(),vals)
inst.setDataset(instance.dataset())
self.push(inst,not hasMissing)
def evaluationForSingleInstance(self, a0, instance:Instance, storePredictions:bool):
if isinstance(a0,List):
if self.m_ClassIsNominal:
pred= Utils.maxIndex(a0)
if a0[int(pred)] <= 0:
pred= Utils.missingValue()
self.updateStatsForClassifier(a0, instance)
if storePredictions and not self.m_DiscardPredictions:
if self.m_Predictions is None:
self.m_Predictions=[]
self.m_Predictions.append(NominalPrediction(instance.classValue(), a0, instance.weight()))
else:
pred=a0[0]
self.updateStatsForPredictor(pred,instance)
if storePredictions and not self.m_DiscardPredictions:
if self.m_Predictions is None:
self.m_Predictions=[]
self.m_Predictions.append(NumericPrediction(instance.classValue(),pred,instance.weight()))
return pred
elif isinstance(a0,Classifier):
classMissing=copy.deepcopy(instance)
classMissing.setDataset(instance.dataset())
#TODO
# if isinstance(a0,InputMappedClassifier)
# else:
classMissing.setClassMissing()
# print("isMiss: ", instance.value(5))
pred=self.evaluationForSingleInstance(a0.distributionForInstance(classMissing),instance,storePredictions)
if not self.m_ClassIsNominal:
if not instance.classIsMissing() and not Utils.isMissingValue(pred):
if isinstance(a0,IntervalEstimator):
self.updateStatsForIntervalEstimator(a0,classMissing,instance.classValue())
else:
self.m_CoverageStatisticsAvailable=False
if isinstance(a0,ConditionalDensityEstimator):
self.updateStatsForConditionalDensityEstimator(a0,classMissing,instance.classValue())
else:
self.m_ComplexityStatisticsAvailable=False
return pred
def input(self, instance: Instance):
if self.getInputFormat() is None:
raise Exception("No input instance format defined")
if self.m_NewBatch:
self.resetQueue()
self.m_NewBatch = False
if self.getOutputFormat().numAttributes() == 0:
return False
if len(self.m_SelectedAttributes) == self.getInputFormat(
).numAttributes():
inst = copy.deepcopy(instance)
inst.setDataset(None)
else:
vals = [0] * self.getOutputFormat().numAttributes()
for i in range(len(self.m_SelectedAttributes)):
current = self.m_SelectedAttributes[i]
vals[i] = instance.value(current)
inst = Instance(instance.weight(), vals)
self.copyValues(inst, False, instance.dataset(),
self.outputFormatPeek())
self.push(inst)
return True
def process(self, toPredict: Instance, classifier: Classifier,
evaluation: Evaluation):
probActual = probNext = pred = 0
classMissing = copy.deepcopy(toPredict)
classMissing.setDataset(toPredict.dataset())
if toPredict.classAttribute().isNominal():
#返回分类预测的概率分布
preds = classifier.distributionForInstance(classMissing)
#若概率全部为0，则表示不属于任何一类
val = 0
if sum(preds) == 0:
pred = Utils.missingValue()
probActual = Utils.missingValue()
else:
#分类结果为概率最大的一项下标
pred = Utils.maxIndex(preds)
if not Utils.isMissingValue(toPredict.classIndex()):
#如果值不缺失，表示非预测样本，不做修改
if not Utils.isMissingValue(toPredict.classValue()):
val = int(toPredict.classValue())
probActual = preds[val]
else:
probActual = preds[Utils.maxIndex(preds)]
for i in range(toPredict.classAttribute().numValues()):
if i != val and preds[i] > probNext:
probNext = preds[i]
evaluation.evaluationForSingleInstance(preds, toPredict, True)
else:
#单项评估
pred = evaluation.evaluateModelOnceAndRecordPrediction(
classifier, toPredict)
if not self.m_SaveForVisualization:
return
#保存可视化数据
if self.m_PlotInstances is not None:
isNominal = toPredict.classAttribute().isNominal()
values = [0] * self.m_PlotInstances.numAttributes()
i = 0
while i < self.m_PlotInstances.numAttributes():
#预测值前的所有值照原来的拷贝
if i < toPredict.classIndex():
values[i] = toPredict.value(i)
elif i == toPredict.classIndex():
if isNominal:
#首选结果与备选结果的差值
values[i] = probActual - probNext
#预测结果
values[i + 1] = pred
#原始值
values[i + 2] = toPredict.value(i)
i += 2
else:
values[i] = pred
values[i + 1] = toPredict.value(i)
i += 1
else:
if isNominal:
values[i] = toPredict.value(i - 2)
else:
values[i] = toPredict.value(i - 1)
i += 1
# print("============")
# for m in values:
# print("val:",m)
# print("============")
self.m_PlotInstances.add(Instance(1.0, values))
if toPredict.classAttribute().isNominal():
if toPredict.isMissing(
toPredict.classIndex()) or Utils.isMissingValue(pred):
self.m_PlotShapes.append(Plot2D.MISSING_SHAPE)
elif pred != toPredict.classValue():
self.m_PlotShapes.append(Plot2D.ERROR_SHAPE)
else:
self.m_PlotShapes.append(Plot2D.CONST_AUTOMATIC_SHAPE)
if self.m_pointSizeProportionalToMargin:
self.m_PlotSizes.append(probActual - probNext)
else:
sizeAdj = 0
if pred != toPredict.classValue():
sizeAdj = 1
self.m_PlotSizes.append(Plot2D.DEFAULT_SHAPE_SIZE.value +
sizeAdj)
else:
errd = None
if not toPredict.isMissing(toPredict.classIndex(
)) and not Utils.isMissingValue(pred):
errd = pred - toPredict.classValue()
self.m_PlotShapes.append(Plot2D.CONST_AUTOMATIC_SHAPE)
else:
self.m_PlotShapes.append(Plot2D.MISSING_SHAPE)
self.m_PlotSizes.append(errd)
