def saveData(self):
# Saves data into root directory
rootDir = self.recentDirs[self.dircombo.currentIndex()]
if rootDir == "(none)" or self.dataStructure == None:
self.infoa.setText("Select a directory first.")
return
# count number of files to save
n = sum([sum([1 for d in ds]) for (sdn, ds) in self.dataStructure])
if n == 0:
self.infoa.setText("No files to save.")
return
pbStep = 100./n
self.progressBarInit()
for (subDirName, datasets) in self.dataStructure:
targetDir = os.path.join(rootDir, subDirName)
if not os.path.exists(targetDir):
try:
os.mkdir(targetDir)
except:
self.infoa.setText("Could not create target directory: " + targetDir)
self.error("Could not create target directory: " + targetDir)
for data in datasets:
fname = os.path.join(targetDir, data.name + '.tab')
orange.saveTabDelimited(fname, data)
self.progressBarAdvance(pbStep)
self.infoa.setText("Data saved to %s" % rootDir)
self.progressBarFinished()
def saveData(self):
# Saves data into root directory
rootDir = self.recentDirs[self.dircombo.currentIndex()]
if rootDir == "(none)" or self.dataStructure == None:
self.infoa.setText("Select a directory first.")
return
# count number of files to save
n = sum([sum([1 for d in ds]) for (sdn, ds) in self.dataStructure])
if n == 0:
self.infoa.setText("No files to save.")
return
pbStep = 100. / n
self.progressBarInit()
for (subDirName, datasets) in self.dataStructure:
targetDir = os.path.join(rootDir, subDirName)
if not os.path.exists(targetDir):
try:
os.mkdir(targetDir)
except:
self.infoa.setText("Could not create target directory: " +
targetDir)
self.error("Could not create target directory: " +
targetDir)
for data in datasets:
fname = os.path.join(targetDir, data.name + '.tab')
orange.saveTabDelimited(fname, data)
self.progressBarAdvance(pbStep)
self.infoa.setText("Data saved to %s" % rootDir)
self.progressBarFinished()
def save_table(self, filename):
'''
It stores the term-docuemtn matrix as a tab delimited file
which is supported by Orange.
'''
if self.td_matrix != None:
t = construct_orange_table(self.attributes, self.td_matrix)
t = add_metas_to_table(t, self.document_dict.keys())
orange.saveTabDelimited (filename+".tab", t)
self.table_name = filename
else:
raise Exception("Oops. It seems that you have not constructed a term-document matrix. Use construct_term_document_matrix()")
def save_table(self, filename):
'''
It stores the term-docuemtn matrix as a tab delimited file
which is supported by Orange.
'''
if self.td_matrix != None:
t = construct_orange_table(self.attributes, self.td_matrix)
t = add_metas_to_table(t, self.document_dict.keys())
orange.saveTabDelimited(filename + ".tab", t)
self.table_name = filename
else:
raise Exception(
"Oops. It seems that you have not constructed a term-document matrix. Use construct_term_document_matrix()"
)
def generateETStruct(path, medaData, numGenes=None):
ddbList = Dicty.DAnnotation.getDDBList()
if not os.path.exists(path):
os.mkdir(path)
medaData = Dicty.DData.DData_Nancy()
for st in medaData.strains:
pathSt = path + "\\" + st
if not os.path.exists(pathSt):
os.mkdir(pathSt)
for rep in medaData.strain2replicaList(st):
ma2d = medaData.getRaw2d(rep)
et = Meda.Preproc.ma2orng(ma2d,Meda.Preproc.getTcDomain(ma2d.shape[1], False, [], None))
et.domain.addmeta(orange.newmetaid(), orange.StringVariable("DDB"))
for eIdx,e in enumerate(et):
e["DDB"] = ddbList[eIdx]
if numGenes:
orange.saveTabDelimited(pathSt + "\\" + rep + ".tab", orange.ExampleTable(et[:numGenes]))
else:
orange.saveTabDelimited(pathSt + "\\" + rep + ".tab", et)
def testOrangeTableCreation(self):
x = Orange.data.variable.Continuous("word1")
y = Orange.data.variable.Continuous("word2")
