def _getProbabilities(self, ProbOf1):
"""Get the orange like output probabilities for the current predicted example"""
#This is only valid for binary classifiers opencv limitation!
# From openCv we know that the probability returned for this example represents the fraction of tree votes for class 1
#Find the classValue string that is represented by the scalar 1 in opencvRF
class1 = dataUtilities.CvMat2orangeResponse(1, self.classVar).value
dist = orange.DiscDistribution(self.classVar)
dist[self.classVar.values.index(class1)] = ProbOf1
dist[not self.classVar.values.index(class1)] = 1 - ProbOf1
return dist
def _singlePredict(self, origExamples = None, resultType = orange.GetValue, returnDFV = False):
"""
orange.GetBoth - <type 'tuple'> -> (<orange.Value 'Act'='3.44158792'>, <3.442: 1.000>)
orange.GetValue - <type 'orange.Value'> -> <orange.Value 'Act'='3.44158792'>
orange.GetProbabilities - <type 'orange.DiscDistribution'> -> <0.000, 0.000>
returnDFV - Flag indicating to return the Decision Function Value. If set to True, it will encapsulate the original result asked by the keyword resultType and the DFV into a tuple:
((<orange.Value 'Act'='3.44158792'>, <3.442: 1.000>), 2.34443)
(<orange.Value 'Act'='3.44158792'>, 2.34443)
(<0.000, 0.000>, 2.34443)
If it is not a binary classifier, DFV will be equal to None
DFV will be a value from greater or equal to 0
"""
res = None
#dataUtilities.rmAllMeta(examples)
if len(origExamples.domain.getmetas()) == 0:
examples = origExamples
else:
examples = dataUtilities.getCopyWithoutMeta(origExamples)
#Check if the examples are compatible with the classifier (attributes order and varType compatibility)
if self.imputer:
dataUtilities.verbose = self.verbose
if not self.ExFix.ready:
self.ExFix.set_domain(self.imputer.defaults.domain)
self.ExFix.set_examplesFixedLog(self.examplesFixedLog)
inExamples = self.ExFix.fixExample(examples)
if not inExamples:
if self.verbose > 0: print "Warning no example. Returning None prediction"
return None
#Imput the examples if there are missing values
examplesImp = self.imputer(inExamples)
# There is a problem with using the imputer when examples contain meta attributes.
# Unable to remove meta attributes from the examples. OK to rm meta from ExampleTables, but not from Example objects.
if not examplesImp:
if self.verbose > 0: print "Unable to predict with the SVM model."
if self.verbose > 0: print "Perhaps you need to remove meta attributes from your examples."
return None
else:
if self.verbose > 0: print "Warning: No Imputer in SVM Classifier"
examplesImp = examples
if self.classifier.get_support_vector_count() ==0:
if self.verbose > 0: print "WARNING: Support Vectors count is 0 (zero)"
DFV = None
if examplesImp:
if self.scalizer:
exToPredict = dataUtilities.Example2CvMat(self.scalizer.scaleEx(examplesImp,True), self.varNames)
res = self.classifier.predict(exToPredict)
res = self.scalizer.convertClass(res)
if self.classVar.varType != orange.VarTypes.Continuous and len(self.classVar.values) == 2 and returnDFV:
DFV = self.classifier.predict(exToPredict, True)
else:
#On Regression models assume the DVF as the value predicted
DFV = res
self._updateDFVExtremes(DFV)
res = dataUtilities.CvMat2orangeResponse(res,self.classVar)
else:
exToPredict = dataUtilities.Example2CvMat(examplesImp,self.varNames)
res = self.classifier.predict(exToPredict)
if self.classVar.varType != orange.VarTypes.Continuous and len(self.classVar.values) == 2 and returnDFV:
DFV = self.classifier.predict(exToPredict, True)
else:
#On Regression models assume the DVF as the value predicted
DFV = res
self._updateDFVExtremes(DFV)
res = dataUtilities.CvMat2orangeResponse(res,self.classVar)
if resultType!=orange.GetValue:
if examplesImp.domain.classVar.varType != orange.VarTypes.Continuous:
dist = orange.DiscDistribution(examplesImp.domain.classVar)
dist[res]=1
else:
y_hat = self.classVar(res)
dist = Orange.statistics.distribution.Continuous(self.classVar)
dist[y_hat] = 1.0
if resultType==orange.GetProbabilities:
res = dist
else:
res = (res,dist)
if returnDFV:
res = (res,DFV)
self.nPredictions += 1
return res
def _singlePredict(self,
origExamples=None,
resultType=orange.GetValue,
returnDFV=False):
res = None
"""
orange.GetBoth - <type 'tuple'> -> (<orange.Value 'Act'='3.44158792'>, <3.442: 1.000>)
orange.GetValue - <type 'orange.Value'> -> <orange.Value 'Act'='3.44158792'>
orange.GetProbabilities - <type 'orange.DiscDistribution'> -> <0.000, 0.000>
"""
#dataUtilities.rmAllMeta(examples)
if len(origExamples.domain.getmetas()) == 0:
examples = origExamples
else:
examples = dataUtilities.getCopyWithoutMeta(origExamples)
#Check if the examples are compatible with the classifier (attributes order and varType compatibility)
if self.verbose > 1: dataUtilities.verbose = self.verbose
if not self.ExFix.ready:
self.ExFix.set_domain(self.imputer.defaults.domain)
self.ExFix.set_examplesFixedLog(self.examplesFixedLog)
inExamples = self.ExFix.fixExample(examples)
if not inExamples:
return None
#Imput the examples if there are missing values
examplesImp = self.imputer(inExamples)
