def CvBayesread(path, verbose=0):
'''Read a CvBayes classifier from disk and return as a CvBayesClassifier instance. '''
NTrainEx = 0
basicStat = None
thePath = str(path)
try:
if not os.path.isdir(thePath):
if verbose > 0: print "ERROR: no such path: ", path
return None
if not os.path.isfile(str(os.path.join(
thePath, "ImputeData.tab"))) or not os.path.isfile(
str(os.path.join(thePath, "model.bayes"))):
if verbose > 0:
print "ERROR: Missing saved model/data files in: ", path
return None
impData = dataUtilities.DataTable(
str(os.path.join(thePath, "ImputeData.tab")),
createNewOn=orange.Variable.MakeStatus.OK)
loadedbayes = ml.CvNormalBayesClassifier()
loadedbayes.load(os.path.join(thePath, "model.bayes"))
# Load Scaling Values
if os.path.isdir(str(os.path.join(thePath, "scalingValues"))):
scalizer = dataUtilities.scalizer(
file=str(os.path.join(thePath, "scalingValues")))
else:
scalizer = None
#Load the var names oredered the way it was used when training
varNamesFile = open(os.path.join(thePath, "varNames.txt"), "r")
lines = varNamesFile.readlines()
varNames = eval(lines[0].strip())
if len(lines) >= 3:
NTrainEx = eval(lines[1].strip())
basicStat = eval(lines[2].strip())
varNamesFile.close()
# Read the parameters
if os.path.isfile(os.path.join(thePath, "parameters.pkl")):
fileh = open(os.path.join(thePath, "parameters.pkl"), "r")
parameters = pickle.load(fileh)
fileh.close()
else:
parameters = {}
return CvBayesClassifier(classifier=loadedbayes,
imputeData=impData[0],
classVar=impData.domain.classVar,
verbose=verbose,
loadedModel=True,
varNames=varNames,
NTrainEx=NTrainEx,
basicStat=basicStat,
scalizer=scalizer,
parameters=parameters)
except:
if verbose > 0: print "ERROR: Could not read model from ", path
def __call__(self, data, weight=None):
"""Creates a Bayes model from the data in origTrainingData. """
if not AZBaseClasses.AZLearner.__call__(self, data, weight):
return None
if data.domain.classVar.varType != orange.VarTypes.Discrete:
raise Exception(
"AZorngCvBayes can only be used for classification.")
#Remove from the domain any unused values of discrete attributes including class
data = dataUtilities.getDataWithoutUnusedValues(data, True)
#dataUtilities.rmAllMeta(data)
if len(data.domain.getmetas()) == 0:
trainingData = data
else:
trainingData = dataUtilities.getCopyWithoutMeta(data)
# Create the imputer
self.imputer = orange.ImputerConstructor_average(trainingData)
# Impute the data
trainingData = self.imputer(trainingData)
if self.scale:
self.scalizer = dataUtilities.scalizer()
self.scalizer.scaleClass = False
self.scalizer.nMin = -1
self.scalizer.nMax = 1
self.trainData = self.scalizer.scaleAndContinuizeData(trainingData)
else:
self.trainData = trainingData
self.scalizer = None
impData = self.imputer.defaults
#Convert the ExampleTable to CvMat
CvMatrices = dataUtilities.ExampleTable2CvMat(self.trainData)
mat = CvMatrices["matrix"]
responses = CvMatrices["responses"]
varTypes = CvMatrices["varTypes"]
missingDataMask = CvMatrices["missing_data_mask"]
#Create the model it MUST be created with the NON DEFAULT constructor or must call create
classifier = ml.CvNormalBayesClassifier()
classifier.clear()
#Train the model
#CvNormalBayesClassifier::train(const CvMat* _train_data, const CvMat* _responses, const CvMat* _var_idx =0, const CvMat* _sample_idx=0, bool update=false)
classifier.train(mat, responses, None, None, False)
return CvBayesClassifier(classifier=classifier,
classVar=trainingData.domain.classVar,
imputeData=impData,
verbose=self.verbose,
varNames=CvMatrices["varNames"],
nIter=None,
basicStat=self.basicStat,
NTrainEx=len(trainingData),
scalizer=self.scalizer,
parameters=self.parameters)
def __call__(self, data, weight=None):
"""Creates a Bayes model from the data in origTrainingData. """
if not AZBaseClasses.AZLearner.__call__(self, data, weight):
return None
if data.domain.classVar.varType != orange.VarTypes.Discrete:
raise Exception("AZorngCvBayes can only be used for classification.")