z = Orange.data.variable.Continuous("word3")
domain = Orange.data.Domain([x, y, z], False)
#Data
data = numpy.array([[1, 2, 3], [3, 2, 1]])
t = Orange.data.Table(domain, data)
#Meta
tweet_id = Orange.data.variable.String("id")
id = Orange.data.new_meta_id()
t.add_meta_attribute(id)
t.domain.add_meta(id, tweet_id)
for inst in t:
inst[id] = "hello_id"
orange.saveTabDelimited ("test_table_creation.tab", t)
def testOrangeTableCreation(self):
x = Orange.data.variable.Continuous("word1")
y = Orange.data.variable.Continuous("word2")
z = Orange.data.variable.Continuous("word3")
domain = Orange.data.Domain([x, y, z], False)
#Data
data = numpy.array([[1, 2, 3], [3, 2, 1]])
t = Orange.data.Table(domain, data)
#Meta
tweet_id = Orange.data.variable.String("id")
id = Orange.data.new_meta_id()
t.add_meta_attribute(id)
t.domain.add_meta(id, tweet_id)
for inst in t:
inst[id] = "hello_id"
orange.saveTabDelimited("test_table_creation.tab", t)
def generateETStruct(path, medaData, numGenes=None):
ddbList = Dicty.DAnnotation.getDDBList()
if not os.path.exists(path):
os.mkdir(path)
medaData = Dicty.DData.DData_Nancy()
for st in medaData.strains:
pathSt = path + "\\" + st
if not os.path.exists(pathSt):
os.mkdir(pathSt)
for rep in medaData.strain2replicaList(st):
ma2d = medaData.getRaw2d(rep)
et = Meda.Preproc.ma2orng(
ma2d,
Meda.Preproc.getTcDomain(ma2d.shape[1], False, [], None))
et.domain.addmeta(orange.newmetaid(),
orange.StringVariable("DDB"))
for eIdx, e in enumerate(et):
e["DDB"] = ddbList[eIdx]
if numGenes:
orange.saveTabDelimited(pathSt + "\\" + rep + ".tab",
orange.ExampleTable(et[:numGenes]))
else:
orange.saveTabDelimited(pathSt + "\\" + rep + ".tab", et)
class DateVariable(orange.PythonVariable):
def str2val(self, str):
return time.strptime(str, "%b %d %Y")
def val2str(self, val):
return time.strftime("%b %d %Y (%a)", val)
def filestr2val(self, str, example):
if str == "unknown":
return orange.PythonValueSpecial(orange.ValueTypes.DK)
return DateValue(time.strptime(str, "%m/%d/%Y"))
def val2filestr(self, val, example):
return time.strftime("%m/%d/%Y", val)
birth = DateVariable("birth")
val = birth("Aug 19 2003")
print val
data = orange.ExampleTable("lenses")
newdomain = orange.Domain(data.domain.attributes + [birth],
data.domain.classVar)
newdata = orange.ExampleTable(newdomain, data)
newdata[0]["birth"] = "Aug 19 2003"
print newdata[0]
orange.saveTabDelimited("del2", newdata)
def __call__(self, trainingData, weight=None):
"""Creates an PLS model from the data in trainingData. """
if not AZBaseClasses.AZLearner.__call__(self,trainingData, weight):
return None
#Remove from the domain any unused values of discrete attributes including class
trainingData = dataUtilities.getDataWithoutUnusedValues(trainingData,True)
# Create path for the Orange data
scratchdir = miscUtilities.createScratchDir(desc="PLS")
OrngFile = os.path.join(scratchdir,"OrngData.tab")
# Remove meta attributes from training data to make the imputer work with examples without the meta attributes.
#dataUtilities.rmAllMeta(trainingData)
if len(trainingData.domain.getmetas()) == 0:
trainData = trainingData
else:
trainData = dataUtilities.getCopyWithoutMeta(trainingData)
# Create the imputer
self.imputer = orange.ImputerConstructor_average(trainData)
# Impute the data
trainData = self.imputer(trainData)
# Save the Data already imputed to an Orange formated file
if self.verbose > 1: print time.asctime(), "Saving Orange Data to a tab file..."
orange.saveTabDelimited(OrngFile,trainData)
if self.verbose > 1: print time.asctime(), "done"
# Create the PLS instance
if self.verbose > 1: print time.asctime(), "Creating PLS Object..."