# There is a problem with using the imputer when examples contain meta attributes.
# Unable to remove meta attributes from the examples. OK to rm meta from ExampleTables, but not from Example objects.
if not examplesImp:
if self.verbose > 0: print "Unable to predict with the ANN model."
if self.verbose > 0:
print "Perhaps you need to remove meta attributes from your examples."
return None
res = None
if self.classVar.varType == orange.VarTypes.Continuous:
Nout = 1
else:
Nout = len(self.classVar.values)
out = cv.cvCreateMat(1, Nout, cv.CV_32FC1)
self.classifier.predict(
dataUtilities.Example2CvMat(examplesImp, self.varNames), out)
#print "OUT = ",out
#print out,"->",dataUtilities.CvMat2orangeResponse(out,self.classVar,True),":",origExamples[self.classVar.name].value
res = dataUtilities.CvMat2orangeResponse(out, self.classVar, True)
#print "RES=",res
DFV = None
if out.cols > 1:
fannOutVector = dataUtilities.CvMat2List(out)[0]
probabilities = self.__getProbabilities(fannOutVector)
#Compute the DFV
if self.classVar.varType == orange.VarTypes.Discrete and len(
self.classVar.values) == 2:
DFV = probabilities[0]
# Subtract 0.5 so that the threshold is 0 as all learners DFV
DFV -= 0.5
self._updateDFVExtremes(DFV)
# Retrun the desired quantity
if resultType == orange.GetProbabilities:
res = probabilities
else:
if resultType == orange.GetBoth:
res = (res, probabilities)
else:
#On Regression models, assume the DFV as the value predicted
DFV = res.value
self._updateDFVExtremes(DFV)
y_hat = self.classVar(res.value)
dist = Orange.statistics.distribution.Continuous(self.classVar)
dist[y_hat] = 1.0
if resultType == orange.GetProbabilities:
res = dist
else:
if resultType == orange.GetBoth:
res = (res, dist)
self.nPredictions += 1
if returnDFV:
return (res, DFV)
else:
return res
def _singlePredict(self, origExample = None, resultType = orange.GetValue, returnDFV = False):
"""
orange.GetBoth - <type 'tuple'> -> (<orange.Value 'Act'='3.44158792'>, <3.442: 1.000>)
orange.GetValue - <type 'orange.Value'> -> <orange.Value 'Act'='3.44158792'>
orange.GetProbabilities - <type 'orange.DiscDistribution'> -> <0.000, 0.000>
returnDFV - Flag indicating to return the Decision Function Value. If set to True, it will encapsulate the original result asked by the keyword resultType and the DFV into a tuple:
((<orange.Value 'Act'='3.44158792'>, <3.442: 1.000>), 0.34443)
(<orange.Value 'Act'='3.44158792'>, 0.34443)
(<0.000, 0.000>, 0.34443)
If it is not a binary classifier, DFV will be equal to None
DFV will be a value from -0.5 to 0.5
"""
if origExample == None:
return self.classifier(None, resultType)
else:
##scPA
# Remove Meta attributes from example
#dataUtilities.rmAllMeta(example)
if len(origExample.domain.getmetas()) == 0:
example = origExample
else:
example = dataUtilities.getCopyWithoutMeta(origExample)
if not self.ExFix.ready:
self.ExFix.set_domain(self.domain)
self.ExFix.set_examplesFixedLog(self.examplesFixedLog)
inExample = self.ExFix.fixExample(example)
if inExample: ##only procceds if the example was fixed or already ok, i.e. inExample != None
##ecPA
##scPA
if self.useBuiltInMissValHandling:
#compute the missing _mask
(exampleCvMat, missing_mask) = dataUtilities.Example2CvMat(inExample,self.varNames,self.thisVer,True)
else:
missing_mask = None
if self.imputer:
examplesImp = self.imputer(inExample)
# There is a problem with using the imputer when examples contain meta attributes.
# Unable to remove meta attributes from the examples. OK to rm meta from ExampleTables, but not from Example objects.
if not examplesImp:
if self.verbose > 0: print "Unable to predict with the RF model."
if self.verbose > 0: print "Perhaps you need to remove meta attributes from your examples."