# Remove from the domain any unused values of discrete attributes including class
data = dataUtilities.getDataWithoutUnusedValues(data, True)
# dataUtilities.rmAllMeta(data)
if len(data.domain.getmetas()) == 0:
trainingData = data
else:
trainingData = dataUtilities.getCopyWithoutMeta(data)
# Create the imputer
self.imputer = orange.ImputerConstructor_average(trainingData)
# Impute the data
trainingData = self.imputer(trainingData)
if self.scale:
self.scalizer = dataUtilities.scalizer()
self.scalizer.scaleClass = False
self.scalizer.nMin = -1
self.scalizer.nMax = 1
self.trainData = self.scalizer.scaleAndContinuizeData(trainingData)
else:
self.trainData = trainingData
self.scalizer = None
impData = self.imputer.defaults
# Convert the ExampleTable to CvMat
CvMatrices = dataUtilities.ExampleTable2CvMat(self.trainData)
mat = CvMatrices["matrix"]
responses = CvMatrices["responses"]
varTypes = CvMatrices["varTypes"]
missingDataMask = CvMatrices["missing_data_mask"]
# Create the model it MUST be created with the NON DEFAULT constructor or must call create
classifier = ml.CvNormalBayesClassifier()
classifier.clear()
# Train the model
# CvNormalBayesClassifier::train(const CvMat* _train_data, const CvMat* _responses, const CvMat* _var_idx =0, const CvMat* _sample_idx=0, bool update=false)
classifier.train(mat, responses, None, None, False)
return CvBayesClassifier(
classifier=classifier,
classVar=trainingData.domain.classVar,
imputeData=impData,
verbose=self.verbose,
varNames=CvMatrices["varNames"],
nIter=None,
basicStat=self.basicStat,
NTrainEx=len(trainingData),
scalizer=self.scalizer,
)
def CvBayesread(path, verbose=0):
"""Read a CvBayes classifier from disk and return as a CvBayesClassifier instance. """
NTrainEx = 0
basicStat = None
thePath = str(path)
try:
if not os.path.isdir(thePath):
if verbose > 0:
print "ERROR: no such path: ", path
return None
if not os.path.isfile(str(os.path.join(thePath, "ImputeData.tab"))) or not os.path.isfile(
str(os.path.join(thePath, "model.bayes"))
):
if verbose > 0:
print "ERROR: Missing saved model/data files in: ", path
return None
impData = dataUtilities.DataTable(
str(os.path.join(thePath, "ImputeData.tab")), createNewOn=orange.Variable.MakeStatus.OK
)
loadedbayes = ml.CvNormalBayesClassifier()
loadedbayes.load(os.path.join(thePath, "model.bayes"))
# Load Scaling Values
if os.path.isdir(str(os.path.join(thePath, "scalingValues"))):
scalizer = dataUtilities.scalizer(file=str(os.path.join(thePath, "scalingValues")))
else:
scalizer = None
# Load the var names oredered the way it was used when training
varNamesFile = open(os.path.join(thePath, "varNames.txt"), "r")
lines = varNamesFile.readlines()
varNames = eval(lines[0].strip())
if len(lines) >= 3:
NTrainEx = eval(lines[1].strip())
basicStat = eval(lines[2].strip())
varNamesFile.close()
return CvBayesClassifier(
classifier=loadedbayes,
imputeData=impData[0],
classVar=impData.domain.classVar,
verbose=verbose,
loadedModel=True,
varNames=varNames,
NTrainEx=NTrainEx,
basicStat=basicStat,
scalizer=scalizer,
)
except:
if verbose > 0:
print "ERROR: Could not read model from ", path
def CvSVMread(path, verbose = 0):
'''Read a PLS classifier from disk and return as a PLSClassifier instance. '''
thePath = str(path)
NTrainEx = 0
basicStat = None
try:
if not os.path.isdir(thePath):
if verbose > 0: print "ERROR: no such path: ", path
return None
if not os.path.isfile(str(os.path.join(thePath,"ImputeData.tab"))) or not os.path.isfile(str(os.path.join(thePath,"model.svm"))):