learner = pls.PlsAPI()
if self.verbose > 1: print time.asctime(), "done"
# Assign the PLS parameters
learner.SetParameter('v',str(self.verbose))
learner.SetParameter('debug',str(int(self.verbose > 0)))
learner.SetParameter('method',self.method)
if types.IntType(self.k) > len(trainData.domain.attributes):
learner.SetParameter('k',str(len(trainData.domain.attributes)))
if self.verbose > 0: print "Warning! The number of components were more than the number of attributes."
if self.verbose > 0: print " Components were set to ",len(trainData.domain.attributes)
else:
learner.SetParameter('k',self.k)
learner.SetParameter('precision',self.precision)
learner.SetParameter('sDir',scratchdir) #AZOC.SCRATCHDIR)
# Read the Orange Formated file and Train the Algorithm
# TRAIN
if self.verbose > 1: print time.asctime(), "Training..."
learner.Train(OrngFile)
if self.verbose > 1:
print "Train finished at ", time.asctime()
print "PLS trained in: " + str(learner.GetCPUTrainTime()) + " seconds";
print "Method: " + learner.GetParameter("method")
print "Components: " + learner.GetParameter("k")
print "Precision: " + learner.GetParameter("precision")
# Remove the scratch file
if self.verbose == 0:
miscUtilities.removeDir(scratchdir)
else:
print "The directory " + scratchdir + " was not deleted because DEBUG flag is ON"
del trainData
impData=self.imputer.defaults
return PLSClassifier(classifier = learner, name = "Classifier of " + self.name, classVar = trainingData.domain.classVar, imputeData=impData, verbose = self.verbose, varNames = [attr.name for attr in trainingData.domain.attributes], NTrainEx = len(trainingData), basicStat = self.basicStat, parameters = self.parameters)#learner.GetClassVarName())#
import orange, time
class DateVariable(orange.PythonVariable):
def str2val(self, str):
return time.strptime(str, "%b %d %Y")
def val2str(self, val):
return time.strftime("%b %d %Y (%a)", val)
def filestr2val(self, str, example):
if str == "unknown":
return orange.PythonValueSpecial(orange.ValueTypes.DK)
return DateValue(time.strptime(str, "%m/%d/%Y"))
def val2filestr(self, val, example):
return time.strftime("%m/%d/%Y", val)
birth = DateVariable("birth")
val = birth("Aug 19 2003")
print val
data = orange.ExampleTable("lenses")
newdomain = orange.Domain(data.domain.attributes + [birth], data.domain.classVar)
newdata = orange.ExampleTable(newdomain, data)
newdata[0]["birth"] = "Aug 19 2003"
print newdata[0]
orange.saveTabDelimited("del2", newdata)
def optimizeParameters(self):
""" Sets up the input learner with tuned parameters """
self.clearErrors()
self.tunedPars = None
if hasattr(self.learner,"optimized"):
self.learner.optimized = False
if not self.learner:
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
self.updateInfo()
return
# Apply the parameters var with values on configuration table of GUI (user could have changed them!)
if not self.updateParametersFromTable():
return
if not self.dataset:
self.dataset = None
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
self.updateInfo()
return
# Progess Bar 1
optSteps = 3
progress1 = QProgressDialog("Gathering data and configuring the optimizer...", "Cancel", 0, optSteps, self,Qt.Dialog)#, "progress", True )
progress1.setWindowModality(Qt.WindowModal)
bar1 = QProgressBar(progress1)
bar1.show()
progress1.setBar(bar1)
#progress1.setTotalSteps(optSteps)
progress1.setMinimumDuration(0)
progress1.forceShow()
progress1.setValue(0)
time.sleep(0.1)
progress1.setValue(0)
# Create path for running the optimizer
randNr = random.randint(0,10000)
if self.execEnv == 0:
scratchdir = miscUtilities.createScratchDir(desc = "OWParamOpt_Serial")
else:
scratchdir = miscUtilities.createScratchDir(desc ="OWParamOpt_MPI", baseDir = AZOC.NFS_SCRATCHDIR)
# Save the dataset to the optimizer running path
OrngFile = os.path.join(scratchdir,"OrngData.tab")
orange.saveTabDelimited(OrngFile,self.dataset)
# Advance Progress Bar
progress1.setValue(1)
# Define the evaluation method to use
if self.dataset.domain.classVar.varType == orange.VarTypes.Continuous:
fMin = self.RMethods[self.RMethod][2]
evalM = self.RMethods[self.RMethod][1]
else:
fMin = self.CMethods[self.CMethod][2]
evalM= self.CMethods[self.CMethod][1]
try:
if os.path.exists(os.path.join(scratchdir,"AZLearnersParamsConfig.py")):
os.system("rm "+str(os.path.join(scratchdir,"AZLearnersParamsConfig.py")))
paramFile=file(os.path.join(scratchdir,"AZLearnersParamsConfig.py"),"w")
paramFile.write(self.learnerType + "= " + str(self.parameters)+"\r\n")
paramFile.close()
progress1.setValue(2)
# Run the optimizer which will configure the input learner and aditionaly return [<minimum of objective function found>, <optimized parameters>]
# Serial
print "ENV:",self.execEnv
if self.execEnv == 0:
print "Executing the optimizer in serial mode on local machine"
optPID = self.optimizer(learner=self.learner, dataSet=OrngFile, evaluateMethod = evalM , findMin=fMin, nFolds = self.nFolds, samplingMethod = self.SMethods[self.SMethod][1], runPath = scratchdir, verbose = self.verbose, externalControl = 1,useParameters = self.parameters, useGridSearchFirst = self.UseGridSearch, gridSearchInnerPoints=self.nInnerPoints, np = None, machinefile = None, advancedMPIoptions = "",)
# Local mpi
elif self.execEnv == 1:
print "Executing the optimizer in parallel mode on local machine"
optPID = self.optimizer(learner=self.learner, dataSet=OrngFile, evaluateMethod = evalM , findMin=fMin, nFolds = self.nFolds, samplingMethod = self.SMethods[self.SMethod][1], runPath = scratchdir, verbose = self.verbose, externalControl = 1,useParameters = self.parameters, useGridSearchFirst = self.UseGridSearch, gridSearchInnerPoints=self.nInnerPoints, machinefile = 0)
# Sge Molndal
elif self.execEnv == 2:
print "Executing the optimizer in parallel mode on the sge in Molndal"
optPID = self.optimizer(learner=self.learner, dataSet=OrngFile, evaluateMethod = evalM , findMin=fMin, nFolds = self.nFolds, samplingMethod = self.SMethods[self.SMethod][1], runPath = scratchdir, verbose = self.verbose, externalControl = 1,useParameters = self.parameters, useGridSearchFirst = self.UseGridSearch, gridSearchInnerPoints=self.nInnerPoints, np = 8,machinefile = "qsub")#, sgeEnv = "sge_seml")
# Sge Lund
else:
optPID = None
print "Executing the optimizer in parallel mode on the sge in Lund"
print "Not verified yet. Nothing will happen."
except:
progress1.close()
self.updateInfo()
self.setErrors("Some error(s) occurred during the optimization.\nCheck the "+str(scratchdir)+" and the output terminal for more information")
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
return
progress1.setValue(3)
if type(optPID)!=types.IntType:
progress1.close()
self.updateInfo()
self.setErrors("Some error(s) occurred during optimization:\n"+str(optPID))
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
return
progress1.close()
# Progess Bar
optSteps = (1+round((len(self.dataset)*len(self.dataset.domain.attributes)*self.nParameters)/1000))*8
print "Learner optimization started at "+time.asctime()
print "Optimization steps = ",int(optSteps)," (estimated to aprox. ",optSteps/2," seconds)"
progress = QProgressDialog("Learner optimization started at "+time.asctime()+" ,please wait...", "Abort Optimization", 0,optSteps ,self,Qt.Dialog)#, "progress", True )
progress.setWindowModality(Qt.WindowModal)
bar = QProgressBar(progress)
bar.show()
progress.setBar(bar)
#progress.setTotalSteps(optSteps)
progress.setMinimumDuration(0)
stepsDone = 0
progress.setValue(stepsDone)
progress.forceShow()
#Loop waiting for the optimizer to finish
while 1:
if stepsDone < (progress.maximum()-1):
progress.setValue(stepsDone)
stepsDone+=1
time.sleep(0.5)
else:
bar.setTextVisible(False)
progress.setLabelText("The optimizer is taking longer than expected, please wait some more time...")
stepsDone = 0
progress.setValue(stepsDone)
time.sleep(0.5)
if progress.wasCanceled():
if not self.optimizer.stop():
progress.setLabelText("Could not stop the optimizer! Please wait until it finish...")