return None
else:
examplesImp = inExample
##ecPA
# Remove the response variable from the example to be predicted and transfrom the example to a tab sep string
exampleCvMat = dataUtilities.Example2CvMat(examplesImp,self.varNames,self.thisVer)
del examplesImp
if not exampleCvMat:
if self.verbose > 0: print "Could not convert the example to a valid CvMat objct for prediction"
return none
# Predict using the RFmodel object
prediction = self.classifier.predict(exampleCvMat,missing_mask)
probabilities = None
DFV = None
# Back transform the prediction to the original classes and calc probabilities
prediction = dataUtilities.CvMat2orangeResponse(prediction, self.classVar)
# Calculate artificial probabilities - not returned by the OpenCV RF algorithm
if self.classVar.varType == orange.VarTypes.Discrete:
if resultType != orange.GetValue:
if len(self.classVar.values) == 2:
probOf1 = self.classifier.predict_prob(exampleCvMat,missing_mask)
probabilities = self.__getProbabilities(probOf1)
DFV = self.convert2DFV(probOf1)
self._isRealProb = True
else:
#Need to make sure to return meanful probabilities to the cases where opencvRF does not support probabilities
# to be compatible with possible callers asking for probabilities.
probabilities = self.__generateProbabilities(prediction)
self._isRealProb = False
elif len(self.classVar.values) == 2 and returnDFV:
DFV = self.convert2DFV(self.classifier.predict_prob(exampleCvMat,missing_mask))
else:
#On Regression models assume the DVF as the value predicted
if not prediction.isSpecial():
DFV = float(prediction.value)
self._updateDFVExtremes(DFV)
y_hat = self.classVar(prediction)
probabilities = Orange.statistics.distribution.Continuous(self.classVar)
probabilities[y_hat] = 1.0
del exampleCvMat
del inExample
else:
if self.verbose > 0:
print "No prediction made for example:"
print example
print "The example does not have the same variables as the model."
prediction = None
probabilities = None
DFV = None
##scPA
del example
##ecPA
if resultType == orange.GetBoth:
if prediction:
orangePrediction = orange.Value(self.classVar, prediction)
else:
orangePrediction = None
res = orangePrediction, probabilities
elif resultType == orange.GetProbabilities:
res = probabilities
else:
if prediction:
orangePrediction = orange.Value(self.classVar, prediction)
else:
orangePrediction = None
res = orangePrediction
self.nPredictions += 1
if returnDFV:
return (res,DFV)
else:
return res
def _singlePredict(self,
origExamples=None,
resultType=orange.GetValue,
returnDFV=False):
res = None
"""
orange.GetBoth - <type 'tuple'> -> (<orange.Value 'Act'='3.44158792'>, <3.442: 1.000>)
orange.GetValue - <type 'orange.Value'> -> <orange.Value 'Act'='3.44158792'>
orange.GetProbabilities - <type 'orange.DiscDistribution'> -> <0.000, 0.000>
"""
#dataUtilities.rmAllMeta(examples)
if len(origExamples.domain.getmetas()) == 0:
examples = origExamples
else:
examples = dataUtilities.getCopyWithoutMeta(origExamples)
#Check if the examples are compatible with the classifier (attributes order and varType compatibility)
dataUtilities.verbose = self.verbose
if not self.ExFix.ready:
self.ExFix.set_domain(self.imputer.defaults.domain)
self.ExFix.set_examplesFixedLog(self.examplesFixedLog)
inExamples = self.ExFix.fixExample(examples)
if not inExamples:
return None
#Imput the examples if there are missing values
examplesImp = self.imputer(inExamples)
# There is a problem with using the imputer when examples contain meta attributes.
# Unable to remove meta attributes from the examples. OK to rm meta from ExampleTables, but not from Example objects.
if not examplesImp:
if self.verbose > 0:
print "Unable to predict with the Bayes model."
if self.verbose > 0:
print "Perhaps you need to remove meta attributes from your examples."
return None
if self.scalizer:
ex = self.scalizer.scaleEx(examplesImp)
else:
ex = examplesImp
out = self.classifier.predict(
dataUtilities.Example2CvMat(ex, self.varNames))
#print "OUT:",out
probabilities = None
DFV = None
# Back transform the prediction to the original classes and calc probabilities
prediction = dataUtilities.CvMat2orangeResponse(out, self.classVar)
#print "Prediction:",prediction
# Calculate artificial probabilities - not returned by the OpenCV RF algorithm
if self.classVar.varType == orange.VarTypes.Discrete:
if resultType != orange.GetValue:
#Need to make sure to return meanful probabilities to the cases where opencvRF does not support probabilities
# to be compatible with possible callers asking for probabilities.
probabilities = self.__generateProbabilities(prediction)
self._isRealProb = False
else:
#On Regression models assume the DVF as the value predicted
DFV = prediction
self._updateDFVExtremes(DFV)
if resultType == orange.GetBoth:
if prediction:
orangePrediction = orange.Value(self.classVar, prediction)
else:
orangePrediction = None
res = orangePrediction, probabilities
elif resultType == orange.GetProbabilities:
res = probabilities
else:
if prediction:
orangePrediction = orange.Value(self.classVar, prediction)
else:
orangePrediction = None
res = orangePrediction
self.nPredictions += 1
if returnDFV:
return (res, DFV)
else:
return res