if verbose > 0: print "ERROR: Missing saved model/data files in: ", path
return None
if os.path.isdir(str(os.path.join(thePath,"scalingValues"))):
scalizer = dataUtilities.scalizer(file=str(os.path.join(thePath,"scalingValues")))
else:
scalizer = None
impData = dataUtilities.DataTable(str(os.path.join(thePath,"ImputeData.tab")),createNewOn=orange.Variable.MakeStatus.OK)
loadedsvm = ml.CvSVM()
loadedsvm.load(os.path.join(thePath,"model.svm"))
#Load the var names oredered the way it was used when training
if (os.path.isfile(os.path.join(thePath,"varNames.txt"))):
varNamesFile = open(os.path.join(thePath,"varNames.txt"),"r")
lines = varNamesFile.readlines()
varNames = eval(lines[0].strip())
if len(lines) >= 3:
NTrainEx = eval(lines[1].strip())
basicStat = eval(lines[2].strip())
varNamesFile.close()
#thisVer = True
else:
if verbose > 0: print "WARNING: The model loaded was probably saved with azorange version 0.2.1 or lower"
varNames = [attr.name for attr in impData.domain.attributes]
#thisVer = False
# Read the parameters
if os.path.isfile(os.path.join(thePath,"parameters.pkl")):
fileh = open(os.path.join(thePath,"parameters.pkl"),"r")
parameters = pickle.load(fileh)
fileh.close()
else:
parameters = {}
return CvSVMClassifier(classifier = loadedsvm, scalizer = scalizer,imputeData=impData[0], classVar = impData.domain.classVar, verbose = verbose, loadedModel = True, varNames = varNames, NTrainEx = NTrainEx, basicStat = basicStat, parameters = parameters)
except:
if verbose > 0: print "ERROR: Could not read model from ", path
def CvSVMread(path, verbose = 0):
'''Read a PLS classifier from disk and return as a PLSClassifier instance. '''
thePath = str(path)
NTrainEx = 0
basicStat = None
try:
if not os.path.isdir(thePath):
if verbose > 0: print "ERROR: no such path: ", path
return None
if not os.path.isfile(str(os.path.join(thePath,"ImputeData.tab"))) or not os.path.isfile(str(os.path.join(thePath,"model.svm"))):
if verbose > 0: print "ERROR: Missing saved model/data files in: ", path
return None
if os.path.isdir(str(os.path.join(thePath,"scalingValues"))):
scalizer = dataUtilities.scalizer(file=str(os.path.join(thePath,"scalingValues")))
else:
scalizer = None
impData = dataUtilities.DataTable(str(os.path.join(thePath,"ImputeData.tab")),createNewOn=orange.Variable.MakeStatus.OK)
loadedsvm = ml.CvSVM()
loadedsvm.load(os.path.join(thePath,"model.svm"))
#Load the var names oredered the way it was used when training
if (os.path.isfile(os.path.join(thePath,"varNames.txt"))):
varNamesFile = open(os.path.join(thePath,"varNames.txt"),"r")
lines = varNamesFile.readlines()
varNames = eval(lines[0].strip())
if len(lines) >= 3:
NTrainEx = eval(lines[1].strip())
basicStat = eval(lines[2].strip())
varNamesFile.close()
#thisVer = True
else:
if verbose > 0: print "WARNING: The model loaded was probably saved with azorange version 0.2.1 or lower"
varNames = [attr.name for attr in impData.domain.attributes]
#thisVer = False
# Read the parameters
if os.path.isfile(os.path.join(thePath,"parameters.pkl")):
fileh = open(os.path.join(thePath,"parameters.pkl"),"r")
parameters = pickle.load(fileh)
fileh.close()
else:
parameters = {}
return CvSVMClassifier(classifier = loadedsvm, scalizer = scalizer,imputeData=impData[0], classVar = impData.domain.classVar, verbose = verbose, loadedModel = True, varNames = varNames, NTrainEx = NTrainEx, basicStat = basicStat, parameters = parameters)
except:
if verbose > 0: print "ERROR: Could not read model from ", path