else:
self.setErrors("Learner optimization stopped by user at "+time.asctime(),"WARNING")
break
if self.optimizer.isFinished():
print "Learner optimization finished at "+time.asctime()
break
progress.setValue(progress.maximum()-1)
time.sleep(0.5)
progress.setValue(progress.maximum())
self.tunedPars = self.optimizer.tunedParameters
if self.verbose > 0:
if self.optimizer.usedMPI:
print "appspack version used in fact: MPI"
else:
print "appspack version used in fact: SERIAL"
if type(self.tunedPars) != types.ListType or self.learner.optimized == False:
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
else:
self.send("Learner - Tuned", self.learner)
self.intRes = dataUtilities.DataTable(scratchdir+"/optimizationLog.txt")
self.send("Examples - Optimization Steps", self.intRes)
self.updateInfo()
if self.verbose == 0:
miscUtilities.removeDir(scratchdir)
else:
self.setErrors("The directory " + str(scratchdir) + " was not deleted because verbose flag is ON","DEBUG")
# Description: Shows how to specify the symbols for undefined values in tab-delimited files
# Category: data input
# Classes: ExampleTable
# Uses: undefineds
# Referenced: tabdelimited.htm
import orange
data = orange.ExampleTable("undefineds", DK="GDK", DC="GDC")
for ex in data:
print ex
print "Default saving\n"
orange.saveTabDelimited("undefined-saved.tab", data)
print open("undefined-saved.tab", "rt").read()
print "Saving with all undefined as NA\n"
orange.saveTabDelimited("undefined-saved-na.tab", data, NA="NA")
print open("undefined-saved.tab", "rt").read()
print "Saving with all undefined as NA\n"
orange.saveTabDelimited("undefined-saved-dc-dk", data, DC="GDC", DK="GDK")
print open("undefined-saved.tab", "rt").read()
import os
os.remove("undefined-saved.tab")
def optimizeParameters(self):
""" Sets up the input learner with tuned parameters """
self.clearErrors()
self.tunedPars = None
if hasattr(self.learner, "optimized"):
self.learner.optimized = False
if not self.learner:
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
self.updateInfo()
return
# Apply the parameters var with values on configuration table of GUI (user could have changed them!)
if not self.updateParametersFromTable():
return
if not self.dataset:
self.dataset = None
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
self.updateInfo()
return
# Progess Bar 1
optSteps = 3
progress1 = QProgressDialog(
"Gathering data and configuring the optimizer...", "Cancel", 0,
optSteps, self, Qt.Dialog) #, "progress", True )
progress1.setWindowModality(Qt.WindowModal)
bar1 = QProgressBar(progress1)
bar1.show()
progress1.setBar(bar1)
#progress1.setTotalSteps(optSteps)
progress1.setMinimumDuration(0)
progress1.forceShow()
progress1.setValue(0)
time.sleep(0.1)
progress1.setValue(0)
# Create path for running the optimizer
randNr = random.randint(0, 10000)
if self.execEnv == 0:
scratchdir = miscUtilities.createScratchDir(
desc="OWParamOpt_Serial")
else:
scratchdir = miscUtilities.createScratchDir(
desc="OWParamOpt_MPI", baseDir=AZOC.NFS_SCRATCHDIR)
# Save the dataset to the optimizer running path
OrngFile = os.path.join(scratchdir, "OrngData.tab")
orange.saveTabDelimited(OrngFile, self.dataset)
# Advance Progress Bar
progress1.setValue(1)
# Define the evaluation method to use
if self.dataset.domain.classVar.varType == orange.VarTypes.Continuous:
fMin = self.RMethods[self.RMethod][2]
evalM = self.RMethods[self.RMethod][1]
else:
fMin = self.CMethods[self.CMethod][2]
evalM = self.CMethods[self.CMethod][1]
try:
if os.path.exists(
os.path.join(scratchdir, "AZLearnersParamsConfig.py")):
os.system(
"rm " +
str(os.path.join(scratchdir, "AZLearnersParamsConfig.py")))
paramFile = file(
os.path.join(scratchdir, "AZLearnersParamsConfig.py"), "w")
paramFile.write(self.learnerType + "= " + str(self.parameters) +
"\r\n")
paramFile.close()
progress1.setValue(2)