def __call__(self, data, weight = None):
"""Creates an SVM model from the data in origTrainingData. """
if not AZBaseClasses.AZLearner.__call__(self, data, weight):
if self.verbose > 0: print "Could not create base class instance"
return None
dataUtilities.verbose = self.verbose
#Remove from the domain any unused values of discrete attributes including class
data = dataUtilities.getDataWithoutUnusedValues(data,True)
#dataUtilities.rmAllMeta(data)
if len(data.domain.getmetas()) == 0:
trainingData = data
else:
trainingData = dataUtilities.getCopyWithoutMeta(data)
# Create the imputer
self.imputer = orange.ImputerConstructor_average(trainingData)
# Impute the data
trainingData = self.imputer(trainingData)
if self.scaleData:
self.scalizer = dataUtilities.scalizer()
for attr in ("nMin","nMax","nClassMin","nClassMax"):
setattr(self.scalizer, attr, getattr(self, attr))
#Only scale the class in regression. On classification, set scaleClass to False
self.scalizer.scaleClass = self.scaleClass and trainingData.domain.classVar.varType == orange.VarTypes.Continuous or False
self.scalizer.nClassMin = self.nClassMin
self.scalizer.nClassMax = self.nClassMax
self.trainData = self.scalizer.scaleAndContinuizeData(trainingData)
else:
self.trainData = trainingData
self.scalizer = None
impData=self.imputer.defaults
#Adjust the svm type according to the problem (regression or classification)
if self.svm_type != 102:
if trainingData.domain.classVar.varType == orange.VarTypes.Continuous:
if self.svm_type in (100,101):
self.svm_type += 3
self.eps = self.epsR #Regression eps
else:
if self.svm_type in (103,104):
self.svm_type -= 3
self.eps = self.epsC #Classification eps
#Convert the ExampleTable to CvMat
CvMatices = dataUtilities.ExampleTable2CvMat(self.trainData)
mat = CvMatices["matrix"]
responses = CvMatices["responses"]
varTypes = CvMatices["varTypes"]
#Configure SVM self.params
self.params = ml.CvSVMParams()
self.params.svm_type = self.svm_type
self.params.kernel_type = self.kernel_type
self.params.degree = self.degree
self.params.gamma = self.gamma
self.params.coef0 = self.coef0
self.params.C = self.C
self.params.nu = self.nu
self.params.p = self.p
#Process the priors from a str, list or dict to a valid list
priors = self.convertPriors(self.priors,trainingData.domain.classVar)
if type(priors) == str: #If a string is returned, there was a failure, and it is the respective error mnessage.
print priors
return None
if priors and self.params.svm_type != ml.CvSVM.C_SVC:
priors = None
if self.verbose > 0: print "WARNING: The priors will not have any effect. They can only be used with C_SVC SVM-Type."
elif priors:
priors = dataUtilities. List2CvMat(priors)
self.params.class_weights = priors
term_crit = cv.CvTermCriteria()
term_crit.type = self.stopCrit #cv.CV_TERMCRIT_EPS # or CV_TERMCRIT_ITER
term_crit.epsilon = self.eps #Or use: term_crit.max_iter = x
term_crit.max_iter = self.maxIter #Or use: term_crit.max_iter = x
self.params.term_crit = term_crit
#Create the model
classifier = ml.CvSVM()
#Train the model
#train(trainData, responses, varIdx, SampleIdx, Params)
classifier.train(mat,responses,None,None,self.params)
if classifier.get_support_vector_count() < 1:
print "WARNING: The number of support vectors is 0."
print "This could be becasue the margin between the hyper plane and the support vectors has become zero."
print "Try to modify the parameters controlling the margin. "
print "For example decrease C or p(regression only)."
print "No SVM model returned!"
return None
else:
return CvSVMClassifier(classifier = classifier, classVar = data.domain.classVar, scalizer = self.scalizer, imputeData=impData, verbose = self.verbose, varNames = CvMatices["varNames"], basicStat = self.basicStat, NTrainEx = len(trainingData))
def __call__(self, data, weight = None):
"""Creates an SVM model from the data in origTrainingData. """
if not AZBaseClasses.AZLearner.__call__(self, data, weight):
if self.verbose > 0: print "Could not create base class instance"
return None
dataUtilities.verbose = self.verbose
#Remove from the domain any unused values of discrete attributes including class
data = dataUtilities.getDataWithoutUnusedValues(data,True)
#dataUtilities.rmAllMeta(data)
if len(data.domain.getmetas()) == 0:
trainingData = data
else:
trainingData = dataUtilities.getCopyWithoutMeta(data)
# Create the imputer
self.imputer = orange.ImputerConstructor_average(trainingData)
# Impute the data
trainingData = self.imputer(trainingData)
if self.scaleData:
self.scalizer = dataUtilities.scalizer()
for attr in ("nMin","nMax","nClassMin","nClassMax"):
setattr(self.scalizer, attr, getattr(self, attr))
#Only scale the class in regression. On classification, set scaleClass to False
self.scalizer.scaleClass = self.scaleClass and trainingData.domain.classVar.varType == orange.VarTypes.Continuous or False
self.scalizer.nClassMin = self.nClassMin
self.scalizer.nClassMax = self.nClassMax
self.trainData = self.scalizer.scaleAndContinuizeData(trainingData)
else:
self.trainData = trainingData
self.scalizer = None
impData=self.imputer.defaults
#Adjust the svm type according to the problem (regression or classification)
if self.svm_type != 102:
if trainingData.domain.classVar.varType == orange.VarTypes.Continuous:
if self.svm_type in (100,101):
self.svm_type += 3
self.eps = self.epsR #Regression eps
else:
if self.svm_type in (103,104):
self.svm_type -= 3
self.eps = self.epsC #Classification eps
#Convert the ExampleTable to CvMat
CvMatices = dataUtilities.ExampleTable2CvMat(self.trainData)
mat = CvMatices["matrix"]
responses = CvMatices["responses"]
varTypes = CvMatices["varTypes"]
#Configure SVM self.params
self.params = ml.CvSVMParams()
self.params.svm_type = self.svm_type
self.params.kernel_type = self.kernel_type
self.params.degree = self.degree
self.params.gamma = self.gamma
self.params.coef0 = self.coef0
self.params.C = self.C
self.params.nu = self.nu
self.params.p = self.p
#Process the priors from a str, list or dict to a valid list
priors = self.convertPriors(self.priors,trainingData.domain.classVar)
if type(priors) == str: #If a string is returned, there was a failure, and it is the respective error mnessage.
print priors
return None
if priors and self.params.svm_type != ml.CvSVM.C_SVC:
priors = None
if self.verbose > 0: print "WARNING: The priors will not have any effect. They can only be used with C_SVC SVM-Type."
elif priors:
priors = dataUtilities. List2CvMat(priors)
self.params.class_weights = priors
term_crit = cv.CvTermCriteria()
term_crit.type = self.stopCrit #cv.CV_TERMCRIT_EPS # or CV_TERMCRIT_ITER
term_crit.epsilon = self.eps #Or use: term_crit.max_iter = x
term_crit.max_iter = self.maxIter #Or use: term_crit.max_iter = x
self.params.term_crit = term_crit
#Create the model
classifier = ml.CvSVM()
#Train the model
#train(trainData, responses, varIdx, SampleIdx, Params)
classifier.train(mat,responses,None,None,self.params)
if classifier.get_support_vector_count() < 1:
print "WARNING: The number of support vectors is 0."
print "This could be becasue the margin between the hyper plane and the support vectors has become zero."
print "Try to modify the parameters controlling the margin. "
print "For example decrease C or p(regression only)."
print "No SVM model returned!"
return None
else:
return CvSVMClassifier(classifier = classifier, classVar = data.domain.classVar, scalizer = self.scalizer, imputeData=impData, verbose = self.verbose, varNames = CvMatices["varNames"], basicStat = self.basicStat, NTrainEx = len(trainingData), parameters = self.parameters)