# Run the optimizer which will configure the input learner and aditionaly return [<minimum of objective function found>, <optimized parameters>]
# Serial
print "ENV:", self.execEnv
if self.execEnv == 0:
print "Executing the optimizer in serial mode on local machine"
optPID = self.optimizer(
learner=self.learner,
dataSet=OrngFile,
evaluateMethod=evalM,
findMin=fMin,
nFolds=self.nFolds,
samplingMethod=self.SMethods[self.SMethod][1],
runPath=scratchdir,
verbose=self.verbose,
externalControl=1,
useParameters=self.parameters,
useGridSearchFirst=self.UseGridSearch,
gridSearchInnerPoints=self.nInnerPoints,
np=None,
machinefile=None,
advancedMPIoptions="",
)
# Local mpi
elif self.execEnv == 1:
print "Executing the optimizer in parallel mode on local machine"
optPID = self.optimizer(
learner=self.learner,
dataSet=OrngFile,
evaluateMethod=evalM,
findMin=fMin,
nFolds=self.nFolds,
samplingMethod=self.SMethods[self.SMethod][1],
runPath=scratchdir,
verbose=self.verbose,
externalControl=1,
useParameters=self.parameters,
useGridSearchFirst=self.UseGridSearch,
gridSearchInnerPoints=self.nInnerPoints,
machinefile=0)
# Sge Molndal
elif self.execEnv == 2:
print "Executing the optimizer in parallel mode in the batch queue on the sge"
print "*****************runPath*****************"
optPID = self.optimizer(
learner=self.learner,
dataSet=OrngFile,
evaluateMethod=evalM,
findMin=fMin,
nFolds=self.nFolds,
samplingMethod=self.SMethods[self.SMethod][1],
runPath=scratchdir,
verbose=self.verbose,
externalControl=1,
useParameters=self.parameters,
useGridSearchFirst=self.UseGridSearch,
gridSearchInnerPoints=self.nInnerPoints,
np=8,
machinefile="qsub") #, sgeEnv = "sge_seml")
elif self.execEnv == 3:
print "Executing the optimizer in parallel mode in the quick queue on the sge"
print "*****************runPath*****************"
optPID = self.optimizer(
learner=self.learner,
dataSet=OrngFile,
evaluateMethod=evalM,
findMin=fMin,
nFolds=self.nFolds,
samplingMethod=self.SMethods[self.SMethod][1],
runPath=scratchdir,
verbose=self.verbose,
externalControl=1,
useParameters=self.parameters,
useGridSearchFirst=self.UseGridSearch,
gridSearchInnerPoints=self.nInnerPoints,
np=8,
machinefile="qsub",
queueType="quick.q") #, sgeEnv = "sge_seml")
else:
print "No SGE Env. selected. Nothing will happen."
except:
progress1.close()
self.updateInfo()
self.setErrors(
"Some error(s) occurred during the optimization.\nCheck the " +
str(scratchdir) +
" and the output terminal for more information")
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
return
progress1.setValue(3)
if type(optPID) != types.IntType:
progress1.close()
self.updateInfo()
self.setErrors("Some error(s) occurred during optimization:\n" +
str(optPID))
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
return
progress1.close()
# Progess Bar
optSteps = (1 + round(
(len(self.dataset) * len(self.dataset.domain.attributes) *
self.nParameters) / 1000)) * 8
print "Learner optimization started at " + time.asctime()
print "Optimization steps = ", int(
optSteps), " (estimated to aprox. ", optSteps / 2, " seconds)"
progress = QProgressDialog("Learner optimization started at " +
time.asctime() + " ,please wait...",
"Abort Optimization", 0, optSteps, self,
Qt.Dialog) #, "progress", True )
progress.setWindowModality(Qt.WindowModal)
bar = QProgressBar(progress)
bar.show()
progress.setBar(bar)
#progress.setTotalSteps(optSteps)
progress.setMinimumDuration(0)
stepsDone = 0
progress.setValue(stepsDone)
progress.forceShow()
#Loop waiting for the optimizer to finish
while 1:
if stepsDone < (progress.maximum() - 1):
progress.setValue(stepsDone)
stepsDone += 1
time.sleep(0.5)
else:
bar.setTextVisible(False)
progress.setLabelText(
"The optimizer is taking longer than expected, please wait some more time..."
)
stepsDone = 0
progress.setValue(stepsDone)
time.sleep(0.5)
if progress.wasCanceled():
if not self.optimizer.stop():
progress.setLabelText(
"Could not stop the optimizer! Please wait until it finish..."
)
else:
self.setErrors(
"Learner optimization stopped by user at " +
time.asctime(), "WARNING")
break
if self.optimizer.isFinished():
print "Learner optimization finished at " + time.asctime()
break
progress.setValue(progress.maximum() - 1)
time.sleep(0.5)
progress.setValue(progress.maximum())
self.tunedPars = self.optimizer.tunedParameters
if self.verbose > 0:
if self.optimizer.usedMPI:
print "appspack version used in fact: MPI"
else:
print "appspack version used in fact: SERIAL"
if type(self.tunedPars
) != types.ListType or self.learner.optimized == False:
self.send("Learner - Tuned", None)
self.send("Examples - Optimization Steps", None)
else:
self.send("Learner - Tuned", self.learner)
self.intRes = dataUtilities.DataTable(scratchdir +
"/optimizationLog.txt")
self.send("Examples - Optimization Steps", self.intRes)
self.updateInfo()
if self.verbose == 0:
miscUtilities.removeDir(scratchdir)
else:
self.setErrors(
"The directory " + str(scratchdir) +
" was not deleted because verbose flag is ON", "DEBUG")
def save_table(filename, table):
from orange import saveTabDelimited
return saveTabDelimited(filename, table)
def __call__(self, trainingData, weight=None):
"""Creates an PLS model from the data in trainingData. """
if not AZBaseClasses.AZLearner.__call__(self, trainingData, weight):
return None
#Remove from the domain any unused values of discrete attributes including class
trainingData = dataUtilities.getDataWithoutUnusedValues(
trainingData, True)
# Create path for the Orange data
scratchdir = miscUtilities.createScratchDir(desc="PLS")
OrngFile = os.path.join(scratchdir, "OrngData.tab")
# Remove meta attributes from training data to make the imputer work with examples without the meta attributes.
#dataUtilities.rmAllMeta(trainingData)
if len(trainingData.domain.getmetas()) == 0:
trainData = trainingData
else:
trainData = dataUtilities.getCopyWithoutMeta(trainingData)
# Create the imputer
self.imputer = orange.ImputerConstructor_average(trainData)
# Impute the data
trainData = self.imputer(trainData)
# Save the Data already imputed to an Orange formated file
if self.verbose > 1:
print time.asctime(), "Saving Orange Data to a tab file..."
orange.saveTabDelimited(OrngFile, trainData)
if self.verbose > 1: print time.asctime(), "done"
# Create the PLS instance
if self.verbose > 1: print time.asctime(), "Creating PLS Object..."
learner = pls.PlsAPI()
if self.verbose > 1: print time.asctime(), "done"
# Assign the PLS parameters
learner.SetParameter('v', str(self.verbose))
learner.SetParameter('debug', str(int(self.verbose > 0)))
learner.SetParameter('method', self.method)
if types.IntType(self.k) > len(trainData.domain.attributes):
learner.SetParameter('k', str(len(trainData.domain.attributes)))
if self.verbose > 0:
print "Warning! The number of components were more than the number of attributes."
if self.verbose > 0:
print " Components were set to ", len(
trainData.domain.attributes)
else:
learner.SetParameter('k', self.k)
learner.SetParameter('precision', self.precision)
learner.SetParameter('sDir', scratchdir) #AZOC.SCRATCHDIR)
# Read the Orange Formated file and Train the Algorithm
# TRAIN
if self.verbose > 1: print time.asctime(), "Training..."
learner.Train(OrngFile)
if self.verbose > 1:
print "Train finished at ", time.asctime()
print "PLS trained in: " + str(
learner.GetCPUTrainTime()) + " seconds"
print "Method: " + learner.GetParameter("method")
print "Components: " + learner.GetParameter("k")
print "Precision: " + learner.GetParameter("precision")
# Remove the scratch file
if self.verbose == 0:
miscUtilities.removeDir(scratchdir)
else:
print "The directory " + scratchdir + " was not deleted because DEBUG flag is ON"
del trainData
impData = self.imputer.defaults
return PLSClassifier(
classifier=learner,
name="Classifier of " + self.name,
classVar=trainingData.domain.classVar,
imputeData=impData,
verbose=self.verbose,
varNames=[attr.name for attr in trainingData.domain.attributes],
NTrainEx=len(trainingData),
basicStat=self.basicStat,
parameters=self.parameters) #learner.GetClassVarName())#
